diff options
Diffstat (limited to 'llvm/test/Transforms')
120 files changed, 788 insertions, 793 deletions
diff --git a/llvm/test/Transforms/AddDiscriminators/memcpy-discriminator.ll b/llvm/test/Transforms/AddDiscriminators/memcpy-discriminator.ll index 00642d29502..f70c3dca3bd 100644 --- a/llvm/test/Transforms/AddDiscriminators/memcpy-discriminator.ll +++ b/llvm/test/Transforms/AddDiscriminators/memcpy-discriminator.ll @@ -69,7 +69,7 @@ cond.true: %0 = bitcast { i64, i32 }* %g_b.coerce to i8*, !dbg !8 %1 = bitcast %struct.B* @g_b to i8*, !dbg !8 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 12, i32 4, i1 false), !dbg !8 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 12, i1 false), !dbg !8 %2 = getelementptr inbounds { i64, i32 }, { i64, i32 }* %g_b.coerce, i32 0, i32 0, !dbg !8 %3 = load i64, i64* %2, align 4, !dbg !8 %4 = getelementptr inbounds { i64, i32 }, { i64, i32 }* %g_b.coerce, i32 0, i32 1, !dbg !8 @@ -84,7 +84,7 @@ cond.end: ; preds = %entry, %cond.true declare i32 @bar(i64, i32, i32) -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #1 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #1 attributes #0 = { noinline nounwind uwtable } attributes #1 = { argmemonly nounwind } diff --git a/llvm/test/Transforms/AlignmentFromAssumptions/simple.ll b/llvm/test/Transforms/AlignmentFromAssumptions/simple.ll index b91722839c6..8bbf1c668c9 100644 --- a/llvm/test/Transforms/AlignmentFromAssumptions/simple.ll +++ b/llvm/test/Transforms/AlignmentFromAssumptions/simple.ll @@ -181,11 +181,11 @@ entry: %maskcond = icmp eq i64 %maskedptr, 0 tail call void @llvm.assume(i1 %maskcond) %0 = bitcast i32* %a to i8* - tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 64, i32 4, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* align 4 %0, i8 0, i64 64, i1 false) ret i32 undef ; CHECK-LABEL: @moo -; CHECK: @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 64, i32 32, i1 false) +; CHECK: @llvm.memset.p0i8.i64(i8* align 32 %0, i8 0, i64 64, i1 false) ; CHECK: ret i32 undef } @@ -201,16 +201,16 @@ entry: tail call void @llvm.assume(i1 %maskcond4) %0 = bitcast i32* %a to i8* %1 = bitcast i32* %b to i8* - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 64, i32 4, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 64, i1 false) ret i32 undef ; CHECK-LABEL: @moo2 -; CHECK: @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 64, i32 32, i1 false) +; CHECK: @llvm.memcpy.p0i8.p0i8.i64(i8* align 32 %0, i8* align 32 %1, i64 64, i1 false) ; CHECK: ret i32 undef } declare void @llvm.assume(i1) nounwind -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind diff --git a/llvm/test/Transforms/AlignmentFromAssumptions/simple32.ll b/llvm/test/Transforms/AlignmentFromAssumptions/simple32.ll index e474bd33c31..379a184fd7d 100644 --- a/llvm/test/Transforms/AlignmentFromAssumptions/simple32.ll +++ b/llvm/test/Transforms/AlignmentFromAssumptions/simple32.ll @@ -181,11 +181,11 @@ entry: %maskcond = icmp eq i64 %maskedptr, 0 tail call void @llvm.assume(i1 %maskcond) %0 = bitcast i32* %a to i8* - tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 64, i32 4, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* align 4 %0, i8 0, i64 64, i1 false) ret i32 undef ; CHECK-LABEL: @moo -; CHECK: @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 64, i32 32, i1 false) +; CHECK: @llvm.memset.p0i8.i64(i8* align 32 %0, i8 0, i64 64, i1 false) ; CHECK: ret i32 undef } @@ -201,16 +201,16 @@ entry: tail call void @llvm.assume(i1 %maskcond4) %0 = bitcast i32* %a to i8* %1 = bitcast i32* %b to i8* - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 64, i32 4, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 64, i1 false) ret i32 undef ; CHECK-LABEL: @moo2 -; CHECK: @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 64, i32 32, i1 false) +; CHECK: @llvm.memcpy.p0i8.p0i8.i64(i8* align 32 %0, i8* align 32 %1, i64 64, i1 false) ; CHECK: ret i32 undef } declare void @llvm.assume(i1) nounwind -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind diff --git a/llvm/test/Transforms/CodeGenPrepare/X86/memset_chk-simplify-nobuiltin.ll b/llvm/test/Transforms/CodeGenPrepare/X86/memset_chk-simplify-nobuiltin.ll index 1e12c0192a9..f4c1af5ed46 100644 --- a/llvm/test/Transforms/CodeGenPrepare/X86/memset_chk-simplify-nobuiltin.ll +++ b/llvm/test/Transforms/CodeGenPrepare/X86/memset_chk-simplify-nobuiltin.ll @@ -9,7 +9,7 @@ target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" ; - TLI::has (always returns false thanks to -disable-simplify-libcalls) ; CHECK-NOT: _chk -; CHECK: call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %len, i32 1, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %dst, i8 0, i64 %len, i1 false) define void @test_nobuiltin(i8* %dst, i64 %len) { call i8* @__memset_chk(i8* %dst, i32 0, i64 %len, i64 -1) nobuiltin ret void diff --git a/llvm/test/Transforms/CorrelatedValuePropagation/non-null.ll b/llvm/test/Transforms/CorrelatedValuePropagation/non-null.ll index 6fb4cb6e358..e5882f12565 100644 --- a/llvm/test/Transforms/CorrelatedValuePropagation/non-null.ll +++ b/llvm/test/Transforms/CorrelatedValuePropagation/non-null.ll @@ -30,10 +30,10 @@ bb: ret void } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i1) define void @test4(i8* %dest, i8* %src) { ; CHECK: test4 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 1, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 1, i1 false) br label %bb bb: icmp ne i8* %dest, null @@ -42,10 +42,10 @@ bb: ret void } -declare void @llvm.memmove.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) +declare void @llvm.memmove.p0i8.p0i8.i32(i8*, i8*, i32, i1) define void @test5(i8* %dest, i8* %src) { ; CHECK: test5 - call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 1, i32 1, i1 false) + call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 1, i1 false) br label %bb bb: icmp ne i8* %dest, null @@ -54,10 +54,10 @@ bb: ret void } -declare void @llvm.memset.p0i8.i32(i8*, i8, i32, i32, i1) +declare void @llvm.memset.p0i8.i32(i8*, i8, i32, i1) define void @test6(i8* %dest) { ; CHECK: test6 - call void @llvm.memset.p0i8.i32(i8* %dest, i8 255, i32 1, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* %dest, i8 255, i32 1, i1 false) br label %bb bb: icmp ne i8* %dest, null @@ -67,7 +67,7 @@ bb: define void @test7(i8* %dest, i8* %src, i32 %len) { ; CHECK: test7 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 %len, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 %len, i1 false) br label %bb bb: %KEEP1 = icmp ne i8* %dest, null @@ -77,10 +77,10 @@ bb: ret void } -declare void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1) *, i8 addrspace(1) *, i32, i32, i1) +declare void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1) *, i8 addrspace(1) *, i32, i1) define void @test8(i8 addrspace(1) * %dest, i8 addrspace(1) * %src) { ; CHECK: test8 - call void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1) * %dest, i8 addrspace(1) * %src, i32 1, i32 1, i1 false) + call void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1) * %dest, i8 addrspace(1) * %src, i32 1, i1 false) br label %bb bb: %KEEP1 = icmp ne i8 addrspace(1) * %dest, null @@ -92,7 +92,7 @@ bb: define void @test9(i8* %dest, i8* %src) { ; CHECK: test9 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 1, i32 1, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 1, i1 true) br label %bb bb: %KEEP1 = icmp ne i8* %dest, null diff --git a/llvm/test/Transforms/DeadStoreElimination/2011-09-06-MemCpy.ll b/llvm/test/Transforms/DeadStoreElimination/2011-09-06-MemCpy.ll index d30e9a2e6c1..665d772d03b 100644 --- a/llvm/test/Transforms/DeadStoreElimination/2011-09-06-MemCpy.ll +++ b/llvm/test/Transforms/DeadStoreElimination/2011-09-06-MemCpy.ll @@ -60,7 +60,7 @@ target triple = "x86_64-unknown-linux-gnu" %struct.AttrListPtr = type { %struct.AttributeListImpl* } %struct.AttributeListImpl = type opaque -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind ; CHECK: _ZSt9iter_swapIPSt4pairIPN4llvm10BasicBlockEjES5_EvT_T0_ ; CHECK: store @@ -78,8 +78,8 @@ entry: store i32 %5, i32* %3, align 8 %6 = bitcast %struct.pair.162* %__a to i8* %7 = bitcast %struct.pair.162* %__b to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %6, i8* %7, i64 12, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %6, i8* %7, i64 12, i1 false) %8 = bitcast %struct.pair.162* %memtmp to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %7, i8* %8, i64 12, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %7, i8* %8, i64 12, i1 false) ret void } diff --git a/llvm/test/Transforms/DeadStoreElimination/2016-07-17-UseAfterFree.ll b/llvm/test/Transforms/DeadStoreElimination/2016-07-17-UseAfterFree.ll index 0a39ccbef64..90629a263f7 100644 --- a/llvm/test/Transforms/DeadStoreElimination/2016-07-17-UseAfterFree.ll +++ b/llvm/test/Transforms/DeadStoreElimination/2016-07-17-UseAfterFree.ll @@ -9,10 +9,10 @@ define void @_UPT_destroy(i8* nocapture %ptr) local_unnamed_addr #0 { entry: %edi = getelementptr inbounds i8, i8* %ptr, i64 8 -; CHECK-NOT: tail call void @llvm.memset.p0i8.i64(i8* %edi, i8 0, i64 176, i32 8, i1 false) +; CHECK-NOT: tail call void @llvm.memset.p0i8.i64(i8* align 8 %edi, i8 0, i64 176, i1 false) ; CHECK-NOT: store i32 -1, i32* %addr - tail call void @llvm.memset.p0i8.i64(i8* %edi, i8 0, i64 176, i32 8, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* align 8 %edi, i8 0, i64 176, i1 false) %format4.i = getelementptr inbounds i8, i8* %ptr, i64 144 %addr = bitcast i8* %format4.i to i32* store i32 -1, i32* %addr, align 8 @@ -26,7 +26,7 @@ entry: declare void @free(i8* nocapture) local_unnamed_addr #0 ; Function Attrs: argmemonly nounwind -declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i32, i1) #1 +declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1) #1 attributes #0 = { nounwind } attributes #1 = { argmemonly nounwind } diff --git a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll index 1614a529ddd..843436fd7da 100644 --- a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll +++ b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreBegin.ll @@ -6,8 +6,8 @@ entry: %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1 %p3 = bitcast i32* %arrayidx0 to i8* ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 4 -; CHECK: call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 24, i32 4, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 28, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false) %arrayidx1 = getelementptr inbounds i32, i32* %p, i64 1 store i32 1, i32* %arrayidx1, align 4 ret void @@ -18,8 +18,8 @@ define void @write0to3(i32* nocapture %p) { entry: %p3 = bitcast i32* %p to i8* ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 4 -; CHECK: call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 24, i32 4, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 28, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false) store i32 1, i32* %p, align 4 ret void } @@ -29,8 +29,8 @@ define void @write0to7(i32* nocapture %p) { entry: %p3 = bitcast i32* %p to i8* ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 8 -; CHECK: call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 24, i32 4, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false) %p4 = bitcast i32* %p to i64* store i64 1, i64* %p4, align 8 ret void @@ -42,8 +42,8 @@ entry: %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1 %p3 = bitcast i32* %arrayidx0 to i8* ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %p3, i64 4 -; CHECK: call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 24, i32 4, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 28, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 [[GEP]], i8 0, i64 24, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false) %p4 = bitcast i32* %p to i64* store i64 1, i64* %p4, align 8 ret void @@ -55,8 +55,8 @@ define void @dontwrite0to3_align8(i32* nocapture %p) { ; CHECK-LABEL: @dontwrite0to3_align8( entry: %p3 = bitcast i32* %p to i8* -; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 8, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 8, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %p3, i8 0, i64 32, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %p3, i8 0, i64 32, i1 false) store i32 1, i32* %p, align 4 ret void } @@ -65,8 +65,8 @@ define void @dontwrite0to1(i32* nocapture %p) { ; CHECK-LABEL: @dontwrite0to1( entry: %p3 = bitcast i32* %p to i8* -; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false) %p4 = bitcast i32* %p to i16* store i16 1, i16* %p4, align 4 ret void @@ -77,8 +77,8 @@ define void @dontwrite2to9(i32* nocapture %p) { entry: %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1 %p3 = bitcast i32* %arrayidx0 to i8* -; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false) %p4 = bitcast i32* %p to i16* %arrayidx2 = getelementptr inbounds i16, i16* %p4, i64 1 %p5 = bitcast i16* %arrayidx2 to i64* @@ -90,11 +90,11 @@ define void @write8To15AndThen0To7(i64* nocapture %P) { entry: ; CHECK-LABEL: @write8To15AndThen0To7( ; CHECK: [[GEP:%[0-9]+]] = getelementptr inbounds i8, i8* %mybase0, i64 16 -; CHECK: tail call void @llvm.memset.p0i8.i64(i8* [[GEP]], i8 0, i64 16, i32 8, i1 false) +; CHECK: tail call void @llvm.memset.p0i8.i64(i8* align 8 [[GEP]], i8 0, i64 16, i1 false) %base0 = bitcast i64* %P to i8* %mybase0 = getelementptr inbounds i8, i8* %base0, i64 0 - tail call void @llvm.memset.p0i8.i64(i8* %mybase0, i8 0, i64 32, i32 8, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* align 8 %mybase0, i8 0, i64 32, i1 false) %base64_0 = getelementptr inbounds i64, i64* %P, i64 0 %base64_1 = getelementptr inbounds i64, i64* %P, i64 1 @@ -104,5 +104,5 @@ entry: ret void } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind diff --git a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll index 65acc08629a..7743c619ae1 100644 --- a/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll +++ b/llvm/test/Transforms/DeadStoreElimination/OverwriteStoreEnd.ll @@ -12,8 +12,8 @@ define void @write24to28(i32* nocapture %p) nounwind uwtable ssp { entry: %arrayidx0 = getelementptr inbounds i32, i32* %p, i64 1 %p3 = bitcast i32* %arrayidx0 to i8* -; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 24, i32 4, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 28, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 24, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false) %arrayidx1 = getelementptr inbounds i32, i32* %p, i64 7 store i32 1, i32* %arrayidx1, align 4 ret void @@ -23,8 +23,8 @@ define void @write28to32(i32* nocapture %p) nounwind uwtable ssp { ; CHECK-LABEL: @write28to32( entry: %p3 = bitcast i32* %p to i8* -; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 28, i32 4, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 28, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %p3, i8 0, i64 32, i1 false) %arrayidx1 = getelementptr inbounds i32, i32* %p, i64 7 store i32 1, i32* %arrayidx1, align 4 ret void @@ -34,8 +34,8 @@ define void @dontwrite28to32memset(i32* nocapture %p) nounwind uwtable ssp { ; CHECK-LABEL: @dontwrite28to32memset( entry: %p3 = bitcast i32* %p to i8* -; CHECK: call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 16, i1 false) - call void @llvm.memset.p0i8.i64(i8* %p3, i8 0, i64 32, i32 16, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 16 %p3, i8 0, i64 32, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 16 %p3, i8 0, i64 32, i1 false) %arrayidx1 = getelementptr inbounds i32, i32* %p, i64 7 store i32 1, i32* %arrayidx1, align 4 ret void @@ -45,8 +45,8 @@ define void @write32to36(%struct.vec2plusi* nocapture %p) nounwind uwtable ssp { ; CHECK-LABEL: @write32to36( entry: %0 = bitcast %struct.vec2plusi* %p to i8* -; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2plusi* @glob2 to i8*), i64 32, i32 16, i1 false) - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2plusi* @glob2 to i8*), i64 36, i32 16, i1 false) +; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2plusi* @glob2 to i8*), i64 32, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2plusi* @glob2 to i8*), i64 36, i1 false) %c = getelementptr inbounds %struct.vec2plusi, %struct.vec2plusi* %p, i64 0, i32 2 store i32 1, i32* %c, align 4 ret void @@ -56,8 +56,8 @@ define void @write16to32(%struct.vec2* nocapture %p) nounwind uwtable ssp { ; CHECK-LABEL: @write16to32( entry: %0 = bitcast %struct.vec2* %p to i8* -; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2* @glob1 to i8*), i64 16, i32 16, i1 false) - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2* @glob1 to i8*), i64 32, i32 16, i1 false) +; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 16, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false) %c = getelementptr inbounds %struct.vec2, %struct.vec2* %p, i64 0, i32 1 store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32>* %c, align 4 ret void @@ -67,15 +67,15 @@ define void @dontwrite28to32memcpy(%struct.vec2* nocapture %p) nounwind uwtable ; CHECK-LABEL: @dontwrite28to32memcpy( entry: %0 = bitcast %struct.vec2* %p to i8* -; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2* @glob1 to i8*), i64 32, i32 16, i1 false) - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast (%struct.vec2* @glob1 to i8*), i64 32, i32 16, i1 false) +; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %0, i8* align 16 bitcast (%struct.vec2* @glob1 to i8*), i64 32, i1 false) %arrayidx1 = getelementptr inbounds %struct.vec2, %struct.vec2* %p, i64 0, i32 0, i64 7 store i32 1, i32* %arrayidx1, align 4 ret void } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind %struct.trapframe = type { i64, i64, i64 } @@ -87,8 +87,8 @@ entry: %add.ptr = getelementptr inbounds %struct.trapframe, %struct.trapframe* %0, i64 -1 %1 = bitcast %struct.trapframe* %add.ptr to i8* %2 = bitcast %struct.trapframe* %md_regs to i8* -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 24, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 24, i32 1, i1 false) +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 24, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %2, i64 24, i1 false) %tf_trapno = getelementptr inbounds %struct.trapframe, %struct.trapframe* %0, i64 -1, i32 1 store i64 3, i64* %tf_trapno, align 8 ret void @@ -97,11 +97,11 @@ entry: define void @write16To23AndThen24To31(i64* nocapture %P, i64 %n64, i32 %n32, i16 %n16, i8 %n8) { entry: ; CHECK-LABEL: @write16To23AndThen24To31( -; CHECK: tail call void @llvm.memset.p0i8.i64(i8* %mybase0, i8 0, i64 16, i32 8, i1 false) +; CHECK: tail call void @llvm.memset.p0i8.i64(i8* align 8 %mybase0, i8 0, i64 16, i1 false) %base0 = bitcast i64* %P to i8* %mybase0 = getelementptr inbounds i8, i8* %base0, i64 0 - tail call void @llvm.memset.p0i8.i64(i8* %mybase0, i8 0, i64 32, i32 8, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* align 8 %mybase0, i8 0, i64 32, i1 false) %base64_2 = getelementptr inbounds i64, i64* %P, i64 2 %base64_3 = getelementptr inbounds i64, i64* %P, i64 3 diff --git a/llvm/test/Transforms/DeadStoreElimination/combined-partial-overwrites.ll b/llvm/test/Transforms/DeadStoreElimination/combined-partial-overwrites.ll index 2932307beaf..2a61fff15ad 100644 --- a/llvm/test/Transforms/DeadStoreElimination/combined-partial-overwrites.ll +++ b/llvm/test/Transforms/DeadStoreElimination/combined-partial-overwrites.ll @@ -146,7 +146,7 @@ i32 (i8*, i8**, i32, i8, i8*)*, i32 (i8*, i8**, i32, i8, i8*)*, void (i8*, i32, i32)* } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) declare void @goFunc(%struct.foostruct*) declare i32 @fa(i8*, i8**, i32, i8, i8*) @@ -156,7 +156,7 @@ entry: %bang = alloca %struct.foostruct, align 8 %v1 = bitcast %struct.foostruct* %bang to i8* - call void @llvm.memset.p0i8.i64(i8* %v1, i8 0, i64 40, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %v1, i8 0, i64 40, i1 false) %v2 = getelementptr inbounds %struct.foostruct, %struct.foostruct* %bang, i64 0, i32 0 store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** %v2, align 8 %v3 = getelementptr inbounds %struct.foostruct, %struct.foostruct* %bang, i64 0, i32 1 diff --git a/llvm/test/Transforms/DeadStoreElimination/crash.ll b/llvm/test/Transforms/DeadStoreElimination/crash.ll index 78cb842e60e..92765697429 100644 --- a/llvm/test/Transforms/DeadStoreElimination/crash.ll +++ b/llvm/test/Transforms/DeadStoreElimination/crash.ll @@ -36,11 +36,11 @@ bb14: ; preds = %bb4 %6 = getelementptr inbounds i16, i16* %2, i64 undef ; <i16*> [#uses=1] store i16 undef, i16* %6, align 2 %7 = getelementptr inbounds i8, i8* %5, i64 undef ; <i8*> [#uses=1] - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %7, i8* undef, i64 undef, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %7, i8* undef, i64 undef, i1 false) unreachable } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind ; rdar://7635088 diff --git a/llvm/test/Transforms/DeadStoreElimination/cs-cs-aliasing.ll b/llvm/test/Transforms/DeadStoreElimination/cs-cs-aliasing.ll index 30bb96fa2b4..a225a9023ec 100644 --- a/llvm/test/Transforms/DeadStoreElimination/cs-cs-aliasing.ll +++ b/llvm/test/Transforms/DeadStoreElimination/cs-cs-aliasing.ll @@ -9,7 +9,7 @@ target triple = "x86_64-unknown-linux-gnu" %union.anon = type { i64, [8 x i8] } ; Function Attrs: nounwind -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) #0 +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) #0 ; Function Attrs: noinline nounwind readonly uwtable declare zeroext i1 @callee_takes_string(%class.basic_string* nonnull) #1 align 2 @@ -61,10 +61,10 @@ _ZN9__gnu_cxx17__sso_string_baseIcSt11char_traitsIcESaIcEED2Ev.exit3: ; preds = ; CHECK: store i8 0, i8* %tmp14, align 1 %tmp17 = call zeroext i1 @callee_takes_string(%class.basic_string* nonnull %tmp1) - call void @llvm.memset.p0i8.i64(i8* %tmp11, i8 -51, i64 16, i32 8, i1 false) #0 - call void @llvm.memset.p0i8.i64(i8* %tmp15, i8 -51, i64 32, i32 8, i1 false) #0 - call void @llvm.memset.p0i8.i64(i8* %tmp4, i8 -51, i64 16, i32 8, i1 false) #0 - call void @llvm.memset.p0i8.i64(i8* %tmp8, i8 -51, i64 32, i32 8, i1 false) #0 + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp11, i8 -51, i64 16, i1 false) #0 + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp15, i8 -51, i64 32, i1 false) #0 + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp4, i8 -51, i64 16, i1 false) #0 + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp8, i8 -51, i64 32, i1 false) #0 ret i1 %tmp17 } diff --git a/llvm/test/Transforms/DeadStoreElimination/lifetime.ll b/llvm/test/Transforms/DeadStoreElimination/lifetime.ll index 97f199b5e0f..28a164cd8b5 100644 --- a/llvm/test/Transforms/DeadStoreElimination/lifetime.ll +++ b/llvm/test/Transforms/DeadStoreElimination/lifetime.ll @@ -4,7 +4,7 @@ target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:1 declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) nounwind declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) nounwind -declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i32, i1) nounwind +declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i1) nounwind define void @test1() { ; CHECK-LABEL: @test1( @@ -14,7 +14,7 @@ define void @test1() { call void @llvm.lifetime.end.p0i8(i64 1, i8* %A) ; CHECK: lifetime.end - call void @llvm.memset.p0i8.i8(i8* %A, i8 0, i8 -1, i32 0, i1 false) + call void @llvm.memset.p0i8.i8(i8* %A, i8 0, i8 -1, i1 false) ; CHECK-NOT: memset ret void diff --git a/llvm/test/Transforms/DeadStoreElimination/mda-with-dbg-values.ll b/llvm/test/Transforms/DeadStoreElimination/mda-with-dbg-values.ll index ad61a165d72..23cd93ac387 100644 --- a/llvm/test/Transforms/DeadStoreElimination/mda-with-dbg-values.ll +++ b/llvm/test/Transforms/DeadStoreElimination/mda-with-dbg-values.ll @@ -21,7 +21,7 @@ entry: store i8 1, i8* %i, align 1, !dbg !19 call void @llvm.dbg.value(metadata i32 0, i64 0, metadata !17, metadata !DIExpression()), !dbg !18 %0 = bitcast [1 x i8]* @g to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %i, i8* %0, i64 1, i32 1, i1 false), !dbg !20 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %i, i8* %0, i64 1, i1 false), !dbg !20 br label %bb2 bb2: ; preds = %0 @@ -32,7 +32,7 @@ bb2: ; preds = %0 declare void @llvm.dbg.value(metadata, i64, metadata, metadata) #1 ; Function Attrs: argmemonly nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #2 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #2 attributes #0 = { noinline nounwind uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" } attributes #1 = { nounwind readnone speculatable } diff --git a/llvm/test/Transforms/DeadStoreElimination/memintrinsics.ll b/llvm/test/Transforms/DeadStoreElimination/memintrinsics.ll index 5bbb8e099c4..aa9f1a13bba 100644 --- a/llvm/test/Transforms/DeadStoreElimination/memintrinsics.ll +++ b/llvm/test/Transforms/DeadStoreElimination/memintrinsics.ll @@ -1,8 +1,8 @@ ; RUN: opt -S -dse < %s | FileCheck %s -declare void @llvm.memcpy.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i32, i1) nounwind -declare void @llvm.memmove.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i32, i1) nounwind -declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i1) nounwind +declare void @llvm.memmove.p0i8.p0i8.i8(i8* nocapture, i8* nocapture, i8, i1) nounwind +declare void @llvm.memset.p0i8.i8(i8* nocapture, i8, i8, i1) nounwind define void @test1() { ; CHECK-LABEL: @test1( @@ -12,7 +12,7 @@ define void @test1() { store i8 0, i8* %A ;; Written to by memcpy ; CHECK-NOT: store - call void @llvm.memcpy.p0i8.p0i8.i8(i8* %A, i8* %B, i8 -1, i32 0, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i8(i8* %A, i8* %B, i8 -1, i1 false) ret void ; CHECK: ret void @@ -26,7 +26,7 @@ define void @test2() { store i8 0, i8* %A ;; Written to by memmove ; CHECK-NOT: store - call void @llvm.memmove.p0i8.p0i8.i8(i8* %A, i8* %B, i8 -1, i32 0, i1 false) + call void @llvm.memmove.p0i8.p0i8.i8(i8* %A, i8* %B, i8 -1, i1 false) ret void ; CHECK: ret void @@ -40,7 +40,7 @@ define void @test3() { store i8 0, i8* %A ;; Written to by memset ; CHECK-NOT: store - call void @llvm.memset.p0i8.i8(i8* %A, i8 0, i8 -1, i32 0, i1 false) + call void @llvm.memset.p0i8.i8(i8* %A, i8 0, i8 -1, i1 false) ret void ; CHECK: ret void diff --git a/llvm/test/Transforms/DeadStoreElimination/no-targetdata.ll b/llvm/test/Transforms/DeadStoreElimination/no-targetdata.ll index f9262ed54b3..b66b75e14d8 100644 --- a/llvm/test/Transforms/DeadStoreElimination/no-targetdata.ll +++ b/llvm/test/Transforms/DeadStoreElimination/no-targetdata.ll @@ -1,6 +1,6 @@ ; RUN: opt -basicaa -dse -S < %s | FileCheck %s -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind define void @fn(i8* nocapture %buf) #0 { entry: @@ -13,9 +13,9 @@ entry: ; CHECK: ret void %arrayidx = getelementptr i8, i8* %buf, i64 18 - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arrayidx, i8* %buf, i64 18, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arrayidx, i8* %buf, i64 18, i1 false) store i8 1, i8* %arrayidx, align 1 - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %buf, i8* %arrayidx, i64 18, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %buf, i8* %arrayidx, i64 18, i1 false) ret void } diff --git a/llvm/test/Transforms/DeadStoreElimination/pr11390.ll b/llvm/test/Transforms/DeadStoreElimination/pr11390.ll index faf3b8b47a9..6105a2e3346 100644 --- a/llvm/test/Transforms/DeadStoreElimination/pr11390.ll +++ b/llvm/test/Transforms/DeadStoreElimination/pr11390.ll @@ -17,12 +17,12 @@ entry: br i1 %tobool, label %return, label %if.end if.end: ; preds = %entry - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %call4, i8* %name, i64 %call, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %call4, i8* %name, i64 %call, i1 false) %arrayidx = getelementptr inbounds i8, i8* %call4, i64 %call store i8 46, i8* %arrayidx, align 1 ; CHECK: store i8 46 %add.ptr5 = getelementptr inbounds i8, i8* %call4, i64 %add - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %add.ptr5, i8* %domain, i64 %call1, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %add.ptr5, i8* %domain, i64 %call1, i1 false) %arrayidx8 = getelementptr inbounds i8, i8* %call4, i64 %add2 store i8 0, i8* %arrayidx8, align 1 br label %return @@ -35,4 +35,4 @@ declare i64 @strlen(i8* nocapture) nounwind readonly declare noalias i8* @malloc(i64) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind diff --git a/llvm/test/Transforms/DeadStoreElimination/simple.ll b/llvm/test/Transforms/DeadStoreElimination/simple.ll index 4ed27ebfd66..6130fbbf807 100644 --- a/llvm/test/Transforms/DeadStoreElimination/simple.ll +++ b/llvm/test/Transforms/DeadStoreElimination/simple.ll @@ -2,8 +2,8 @@ ; RUN: opt < %s -aa-pipeline=basic-aa -passes=dse -S | FileCheck %s target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128" -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind declare void @llvm.init.trampoline(i8*, i8*, i8*) define void @test1(i32* %Q, i32* %P) { @@ -64,7 +64,7 @@ define void @test5(i32* %Q) { ; alias). define void @test6(i32 *%p, i8 *%q) { store i32 10, i32* %p, align 4 ;; dead. - call void @llvm.memset.p0i8.i64(i8* %q, i8 42, i64 900, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %q, i8 42, i64 900, i1 false) store i32 30, i32* %p, align 4 ret void ; CHECK-LABEL: @test6( @@ -75,7 +75,7 @@ define void @test6(i32 *%p, i8 *%q) { ; alias). define void @test7(i32 *%p, i8 *%q, i8* noalias %r) { store i32 10, i32* %p, align 4 ;; dead. - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %q, i8* %r, i64 900, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %q, i8* %r, i64 900, i1 false) store i32 30, i32* %p, align 4 ret void ; CHECK-LABEL: @test7( @@ -209,8 +209,8 @@ define void @test14(i32* %Q) { ;; Fully dead overwrite of memcpy. define void @test15(i8* %P, i8* %Q) nounwind ssp { - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) ret void ; CHECK-LABEL: @test15( ; CHECK-NEXT: call void @llvm.memcpy @@ -219,8 +219,8 @@ define void @test15(i8* %P, i8* %Q) nounwind ssp { ;; Full overwrite of smaller memcpy. define void @test16(i8* %P, i8* %Q) nounwind ssp { - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i32 1, i1 false) - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) ret void ; CHECK-LABEL: @test16( ; CHECK-NEXT: call void @llvm.memcpy @@ -229,8 +229,8 @@ define void @test16(i8* %P, i8* %Q) nounwind ssp { ;; Overwrite of memset by memcpy. define void @test17(i8* %P, i8* noalias %Q) nounwind ssp { - tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 false) - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) ret void ; CHECK-LABEL: @test17( ; CHECK-NEXT: call void @llvm.memcpy @@ -239,8 +239,8 @@ define void @test17(i8* %P, i8* noalias %Q) nounwind ssp { ; Should not delete the volatile memset. define void @test17v(i8* %P, i8* %Q) nounwind ssp { - tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i32 1, i1 true) - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %P, i8 42, i64 8, i1 true) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) ret void ; CHECK-LABEL: @test17v( ; CHECK-NEXT: call void @llvm.memset @@ -253,8 +253,8 @@ define void @test17v(i8* %P, i8* %Q) nounwind ssp { ; A = B ; A = A define void @test18(i8* %P, i8* %Q, i8* %R) nounwind ssp { - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i32 1, i1 false) - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) ret void ; CHECK-LABEL: @test18( ; CHECK-NEXT: call void @llvm.memcpy diff --git a/llvm/test/Transforms/FunctionAttrs/norecurse.ll b/llvm/test/Transforms/FunctionAttrs/norecurse.ll index 42de757fbad..cd9044d0720 100644 --- a/llvm/test/Transforms/FunctionAttrs/norecurse.ll +++ b/llvm/test/Transforms/FunctionAttrs/norecurse.ll @@ -32,10 +32,10 @@ declare i32 @k() readnone ; CHECK: define void @intrinsic(i8* nocapture %dest, i8* nocapture readonly %src, i32 %len) { define void @intrinsic(i8* %dest, i8* %src, i32 %len) { - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 %len, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 %len, i1 false) ret void } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i1) ; CHECK: define internal i32 @called_by_norecurse() #0 define internal i32 @called_by_norecurse() { diff --git a/llvm/test/Transforms/GVN/PRE/rle.ll b/llvm/test/Transforms/GVN/PRE/rle.ll index 1d2cba2f1f6..5ff2927ed27 100644 --- a/llvm/test/Transforms/GVN/PRE/rle.ll +++ b/llvm/test/Transforms/GVN/PRE/rle.ll @@ -27,7 +27,7 @@ define i8 @crash0({i32, i32} %A, {i32, i32}* %P) { ;; No PR filed, crashed in CaptureTracker. declare void @helper() define void @crash1() { - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* undef, i64 undef, i32 1, i1 false) nounwind + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* undef, i64 undef, i1 false) nounwind %tmp = load i8, i8* bitcast (void ()* @helper to i8*) %x = icmp eq i8 %tmp, 15 ret void @@ -142,7 +142,7 @@ define i8* @coerce_mustalias7(i64 %V, i64* %P) { define signext i16 @memset_to_i16_local(i16* %A) nounwind ssp { entry: %conv = bitcast i16* %A to i8* - tail call void @llvm.memset.p0i8.i64(i8* %conv, i8 1, i64 200, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %conv, i8 1, i64 200, i1 false) %arrayidx = getelementptr inbounds i16, i16* %A, i64 42 %tmp2 = load i16, i16* %arrayidx ret i16 %tmp2 @@ -155,7 +155,7 @@ entry: define float @memset_to_float_local(float* %A, i8 %Val) nounwind ssp { entry: %conv = bitcast float* %A to i8* ; <i8*> [#uses=1] - tail call void @llvm.memset.p0i8.i64(i8* %conv, i8 %Val, i64 400, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %conv, i8 %Val, i64 400, i1 false) %arrayidx = getelementptr inbounds float, float* %A, i64 42 ; <float*> [#uses=1] %tmp2 = load float, float* %arrayidx ; <float> [#uses=1] ret float %tmp2 @@ -175,11 +175,11 @@ define i16 @memset_to_i16_nonlocal0(i16* %P, i1 %cond) { %P3 = bitcast i16* %P to i8* br i1 %cond, label %T, label %F T: - tail call void @llvm.memset.p0i8.i64(i8* %P3, i8 1, i64 400, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %P3, i8 1, i64 400, i1 false) br label %Cont F: - tail call void @llvm.memset.p0i8.i64(i8* %P3, i8 2, i64 400, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %P3, i8 2, i64 400, i1 false) br label %Cont Cont: @@ -201,7 +201,7 @@ Cont: define float @memcpy_to_float_local(float* %A) nounwind ssp { entry: %conv = bitcast float* %A to i8* ; <i8*> [#uses=1] - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %conv, i8* bitcast ({i32, float, i32 }* @GCst to i8*), i64 12, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %conv, i8* bitcast ({i32, float, i32 }* @GCst to i8*), i64 12, i1 false) %arrayidx = getelementptr inbounds float, float* %A, i64 1 ; <float*> [#uses=1] %tmp2 = load float, float* %arrayidx ; <float> [#uses=1] ret float %tmp2 @@ -214,7 +214,7 @@ entry: define float @memcpy_to_float_local_as1(float* %A) nounwind ssp { entry: %conv = bitcast float* %A to i8* ; <i8*> [#uses=1] - tail call void @llvm.memcpy.p0i8.p1i8.i64(i8* %conv, i8 addrspace(1)* bitcast ({i32, float, i32 } addrspace(1)* @GCst_as1 to i8 addrspace(1)*), i64 12, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p1i8.i64(i8* %conv, i8 addrspace(1)* bitcast ({i32, float, i32 } addrspace(1)* @GCst_as1 to i8 addrspace(1)*), i64 12, i1 false) %arrayidx = getelementptr inbounds float, float* %A, i64 1 ; <float*> [#uses=1] %tmp2 = load float, float* %arrayidx ; <float> [#uses=1] ret float %tmp2 @@ -552,7 +552,7 @@ define i32 @memset_to_load() nounwind readnone { entry: %x = alloca [256 x i32], align 4 ; <[256 x i32]*> [#uses=2] %tmp = bitcast [256 x i32]* %x to i8* ; <i8*> [#uses=1] - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 1024, i32 4, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %tmp, i8 0, i64 1024, i1 false) %arraydecay = getelementptr inbounds [256 x i32], [256 x i32]* %x, i32 0, i32 0 ; <i32*> %tmp1 = load i32, i32* %arraydecay ; <i32> [#uses=1] ret i32 %tmp1 @@ -661,10 +661,10 @@ entry: ; CHECK: ret i32 } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind +declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind ;;===----------------------------------------------------------------------===;; diff --git a/llvm/test/Transforms/GVN/nonescaping-malloc.ll b/llvm/test/Transforms/GVN/nonescaping-malloc.ll index 250e27c88f4..639fc686e19 100644 --- a/llvm/test/Transforms/GVN/nonescaping-malloc.ll +++ b/llvm/test/Transforms/GVN/nonescaping-malloc.ll @@ -82,7 +82,7 @@ bb.i.i: ; preds = %bb4.i _ZN4llvm14StringMapEntryIPvE6CreateINS_15MallocAllocatorES1_EEPS2_PKcS7_RT_T0_.exit.i: ; preds = %bb.i.i, %bb4.i %tmp.i18.i.i = getelementptr inbounds i8, i8* %tmp.i20.i.i, i64 16 %tmp15.i.i = zext i32 %tmp4.i.i to i64 - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp.i18.i.i, i8* %tmp41.i, i64 %tmp15.i.i, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp.i18.i.i, i8* %tmp41.i, i64 %tmp15.i.i, i1 false) %tmp.i18.sum.i.i = add i64 %tmp15.i.i, 16 %tmp17.i.i = getelementptr inbounds i8, i8* %tmp.i20.i.i, i64 %tmp.i18.sum.i.i store i8 0, i8* %tmp17.i.i, align 1 @@ -108,4 +108,4 @@ _ZN4llvm9StringMapIPvNS_15MallocAllocatorEE16GetOrCreateValueIS1_EERNS_14StringM ret %"struct.llvm::StringMapEntry<void*>"* %tmp10.i.i } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind diff --git a/llvm/test/Transforms/GVN/pr17732.ll b/llvm/test/Transforms/GVN/pr17732.ll index 6c40ccf4501..d056d5251c7 100644 --- a/llvm/test/Transforms/GVN/pr17732.ll +++ b/llvm/test/Transforms/GVN/pr17732.ll @@ -14,10 +14,10 @@ target triple = "x86_64-unknown-linux-gnu" define i32 @main() { entry: - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds (%struct.with_array, %struct.with_array* @array_with_zeroinit, i64 0, i32 0, i64 0), i8* getelementptr inbounds ({ [2 x i8], i32, i8, [3 x i8] }, { [2 x i8], i32, i8, [3 x i8] }* @main.obj_with_array, i64 0, i32 0, i64 0), i64 12, i32 4, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 getelementptr inbounds (%struct.with_array, %struct.with_array* @array_with_zeroinit, i64 0, i32 0, i64 0), i8* align 4 getelementptr inbounds ({ [2 x i8], i32, i8, [3 x i8] }, { [2 x i8], i32, i8, [3 x i8] }* @main.obj_with_array, i64 0, i32 0, i64 0), i64 12, i1 false) %0 = load i8, i8* getelementptr inbounds (%struct.with_array, %struct.with_array* @array_with_zeroinit, i64 0, i32 2), align 4 - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds (%struct.with_vector, %struct.with_vector* @vector_with_zeroinit, i64 0, i32 0, i64 0), i8* getelementptr inbounds ({ <2 x i8>, i32, i8, [3 x i8] }, { <2 x i8>, i32, i8, [3 x i8] }* @main.obj_with_vector, i64 0, i32 0, i64 0), i64 12, i32 4, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 getelementptr inbounds (%struct.with_vector, %struct.with_vector* @vector_with_zeroinit, i64 0, i32 0, i64 0), i8* align 4 getelementptr inbounds ({ <2 x i8>, i32, i8, [3 x i8] }, { <2 x i8>, i32, i8, [3 x i8] }* @main.obj_with_vector, i64 0, i32 0, i64 0), i64 12, i1 false) %1 = load i8, i8* getelementptr inbounds (%struct.with_vector, %struct.with_vector* @vector_with_zeroinit, i64 0, i32 2), align 4 %conv0 = sext i8 %0 to i32 %conv1 = sext i8 %1 to i32 @@ -27,4 +27,4 @@ entry: ; CHECK: ret i32 1 } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) diff --git a/llvm/test/Transforms/GlobalOpt/crash.ll b/llvm/test/Transforms/GlobalOpt/crash.ll index 8e39931c852..8cfe9ea0570 100644 --- a/llvm/test/Transforms/GlobalOpt/crash.ll +++ b/llvm/test/Transforms/GlobalOpt/crash.ll @@ -60,10 +60,10 @@ entry: @data8 = internal global [8000 x i8] zeroinitializer, align 16 define void @memset_with_strange_user() ssp { - call void @llvm.memset.p0i8.i64(i8* getelementptr inbounds ([8000 x i8], [8000 x i8]* @data8, i64 0, i64 0), i8 undef, i64 ptrtoint (i8* getelementptr ([8000 x i8], [8000 x i8]* @data8, i64 1, i64 sub (i64 0, i64 ptrtoint ([8000 x i8]* @data8 to i64))) to i64), i32 16, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 16 getelementptr inbounds ([8000 x i8], [8000 x i8]* @data8, i64 0, i64 0), i8 undef, i64 ptrtoint (i8* getelementptr ([8000 x i8], [8000 x i8]* @data8, i64 1, i64 sub (i64 0, i64 ptrtoint ([8000 x i8]* @data8 to i64))) to i64), i1 false) ret void } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind ; PR9856 diff --git a/llvm/test/Transforms/GlobalOpt/memcpy.ll b/llvm/test/Transforms/GlobalOpt/memcpy.ll index e47497114b2..0e65f381c1c 100644 --- a/llvm/test/Transforms/GlobalOpt/memcpy.ll +++ b/llvm/test/Transforms/GlobalOpt/memcpy.ll @@ -6,8 +6,8 @@ define void @foo() { %Blah = alloca [58 x i8] %tmp.0 = getelementptr [58 x i8], [58 x i8]* %Blah, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp.0, i8* getelementptr inbounds ([58 x i8], [58 x i8]* @G1, i32 0, i32 0), i32 58, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %tmp.0, i8* align 1 getelementptr inbounds ([58 x i8], [58 x i8]* @G1, i32 0, i32 0), i32 58, i1 false) ret void } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind diff --git a/llvm/test/Transforms/GlobalOpt/memset-null.ll b/llvm/test/Transforms/GlobalOpt/memset-null.ll index 838ac0979e3..32bd21cfc58 100644 --- a/llvm/test/Transforms/GlobalOpt/memset-null.ll +++ b/llvm/test/Transforms/GlobalOpt/memset-null.ll @@ -8,12 +8,12 @@ @a = global %struct.A zeroinitializer, align 4 @llvm.global_ctors = appending global [2 x %0] [%0 { i32 65535, void ()* @_GLOBAL__I_a }, %0 { i32 65535, void ()* @_GLOBAL__I_b }] -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind ; CHECK-NOT: GLOBAL__I_a define internal void @_GLOBAL__I_a() nounwind { entry: - tail call void @llvm.memset.p0i8.i64(i8* bitcast (%struct.A* @a to i8*), i8 0, i64 400, i32 4, i1 false) nounwind + tail call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.A* @a to i8*), i8 0, i64 400, i1 false) nounwind ret void } @@ -24,6 +24,6 @@ entry: define internal void @_GLOBAL__I_b() nounwind { entry: %tmp.i.i.i = load i8*, i8** @y, align 8 - tail call void @llvm.memset.p0i8.i64(i8* %tmp.i.i.i, i8 0, i64 10, i32 1, i1 false) nounwind + tail call void @llvm.memset.p0i8.i64(i8* %tmp.i.i.i, i8 0, i64 10, i1 false) nounwind ret void } diff --git a/llvm/test/Transforms/GlobalOpt/memset.ll b/llvm/test/Transforms/GlobalOpt/memset.ll index 1dfdd642233..90a3db8cb7b 100644 --- a/llvm/test/Transforms/GlobalOpt/memset.ll +++ b/llvm/test/Transforms/GlobalOpt/memset.ll @@ -10,8 +10,8 @@ define void @foo() { %Blah = alloca [58 x i8] %tmp3 = bitcast [58 x i8]* %Blah to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* bitcast ([4 x i32]* @G1 to i8*), i8* %tmp3, i32 16, i32 1, i1 false) - call void @llvm.memset.p0i8.i32(i8* getelementptr inbounds ([58 x i8], [58 x i8]* @G0, i32 0, i32 0), i8 17, i32 58, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* bitcast ([4 x i32]* @G1 to i8*), i8* %tmp3, i32 16, i1 false) + call void @llvm.memset.p0i8.i32(i8* getelementptr inbounds ([58 x i8], [58 x i8]* @G0, i32 0, i32 0), i8 17, i32 58, i1 false) ret void } @@ -21,11 +21,11 @@ define void @foo() { define void @foo_as1() { %Blah = alloca [58 x i8] %tmp3 = bitcast [58 x i8]* %Blah to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* addrspacecast ([4 x i32] addrspace(1)* @G1_as1 to i8*), i8* %tmp3, i32 16, i32 1, i1 false) - call void @llvm.memset.p1i8.i32(i8 addrspace(1)* getelementptr inbounds ([58 x i8], [58 x i8] addrspace(1)* @G0_as1, i32 0, i32 0), i8 17, i32 58, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* addrspacecast ([4 x i32] addrspace(1)* @G1_as1 to i8*), i8* %tmp3, i32 16, i1 false) + call void @llvm.memset.p1i8.i32(i8 addrspace(1)* getelementptr inbounds ([58 x i8], [58 x i8] addrspace(1)* @G0_as1, i32 0, i32 0), i8 17, i32 58, i1 false) ret void } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind -declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind -declare void @llvm.memset.p1i8.i32(i8 addrspace(1)* nocapture, i8, i32, i32, i1) nounwind
\ No newline at end of file +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind +declare void @llvm.memset.p1i8.i32(i8 addrspace(1)* nocapture, i8, i32, i1) nounwind diff --git a/llvm/test/Transforms/InferAddressSpaces/AMDGPU/mem-intrinsics.ll b/llvm/test/Transforms/InferAddressSpaces/AMDGPU/mem-intrinsics.ll index 557a80f1a5d..dd0bbfdc6d2 100644 --- a/llvm/test/Transforms/InferAddressSpaces/AMDGPU/mem-intrinsics.ll +++ b/llvm/test/Transforms/InferAddressSpaces/AMDGPU/mem-intrinsics.ll @@ -1,125 +1,125 @@ ; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -infer-address-spaces %s | FileCheck %s ; CHECK-LABEL: @memset_group_to_flat( -; CHECK: call void @llvm.memset.p3i8.i64(i8 addrspace(3)* %group.ptr, i8 4, i64 32, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 +; CHECK: call void @llvm.memset.p3i8.i64(i8 addrspace(3)* align 4 %group.ptr, i8 4, i64 32, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 define amdgpu_kernel void @memset_group_to_flat(i8 addrspace(3)* %group.ptr, i32 %y) #0 { %cast = addrspacecast i8 addrspace(3)* %group.ptr to i8 addrspace(4)* - call void @llvm.memset.p4i8.i64(i8 addrspace(4)* %cast, i8 4, i64 32, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 + call void @llvm.memset.p4i8.i64(i8 addrspace(4)* align 4 %cast, i8 4, i64 32, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 ret void } ; CHECK-LABEL: @memset_global_to_flat( -; CHECK: call void @llvm.memset.p1i8.i64(i8 addrspace(1)* %global.ptr, i8 4, i64 32, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 +; CHECK: call void @llvm.memset.p1i8.i64(i8 addrspace(1)* align 4 %global.ptr, i8 4, i64 32, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 define amdgpu_kernel void @memset_global_to_flat(i8 addrspace(1)* %global.ptr, i32 %y) #0 { %cast = addrspacecast i8 addrspace(1)* %global.ptr to i8 addrspace(4)* - call void @llvm.memset.p4i8.i64(i8 addrspace(4)* %cast, i8 4, i64 32, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 + call void @llvm.memset.p4i8.i64(i8 addrspace(4)* align 4 %cast, i8 4, i64 32, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 ret void } ; CHECK-LABEL: @memset_group_to_flat_no_md( -; CHECK: call void @llvm.memset.p3i8.i64(i8 addrspace(3)* %group.ptr, i8 4, i64 %size, i32 4, i1 false){{$}} +; CHECK: call void @llvm.memset.p3i8.i64(i8 addrspace(3)* align 4 %group.ptr, i8 4, i64 %size, i1 false){{$}} define amdgpu_kernel void @memset_group_to_flat_no_md(i8 addrspace(3)* %group.ptr, i64 %size) #0 { %cast = addrspacecast i8 addrspace(3)* %group.ptr to i8 addrspace(4)* - call void @llvm.memset.p4i8.i64(i8 addrspace(4)* %cast, i8 4, i64 %size, i32 4, i1 false) + call void @llvm.memset.p4i8.i64(i8 addrspace(4)* align 4 %cast, i8 4, i64 %size, i1 false) ret void } ; CHECK-LABEL: @memset_global_to_flat_no_md( -; CHECK: call void @llvm.memset.p1i8.i64(i8 addrspace(1)* %global.ptr, i8 4, i64 %size, i32 4, i1 false){{$}} +; CHECK: call void @llvm.memset.p1i8.i64(i8 addrspace(1)* align 4 %global.ptr, i8 4, i64 %size, i1 false){{$}} define amdgpu_kernel void @memset_global_to_flat_no_md(i8 addrspace(1)* %global.ptr, i64 %size) #0 { %cast = addrspacecast i8 addrspace(1)* %global.ptr to i8 addrspace(4)* - call void @llvm.memset.p4i8.i64(i8 addrspace(4)* %cast, i8 4, i64 %size, i32 4, i1 false) + call void @llvm.memset.p4i8.i64(i8 addrspace(4)* align 4 %cast, i8 4, i64 %size, i1 false) ret void } ; CHECK-LABEL: @memcpy_flat_to_flat_replace_src_with_group( -; CHCK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* %dest, i8 addrspace(3)* %src.group.ptr, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 +; CHCK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* align 4 %dest, i8 addrspace(3)* align 4 %src.group.ptr, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 define amdgpu_kernel void @memcpy_flat_to_flat_replace_src_with_group(i8 addrspace(4)* %dest, i8 addrspace(3)* %src.group.ptr, i64 %size) #0 { %cast.src = addrspacecast i8 addrspace(3)* %src.group.ptr to i8 addrspace(4)* - call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* %dest, i8 addrspace(4)* %cast.src, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 + call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %dest, i8 addrspace(4)* align 4 %cast.src, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 ret void } ; CHECK-LABEL: @memcpy_flat_to_flat_replace_dest_with_group( -; CHECK: call void @llvm.memcpy.p3i8.p4i8.i64(i8 addrspace(3)* %dest.group.ptr, i8 addrspace(4)* %src.ptr, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 +; CHECK: call void @llvm.memcpy.p3i8.p4i8.i64(i8 addrspace(3)* align 4 %dest.group.ptr, i8 addrspace(4)* align 4 %src.ptr, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 define amdgpu_kernel void @memcpy_flat_to_flat_replace_dest_with_group(i8 addrspace(3)* %dest.group.ptr, i8 addrspace(4)* %src.ptr, i64 %size) #0 { %cast.dest = addrspacecast i8 addrspace(3)* %dest.group.ptr to i8 addrspace(4)* - call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* %cast.dest, i8 addrspace(4)* %src.ptr, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 + call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %cast.dest, i8 addrspace(4)* align 4 %src.ptr, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 ret void } ; CHECK-LABEL: @memcpy_flat_to_flat_replace_dest_src_with_group( -; CHECK: call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* %src.group.ptr, i8 addrspace(3)* %src.group.ptr, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 +; CHECK: call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* align 4 %src.group.ptr, i8 addrspace(3)* align 4 %src.group.ptr, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 define amdgpu_kernel void @memcpy_flat_to_flat_replace_dest_src_with_group(i8 addrspace(3)* %dest.group.ptr, i8 addrspace(3)* %src.group.ptr, i64 %size) #0 { %cast.src = addrspacecast i8 addrspace(3)* %src.group.ptr to i8 addrspace(4)* %cast.dest = addrspacecast i8 addrspace(3)* %src.group.ptr to i8 addrspace(4)* - call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* %cast.dest, i8 addrspace(4)* %cast.src, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 + call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %cast.dest, i8 addrspace(4)* align 4 %cast.src, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 ret void } ; CHECK-LABEL: @memcpy_flat_to_flat_replace_dest_group_src_global( -; CHECK: call void @llvm.memcpy.p3i8.p1i8.i64(i8 addrspace(3)* %dest.group.ptr, i8 addrspace(1)* %src.global.ptr, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 +; CHECK: call void @llvm.memcpy.p3i8.p1i8.i64(i8 addrspace(3)* align 4 %dest.group.ptr, i8 addrspace(1)* align 4 %src.global.ptr, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 define amdgpu_kernel void @memcpy_flat_to_flat_replace_dest_group_src_global(i8 addrspace(3)* %dest.group.ptr, i8 addrspace(1)* %src.global.ptr, i64 %size) #0 { %cast.src = addrspacecast i8 addrspace(1)* %src.global.ptr to i8 addrspace(4)* %cast.dest = addrspacecast i8 addrspace(3)* %dest.group.ptr to i8 addrspace(4)* - call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* %cast.dest, i8 addrspace(4)* %cast.src, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 + call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %cast.dest, i8 addrspace(4)* align 4 %cast.src, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 ret void } ; CHECK-LABEL: @memcpy_group_to_flat_replace_dest_global( -; CHECK: call void @llvm.memcpy.p1i8.p3i8.i32(i8 addrspace(1)* %dest.global.ptr, i8 addrspace(3)* %src.group.ptr, i32 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 +; CHECK: call void @llvm.memcpy.p1i8.p3i8.i32(i8 addrspace(1)* align 4 %dest.global.ptr, i8 addrspace(3)* align 4 %src.group.ptr, i32 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 define amdgpu_kernel void @memcpy_group_to_flat_replace_dest_global(i8 addrspace(1)* %dest.global.ptr, i8 addrspace(3)* %src.group.ptr, i32 %size) #0 { %cast.dest = addrspacecast i8 addrspace(1)* %dest.global.ptr to i8 addrspace(4)* - call void @llvm.memcpy.p4i8.p3i8.i32(i8 addrspace(4)* %cast.dest, i8 addrspace(3)* %src.group.ptr, i32 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 + call void @llvm.memcpy.p4i8.p3i8.i32(i8 addrspace(4)* align 4 %cast.dest, i8 addrspace(3)* align 4 %src.group.ptr, i32 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 ret void } ; CHECK-LABEL: @memcpy_flat_to_flat_replace_src_with_group_tbaa_struct( -; CHECK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* %dest, i8 addrspace(3)* %src.group.ptr, i64 %size, i32 4, i1 false), !tbaa.struct !7 +; CHECK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* align 4 %dest, i8 addrspace(3)* align 4 %src.group.ptr, i64 %size, i1 false), !tbaa.struct !7 define amdgpu_kernel void @memcpy_flat_to_flat_replace_src_with_group_tbaa_struct(i8 addrspace(4)* %dest, i8 addrspace(3)* %src.group.ptr, i64 %size) #0 { %cast.src = addrspacecast i8 addrspace(3)* %src.group.ptr to i8 addrspace(4)* - call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* %dest, i8 addrspace(4)* %cast.src, i64 %size, i32 4, i1 false), !tbaa.struct !7 + call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %dest, i8 addrspace(4)* align 4 %cast.src, i64 %size, i1 false), !tbaa.struct !7 ret void } ; CHECK-LABEL: @memcpy_flat_to_flat_replace_src_with_group_no_md( -; CHECK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* %dest, i8 addrspace(3)* %src.group.ptr, i64 %size, i32 4, i1 false){{$}} +; CHECK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* align 4 %dest, i8 addrspace(3)* align 4 %src.group.ptr, i64 %size, i1 false){{$}} define amdgpu_kernel void @memcpy_flat_to_flat_replace_src_with_group_no_md(i8 addrspace(4)* %dest, i8 addrspace(3)* %src.group.ptr, i64 %size) #0 { %cast.src = addrspacecast i8 addrspace(3)* %src.group.ptr to i8 addrspace(4)* - call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* %dest, i8 addrspace(4)* %cast.src, i64 %size, i32 4, i1 false) + call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %dest, i8 addrspace(4)* align 4 %cast.src, i64 %size, i1 false) ret void } ; CHECK-LABEL: @multiple_memcpy_flat_to_flat_replace_src_with_group_no_md( -; CHECK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* %dest0, i8 addrspace(3)* %src.group.ptr, i64 %size, i32 4, i1 false){{$}} -; CHECK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* %dest1, i8 addrspace(3)* %src.group.ptr, i64 %size, i32 4, i1 false){{$}} +; CHECK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* align 4 %dest0, i8 addrspace(3)* align 4 %src.group.ptr, i64 %size, i1 false){{$}} +; CHECK: call void @llvm.memcpy.p4i8.p3i8.i64(i8 addrspace(4)* align 4 %dest1, i8 addrspace(3)* align 4 %src.group.ptr, i64 %size, i1 false){{$}} define amdgpu_kernel void @multiple_memcpy_flat_to_flat_replace_src_with_group_no_md(i8 addrspace(4)* %dest0, i8 addrspace(4)* %dest1, i8 addrspace(3)* %src.group.ptr, i64 %size) #0 { %cast.src = addrspacecast i8 addrspace(3)* %src.group.ptr to i8 addrspace(4)* - call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* %dest0, i8 addrspace(4)* %cast.src, i64 %size, i32 4, i1 false) - call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* %dest1, i8 addrspace(4)* %cast.src, i64 %size, i32 4, i1 false) + call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %dest0, i8 addrspace(4)* align 4 %cast.src, i64 %size, i1 false) + call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %dest1, i8 addrspace(4)* align 4 %cast.src, i64 %size, i1 false) ret void } ; Check for iterator problems if the pointer has 2 uses in the same call ; CHECK-LABEL: @memcpy_group_flat_to_flat_self( -; CHECK: call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* %group.ptr, i8 addrspace(3)* %group.ptr, i64 32, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 +; CHECK: call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* align 4 %group.ptr, i8 addrspace(3)* align 4 %group.ptr, i64 32, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 define amdgpu_kernel void @memcpy_group_flat_to_flat_self(i8 addrspace(3)* %group.ptr) #0 { %cast = addrspacecast i8 addrspace(3)* %group.ptr to i8 addrspace(4)* - call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* %cast, i8 addrspace(4)* %cast, i64 32, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 + call void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %cast, i8 addrspace(4)* align 4 %cast, i64 32, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 ret void } ; CHECK-LABEL: @memmove_flat_to_flat_replace_src_with_group( -; CHECK: call void @llvm.memmove.p4i8.p3i8.i64(i8 addrspace(4)* %dest, i8 addrspace(3)* %src.group.ptr, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 +; CHECK: call void @llvm.memmove.p4i8.p3i8.i64(i8 addrspace(4)* align 4 %dest, i8 addrspace(3)* align 4 %src.group.ptr, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 define amdgpu_kernel void @memmove_flat_to_flat_replace_src_with_group(i8 addrspace(4)* %dest, i8 addrspace(3)* %src.group.ptr, i64 %size) #0 { %cast.src = addrspacecast i8 addrspace(3)* %src.group.ptr to i8 addrspace(4)* - call void @llvm.memmove.p4i8.p4i8.i64(i8 addrspace(4)* %dest, i8 addrspace(4)* %cast.src, i64 %size, i32 4, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 + call void @llvm.memmove.p4i8.p4i8.i64(i8 addrspace(4)* align 4 %dest, i8 addrspace(4)* align 4 %cast.src, i64 %size, i1 false), !tbaa !0, !alias.scope !3, !noalias !4 ret void } -declare void @llvm.memset.p4i8.i64(i8 addrspace(4)* nocapture writeonly, i8, i64, i32, i1) #1 -declare void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* nocapture writeonly, i8 addrspace(4)* nocapture readonly, i64, i32, i1) #1 -declare void @llvm.memcpy.p4i8.p3i8.i32(i8 addrspace(4)* nocapture writeonly, i8 addrspace(3)* nocapture readonly, i32, i32, i1) #1 -declare void @llvm.memmove.p4i8.p4i8.i64(i8 addrspace(4)* nocapture writeonly, i8 addrspace(4)* nocapture readonly, i64, i32, i1) #1 +declare void @llvm.memset.p4i8.i64(i8 addrspace(4)* nocapture writeonly, i8, i64, i1) #1 +declare void @llvm.memcpy.p4i8.p4i8.i64(i8 addrspace(4)* nocapture writeonly, i8 addrspace(4)* nocapture readonly, i64, i1) #1 +declare void @llvm.memcpy.p4i8.p3i8.i32(i8 addrspace(4)* nocapture writeonly, i8 addrspace(3)* nocapture readonly, i32, i1) #1 +declare void @llvm.memmove.p4i8.p4i8.i64(i8 addrspace(4)* nocapture writeonly, i8 addrspace(4)* nocapture readonly, i64, i1) #1 attributes #0 = { nounwind } attributes #1 = { argmemonly nounwind } @@ -131,4 +131,4 @@ attributes #1 = { argmemonly nounwind } !4 = !{!5} !5 = distinct !{!5, !6, !"some scope"} !6 = distinct !{!6, !"some domain"} -!7 = !{i64 0, i64 8, null}
\ No newline at end of file +!7 = !{i64 0, i64 8, null} diff --git a/llvm/test/Transforms/InferAddressSpaces/AMDGPU/volatile.ll b/llvm/test/Transforms/InferAddressSpaces/AMDGPU/volatile.ll index 79bf92610a8..49467cea930 100644 --- a/llvm/test/Transforms/InferAddressSpaces/AMDGPU/volatile.ll +++ b/llvm/test/Transforms/InferAddressSpaces/AMDGPU/volatile.ll @@ -118,23 +118,23 @@ define { i32, i1 } @volatile_cmpxchg_group_to_flat(i32 addrspace(3)* %group.ptr, ; FIXME: Shouldn't be losing names ; CHECK-LABEL: @volatile_memset_group_to_flat( ; CHECK: addrspacecast i8 addrspace(3)* %group.ptr to i8 addrspace(4)* -; CHECK: call void @llvm.memset.p4i8.i64(i8 addrspace(4)* %1, i8 4, i64 32, i32 4, i1 true) +; CHECK: call void @llvm.memset.p4i8.i64(i8 addrspace(4)* align 4 %1, i8 4, i64 32, i1 true) define amdgpu_kernel void @volatile_memset_group_to_flat(i8 addrspace(3)* %group.ptr, i32 %y) #0 { %cast = addrspacecast i8 addrspace(3)* %group.ptr to i8 addrspace(4)* - call void @llvm.memset.p4i8.i64(i8 addrspace(4)* %cast, i8 4, i64 32, i32 4, i1 true) + call void @llvm.memset.p4i8.i64(i8 addrspace(4)* align 4 %cast, i8 4, i64 32, i1 true) ret void } ; CHECK-LABEL: @volatile_memset_global_to_flat( ; CHECK: addrspacecast i8 addrspace(1)* %global.ptr to i8 addrspace(4)* -; CHECK: call void @llvm.memset.p4i8.i64(i8 addrspace(4)* %1, i8 4, i64 32, i32 4, i1 true) +; CHECK: call void @llvm.memset.p4i8.i64(i8 addrspace(4)* align 4 %1, i8 4, i64 32, i1 true) define amdgpu_kernel void @volatile_memset_global_to_flat(i8 addrspace(1)* %global.ptr, i32 %y) #0 { %cast = addrspacecast i8 addrspace(1)* %global.ptr to i8 addrspace(4)* - call void @llvm.memset.p4i8.i64(i8 addrspace(4)* %cast, i8 4, i64 32, i32 4, i1 true) + call void @llvm.memset.p4i8.i64(i8 addrspace(4)* align 4 %cast, i8 4, i64 32, i1 true) ret void } -declare void @llvm.memset.p4i8.i64(i8 addrspace(4)* nocapture writeonly, i8, i64, i32, i1) #1 +declare void @llvm.memset.p4i8.i64(i8 addrspace(4)* nocapture writeonly, i8, i64, i1) #1 attributes #0 = { nounwind } attributes #1 = { argmemonly nounwind } diff --git a/llvm/test/Transforms/Inline/alloca-dbgdeclare.ll b/llvm/test/Transforms/Inline/alloca-dbgdeclare.ll index 9fb2a6940d3..b45f38c7ec6 100644 --- a/llvm/test/Transforms/Inline/alloca-dbgdeclare.ll +++ b/llvm/test/Transforms/Inline/alloca-dbgdeclare.ll @@ -33,7 +33,7 @@ declare void @_Z3fn31A(%struct.A* nocapture readonly) #0 declare void @llvm.dbg.declare(metadata, metadata, metadata) #1 ; Function Attrs: argmemonly nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #2 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #2 ; Function Attrs: nounwind define void @_Z3fn4v() #0 !dbg !22 { @@ -48,14 +48,14 @@ entry: %agg.tmp.sroa.0.0.copyload = load i32, i32* getelementptr inbounds (%struct.A, %struct.A* @b, i64 0, i32 0), align 8, !dbg !33 tail call void @llvm.dbg.value(metadata i32 %agg.tmp.sroa.0.0.copyload, metadata !25, metadata !34), !dbg !31 %agg.tmp.sroa.3.0..sroa_idx = getelementptr inbounds [20 x i8], [20 x i8]* %agg.tmp.sroa.3, i64 0, i64 0, !dbg !33 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %agg.tmp.sroa.3.0..sroa_idx, i8* getelementptr (i8, i8* bitcast (%struct.A* @b to i8*), i64 4), i64 20, i32 4, i1 false), !dbg !33 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %agg.tmp.sroa.3.0..sroa_idx, i8* align 4 getelementptr (i8, i8* bitcast (%struct.A* @b to i8*), i64 4), i64 20, i1 false), !dbg !33 tail call void @llvm.dbg.declare(metadata %struct.A* undef, metadata !25, metadata !35) #0, !dbg !31 %tobool.i = icmp eq i32 %agg.tmp.sroa.0.0.copyload, 0, !dbg !36 br i1 %tobool.i, label %_Z3fn31A.exit, label %if.then.i, !dbg !38 if.then.i: ; preds = %entry store i32 %agg.tmp.sroa.0.0.copyload, i32* getelementptr inbounds (%struct.A, %struct.A* @a, i64 0, i32 0), align 8, !dbg !39 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr (i8, i8* bitcast (%struct.A* @a to i8*), i64 4), i8* %agg.tmp.sroa.3.0..sroa_idx, i64 20, i32 4, i1 false), !dbg !39 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 getelementptr (i8, i8* bitcast (%struct.A* @a to i8*), i64 4), i8* align 4 %agg.tmp.sroa.3.0..sroa_idx, i64 20, i1 false), !dbg !39 br label %_Z3fn31A.exit, !dbg !39 _Z3fn31A.exit: ; preds = %if.then.i, %entry diff --git a/llvm/test/Transforms/Inline/inline-invoke-tail.ll b/llvm/test/Transforms/Inline/inline-invoke-tail.ll index 5ae27bc0fe2..d85ef50fff8 100644 --- a/llvm/test/Transforms/Inline/inline-invoke-tail.ll +++ b/llvm/test/Transforms/Inline/inline-invoke-tail.ll @@ -6,7 +6,7 @@ define internal void @foo(i32* %p, i32* %q) { entry: %pp = bitcast i32* %p to i8* %qq = bitcast i32* %q to i8* - tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %pp, i8* %qq, i32 4, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %pp, i8* %qq, i32 4, i1 false) ret void } @@ -37,4 +37,4 @@ lpad: declare i32 @__gxx_personality_v0(...) -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind diff --git a/llvm/test/Transforms/Inline/inline-vla.ll b/llvm/test/Transforms/Inline/inline-vla.ll index fd4510c4f09..88dfc2be87f 100644 --- a/llvm/test/Transforms/Inline/inline-vla.ll +++ b/llvm/test/Transforms/Inline/inline-vla.ll @@ -22,13 +22,13 @@ define internal fastcc void @memcpy2(i8* nocapture %dst, i8* nocapture readonly entry: %vla = alloca i64, i64 %size, align 16 %0 = bitcast i64* %vla to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %src, i64 %size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %0, i64 %size, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %src, i64 %size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %0, i64 %size, i1 false) ret void } ; Function Attrs: nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) #2 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) #2 attributes #0 = { nounwind ssp uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" } attributes #1 = { inlinehint nounwind ssp uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" } diff --git a/llvm/test/Transforms/Inline/noalias-calls.ll b/llvm/test/Transforms/Inline/noalias-calls.ll index 56d5c6dc081..f4fe6fe9ff8 100644 --- a/llvm/test/Transforms/Inline/noalias-calls.ll +++ b/llvm/test/Transforms/Inline/noalias-calls.ll @@ -2,17 +2,17 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) #0 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) #0 declare void @hey() #0 define void @hello(i8* noalias nocapture %a, i8* noalias nocapture readonly %c, i8* nocapture %b) #1 { entry: %l = alloca i8, i32 512, align 1 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 16, i32 16, i1 0) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %c, i64 16, i32 16, i1 0) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %c, i64 16, i32 16, i1 0) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %a, i8* align 16 %b, i64 16, i1 0) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %b, i8* align 16 %c, i64 16, i1 0) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %a, i8* align 16 %c, i64 16, i1 0) call void @hey() - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %l, i8* %c, i64 16, i32 16, i1 0) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %l, i8* align 16 %c, i64 16, i1 0) ret void } @@ -24,11 +24,11 @@ entry: ; CHECK: define void @foo(i8* nocapture %a, i8* nocapture readonly %c, i8* nocapture %b) #2 { ; CHECK: entry: -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 16, i32 16, i1 false) #1, !noalias !0 -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %c, i64 16, i32 16, i1 false) #1, !noalias !3 -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %c, i64 16, i32 16, i1 false) #1, !alias.scope !5 +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %a, i8* align 16 %b, i64 16, i1 false) #1, !noalias !0 +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %b, i8* align 16 %c, i64 16, i1 false) #1, !noalias !3 +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %a, i8* align 16 %c, i64 16, i1 false) #1, !alias.scope !5 ; CHECK: call void @hey() #1, !noalias !5 -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %{{.*}}, i8* %c, i64 16, i32 16, i1 false) #1, !noalias !3 +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %{{.*}}, i8* align 16 %c, i64 16, i1 false) #1, !noalias !3 ; CHECK: ret void ; CHECK: } diff --git a/llvm/test/Transforms/InstCombine/2007-10-10-EliminateMemCpy.ll b/llvm/test/Transforms/InstCombine/2007-10-10-EliminateMemCpy.ll index 67a94e5c8cc..427d0e3b0d1 100644 --- a/llvm/test/Transforms/InstCombine/2007-10-10-EliminateMemCpy.ll +++ b/llvm/test/Transforms/InstCombine/2007-10-10-EliminateMemCpy.ll @@ -10,11 +10,11 @@ entry: store i8* %P, i8** %P_addr %tmp = load i8*, i8** %P_addr, align 4 %tmp1 = getelementptr [4 x i8], [4 x i8]* @.str, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp, i8* %tmp1, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp, i8* %tmp1, i32 4, i1 false) br label %return return: ; preds = %entry ret void } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind diff --git a/llvm/test/Transforms/InstCombine/2009-02-20-InstCombine-SROA.ll b/llvm/test/Transforms/InstCombine/2009-02-20-InstCombine-SROA.ll index 35cd3affec6..d8c8e1e0202 100644 --- a/llvm/test/Transforms/InstCombine/2009-02-20-InstCombine-SROA.ll +++ b/llvm/test/Transforms/InstCombine/2009-02-20-InstCombine-SROA.ll @@ -64,7 +64,7 @@ entry: %val.i = load i32*, i32** %elt.i %tmp.i = bitcast %"struct.std::bidirectional_iterator_tag"* %unnamed_arg.i to i8* %tmp9.i = bitcast %"struct.std::bidirectional_iterator_tag"* %2 to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp.i, i8* %tmp9.i, i64 1, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp.i, i8* %tmp9.i, i64 1, i1 false) %26 = getelementptr %"struct.__gnu_cxx::__normal_iterator<int*,std::vector<int, std::allocator<int> > >", %"struct.__gnu_cxx::__normal_iterator<int*,std::vector<int, std::allocator<int> > >"* %__first_addr.i.i, i32 0, i32 0 store i32* %val.i, i32** %26 %27 = getelementptr %"struct.__gnu_cxx::__normal_iterator<int*,std::vector<int, std::allocator<int> > >", %"struct.__gnu_cxx::__normal_iterator<int*,std::vector<int, std::allocator<int> > >"* %__last_addr.i.i, i32 0, i32 0 @@ -276,4 +276,4 @@ return: ; preds = %_ZSt4findIN9__gnu_c ret i32* %tmp14 } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind diff --git a/llvm/test/Transforms/InstCombine/addrspacecast.ll b/llvm/test/Transforms/InstCombine/addrspacecast.ll index e375a7aa34b..6caefb166db 100644 --- a/llvm/test/Transforms/InstCombine/addrspacecast.ll +++ b/llvm/test/Transforms/InstCombine/addrspacecast.ll @@ -3,9 +3,9 @@ target datalayout = "e-p:64:64:64-p1:32:32:32-p2:16:16:16-n8:16:32:64" -declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p1i8.i32(i8*, i8 addrspace(1)*, i32, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p2i8.i32(i8*, i8 addrspace(2)*, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p1i8.i32(i8*, i8 addrspace(1)*, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p2i8.i32(i8*, i8 addrspace(2)*, i32, i1) nounwind define i32* @combine_redundant_addrspacecast(i32 addrspace(1)* %x) nounwind { @@ -127,7 +127,7 @@ declare void @foo(i8*) nounwind define i32 @memcpy_addrspacecast() nounwind { entry: %alloca = alloca i8, i32 48 - call void @llvm.memcpy.p0i8.p1i8.i32(i8* %alloca, i8 addrspace(1)* addrspacecast (i8 addrspace(2)* getelementptr inbounds ([60 x i8], [60 x i8] addrspace(2)* @const_array, i16 0, i16 4) to i8 addrspace(1)*), i32 48, i32 4, i1 false) nounwind + call void @llvm.memcpy.p0i8.p1i8.i32(i8* align 4 %alloca, i8 addrspace(1)* align 4 addrspacecast (i8 addrspace(2)* getelementptr inbounds ([60 x i8], [60 x i8] addrspace(2)* @const_array, i16 0, i16 4) to i8 addrspace(1)*), i32 48, i1 false) nounwind br label %loop.body loop.body: diff --git a/llvm/test/Transforms/InstCombine/align-addr.ll b/llvm/test/Transforms/InstCombine/align-addr.ll index ab0ae390b14..d92daddd761 100644 --- a/llvm/test/Transforms/InstCombine/align-addr.ll +++ b/llvm/test/Transforms/InstCombine/align-addr.ll @@ -80,7 +80,7 @@ define double @test2(double* %p, double %n) nounwind { ret double %t } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind declare void @use(i8*) @@ -90,8 +90,8 @@ define void @test3(%struct.s* sret %a4) { ; Check that the alignment is bumped up the alignment of the sret type. ; CHECK-LABEL: @test3( %a4.cast = bitcast %struct.s* %a4 to i8* - call void @llvm.memset.p0i8.i64(i8* %a4.cast, i8 0, i64 16, i32 1, i1 false) -; CHECK: call void @llvm.memset.p0i8.i64(i8* %a4.cast, i8 0, i64 16, i32 4, i1 false) + call void @llvm.memset.p0i8.i64(i8* %a4.cast, i8 0, i64 16, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %a4.cast, i8 0, i64 16, i1 false) call void @use(i8* %a4.cast) ret void } diff --git a/llvm/test/Transforms/InstCombine/alloca.ll b/llvm/test/Transforms/InstCombine/alloca.ll index 490830af2d8..c1ec9b3d00e 100644 --- a/llvm/test/Transforms/InstCombine/alloca.ll +++ b/llvm/test/Transforms/InstCombine/alloca.ll @@ -108,11 +108,11 @@ define void @test7() { entry: %0 = alloca %real_type, align 4 %1 = bitcast %real_type* %0 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* bitcast (%opaque_type* @opaque_global to i8*), i32 8, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* bitcast (%opaque_type* @opaque_global to i8*), i32 8, i1 false) ret void } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind ; Check that the GEP indices use the pointer size, or 64 if unknown @@ -148,7 +148,7 @@ entry: %0 = getelementptr inbounds <{ %struct_type }>, <{ %struct_type }>* %argmem, i32 0, i32 0 %1 = bitcast %struct_type* %0 to i8* %2 = bitcast %struct_type* %a to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %1, i8* %2, i32 8, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %1, i8* align 4 %2, i32 8, i1 false) call void @test9_aux(<{ %struct_type }>* inalloca %argmem) call void @llvm.stackrestore(i8* %inalloca.save) ret void diff --git a/llvm/test/Transforms/InstCombine/call-intrinsics.ll b/llvm/test/Transforms/InstCombine/call-intrinsics.ll index 3e37a71e1bf..1f327b99e9c 100644 --- a/llvm/test/Transforms/InstCombine/call-intrinsics.ll +++ b/llvm/test/Transforms/InstCombine/call-intrinsics.ll @@ -3,17 +3,17 @@ @X = global i8 0 ; <i8*> [#uses=3] @Y = global i8 12 ; <i8*> [#uses=2] -declare void @llvm.memmove.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) +declare void @llvm.memmove.p0i8.p0i8.i32(i8*, i8*, i32, i1) -declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i1) -declare void @llvm.memset.p0i8.i32(i8*, i8, i32, i32, i1) +declare void @llvm.memset.p0i8.i32(i8*, i8, i32, i1) define void @zero_byte_test() { ; These process zero bytes, so they are a noop. - call void @llvm.memmove.p0i8.p0i8.i32( i8* @X, i8* @Y, i32 0, i32 128, i1 false ) - call void @llvm.memcpy.p0i8.p0i8.i32( i8* @X, i8* @Y, i32 0, i32 128, i1 false ) - call void @llvm.memset.p0i8.i32( i8* @X, i8 123, i32 0, i32 128, i1 false ) + call void @llvm.memmove.p0i8.p0i8.i32(i8* align 128 @X, i8* align 128 @Y, i32 0, i1 false ) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 128 @X, i8* align 128 @Y, i32 0, i1 false ) + call void @llvm.memset.p0i8.i32(i8* align 128 @X, i8 123, i32 0, i1 false ) ret void } diff --git a/llvm/test/Transforms/InstCombine/malloc-free-delete.ll b/llvm/test/Transforms/InstCombine/malloc-free-delete.ll index 7a5c7457e36..d2cf5d02fe3 100644 --- a/llvm/test/Transforms/InstCombine/malloc-free-delete.ll +++ b/llvm/test/Transforms/InstCombine/malloc-free-delete.ll @@ -27,9 +27,9 @@ define i1 @foo() { declare void @llvm.lifetime.start.p0i8(i64, i8*) declare void @llvm.lifetime.end.p0i8(i64, i8*) declare i64 @llvm.objectsize.i64(i8*, i1) -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind -declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind -declare void @llvm.memset.p0i8.i32(i8*, i8, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memset.p0i8.i32(i8*, i8, i32, i1) nounwind define void @test3(i8* %src) { ; CHECK-LABEL: @test3( @@ -39,9 +39,9 @@ define void @test3(i8* %src) { call void @llvm.lifetime.end.p0i8(i64 10, i8* %a) %size = call i64 @llvm.objectsize.i64(i8* %a, i1 true) store i8 42, i8* %a - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %src, i32 32, i32 1, i1 false) - call void @llvm.memmove.p0i8.p0i8.i32(i8* %a, i8* %src, i32 32, i32 1, i1 false) - call void @llvm.memset.p0i8.i32(i8* %a, i8 5, i32 32, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %src, i32 32, i1 false) + call void @llvm.memmove.p0i8.p0i8.i32(i8* %a, i8* %src, i32 32, i1 false) + call void @llvm.memset.p0i8.i32(i8* %a, i8 5, i32 32, i1 false) %alloc2 = call noalias i8* @calloc(i32 5, i32 7) nounwind %z = icmp ne i8* %alloc2, null ret void @@ -82,12 +82,12 @@ define void @test5(i8* %ptr, i8** %esc) { %e = call i8* @malloc(i32 700) %f = call i8* @malloc(i32 700) %g = call i8* @malloc(i32 700) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %a, i32 32, i32 1, i1 false) - call void @llvm.memmove.p0i8.p0i8.i32(i8* %ptr, i8* %b, i32 32, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %a, i32 32, i1 false) + call void @llvm.memmove.p0i8.p0i8.i32(i8* %ptr, i8* %b, i32 32, i1 false) store i8* %c, i8** %esc - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %ptr, i32 32, i32 1, i1 true) - call void @llvm.memmove.p0i8.p0i8.i32(i8* %e, i8* %ptr, i32 32, i32 1, i1 true) - call void @llvm.memset.p0i8.i32(i8* %f, i8 5, i32 32, i32 1, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %ptr, i32 32, i1 true) + call void @llvm.memmove.p0i8.p0i8.i32(i8* %e, i8* %ptr, i32 32, i1 true) + call void @llvm.memset.p0i8.i32(i8* %f, i8 5, i32 32, i1 true) store volatile i8 4, i8* %g ret void } diff --git a/llvm/test/Transforms/InstCombine/mem-par-metadata-memcpy.ll b/llvm/test/Transforms/InstCombine/mem-par-metadata-memcpy.ll index 6b482b17ee7..82231bae981 100644 --- a/llvm/test/Transforms/InstCombine/mem-par-metadata-memcpy.ll +++ b/llvm/test/Transforms/InstCombine/mem-par-metadata-memcpy.ll @@ -36,7 +36,7 @@ for.body: ; preds = %for.cond %arrayidx = getelementptr inbounds i8, i8* %out, i64 %i.0 %add = add nsw i64 %i.0, %size %arrayidx1 = getelementptr inbounds i8, i8* %out, i64 %add - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arrayidx, i8* %arrayidx1, i64 2, i32 1, i1 false), !llvm.mem.parallel_loop_access !1 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arrayidx, i8* %arrayidx1, i64 2, i1 false), !llvm.mem.parallel_loop_access !1 br label %for.inc for.inc: ; preds = %for.body @@ -48,7 +48,7 @@ for.end: ; preds = %for.cond } ; Function Attrs: argmemonly nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #1 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #1 attributes #0 = { nounwind uwtable "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" } attributes #1 = { argmemonly nounwind } diff --git a/llvm/test/Transforms/InstCombine/memcpy-1.ll b/llvm/test/Transforms/InstCombine/memcpy-1.ll index b373ea2619f..dceb7c39286 100644 --- a/llvm/test/Transforms/InstCombine/memcpy-1.ll +++ b/llvm/test/Transforms/InstCombine/memcpy-1.ll @@ -10,7 +10,7 @@ declare i8* @memcpy(i8*, i8*, i32) define i8* @test_simplify1(i8* %mem1, i8* %mem2, i32 %size) { ; CHECK-LABEL: @test_simplify1( -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %mem1, i8* %mem2, i32 %size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %mem1, i8* align 1 %mem2, i32 %size, i1 false) ; CHECK-NEXT: ret i8* %mem1 ; %ret = call i8* @memcpy(i8* %mem1, i8* %mem2, i32 %size) diff --git a/llvm/test/Transforms/InstCombine/memcpy-addrspace.ll b/llvm/test/Transforms/InstCombine/memcpy-addrspace.ll index f0018c23642..18615889dd8 100644 --- a/llvm/test/Transforms/InstCombine/memcpy-addrspace.ll +++ b/llvm/test/Transforms/InstCombine/memcpy-addrspace.ll @@ -13,7 +13,7 @@ define void @test_load(i32 addrspace(1)* %out, i64 %x) { entry: %data = alloca [8 x i32], align 4 %0 = bitcast [8 x i32]* %data to i8* - call void @llvm.memcpy.p0i8.p2i8.i64(i8* %0, i8 addrspace(2)* bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p2i8.i64(i8* align 4 %0, i8 addrspace(2)* align 4 bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i1 false) %arrayidx = getelementptr inbounds [8 x i32], [8 x i32]* %data, i64 0, i64 %x %1 = load i32, i32* %arrayidx, align 4 %arrayidx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %x @@ -32,7 +32,7 @@ define void @test_load_bitcast_chain(i32 addrspace(1)* %out, i64 %x) { entry: %data = alloca [8 x i32], align 4 %0 = bitcast [8 x i32]* %data to i8* - call void @llvm.memcpy.p0i8.p2i8.i64(i8* %0, i8 addrspace(2)* bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p2i8.i64(i8* align 4 %0, i8 addrspace(2)* align 4 bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i1 false) %1 = bitcast i8* %0 to i32* %arrayidx = getelementptr inbounds i32, i32* %1, i64 %x %2 = load i32, i32* %arrayidx, align 4 @@ -50,7 +50,7 @@ define void @test_call(i32 addrspace(1)* %out, i64 %x) { entry: %data = alloca [8 x i32], align 4 %0 = bitcast [8 x i32]* %data to i8* - call void @llvm.memcpy.p0i8.p2i8.i64(i8* %0, i8 addrspace(2)* bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p2i8.i64(i8* align 4 %0, i8 addrspace(2)* align 4 bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i1 false) %arrayidx = getelementptr inbounds [8 x i32], [8 x i32]* %data, i64 0, i64 %x %1 = call i32 @foo(i32* %arrayidx) %arrayidx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %x @@ -69,7 +69,7 @@ define void @test_load_and_call(i32 addrspace(1)* %out, i64 %x, i64 %y) { entry: %data = alloca [8 x i32], align 4 %0 = bitcast [8 x i32]* %data to i8* - call void @llvm.memcpy.p0i8.p2i8.i64(i8* %0, i8 addrspace(2)* bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p2i8.i64(i8* align 4 %0, i8 addrspace(2)* align 4 bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i1 false) %arrayidx = getelementptr inbounds [8 x i32], [8 x i32]* %data, i64 0, i64 %x %1 = load i32, i32* %arrayidx, align 4 %arrayidx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %x @@ -81,5 +81,5 @@ entry: } -declare void @llvm.memcpy.p0i8.p2i8.i64(i8* nocapture writeonly, i8 addrspace(2)* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p2i8.i64(i8* nocapture writeonly, i8 addrspace(2)* nocapture readonly, i64, i1) declare i32 @foo(i32* %x) diff --git a/llvm/test/Transforms/InstCombine/memcpy-from-global.ll b/llvm/test/Transforms/InstCombine/memcpy-from-global.ll index cbd21389e90..ce1aa2aba30 100644 --- a/llvm/test/Transforms/InstCombine/memcpy-from-global.ll +++ b/llvm/test/Transforms/InstCombine/memcpy-from-global.ll @@ -6,7 +6,7 @@ define float @test1(i32 %hash, float %x, float %y, float %z, float %w) { entry: %lookupTable = alloca [128 x float], align 16 ; <[128 x float]*> [#uses=5] %lookupTable1 = bitcast [128 x float]* %lookupTable to i8* ; <i8*> [#uses=1] - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %lookupTable1, i8* bitcast ([128 x float]* @C.0.1248 to i8*), i64 512, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %lookupTable1, i8* align 16 bitcast ([128 x float]* @C.0.1248 to i8*), i64 512, i1 false) ; CHECK-LABEL: @test1( ; CHECK-NOT: alloca @@ -36,10 +36,10 @@ entry: ret float %tmp43 } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind -declare void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* nocapture, i8* nocapture, i64, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind -declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind +declare void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* nocapture, i8* nocapture, i64, i1) nounwind +declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind +declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind %T = type { i8, [123 x i8] } %U = type { i32, i32, i32, i32, i32 } @@ -60,9 +60,9 @@ define void @test2() { ; CHECK-NEXT: getelementptr inbounds [124 x i8], [124 x i8]* ; use @G instead of %A -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull %{{.*}}, i8* getelementptr inbounds (%T, %T* @G, i64 0, i32 0) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* nonnull align 8 %{{.*}}, i8* align 8 getelementptr inbounds (%T, %T* @G, i64 0, i32 0) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %b, i8* align 4 %a, i64 124, i1 false) call void @bar(i8* %b) ret void } @@ -83,9 +83,9 @@ define void @test2_addrspacecast() { ; CHECK-NEXT: addrspacecast ; use @G instead of %A -; CHECK-NEXT: call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %{{.*}}, - call void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false) - call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %b, i8 addrspace(1)* %a, i64 124, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* align 4 %{{.*}}, + call void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false) + call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* align 4 %b, i8 addrspace(1)* align 4 %a, i64 124, i1 false) call void @bar_as1(i8 addrspace(1)* %b) ret void } @@ -98,7 +98,7 @@ declare void @bar_as1(i8 addrspace(1)*) define void @test3() { %A = alloca %T %a = bitcast %T* %A to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false) call void @bar(i8* %a) readonly ; CHECK-LABEL: @test3( ; CHECK-NEXT: call void @bar(i8* getelementptr inbounds (%T, %T* @G, i64 0, i32 0)) @@ -108,7 +108,7 @@ define void @test3() { define void @test3_addrspacecast() { %A = alloca %T %a = bitcast %T* %A to i8* - call void @llvm.memcpy.p0i8.p1i8.i64(i8* %a, i8 addrspace(1)* addrspacecast (%T* @G to i8 addrspace(1)*), i64 124, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p1i8.i64(i8* align 4 %a, i8 addrspace(1)* align 4 addrspacecast (%T* @G to i8 addrspace(1)*), i64 124, i1 false) call void @bar(i8* %a) readonly ; CHECK-LABEL: @test3_addrspacecast( ; CHECK-NEXT: call void @bar(i8* getelementptr inbounds (%T, %T* @G, i64 0, i32 0)) @@ -119,7 +119,7 @@ define void @test3_addrspacecast() { define void @test4() { %A = alloca %T %a = bitcast %T* %A to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false) call void @baz(i8* byval %a) ; CHECK-LABEL: @test4( ; CHECK-NEXT: call void @baz(i8* byval getelementptr inbounds (%T, %T* @G, i64 0, i32 0)) @@ -131,7 +131,7 @@ define void @test5() { %A = alloca %T %a = bitcast %T* %A to i8* call void @llvm.lifetime.start.p0i8(i64 -1, i8* %a) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%T* @G to i8*), i64 124, i1 false) call void @baz(i8* byval %a) ; CHECK-LABEL: @test5( ; CHECK-NEXT: call void @baz(i8* byval getelementptr inbounds (%T, %T* @G, i64 0, i32 0)) @@ -145,7 +145,7 @@ declare void @baz(i8* byval) define void @test6() { %A = alloca %U, align 16 %a = bitcast %U* %A to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast ([2 x %U]* @H to i8*), i64 20, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %a, i8* align 16 bitcast ([2 x %U]* @H to i8*), i64 20, i1 false) call void @bar(i8* %a) readonly ; CHECK-LABEL: @test6( ; CHECK-NEXT: call void @bar(i8* bitcast ([2 x %U]* @H to i8*)) @@ -155,7 +155,7 @@ define void @test6() { define void @test7() { %A = alloca %U, align 16 %a = bitcast %U* %A to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 0) to i8*), i64 20, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 0) to i8*), i64 20, i1 false) call void @bar(i8* %a) readonly ; CHECK-LABEL: @test7( ; CHECK-NEXT: call void @bar(i8* bitcast ([2 x %U]* @H to i8*)) @@ -165,7 +165,7 @@ define void @test7() { define void @test8() { %A = alloca %U, align 16 %a = bitcast %U* %A to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8*), i64 20, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8*), i64 20, i1 false) call void @bar(i8* %a) readonly ; CHECK-LABEL: @test8( ; CHECK: llvm.memcpy @@ -177,7 +177,7 @@ define void @test8() { define void @test8_addrspacecast() { %A = alloca %U, align 16 %a = bitcast %U* %A to i8* - call void @llvm.memcpy.p0i8.p1i8.i64(i8* %a, i8 addrspace(1)* addrspacecast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8 addrspace(1)*), i64 20, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p1i8.i64(i8* align 4 %a, i8 addrspace(1)* align 4 addrspacecast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8 addrspace(1)*), i64 20, i1 false) call void @bar(i8* %a) readonly ; CHECK-LABEL: @test8_addrspacecast( ; CHECK: llvm.memcpy @@ -188,7 +188,7 @@ define void @test8_addrspacecast() { define void @test9() { %A = alloca %U, align 4 %a = bitcast %U* %A to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8*), i64 20, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 bitcast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8*), i64 20, i1 false) call void @bar(i8* %a) readonly ; CHECK-LABEL: @test9( ; CHECK-NEXT: call void @bar(i8* bitcast (%U* getelementptr inbounds ([2 x %U], [2 x %U]* @H, i64 0, i64 1) to i8*)) @@ -198,7 +198,7 @@ define void @test9() { define void @test9_addrspacecast() { %A = alloca %U, align 4 %a = bitcast %U* %A to i8* - call void @llvm.memcpy.p0i8.p1i8.i64(i8* %a, i8 addrspace(1)* addrspacecast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8 addrspace(1)*), i64 20, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p1i8.i64(i8* align 4 %a, i8 addrspace(1)* align 4 addrspacecast (%U* getelementptr ([2 x %U], [2 x %U]* @H, i64 0, i32 1) to i8 addrspace(1)*), i64 20, i1 false) call void @bar(i8* %a) readonly ; CHECK-LABEL: @test9_addrspacecast( ; CHECK-NEXT: call void @bar(i8* bitcast (%U* getelementptr inbounds ([2 x %U], [2 x %U]* @H, i64 0, i64 1) to i8*)) @@ -217,8 +217,8 @@ entry: %cc = alloca [1000000 x i8], align 16 %cc.0..sroa_idx = getelementptr inbounds [1000000 x i8], [1000000 x i8]* %cc, i64 0, i64 0 %arraydecay = getelementptr inbounds [1000000 x i8], [1000000 x i8]* %cc, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arraydecay, i8* getelementptr inbounds ([3 x i8], [3 x i8]* @_ZL3KKK, i32 0, i32 0), i64 3, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds ([1000000 x i8], [1000000 x i8]* @bbb, i32 0, i32 0), i8* %arraydecay, i64 1000000, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arraydecay, i8* getelementptr inbounds ([3 x i8], [3 x i8]* @_ZL3KKK, i32 0, i32 0), i64 3, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 getelementptr inbounds ([1000000 x i8], [1000000 x i8]* @bbb, i32 0, i32 0), i8* align 16 %arraydecay, i64 1000000, i1 false) ret void } @@ -231,7 +231,7 @@ entry: %cc = alloca [3 x i8], align 1 %cc.0..sroa_idx = getelementptr inbounds [3 x i8], [3 x i8]* %cc, i64 0, i64 0 %arraydecay = getelementptr inbounds [3 x i8], [3 x i8]* %cc, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arraydecay, i8* getelementptr inbounds ([3 x i8], [3 x i8]* @_ZL3KKK, i32 0, i32 0), i64 3, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds ([1000000 x i8], [1000000 x i8]* @bbb, i32 0, i32 0), i8* %arraydecay, i64 3, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arraydecay, i8* getelementptr inbounds ([3 x i8], [3 x i8]* @_ZL3KKK, i32 0, i32 0), i64 3, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds ([1000000 x i8], [1000000 x i8]* @bbb, i32 0, i32 0), i8* %arraydecay, i64 3, i1 false) ret void } diff --git a/llvm/test/Transforms/InstCombine/memcpy-to-load.ll b/llvm/test/Transforms/InstCombine/memcpy-to-load.ll index 2b66552e4f7..614ae186406 100644 --- a/llvm/test/Transforms/InstCombine/memcpy-to-load.ll +++ b/llvm/test/Transforms/InstCombine/memcpy-to-load.ll @@ -4,7 +4,7 @@ ; RUN: opt < %s -instcombine -S -data-layout=n32:64 | FileCheck %s --check-prefix=ALL --check-prefix=I64 ; RUN: opt < %s -instcombine -S -data-layout=n32:64:128 | FileCheck %s --check-prefix=ALL --check-prefix=I128 -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind ; memcpy can be expanded inline with load/store (based on the datalayout?) @@ -14,7 +14,7 @@ define void @copy_1_byte(i8* %d, i8* %s) { ; ALL-NEXT: store i8 [[TMP1]], i8* [[D:%.*]], align 1 ; ALL-NEXT: ret void ; - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 1, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 1, i1 false) ret void } @@ -26,7 +26,7 @@ define void @copy_2_bytes(i8* %d, i8* %s) { ; ALL-NEXT: store i16 [[TMP3]], i16* [[TMP2]], align 1 ; ALL-NEXT: ret void ; - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 2, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 2, i1 false) ret void } @@ -34,10 +34,10 @@ define void @copy_2_bytes(i8* %d, i8* %s) { define void @copy_3_bytes(i8* %d, i8* %s) { ; ALL-LABEL: @copy_3_bytes( -; ALL-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[D:%.*]], i8* [[S:%.*]], i32 3, i32 1, i1 false) +; ALL-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[D:%.*]], i8* align 1 [[S:%.*]], i32 3, i1 false) ; ALL-NEXT: ret void ; - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 3, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 3, i1 false) ret void } @@ -49,7 +49,7 @@ define void @copy_4_bytes(i8* %d, i8* %s) { ; ALL-NEXT: store i32 [[TMP3]], i32* [[TMP2]], align 1 ; ALL-NEXT: ret void ; - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 4, i1 false) ret void } @@ -57,10 +57,10 @@ define void @copy_4_bytes(i8* %d, i8* %s) { define void @copy_5_bytes(i8* %d, i8* %s) { ; ALL-LABEL: @copy_5_bytes( -; ALL-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[D:%.*]], i8* [[S:%.*]], i32 5, i32 1, i1 false) +; ALL-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[D:%.*]], i8* align 1 [[S:%.*]], i32 5, i1 false) ; ALL-NEXT: ret void ; - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 5, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 5, i1 false) ret void } @@ -72,16 +72,16 @@ define void @copy_8_bytes(i8* %d, i8* %s) { ; ALL-NEXT: store i64 [[TMP3]], i64* [[TMP2]], align 1 ; ALL-NEXT: ret void ; - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 8, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 8, i1 false) ret void } define void @copy_16_bytes(i8* %d, i8* %s) { ; ALL-LABEL: @copy_16_bytes( -; ALL-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[D:%.*]], i8* [[S:%.*]], i32 16, i32 1, i1 false) +; ALL-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[D:%.*]], i8* align 1 [[S:%.*]], i32 16, i1 false) ; ALL-NEXT: ret void ; - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 16, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %d, i8* %s, i32 16, i1 false) ret void } diff --git a/llvm/test/Transforms/InstCombine/memcpy.ll b/llvm/test/Transforms/InstCombine/memcpy.ll index 8cf640ae5d8..ecdcae0a580 100644 --- a/llvm/test/Transforms/InstCombine/memcpy.ll +++ b/llvm/test/Transforms/InstCombine/memcpy.ll @@ -1,7 +1,7 @@ ; RUN: opt < %s -instcombine -S | FileCheck %s -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind ; Same src/dest. @@ -9,7 +9,7 @@ define void @test1(i8* %a) { ; CHECK-LABEL: @test1( ; CHECK-NEXT: ret void ; - tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 100, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 100, i1 false) ret void } @@ -17,10 +17,10 @@ define void @test1(i8* %a) { define void @test2(i8* %a) { ; CHECK-LABEL: @test2( -; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 100, i32 1, i1 true) +; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 100, i1 true) ; CHECK-NEXT: ret void ; - tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 100, i32 1, i1 true) + tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 100, i1 true) ret void } @@ -28,10 +28,10 @@ define void @test2(i8* %a) { define void @test3(i8* %d, i8* %s) { ; CHECK-LABEL: @test3( -; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %d, i8* %s, i64 17179869184, i32 4, i1 false) +; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %d, i8* align 4 %s, i64 17179869184, i1 false) ; CHECK-NEXT: ret void ; - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %d, i8* %s, i64 17179869184, i32 4, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %d, i8* align 4 %s, i64 17179869184, i1 false) ret void } diff --git a/llvm/test/Transforms/InstCombine/memcpy_chk-1.ll b/llvm/test/Transforms/InstCombine/memcpy_chk-1.ll index ddaaf82a8e2..a372ef2feca 100644 --- a/llvm/test/Transforms/InstCombine/memcpy_chk-1.ll +++ b/llvm/test/Transforms/InstCombine/memcpy_chk-1.ll @@ -20,7 +20,7 @@ define i8* @test_simplify1() { %dst = bitcast %struct.T1* @t1 to i8* %src = bitcast %struct.T2* @t2 to i8* -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* bitcast (%struct.T1* @t1 to i8*), i8* bitcast (%struct.T2* @t2 to i8*), i64 1824, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.T1* @t1 to i8*), i8* align 4 bitcast (%struct.T2* @t2 to i8*), i64 1824, i1 false) ; CHECK-NEXT: ret i8* bitcast (%struct.T1* @t1 to i8*) %ret = call i8* @__memcpy_chk(i8* %dst, i8* %src, i64 1824, i64 1824) ret i8* %ret @@ -31,7 +31,7 @@ define i8* @test_simplify2() { %dst = bitcast %struct.T1* @t1 to i8* %src = bitcast %struct.T3* @t3 to i8* -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* bitcast (%struct.T1* @t1 to i8*), i8* bitcast (%struct.T3* @t3 to i8*), i64 1824, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.T1* @t1 to i8*), i8* align 4 bitcast (%struct.T3* @t3 to i8*), i64 1824, i1 false) ; CHECK-NEXT: ret i8* bitcast (%struct.T1* @t1 to i8*) %ret = call i8* @__memcpy_chk(i8* %dst, i8* %src, i64 1824, i64 2848) ret i8* %ret diff --git a/llvm/test/Transforms/InstCombine/memmove.ll b/llvm/test/Transforms/InstCombine/memmove.ll index 7bc6d9a675d..2df88f64410 100644 --- a/llvm/test/Transforms/InstCombine/memmove.ll +++ b/llvm/test/Transforms/InstCombine/memmove.ll @@ -10,16 +10,16 @@ define void @test1(i8* %A, i8* %B, i32 %N) { ;; CHECK-LABEL: test1 ;; CHECK-NEXT: ret void - call void @llvm.memmove.p0i8.p0i8.i32(i8* %A, i8* %B, i32 0, i32 1, i1 false) + call void @llvm.memmove.p0i8.p0i8.i32(i8* %A, i8* %B, i32 0, i1 false) ret void } define void @test2(i8* %A, i32 %N) { ;; dest can't alias source since we can't write to source! ;; CHECK-LABEL: test2 - ;; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %A, i8* getelementptr inbounds ([33 x i8], [33 x i8]* @S, i{{32|64}} 0, i{{32|64}} 0), i32 %N, i32 1, i1 false) + ;; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %A, i8* align 1 getelementptr inbounds ([33 x i8], [33 x i8]* @S, i{{32|64}} 0, i{{32|64}} 0), i32 %N, i1 false) ;; CHECK-NEXT: ret void - call void @llvm.memmove.p0i8.p0i8.i32(i8* %A, i8* getelementptr inbounds ([33 x i8], [33 x i8]* @S, i32 0, i32 0), i32 %N, i32 1, i1 false) + call void @llvm.memmove.p0i8.p0i8.i32(i8* %A, i8* getelementptr inbounds ([33 x i8], [33 x i8]* @S, i32 0, i32 0), i32 %N, i1 false) ret void } @@ -36,9 +36,9 @@ define i32 @test3([1024 x i8]* %target) { ; arg: [1024 x i8]*> [#uses=1] %hel_p = getelementptr [4 x i8], [4 x i8]* @hel, i32 0, i32 0 ; <i8*> [#uses=1] %hello_u_p = getelementptr [8 x i8], [8 x i8]* @hello_u, i32 0, i32 0 ; <i8*> [#uses=1] %target_p = getelementptr [1024 x i8], [1024 x i8]* %target, i32 0, i32 0 ; <i8*> [#uses=3] - call void @llvm.memmove.p0i8.p0i8.i32(i8* %target_p, i8* %h_p, i32 2, i32 2, i1 false) - call void @llvm.memmove.p0i8.p0i8.i32(i8* %target_p, i8* %hel_p, i32 4, i32 4, i1 false) - call void @llvm.memmove.p0i8.p0i8.i32(i8* %target_p, i8* %hello_u_p, i32 8, i32 8, i1 false) + call void @llvm.memmove.p0i8.p0i8.i32(i8* align 2 %target_p, i8* align 2 %h_p, i32 2, i1 false) + call void @llvm.memmove.p0i8.p0i8.i32(i8* align 4 %target_p, i8* align 4 %hel_p, i32 4, i1 false) + call void @llvm.memmove.p0i8.p0i8.i32(i8* align 8 %target_p, i8* align 8 %hello_u_p, i32 8, i1 false) ret i32 0 } @@ -46,8 +46,8 @@ define i32 @test3([1024 x i8]* %target) { ; arg: [1024 x i8]*> [#uses=1] define void @test4(i8* %a) { ;; CHECK-LABEL: test4 ;; CHECK-NEXT: ret void - tail call void @llvm.memmove.p0i8.p0i8.i32(i8* %a, i8* %a, i32 100, i32 1, i1 false) + tail call void @llvm.memmove.p0i8.p0i8.i32(i8* %a, i8* %a, i32 100, i1 false) ret void } -declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) argmemonly nounwind +declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) argmemonly nounwind diff --git a/llvm/test/Transforms/InstCombine/memmove_chk-1.ll b/llvm/test/Transforms/InstCombine/memmove_chk-1.ll index e4e1f6eedf3..f006985305b 100644 --- a/llvm/test/Transforms/InstCombine/memmove_chk-1.ll +++ b/llvm/test/Transforms/InstCombine/memmove_chk-1.ll @@ -20,7 +20,7 @@ define i8* @test_simplify1() { %dst = bitcast %struct.T1* @t1 to i8* %src = bitcast %struct.T2* @t2 to i8* -; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* bitcast (%struct.T1* @t1 to i8*), i8* bitcast (%struct.T2* @t2 to i8*), i64 1824, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.T1* @t1 to i8*), i8* align 4 bitcast (%struct.T2* @t2 to i8*), i64 1824, i1 false) ; CHECK-NEXT: ret i8* bitcast (%struct.T1* @t1 to i8*) %ret = call i8* @__memmove_chk(i8* %dst, i8* %src, i64 1824, i64 1824) ret i8* %ret @@ -31,7 +31,7 @@ define i8* @test_simplify2() { %dst = bitcast %struct.T1* @t1 to i8* %src = bitcast %struct.T3* @t3 to i8* -; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* bitcast (%struct.T1* @t1 to i8*), i8* bitcast (%struct.T3* @t3 to i8*), i64 1824, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* align 4 bitcast (%struct.T1* @t1 to i8*), i8* align 4 bitcast (%struct.T3* @t3 to i8*), i64 1824, i1 false) ; CHECK-NEXT: ret i8* bitcast (%struct.T1* @t1 to i8*) %ret = call i8* @__memmove_chk(i8* %dst, i8* %src, i64 1824, i64 2848) ret i8* %ret diff --git a/llvm/test/Transforms/InstCombine/memset-1.ll b/llvm/test/Transforms/InstCombine/memset-1.ll index 86f3afdef8d..ca12d181d51 100644 --- a/llvm/test/Transforms/InstCombine/memset-1.ll +++ b/llvm/test/Transforms/InstCombine/memset-1.ll @@ -58,7 +58,7 @@ cleanup: ; CHECK-NEXT: br i1 %cmp, label %cleanup, label %if.end ; CHECK: if.end: ; CHECK-NEXT: %bc = bitcast i8* %call to float* -; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* nonnull %call, i8 0, i32 %size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* nonnull align 1 %call, i8 0, i32 %size, i1 false) ; CHECK-NEXT: br label %cleanup ; CHECK: cleanup: ; CHECK-NEXT: %retval.0 = phi float* [ %bc, %if.end ], [ null, %entry ] diff --git a/llvm/test/Transforms/InstCombine/memset.ll b/llvm/test/Transforms/InstCombine/memset.ll index 08bbf8ba1ef..a41d65cdf5d 100644 --- a/llvm/test/Transforms/InstCombine/memset.ll +++ b/llvm/test/Transforms/InstCombine/memset.ll @@ -12,12 +12,12 @@ define i32 @test([1024 x i8]* %target) { ;; CHECK-NEXT: store i64 72340172838076673, i64* [[P4]], align 8 ;; CHECK-NEXT: ret i32 0 %target_p = getelementptr [1024 x i8], [1024 x i8]* %target, i32 0, i32 0 - call void @llvm.memset.p0i8.i32(i8* %target_p, i8 1, i32 0, i32 1, i1 false) - call void @llvm.memset.p0i8.i32(i8* %target_p, i8 1, i32 1, i32 1, i1 false) - call void @llvm.memset.p0i8.i32(i8* %target_p, i8 1, i32 2, i32 2, i1 false) - call void @llvm.memset.p0i8.i32(i8* %target_p, i8 1, i32 4, i32 4, i1 false) - call void @llvm.memset.p0i8.i32(i8* %target_p, i8 1, i32 8, i32 8, i1 false) + call void @llvm.memset.p0i8.i32(i8* %target_p, i8 1, i32 0, i1 false) + call void @llvm.memset.p0i8.i32(i8* %target_p, i8 1, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* align 2 %target_p, i8 1, i32 2, i1 false) + call void @llvm.memset.p0i8.i32(i8* align 4 %target_p, i8 1, i32 4, i1 false) + call void @llvm.memset.p0i8.i32(i8* align 8 %target_p, i8 1, i32 8, i1 false) ret i32 0 } -declare void @llvm.memset.p0i8.i32(i8* nocapture writeonly, i8, i32, i32, i1) argmemonly nounwind +declare void @llvm.memset.p0i8.i32(i8* nocapture writeonly, i8, i32, i1) argmemonly nounwind diff --git a/llvm/test/Transforms/InstCombine/memset2.ll b/llvm/test/Transforms/InstCombine/memset2.ll index ad4c225846b..094cb6d536a 100644 --- a/llvm/test/Transforms/InstCombine/memset2.ll +++ b/llvm/test/Transforms/InstCombine/memset2.ll @@ -8,8 +8,8 @@ define i32 @test(%struct.Moves addrspace(1)* nocapture %moves) { entry: ; CHECK: bitcast i8 addrspace(1)* %gep to i64 addrspace(1)* %gep = getelementptr inbounds %struct.Moves, %struct.Moves addrspace(1)* %moves, i32 1, i32 0, i32 9 - call void @llvm.memset.p1i8.i64(i8 addrspace(1)* %gep, i8 0, i64 8, i32 1, i1 false) + call void @llvm.memset.p1i8.i64(i8 addrspace(1)* %gep, i8 0, i64 8, i1 false) ret i32 0 } -declare void @llvm.memset.p1i8.i64(i8addrspace(1)* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p1i8.i64(i8addrspace(1)* nocapture, i8, i64, i1) nounwind diff --git a/llvm/test/Transforms/InstCombine/memset_chk-1.ll b/llvm/test/Transforms/InstCombine/memset_chk-1.ll index 79028502b64..7f680ea48b6 100644 --- a/llvm/test/Transforms/InstCombine/memset_chk-1.ll +++ b/llvm/test/Transforms/InstCombine/memset_chk-1.ll @@ -15,7 +15,7 @@ define i8* @test_simplify1() { ; CHECK-LABEL: @test_simplify1( %dst = bitcast %struct.T* @t to i8* -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false) ; CHECK-NEXT: ret i8* bitcast (%struct.T* @t to i8*) %ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 1824) ret i8* %ret @@ -25,7 +25,7 @@ define i8* @test_simplify2() { ; CHECK-LABEL: @test_simplify2( %dst = bitcast %struct.T* @t to i8* -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false) ; CHECK-NEXT: ret i8* bitcast (%struct.T* @t to i8*) %ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 3648) ret i8* %ret @@ -35,7 +35,7 @@ define i8* @test_simplify3() { ; CHECK-LABEL: @test_simplify3( %dst = bitcast %struct.T* @t to i8* -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 bitcast (%struct.T* @t to i8*), i8 0, i64 1824, i1 false) ; CHECK-NEXT: ret i8* bitcast (%struct.T* @t to i8*) %ret = call i8* @__memset_chk(i8* %dst, i32 0, i64 1824, i64 -1) ret i8* %ret @@ -79,7 +79,7 @@ entry: %sub183 = ptrtoint i8* %b to i64 %sub184 = sub i64 %sub182, %sub183 %add52.i.i = add nsw i64 %sub184, 1 -; CHECK: call void @llvm.memset.p0i8.i64(i8* %strchr2 +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %strchr2 %call185 = call i8* @__memset_chk(i8* %call51i, i32 0, i64 %add52.i.i, i64 -1) ret i32 4 } diff --git a/llvm/test/Transforms/InstCombine/objsize.ll b/llvm/test/Transforms/InstCombine/objsize.ll index 5c0a36f5fea..86b087567e2 100644 --- a/llvm/test/Transforms/InstCombine/objsize.ll +++ b/llvm/test/Transforms/InstCombine/objsize.ll @@ -114,7 +114,7 @@ entry: %1 = bitcast %struct.data* %0 to i8* %2 = call i32 @llvm.objectsize.i32.p0i8(i8* %1, i1 false, i1 false) nounwind ; CHECK-NOT: @llvm.objectsize -; CHECK: @llvm.memset.p0i8.i32(i8* %1, i8 0, i32 1824, i32 8, i1 false) +; CHECK: @llvm.memset.p0i8.i32(i8* align 8 %1, i8 0, i32 1824, i1 false) %3 = call i8* @__memset_chk(i8* %1, i32 0, i32 1824, i32 %2) nounwind store i8* %1, i8** %esc ret i32 0 @@ -130,7 +130,7 @@ entry: %1 = tail call i32 @llvm.objectsize.i32.p0i8(i8* %0, i1 false, i1 false) %2 = load i8*, i8** @s, align 8 ; CHECK-NOT: @llvm.objectsize -; CHECK: @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* %1, i32 10, i32 1, i1 false) +; CHECK: @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %0, i8* align 1 %1, i32 10, i1 false) %3 = tail call i8* @__memcpy_chk(i8* %0, i8* %2, i32 10, i32 %1) nounwind ret i8* %0 } diff --git a/llvm/test/Transforms/InstCombine/opaque.ll b/llvm/test/Transforms/InstCombine/opaque.ll index f2a91855d5a..18cbef5281b 100644 --- a/llvm/test/Transforms/InstCombine/opaque.ll +++ b/llvm/test/Transforms/InstCombine/opaque.ll @@ -9,8 +9,7 @@ %Vs4Int8 = type <{ i8 }> %swift.type = type { i64 } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, -i64, i32, i1) #8 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) #8 @_swift_slowAlloc = external global i8* (i64, i64)* @@ -26,7 +25,7 @@ entry: %3 = bitcast i8* %1 to %V* %4 = bitcast %V* %3 to i8* %5 = bitcast %V* %0 to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %4, i8* %5, i64 40, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %4, i8* %5, i64 40, i1 false) %6 = bitcast %V* %3 to %swift.opaque* ret %swift.opaque* %6 } diff --git a/llvm/test/Transforms/InstCombine/pr31990_wrong_memcpy.ll b/llvm/test/Transforms/InstCombine/pr31990_wrong_memcpy.ll index 62ecd0311ff..f7874b9ee23 100644 --- a/llvm/test/Transforms/InstCombine/pr31990_wrong_memcpy.ll +++ b/llvm/test/Transforms/InstCombine/pr31990_wrong_memcpy.ll @@ -11,13 +11,12 @@ entry: %1 = bitcast i8* %0 to i4* call void @bar(i4* %1) %2 = bitcast i4* %1 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %2, i8* @g, i32 1, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %2, i8* @g, i32 1, i1 false) call void @gaz(i8* %2) ret void } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, - i8* nocapture readonly, i32, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1) declare void @bar(i4*) declare void @gaz(i8*) diff --git a/llvm/test/Transforms/InstCombine/simplify-libcalls.ll b/llvm/test/Transforms/InstCombine/simplify-libcalls.ll index bae2822164f..7f198c36907 100644 --- a/llvm/test/Transforms/InstCombine/simplify-libcalls.ll +++ b/llvm/test/Transforms/InstCombine/simplify-libcalls.ll @@ -120,9 +120,9 @@ define i32 @MemCpy() { %hello_u_p = getelementptr [8 x i8], [8 x i8]* @hello_u, i32 0, i32 0 %target = alloca [1024 x i8] %target_p = getelementptr [1024 x i8], [1024 x i8]* %target, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %target_p, i8* %h_p, i32 2, i32 2, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %target_p, i8* %hel_p, i32 4, i32 4, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %target_p, i8* %hello_u_p, i32 8, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %target_p, i8* align 2 %h_p, i32 2, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %target_p, i8* align 4 %hel_p, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %target_p, i8* align 8 %hello_u_p, i32 8, i1 false) ret i32 0 ; CHECK-LABEL: @MemCpy( @@ -130,7 +130,7 @@ define i32 @MemCpy() { ; CHECK: ret i32 0 } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind declare i32 @strcmp(i8*, i8*) #0 diff --git a/llvm/test/Transforms/InstCombine/sprintf-1.ll b/llvm/test/Transforms/InstCombine/sprintf-1.ll index ddf2f2f88e7..1fbdc43bd56 100644 --- a/llvm/test/Transforms/InstCombine/sprintf-1.ll +++ b/llvm/test/Transforms/InstCombine/sprintf-1.ll @@ -22,7 +22,7 @@ define void @test_simplify1(i8* %dst) { ; CHECK-LABEL: @test_simplify1( %fmt = getelementptr [13 x i8], [13 x i8]* @hello_world, i32 0, i32 0 call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* getelementptr inbounds ([13 x i8], [13 x i8]* @hello_world, i32 0, i32 0), i32 13, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %dst, i8* align 1 getelementptr inbounds ([13 x i8], [13 x i8]* @hello_world, i32 0, i32 0), i32 13, i1 false) ret void ; CHECK-NEXT: ret void } @@ -66,7 +66,7 @@ define void @test_simplify5(i8* %dst, i8* %str) { call i32 (i8*, i8*, ...) @sprintf(i8* %dst, i8* %fmt, i8* %str) ; CHECK-NEXT: [[STRLEN:%[a-z0-9]+]] = call i32 @strlen(i8* %str) ; CHECK-NEXT: [[LENINC:%[a-z0-9]+]] = add i32 [[STRLEN]], 1 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %str, i32 [[LENINC]], i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %dst, i8* align 1 %str, i32 [[LENINC]], i1 false) ret void ; CHECK-NEXT: ret void } diff --git a/llvm/test/Transforms/InstCombine/stack-overalign.ll b/llvm/test/Transforms/InstCombine/stack-overalign.ll index a8f086e6cb9..65d004008fa 100644 --- a/llvm/test/Transforms/InstCombine/stack-overalign.ll +++ b/llvm/test/Transforms/InstCombine/stack-overalign.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -instcombine -S | grep "align 32" | count 1 +; RUN: opt < %s -instcombine -S | grep "align 32" | count 2 ; It's tempting to have an instcombine in which the src pointer of a ; memcpy is aligned up to the alignment of the destination, however @@ -12,6 +12,8 @@ ; alignments when they are greater than they need to be. Or, codegen ; could do dynamic alignment for just the one alloca, and leave the ; main stack pointer at its standard alignment. +; + @dst = global [1024 x i8] zeroinitializer, align 32 @@ -19,11 +21,11 @@ define void @foo() nounwind { entry: %src = alloca [1024 x i8], align 1 %src1 = getelementptr [1024 x i8], [1024 x i8]* %src, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([1024 x i8], [1024 x i8]* @dst, i32 0, i32 0), i8* %src1, i32 1024, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 32 getelementptr inbounds ([1024 x i8], [1024 x i8]* @dst, i32 0, i32 0), i8* align 32 %src1, i32 1024, i1 false) call void @frob(i8* %src1) nounwind ret void } declare void @frob(i8*) -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind diff --git a/llvm/test/Transforms/InstCombine/stpcpy_chk-1.ll b/llvm/test/Transforms/InstCombine/stpcpy_chk-1.ll index 45e6879c8d2..aae0d48e41b 100644 --- a/llvm/test/Transforms/InstCombine/stpcpy_chk-1.ll +++ b/llvm/test/Transforms/InstCombine/stpcpy_chk-1.ll @@ -16,7 +16,7 @@ define i8* @test_simplify1() { %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0 %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false) ; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11) %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %src, i32 60) ret i8* %ret @@ -27,7 +27,7 @@ define i8* @test_simplify2() { %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0 %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false) ; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11) %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %src, i32 12) ret i8* %ret @@ -38,7 +38,7 @@ define i8* @test_simplify3() { %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0 %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false) ; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 11) %ret = call i8* @__stpcpy_chk(i8* %dst, i8* %src, i32 -1) ret i8* %ret diff --git a/llvm/test/Transforms/InstCombine/strcpy_chk-1.ll b/llvm/test/Transforms/InstCombine/strcpy_chk-1.ll index 824776c6ca1..a9a1f46b7e2 100644 --- a/llvm/test/Transforms/InstCombine/strcpy_chk-1.ll +++ b/llvm/test/Transforms/InstCombine/strcpy_chk-1.ll @@ -16,7 +16,7 @@ define i8* @test_simplify1() { %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0 %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false) ; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0) %ret = call i8* @__strcpy_chk(i8* %dst, i8* %src, i32 60) ret i8* %ret @@ -27,7 +27,7 @@ define i8* @test_simplify2() { %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0 %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false) ; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0) %ret = call i8* @__strcpy_chk(i8* %dst, i8* %src, i32 12) ret i8* %ret @@ -38,7 +38,7 @@ define i8* @test_simplify3() { %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0 %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false) ; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0) %ret = call i8* @__strcpy_chk(i8* %dst, i8* %src, i32 -1) ret i8* %ret diff --git a/llvm/test/Transforms/InstCombine/strncpy_chk-1.ll b/llvm/test/Transforms/InstCombine/strncpy_chk-1.ll index 03690b9b1e0..bc3ff35ef05 100644 --- a/llvm/test/Transforms/InstCombine/strncpy_chk-1.ll +++ b/llvm/test/Transforms/InstCombine/strncpy_chk-1.ll @@ -16,7 +16,7 @@ define i8* @test_simplify1() { %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0 %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false) ; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0) %ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 12, i32 60) ret i8* %ret @@ -27,7 +27,7 @@ define i8* @test_simplify2() { %dst = getelementptr inbounds [60 x i8], [60 x i8]* @a, i32 0, i32 0 %src = getelementptr inbounds [12 x i8], [12 x i8]* @.str, i32 0, i32 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0), i8* align 1 getelementptr inbounds ([12 x i8], [12 x i8]* @.str, i32 0, i32 0), i32 12, i1 false) ; CHECK-NEXT: ret i8* getelementptr inbounds ([60 x i8], [60 x i8]* @a, i32 0, i32 0) %ret = call i8* @__strncpy_chk(i8* %dst, i8* %src, i32 12, i32 12) ret i8* %ret diff --git a/llvm/test/Transforms/InstCombine/struct-assign-tbaa.ll b/llvm/test/Transforms/InstCombine/struct-assign-tbaa.ll index c75a839f3fb..09a3f435e8f 100644 --- a/llvm/test/Transforms/InstCombine/struct-assign-tbaa.ll +++ b/llvm/test/Transforms/InstCombine/struct-assign-tbaa.ll @@ -2,7 +2,7 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind ; Verify that instcombine preserves TBAA tags when converting a memcpy into ; a scalar load and store. @@ -17,7 +17,7 @@ define void @test1(%struct.test1* nocapture %a, %struct.test1* nocapture %b) { entry: %0 = bitcast %struct.test1* %a to i8* %1 = bitcast %struct.test1* %b to i8* - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 4, i32 4, i1 false), !tbaa.struct !3 + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 4, i1 false), !tbaa.struct !3 ret void } @@ -29,7 +29,7 @@ define i32 (i8*, i32*, double*)*** @test2() { ; CHECK: ret %tmp = alloca %struct.test2, align 8 %tmp1 = bitcast %struct.test2* %tmp to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp1, i8* undef, i64 8, i32 8, i1 false), !tbaa.struct !4 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %tmp1, i8* align 8 undef, i64 8, i1 false), !tbaa.struct !4 %tmp2 = getelementptr %struct.test2, %struct.test2* %tmp, i32 0, i32 0 %tmp3 = load i32 (i8*, i32*, double*)**, i32 (i8*, i32*, double*)*** %tmp2 ret i32 (i8*, i32*, double*)*** %tmp2 diff --git a/llvm/test/Transforms/LICM/pr26843.ll b/llvm/test/Transforms/LICM/pr26843.ll index a14acbef964..e72821d7fdb 100644 --- a/llvm/test/Transforms/LICM/pr26843.ll +++ b/llvm/test/Transforms/LICM/pr26843.ll @@ -19,7 +19,7 @@ entry: for.body: store i32 1, i32* @v, align 4 - tail call void @llvm.memset.p0i8.i32(i8* bitcast (i32* @v to i8*), i8 0, i32 4, i32 4, i1 false) + tail call void @llvm.memset.p0i8.i32(i8* align 4 bitcast (i32* @v to i8*), i8 0, i32 4, i1 false) br label %for.latch for.latch: @@ -29,4 +29,4 @@ end: ret i32 0 } -declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) +declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) diff --git a/llvm/test/Transforms/LICM/pr27262.ll b/llvm/test/Transforms/LICM/pr27262.ll index 5fc6d9389e0..0245ec2ca8b 100644 --- a/llvm/test/Transforms/LICM/pr27262.ll +++ b/llvm/test/Transforms/LICM/pr27262.ll @@ -20,7 +20,7 @@ entry: for.body: store i8 1, i8* %p, align 1 store i8 2, i8* %p1, align 1 - call void @llvm.memset.p0i8.i32(i8* %p, i8 255, i32 4, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* %p, i8 255, i32 4, i1 false) br label %for.latch for.latch: @@ -30,4 +30,4 @@ end: ret i32 0 } -declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) +declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) diff --git a/llvm/test/Transforms/LICM/unrolled-deeply-nested.ll b/llvm/test/Transforms/LICM/unrolled-deeply-nested.ll index c0f2c981800..fad3e8f0c0e 100644 --- a/llvm/test/Transforms/LICM/unrolled-deeply-nested.ll +++ b/llvm/test/Transforms/LICM/unrolled-deeply-nested.ll @@ -49,8 +49,8 @@ l.0.0.0.header: %iv.0.0.0 = phi i64 [ %iv.0.0.0.next, %l.0.0.0.header ], [ 0, %l.0.0.header ] %iv.0.0.0.next = add i64 %iv.0.0.0, 1 %exitcond.0.0.0 = icmp eq i64 %iv.0.0.0.next, %n.0.0.0 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a.i8, i8* %c.i8, i64 4, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b.i8, i8* %c.i8, i64 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a.i8, i8* %c.i8, i64 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b.i8, i8* %c.i8, i64 4, i1 false) br i1 %exitcond.0.0.0, label %l.0.0.0.header, label %l.0.0.latch ; CHECK: call void @llvm.memcpy.{{.*}}(i8* %[[AI8]], i8* %[[CI8]], i64 4 ; CHECK: call void @llvm.memcpy.{{.*}}(i8* %[[BI8]], i8* %[[CI8]], i64 4 @@ -73,4 +73,4 @@ exit: ; CHECK: ret i32 %[[LCSSA]] } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) diff --git a/llvm/test/Transforms/LoopIdiom/basic-address-space.ll b/llvm/test/Transforms/LoopIdiom/basic-address-space.ll index 67cabf36eec..c709b9acd58 100644 --- a/llvm/test/Transforms/LoopIdiom/basic-address-space.ll +++ b/llvm/test/Transforms/LoopIdiom/basic-address-space.ll @@ -7,7 +7,7 @@ target triple = "x86_64-apple-darwin10.0.0" define void @test10(i8 addrspace(2)* %X) nounwind ssp { ; CHECK-LABEL: @test10( ; CHECK: entry: -; CHECK-NEXT: call void @llvm.memset.p2i8.i16(i8 addrspace(2)* %X, i8 0, i16 10000, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p2i8.i16(i8 addrspace(2)* align 1 %X, i8 0, i16 10000, i1 false) ; CHECK-NOT: store ; CHECK: ret void diff --git a/llvm/test/Transforms/LoopIdiom/basic.ll b/llvm/test/Transforms/LoopIdiom/basic.ll index ba3e8a04704..e16817fe364 100644 --- a/llvm/test/Transforms/LoopIdiom/basic.ll +++ b/llvm/test/Transforms/LoopIdiom/basic.ll @@ -24,7 +24,7 @@ for.body: ; preds = %bb.nph, %for.body for.end: ; preds = %for.body, %entry ret void ; CHECK-LABEL: @test1( -; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %Base, i8 0, i64 %Size, i1 false) ; CHECK-NOT: store } @@ -47,7 +47,7 @@ for.body.cont: for.end: ; preds = %for.body, %entry ret void ; CHECK-LABEL: @test1a( -; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %Base, i8 0, i64 %Size, i1 false) ; CHECK-NOT: store } @@ -70,7 +70,7 @@ for.end: ; preds = %for.body, %entry ; CHECK-LABEL: @test2( ; CHECK: br i1 %cmp10, ; CHECK: %0 = shl i64 %Size, 2 -; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base1, i8 1, i64 %0, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %Base1, i8 1, i64 %0, i1 false) ; CHECK-NOT: store } @@ -118,7 +118,7 @@ for.body: ; preds = %bb.nph, %for.body for.end: ; preds = %for.body, %entry ret void ; CHECK-LABEL: @test4( -; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 100, i32 1, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %Base, i8 0, i64 100, i1 false) } ; This can't be promoted: the memset is a store of a loop variant value. @@ -164,7 +164,7 @@ for.body: ; preds = %bb.nph, %for.body for.end: ; preds = %for.body, %entry ret void ; CHECK-LABEL: @test6( -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %Dest, i8* %Base, i64 %Size, i32 1, i1 false) +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i1 false) ; CHECK-NOT: store ; CHECK: ret void } @@ -189,7 +189,7 @@ for.body.cont: for.end: ; preds = %for.body, %entry ret void ; CHECK-LABEL: @test7( -; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %Base, i8 0, i64 %Size, i1 false) ; CHECK-NOT: store } @@ -274,7 +274,7 @@ for.end13: ; preds = %for.inc10 ret void ; CHECK-LABEL: @test10( ; CHECK: entry: -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %X, i8 0, i64 10000, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 %X, i8 0, i64 10000, i1 false) ; CHECK-NOT: store ; CHECK: ret void } @@ -322,7 +322,7 @@ for.end: ; preds = %for.body ; CHECK-LABEL: @test12( ; CHECK-NEXT: entry: ; CHECK-NEXT: bitcast -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %P1, i8 0, i64 80000, i32 4, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 4 %P1, i8 0, i64 80000, i1 false) ; CHECK-NOT: store ; CHECK: ret void } @@ -439,7 +439,7 @@ for.body: for.cond.cleanup: ret void ; CHECK-LABEL: @test15( -; CHECK: call void @llvm.memset.p0i8.i64(i8* %f1, i8 0, i64 262148, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %f1, i8 0, i64 262148, i1 false) ; CHECK-NOT: store ; CHECK: ret void } @@ -559,7 +559,7 @@ for.end6: ; preds = %for.inc4 ret void ; CHECK-LABEL: @test19( ; CHECK: entry: -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %X, i8 0, i64 10000, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 %X, i8 0, i64 10000, i1 false) ; CHECK: ret void } @@ -579,7 +579,7 @@ loop.ph: ; CHECK: loop.ph: ; CHECK-NEXT: %[[ZEXT_SIZE:.*]] = zext i32 %size to i64 ; CHECK-NEXT: %[[SCALED_SIZE:.*]] = shl i64 %[[ZEXT_SIZE]], 3 -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %{{.*}}, i8 0, i64 %[[SCALED_SIZE]], i32 8, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %{{.*}}, i8 0, i64 %[[SCALED_SIZE]], i1 false) loop.body: %storemerge4 = phi i32 [ 0, %loop.ph ], [ %inc, %loop.body ] @@ -611,7 +611,7 @@ loop.ph: ; CHECK: loop.ph: ; CHECK-NEXT: %[[ZEXT_SIZE:.*]] = zext i32 %size to i64 ; CHECK-NEXT: %[[SCALED_SIZE:.*]] = shl i64 %[[ZEXT_SIZE]], 3 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %{{.*}}, i8* %{{.*}}, i64 %[[SCALED_SIZE]], i32 8, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %{{.*}}, i8* align 8 %{{.*}}, i64 %[[SCALED_SIZE]], i1 false) loop.body: %storemerge4 = phi i32 [ 0, %loop.ph ], [ %inc, %loop.body ] diff --git a/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll b/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll index 61c14694c3c..e1e07a06d69 100644 --- a/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll +++ b/llvm/test/Transforms/LoopIdiom/lir-heurs-multi-block-loop.ll @@ -5,7 +5,7 @@ ; - a loop_memset idiom, or ; - a memset/memcpy idiom in a nested loop. -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) @APPLES = common global i32 0, align 4 @ORANGES = common global i32 0, align 4 @@ -28,7 +28,7 @@ for.body: ; preds = %for.body.preheader, %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.inc ] %BASKET.013 = phi i32 [ %BASKET.1, %for.inc ], [ 0, %for.body.preheader ] %arraydecay = getelementptr inbounds [2048 x i8], [2048 x i8]* %DST, i64 %indvars.iv, i64 0 - tail call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 -1, i64 2048, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 -1, i64 2048, i1 false) %0 = trunc i64 %indvars.iv to i32 %rem11 = and i32 %0, 1 %cmp1 = icmp eq i32 %rem11, 0 diff --git a/llvm/test/Transforms/LoopIdiom/pr28196.ll b/llvm/test/Transforms/LoopIdiom/pr28196.ll index 10f49fbcd09..9057bdbb103 100644 --- a/llvm/test/Transforms/LoopIdiom/pr28196.ll +++ b/llvm/test/Transforms/LoopIdiom/pr28196.ll @@ -22,5 +22,5 @@ for.body: ; preds = %for.body, %for.body } ; CHECK-LABEL: define void @test1( -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* null, i8* inttoptr (i64 4 to i8*), i64 24, i32 4, i1 false) +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 null, i8* align 4 inttoptr (i64 4 to i8*), i64 24, i1 false) ; CHECK-NOT: store diff --git a/llvm/test/Transforms/MemCpyOpt/2008-02-24-MultipleUseofSRet.ll b/llvm/test/Transforms/MemCpyOpt/2008-02-24-MultipleUseofSRet.ll index f73addd6268..7ff149f6f77 100644 --- a/llvm/test/Transforms/MemCpyOpt/2008-02-24-MultipleUseofSRet.ll +++ b/llvm/test/Transforms/MemCpyOpt/2008-02-24-MultipleUseofSRet.ll @@ -25,12 +25,12 @@ entry: call fastcc void @initialize(%0* noalias sret %memtmp) %tmp1 = bitcast %0* %tmp to i8* %memtmp2 = bitcast %0* %memtmp to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp1, i8* %memtmp2, i32 24, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %tmp1, i8* align 8 %memtmp2, i32 24, i1 false) %z3 = bitcast %0* %z to i8* %tmp4 = bitcast %0* %tmp to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %z3, i8* %tmp4, i32 24, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %z3, i8* align 8 %tmp4, i32 24, i1 false) %tmp5 = call fastcc x86_fp80 @passed_uninitialized(%0* %z) ret void } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind diff --git a/llvm/test/Transforms/MemCpyOpt/2008-03-13-ReturnSlotBitcast.ll b/llvm/test/Transforms/MemCpyOpt/2008-03-13-ReturnSlotBitcast.ll index ffbb2992557..26c221d6786 100644 --- a/llvm/test/Transforms/MemCpyOpt/2008-03-13-ReturnSlotBitcast.ll +++ b/llvm/test/Transforms/MemCpyOpt/2008-03-13-ReturnSlotBitcast.ll @@ -13,10 +13,10 @@ entry: call void @g(%a* %a_var) %a_i8 = bitcast %a* %a_var to i8* %b_i8 = bitcast %b* %b_var to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b_i8, i8* %a_i8, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b_i8, i8* %a_i8, i32 4, i1 false) %tmp1 = getelementptr %b, %b* %b_var, i32 0, i32 0 %tmp2 = load float, float* %tmp1 ret float %tmp2 } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind diff --git a/llvm/test/Transforms/MemCpyOpt/align.ll b/llvm/test/Transforms/MemCpyOpt/align.ll index 9074684f6c7..738928bac62 100644 --- a/llvm/test/Transforms/MemCpyOpt/align.ll +++ b/llvm/test/Transforms/MemCpyOpt/align.ll @@ -1,15 +1,15 @@ ; RUN: opt < %s -S -basicaa -memcpyopt | FileCheck %s target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64" -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind ; The resulting memset is only 4-byte aligned, despite containing ; a 16-byte aligned store in the middle. define void @foo(i32* %p) { ; CHECK-LABEL: @foo( -; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 16, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 {{.*}}, i8 0, i64 16, i1 false) %a0 = getelementptr i32, i32* %p, i64 0 store i32 0, i32* %a0, align 4 %a1 = getelementptr i32, i32* %p, i64 1 @@ -31,7 +31,7 @@ define void @bar() { %a8 = alloca i32, align 8 %a8.cast = bitcast i32* %a8 to i8* %a4.cast = bitcast i32* %a4 to i8* - call void @llvm.memset.p0i8.i64(i8* %a8.cast, i8 0, i64 4, i32 8, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a4.cast, i8* %a8.cast, i64 4, i32 4, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %a8.cast, i8 0, i64 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a4.cast, i8* align 4 %a8.cast, i64 4, i1 false) ret void } diff --git a/llvm/test/Transforms/MemCpyOpt/atomic.ll b/llvm/test/Transforms/MemCpyOpt/atomic.ll index 5be6b1555b5..f8fc39faa58 100644 --- a/llvm/test/Transforms/MemCpyOpt/atomic.ll +++ b/llvm/test/Transforms/MemCpyOpt/atomic.ll @@ -7,7 +7,7 @@ target triple = "x86_64-apple-macosx10.7.0" declare void @otherf(i32*) -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind ; memcpyopt should not touch atomic ops define void @test1() nounwind uwtable ssp { @@ -15,7 +15,7 @@ define void @test1() nounwind uwtable ssp { ; CHECK: store atomic %x = alloca [101 x i32], align 16 %bc = bitcast [101 x i32]* %x to i8* - call void @llvm.memset.p0i8.i64(i8* %bc, i8 0, i64 400, i32 16, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 16 %bc, i8 0, i64 400, i1 false) %gep1 = getelementptr inbounds [101 x i32], [101 x i32]* %x, i32 0, i32 100 store atomic i32 0, i32* %gep1 unordered, align 4 %gep2 = getelementptr inbounds [101 x i32], [101 x i32]* %x, i32 0, i32 0 diff --git a/llvm/test/Transforms/MemCpyOpt/callslot_aa.ll b/llvm/test/Transforms/MemCpyOpt/callslot_aa.ll index b6ea129ccfa..d840b726a9a 100644 --- a/llvm/test/Transforms/MemCpyOpt/callslot_aa.ll +++ b/llvm/test/Transforms/MemCpyOpt/callslot_aa.ll @@ -6,14 +6,14 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" define void @test(i8* %src) { %tmp = alloca i8 %dst = alloca i8 -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 1, i32 8, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp, i8* %src, i64 1, i32 8, i1 false), !noalias !2 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %tmp, i64 1, i32 8, i1 false) +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst, i8* align 8 %src, i64 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %tmp, i8* align 8 %src, i64 1, i1 false), !noalias !2 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst, i8* align 8 %tmp, i64 1, i1 false) ret void } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i1) ; Check that the noalias for "dst" was removed by checking that the metadata is gone ; CHECK-NOT: "dst" diff --git a/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll b/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll index 4c3e3e86bf3..a1ba2bae79e 100644 --- a/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll +++ b/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll @@ -1,8 +1,8 @@ ; RUN: opt < %s -S -basicaa -memcpyopt | FileCheck %s target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128" -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) unnamed_addr nounwind -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) unnamed_addr nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind ; all bytes of %dst that are touch by the memset are dereferenceable define void @must_remove_memcpy(i8* noalias nocapture dereferenceable(4096) %dst) { @@ -11,8 +11,8 @@ define void @must_remove_memcpy(i8* noalias nocapture dereferenceable(4096) %dst ; CHECK-NOT: call void @llvm.memcpy.p0i8.p0i8.i64 %src = alloca [4096 x i8], align 1 %p = getelementptr inbounds [4096 x i8], [4096 x i8]* %src, i64 0, i64 0 - call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i32 1, i1 false) #2 + call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i1 false) #2 ret void } @@ -24,7 +24,7 @@ define void @must_not_remove_memcpy(i8* noalias nocapture dereferenceable(1024) ; CHECK: call void @llvm.memset.p0i8.i64 %src = alloca [4096 x i8], align 1 %p = getelementptr inbounds [4096 x i8], [4096 x i8]* %src, i64 0, i64 0 - call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i32 1, i1 false) #2 + call void @llvm.memset.p0i8.i64(i8* %p, i8 0, i64 4096, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %p, i64 4096, i1 false) #2 ret void } diff --git a/llvm/test/Transforms/MemCpyOpt/capturing-func.ll b/llvm/test/Transforms/MemCpyOpt/capturing-func.ll index 17614fd181d..2671a9aad81 100644 --- a/llvm/test/Transforms/MemCpyOpt/capturing-func.ll +++ b/llvm/test/Transforms/MemCpyOpt/capturing-func.ll @@ -3,13 +3,13 @@ target datalayout = "e" declare void @foo(i8*) -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind define void @test() { %ptr1 = alloca i8 %ptr2 = alloca i8 call void @foo(i8* %ptr2) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr1, i8* %ptr2, i32 1, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr1, i8* %ptr2, i32 1, i1 false) call void @foo(i8* %ptr1) ret void diff --git a/llvm/test/Transforms/MemCpyOpt/crash.ll b/llvm/test/Transforms/MemCpyOpt/crash.ll index 56757a6d1f8..464a261e4e4 100644 --- a/llvm/test/Transforms/MemCpyOpt/crash.ll +++ b/llvm/test/Transforms/MemCpyOpt/crash.ll @@ -46,13 +46,10 @@ entry: ; PR8753 -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, -i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind define void @test2(i32 %cmd) nounwind { - call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* undef, i64 20, i32 1, i1 -false) nounwind - call void @llvm.memcpy.p0i8.p0i8.i64(i8* null, i8* undef, i64 20, i32 1, i1 -false) nounwind + call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* undef, i64 20, i1 false) nounwind + call void @llvm.memcpy.p0i8.p0i8.i64(i8* null, i8* undef, i64 20, i1 false) nounwind ret void } diff --git a/llvm/test/Transforms/MemCpyOpt/form-memset.ll b/llvm/test/Transforms/MemCpyOpt/form-memset.ll index 7d7f3a6dac3..836a6107d24 100644 --- a/llvm/test/Transforms/MemCpyOpt/form-memset.ll +++ b/llvm/test/Transforms/MemCpyOpt/form-memset.ll @@ -152,11 +152,11 @@ entry: ; CHECK-LABEL: @test2( ; CHECK-NOT: store -; CHECK: call void @llvm.memset.p0i8.i64(i8* %tmp41, i8 -1, i64 8, i32 1, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %tmp41, i8 -1, i64 8, i1 false) ; CHECK-NOT: store -; CHECK: call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 32, i32 8, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %0, i8 0, i64 32, i1 false) ; CHECK-NOT: store -; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 32, i32 8, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %1, i8 0, i64 32, i1 false) ; CHECK-NOT: store ; CHECK: ret } @@ -171,11 +171,11 @@ entry: store i32 0, i32* %arrayidx, align 4 %add.ptr = getelementptr inbounds i32, i32* %P, i64 2 %0 = bitcast i32* %add.ptr to i8* - tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i1 false) ret void ; CHECK-LABEL: @test3( ; CHECK-NOT: store -; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 15, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %1, i8 0, i64 15, i1 false) } ; store followed by memset, different offset scenario @@ -184,40 +184,40 @@ entry: store i32 0, i32* %P, align 4 %add.ptr = getelementptr inbounds i32, i32* %P, i64 1 %0 = bitcast i32* %add.ptr to i8* - tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i1 false) ret void ; CHECK-LABEL: @test4( ; CHECK-NOT: store -; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 15, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %1, i8 0, i64 15, i1 false) } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind ; Memset followed by store. define void @test5(i32* nocapture %P) nounwind ssp { entry: %add.ptr = getelementptr inbounds i32, i32* %P, i64 2 %0 = bitcast i32* %add.ptr to i8* - tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 11, i1 false) %arrayidx = getelementptr inbounds i32, i32* %P, i64 1 store i32 0, i32* %arrayidx, align 4 ret void ; CHECK-LABEL: @test5( ; CHECK-NOT: store -; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 15, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %1, i8 0, i64 15, i1 false) } ;; Memset followed by memset. define void @test6(i32* nocapture %P) nounwind ssp { entry: %0 = bitcast i32* %P to i8* - tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 12, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 12, i1 false) %add.ptr = getelementptr inbounds i32, i32* %P, i64 3 %1 = bitcast i32* %add.ptr to i8* - tail call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 12, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %1, i8 0, i64 12, i1 false) ret void ; CHECK-LABEL: @test6( -; CHECK: call void @llvm.memset.p0i8.i64(i8* %2, i8 0, i64 24, i32 1, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %2, i8 0, i64 24, i1 false) } ; More aggressive heuristic @@ -233,7 +233,7 @@ define void @test7(i32* nocapture %c) nounwind optsize { %4 = getelementptr inbounds i32, i32* %c, i32 4 store i32 -1, i32* %4, align 4 ; CHECK-LABEL: @test7( -; CHECK: call void @llvm.memset.p0i8.i64(i8* %5, i8 -1, i64 20, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %5, i8 -1, i64 20, i1 false) ret void } @@ -270,17 +270,17 @@ define void @test9() nounwind { store i8 -1, i8* getelementptr (i8, i8* bitcast ([16 x i64]* @test9buf to i8*), i64 15), align 1 ret void ; CHECK-LABEL: @test9( -; CHECK: call void @llvm.memset.p0i8.i64(i8* bitcast ([16 x i64]* @test9buf to i8*), i8 -1, i64 16, i32 16, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 16 bitcast ([16 x i64]* @test9buf to i8*), i8 -1, i64 16, i1 false) } ; PR19092 define void @test10(i8* nocapture %P) nounwind { - tail call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 42, i32 1, i1 false) - tail call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 23, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 42, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 23, i1 false) ret void ; CHECK-LABEL: @test10( ; CHECK-NOT: memset -; CHECK: call void @llvm.memset.p0i8.i64(i8* %P, i8 0, i64 42, i32 1, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 1 %P, i8 0, i64 42, i1 false) ; CHECK-NOT: memset ; CHECK: ret void } @@ -290,12 +290,12 @@ define void @test11(i32* nocapture %P) nounwind ssp { entry: %add.ptr = getelementptr inbounds i32, i32* %P, i64 3 %0 = bitcast i32* %add.ptr to i8* - tail call void @llvm.memset.p0i8.i64(i8* %0, i8 1, i64 11, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %0, i8 1, i64 11, i1 false) %arrayidx = getelementptr inbounds i32, i32* %P, i64 0 %arrayidx.cast = bitcast i32* %arrayidx to i96* store i96 310698676526526814092329217, i96* %arrayidx.cast, align 4 ret void ; CHECK-LABEL: @test11( ; CHECK-NOT: store -; CHECK: call void @llvm.memset.p0i8.i64(i8* %1, i8 1, i64 23, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 %1, i8 1, i64 23, i1 false) } diff --git a/llvm/test/Transforms/MemCpyOpt/invariant.start.ll b/llvm/test/Transforms/MemCpyOpt/invariant.start.ll index ed8d7ede7eb..4842114b584 100644 --- a/llvm/test/Transforms/MemCpyOpt/invariant.start.ll +++ b/llvm/test/Transforms/MemCpyOpt/invariant.start.ll @@ -6,11 +6,9 @@ target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f3 target triple = "i686-apple-darwin9" %0 = type { x86_fp80, x86_fp80 } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, -i1) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, -i64, i32, i1) -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) nounwind readonly @@ -20,16 +18,16 @@ declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) nounwind readonly define void @test1(i8* %P, i8* %Q) nounwind { %memtmp = alloca %0, align 16 %R = bitcast %0* %memtmp to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %R, i8* %P, i32 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %R, i8* align 16 %P, i32 32, i1 false) %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %P) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %Q, i8* %R, i32 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %Q, i8* align 16 %R, i32 32, i1 false) ret void ; CHECK-LABEL: @test1( ; CHECK-NEXT: %memtmp = alloca %0, align 16 ; CHECK-NEXT: %R = bitcast %0* %memtmp to i8* -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %R, i8* %P, i32 32, i32 16, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %R, i8* align 16 %P, i32 32, i1 false) ; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %P) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %Q, i8* %R, i32 32, i32 16, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %Q, i8* align 16 %R, i32 32, i1 false) ; CHECK-NEXT: ret void } @@ -38,12 +36,12 @@ define void @test1(i8* %P, i8* %Q) nounwind { ; memset. define void @test2(i8* %dst1, i8* %dst2, i8 %c) { ; CHECK-LABEL: define void @test2( -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) ; CHECK-NEXT: %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %dst1) -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 128, i32 8, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %dst2, i8 %c, i64 128, i1 false) ; CHECK-NEXT: ret void - call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) %i = call {}* @llvm.invariant.start.p0i8(i64 32, i8* %dst1) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst2, i8* align 8 %dst1, i64 128, i1 false) ret void } diff --git a/llvm/test/Transforms/MemCpyOpt/lifetime.ll b/llvm/test/Transforms/MemCpyOpt/lifetime.ll index 77b495f2b58..9ddf3f4f9c2 100644 --- a/llvm/test/Transforms/MemCpyOpt/lifetime.ll +++ b/llvm/test/Transforms/MemCpyOpt/lifetime.ll @@ -3,7 +3,7 @@ ; performCallSlotOptzn in MemCpy should not exchange the calls to ; @llvm.lifetime.start and @llvm.memcpy. -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) #1 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) #1 declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1 declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1 @@ -17,7 +17,7 @@ bb: call void @llvm.lifetime.start.p0i8(i64 16, i8* %tmp5) %tmp10 = getelementptr inbounds i8, i8* %tmp5, i64 7 store i8 0, i8* %tmp10, align 1 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arg1, i8* %tmp5, i64 16, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %arg1, i8* align 8 %tmp5, i64 16, i1 false) call void @llvm.lifetime.end.p0i8(i64 16, i8* %tmp5) ret void } diff --git a/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll b/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll index e21dc87cb6a..1b8e8bc2828 100644 --- a/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll +++ b/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll @@ -8,15 +8,15 @@ entry-block: %a = alloca [8 x i64], align 8 %a.cast = bitcast [8 x i64]* %a to i8* call void @llvm.lifetime.start.p0i8(i64 64, i8* %a.cast) - call void @llvm.memset.p0i8.i64(i8* %a.cast, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %a.cast, i8 0, i64 64, i1 false) %sret.cast = bitcast [8 x i64]* %sret to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %sret.cast, i8* %a.cast, i64 64, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %sret.cast, i8* align 8 %a.cast, i64 64, i1 false) call void @llvm.lifetime.end.p0i8(i64 64, i8* %a.cast) ret void ; CHECK-LABEL: @foo( ; CHECK: %[[sret_cast:[^=]+]] = bitcast [8 x i64]* %sret to i8* -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %[[sret_cast]], i8 0, i64 64 +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %[[sret_cast]], i8 0, i64 64 ; CHECK-NOT: call void @llvm.memcpy ; CHECK: ret void } @@ -26,24 +26,24 @@ entry-block: %a = alloca [8 x i64], align 8 %a.cast = bitcast [8 x i64]* %a to i8* call void @llvm.lifetime.start.p0i8(i64 64, i8* %a.cast) - call void @llvm.memset.p0i8.i64(i8* %a.cast, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %a.cast, i8 0, i64 64, i1 false) %sret.cast = bitcast [8 x i64]* %sret to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %sret.cast, i8* %a.cast, i64 64, i32 8, i1 false) - call void @llvm.memset.p0i8.i64(i8* %a.cast, i8 42, i64 32, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %sret.cast, i8* align 8 %a.cast, i64 64, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %a.cast, i8 42, i64 32, i1 false) %out.cast = bitcast [8 x i64]* %out to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out.cast, i8* %a.cast, i64 64, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %out.cast, i8* align 8 %a.cast, i64 64, i1 false) call void @llvm.lifetime.end.p0i8(i64 64, i8* %a.cast) ret void ; CHECK-LABEL: @bar( ; CHECK: %[[a:[^=]+]] = alloca [8 x i64] ; CHECK: %[[a_cast:[^=]+]] = bitcast [8 x i64]* %[[a]] to i8* -; CHECK: call void @llvm.memset.p0i8.i64(i8* %[[a_cast]], i8 0, i64 64 +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %[[a_cast]], i8 0, i64 64 ; CHECK: %[[sret_cast:[^=]+]] = bitcast [8 x i64]* %sret to i8* -; CHECK: call void @llvm.memset.p0i8.i64(i8* %[[sret_cast]], i8 0, i64 64 -; CHECK: call void @llvm.memset.p0i8.i64(i8* %[[a_cast]], i8 42, i64 32 +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %[[sret_cast]], i8 0, i64 64 +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 %[[a_cast]], i8 42, i64 32 ; CHECK: %[[out_cast:[^=]+]] = bitcast [8 x i64]* %out to i8* -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %[[out_cast]], i8* %[[a_cast]], i64 64 +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %[[out_cast]], i8* align 8 %[[a_cast]], i64 64 ; CHECK-NOT: call void @llvm.memcpy ; CHECK: ret void } @@ -51,5 +51,5 @@ entry-block: declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) nounwind declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) nounwind -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind diff --git a/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset.ll b/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset.ll index fd8b93c19b1..652d1c1d65b 100644 --- a/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset.ll +++ b/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset.ll @@ -2,13 +2,13 @@ @cst = internal constant [3 x i32] [i32 -1, i32 -1, i32 -1], align 4 -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind declare void @foo(i32*) nounwind define void @test1() nounwind { %arr = alloca [3 x i32], align 4 %arr_i8 = bitcast [3 x i32]* %arr to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %arr_i8, i8* bitcast ([3 x i32]* @cst to i8*), i64 12, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %arr_i8, i8* align 4 bitcast ([3 x i32]* @cst to i8*), i64 12, i1 false) %arraydecay = getelementptr inbounds [3 x i32], [3 x i32]* %arr, i64 0, i64 0 call void @foo(i32* %arraydecay) nounwind ret void diff --git a/llvm/test/Transforms/MemCpyOpt/memcpy-undef.ll b/llvm/test/Transforms/MemCpyOpt/memcpy-undef.ll index 06a41829a4e..9cf4f91e6aa 100644 --- a/llvm/test/Transforms/MemCpyOpt/memcpy-undef.ll +++ b/llvm/test/Transforms/MemCpyOpt/memcpy-undef.ll @@ -11,7 +11,7 @@ define i32 @test1(%struct.foo* nocapture %foobie) nounwind noinline ssp uwtable store i8 98, i8* %1, align 4 %2 = getelementptr inbounds %struct.foo, %struct.foo* %foobie, i64 0, i32 1, i64 0 %3 = getelementptr inbounds [7 x i8], [7 x i8]* %bletch.sroa.1, i64 0, i64 0 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %2, i8* %3, i64 7, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %2, i8* %3, i64 7, i1 false) %4 = getelementptr inbounds %struct.foo, %struct.foo* %foobie, i64 0, i32 2 store i32 20, i32* %4, align 4 ret i32 undef @@ -23,7 +23,7 @@ define i32 @test1(%struct.foo* nocapture %foobie) nounwind noinline ssp uwtable define void @test2(i8* sret noalias nocapture %out, i8* %in) nounwind noinline ssp uwtable { call void @llvm.lifetime.start.p0i8(i64 8, i8* %in) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 8, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 8, i1 false) ret void ; Check that the memcpy is removed. @@ -33,7 +33,7 @@ define void @test2(i8* sret noalias nocapture %out, i8* %in) nounwind noinline s define void @test3(i8* sret noalias nocapture %out, i8* %in) nounwind noinline ssp uwtable { call void @llvm.lifetime.start.p0i8(i64 4, i8* %in) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 8, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 8, i1 false) ret void ; Check that the memcpy is not removed. @@ -41,6 +41,6 @@ define void @test3(i8* sret noalias nocapture %out, i8* %in) nounwind noinline s ; CHECK: call void @llvm.memcpy } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) nounwind diff --git a/llvm/test/Transforms/MemCpyOpt/memcpy.ll b/llvm/test/Transforms/MemCpyOpt/memcpy.ll index 9f0ad2df86b..7e1e4d54a24 100644 --- a/llvm/test/Transforms/MemCpyOpt/memcpy.ll +++ b/llvm/test/Transforms/MemCpyOpt/memcpy.ll @@ -14,9 +14,9 @@ entry: call void @ccoshl(%0* sret %memtmp, x86_fp80 %tmp5, x86_fp80 %z.0) nounwind %tmp219 = bitcast %0* %tmp2 to i8* %memtmp20 = bitcast %0* %memtmp to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp219, i8* %memtmp20, i32 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %tmp219, i8* align 16 %memtmp20, i32 32, i1 false) %agg.result21 = bitcast %0* %agg.result to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %agg.result21, i8* %tmp219, i32 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %agg.result21, i8* align 16 %tmp219, i32 32, i1 false) ret void ; Check that one of the memcpy's are removed. @@ -37,12 +37,12 @@ declare void @ccoshl(%0* nocapture sret, x86_fp80, x86_fp80) nounwind define void @test2(i8* %P, i8* %Q) nounwind { %memtmp = alloca %0, align 16 %R = bitcast %0* %memtmp to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %R, i8* %P, i32 32, i32 16, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %Q, i8* %R, i32 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %R, i8* align 16 %P, i32 32, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %Q, i8* align 16 %R, i32 32, i1 false) ret void ; CHECK-LABEL: @test2( -; CHECK-NEXT: call void @llvm.memmove{{.*}}(i8* %Q, i8* %P +; CHECK-NEXT: call void @llvm.memmove{{.*}}(i8* align 16 %Q, i8* align 16 %P ; CHECK-NEXT: ret void } @@ -54,9 +54,9 @@ define void @test2(i8* %P, i8* %Q) nounwind { define void @test3(%0* noalias sret %agg.result) nounwind { %x.0 = alloca %0 %x.01 = bitcast %0* %x.0 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %x.01, i8* bitcast (%0* @x to i8*), i32 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %x.01, i8* align 16 bitcast (%0* @x to i8*), i32 32, i1 false) %agg.result2 = bitcast %0* %agg.result to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %agg.result2, i8* %x.01, i32 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %agg.result2, i8* align 16 %x.01, i32 32, i1 false) ret void ; CHECK-LABEL: @test3( ; CHECK-NEXT: %agg.result1 = bitcast @@ -69,7 +69,7 @@ define void @test3(%0* noalias sret %agg.result) nounwind { define void @test4(i8 *%P) { %A = alloca %1 %a = bitcast %1* %A to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %P, i64 8, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %a, i8* align 4 %P, i64 8, i1 false) call void @test4a(i8* align 1 byval %a) ret void ; CHECK-LABEL: @test4( @@ -80,7 +80,7 @@ define void @test4(i8 *%P) { define void @test4_addrspace(i8 addrspace(1)* %P) { %A = alloca %1 %a = bitcast %1* %A to i8* - call void @llvm.memcpy.p0i8.p1i8.i64(i8* %a, i8 addrspace(1)* %P, i64 8, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p1i8.i64(i8* align 4 %a, i8 addrspace(1)* align 4 %P, i64 8, i1 false) call void @test4a(i8* align 1 byval %a) ret void ; CHECK-LABEL: @test4_addrspace( @@ -89,9 +89,9 @@ define void @test4_addrspace(i8 addrspace(1)* %P) { } declare void @test4a(i8* align 1 byval) -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind -declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind +declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind +declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind %struct.S = type { i128, [4 x i8]} @@ -105,7 +105,7 @@ define i32 @test5(i32 %x) nounwind ssp { entry: %y = alloca %struct.S, align 16 %tmp = bitcast %struct.S* %y to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp, i8* bitcast (%struct.S* @sS to i8*), i64 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 16 %tmp, i8* align 16 bitcast (%struct.S* @sS to i8*), i64 32, i1 false) %a = getelementptr %struct.S, %struct.S* %y, i64 0, i32 1, i64 0 store i8 4, i8* %a call void @test5a(%struct.S* align 16 byval %y) @@ -117,7 +117,7 @@ entry: ;; Noop memcpy should be zapped. define void @test6(i8 *%P) { - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %P, i64 8, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %P, i8* align 4 %P, i64 8, i1 false) ret void ; CHECK-LABEL: @test6( ; CHECK-NEXT: ret void @@ -133,7 +133,7 @@ entry: %agg.tmp = alloca %struct.p, align 4 %tmp = bitcast %struct.p* %agg.tmp to i8* %tmp1 = bitcast %struct.p* %q to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp, i8* %tmp1, i64 48, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %tmp, i8* align 4 %tmp1, i64 48, i1 false) %call = call i32 @g(%struct.p* align 8 byval %agg.tmp) nounwind ret i32 %call ; CHECK-LABEL: @test7( @@ -142,7 +142,7 @@ entry: declare i32 @g(%struct.p* align 8 byval) -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind ; PR11142 - When looking for a memcpy-memcpy dependency, don't get stuck on ; instructions between the memcpy's that only affect the destination pointer. @@ -153,10 +153,10 @@ define void @test8() { ; CHECK-NOT: memcpy %A = tail call i8* @malloc(i32 10) %B = getelementptr inbounds i8, i8* %A, i64 2 - tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %B, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @test8.str, i64 0, i64 0), i32 7, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %B, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @test8.str, i64 0, i64 0), i32 7, i1 false) %C = tail call i8* @malloc(i32 10) %D = getelementptr inbounds i8, i8* %C, i64 2 - tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %D, i8* %B, i32 7, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %D, i8* %B, i32 7, i1 false) ret void ; CHECK: ret void } @@ -177,7 +177,7 @@ entry: call void @f1(%struct.big* sret %tmp) %0 = addrspacecast %struct.big* %b to i8 addrspace(1)* %1 = addrspacecast %struct.big* %tmp to i8 addrspace(1)* - call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %0, i8 addrspace(1)* %1, i64 200, i32 4, i1 false) + call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* align 4 %0, i8 addrspace(1)* align 4 %1, i64 200, i1 false) call void @f2(%struct.big* %b) ret void } @@ -193,7 +193,7 @@ entry: call void @f1(%struct.big* sret %tmp) %0 = bitcast %struct.big* %b to i8* %1 = bitcast %struct.big* %tmp to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 200, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 200, i1 false) call void @f2(%struct.big* %b) ret void } @@ -220,15 +220,15 @@ define void @test11([20 x i32] addrspace(1)* nocapture dereferenceable(80) %P) { %A = alloca [20 x i32], align 4 %a = bitcast [20 x i32]* %A to i8* %b = bitcast [20 x i32] addrspace(1)* %P to i8 addrspace(1)* - call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 80, i32 4, i1 false) - call void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* %b, i8* %a, i64 80, i32 4, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %a, i8 0, i64 80, i1 false) + call void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* align 4 %b, i8* align 4 %a, i64 80, i1 false) ret void ; CHECK-LABEL: @test11( ; CHECK-NOT: addrspacecast } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind -declare void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind +declare void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* nocapture, i8* nocapture, i64, i1) nounwind declare void @f1(%struct.big* nocapture sret) declare void @f2(%struct.big*) diff --git a/llvm/test/Transforms/MemCpyOpt/memmove.ll b/llvm/test/Transforms/MemCpyOpt/memmove.ll index 1af85a1edc5..91f2851ab78 100644 --- a/llvm/test/Transforms/MemCpyOpt/memmove.ll +++ b/llvm/test/Transforms/MemCpyOpt/memmove.ll @@ -4,7 +4,7 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128" target triple = "x86_64-apple-darwin9.0" -declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind define i8* @test1(i8* nocapture %src) nounwind { entry: @@ -14,7 +14,7 @@ entry: %malloccall = tail call i8* @malloc(i32 trunc (i64 mul nuw (i64 ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64), i64 13) to i32)) %call3 = bitcast i8* %malloccall to [13 x i8]* %call3.sub = getelementptr inbounds [13 x i8], [13 x i8]* %call3, i64 0, i64 0 - tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %call3.sub, i8* %src, i64 13, i32 1, i1 false) + tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %call3.sub, i8* %src, i64 13, i1 false) ret i8* %call3.sub } declare noalias i8* @malloc(i32) @@ -25,7 +25,7 @@ entry: ; CHECK-LABEL: @test2( ; CHECK: call void @llvm.memcpy %add.ptr = getelementptr i8, i8* %P, i64 16 - tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 16, i32 1, i1 false) + tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 16, i1 false) ret void } @@ -35,6 +35,6 @@ entry: ; CHECK-LABEL: @test3( ; CHECK: call void @llvm.memmove %add.ptr = getelementptr i8, i8* %P, i64 16 - tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 17, i32 1, i1 false) + tail call void @llvm.memmove.p0i8.p0i8.i64(i8* %P, i8* %add.ptr, i64 17, i1 false) ret void } diff --git a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-redundant-memset.ll b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-redundant-memset.ll index de29caa191d..a3ca96c3ab5 100644 --- a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-redundant-memset.ll +++ b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-redundant-memset.ll @@ -7,12 +7,12 @@ target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i64 %dst_size, %src_size ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i64 0, i64 [[SIZEDIFF]] ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i64 %src_size -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[DST]], i8 %c, i64 [[SIZE]], i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[DST]], i8 %c, i64 [[SIZE]], i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false) ; CHECK-NEXT: ret void define void @test(i8* %src, i64 %src_size, i8* %dst, i64 %dst_size, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false) ret void } @@ -22,12 +22,12 @@ define void @test(i8* %src, i64 %src_size, i8* %dst, i64 %dst_size, i8 %c) { ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i64 [[DSTSIZE]], %src_size ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i64 0, i64 [[SIZEDIFF]] ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i64 %src_size -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[DST]], i8 %c, i64 [[SIZE]], i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[DST]], i8 %c, i64 [[SIZE]], i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false) ; CHECK-NEXT: ret void define void @test_different_types_i32_i64(i8* %dst, i8* %src, i32 %dst_size, i64 %src_size, i8 %c) { - call void @llvm.memset.p0i8.i32(i8* %dst, i8 %c, i32 %dst_size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* %dst, i8 %c, i32 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false) ret void } @@ -37,12 +37,12 @@ define void @test_different_types_i32_i64(i8* %dst, i8* %src, i32 %dst_size, i64 ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i128 %dst_size, [[SRCSIZE]] ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i128 0, i128 [[SIZEDIFF]] ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i128 [[SRCSIZE]] -; CHECK-NEXT: call void @llvm.memset.p0i8.i128(i8* [[DST]], i8 %c, i128 [[SIZE]], i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i128(i8* align 1 [[DST]], i8 %c, i128 [[SIZE]], i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i1 false) ; CHECK-NEXT: ret void define void @test_different_types_i128_i32(i8* %dst, i8* %src, i128 %dst_size, i32 %src_size, i8 %c) { - call void @llvm.memset.p0i8.i128(i8* %dst, i8 %c, i128 %dst_size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i32 1, i1 false) + call void @llvm.memset.p0i8.i128(i8* %dst, i8 %c, i128 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i1 false) ret void } @@ -52,12 +52,12 @@ define void @test_different_types_i128_i32(i8* %dst, i8* %src, i128 %dst_size, i ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i128 [[DSTSIZE]], %src_size ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i128 0, i128 [[SIZEDIFF]] ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i128 %src_size -; CHECK-NEXT: call void @llvm.memset.p0i8.i128(i8* [[DST]], i8 %c, i128 [[SIZE]], i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i128(i8* %dst, i8* %src, i128 %src_size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i128(i8* align 1 [[DST]], i8 %c, i128 [[SIZE]], i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i128(i8* %dst, i8* %src, i128 %src_size, i1 false) ; CHECK-NEXT: ret void define void @test_different_types_i32_i128(i8* %dst, i8* %src, i32 %dst_size, i128 %src_size, i8 %c) { - call void @llvm.memset.p0i8.i32(i8* %dst, i8 %c, i32 %dst_size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i128(i8* %dst, i8* %src, i128 %src_size, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* %dst, i8 %c, i32 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i128(i8* %dst, i8* %src, i128 %src_size, i1 false) ret void } @@ -67,36 +67,36 @@ define void @test_different_types_i32_i128(i8* %dst, i8* %src, i32 %dst_size, i1 ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i64 %dst_size, [[SRCSIZE]] ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i64 0, i64 [[SIZEDIFF]] ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i64 [[SRCSIZE]] -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[DST]], i8 %c, i64 [[SIZE]], i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[DST]], i8 %c, i64 [[SIZE]], i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i1 false) ; CHECK-NEXT: ret void define void @test_different_types_i64_i32(i8* %dst, i8* %src, i64 %dst_size, i32 %src_size, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %src, i32 %src_size, i1 false) ret void } ; CHECK-LABEL: define void @test_align_same -; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 {{.*}}, i32 8, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 {{.*}}, i8 0, i64 {{.*}}, i1 false) define void @test_align_same(i8* %src, i8* %dst, i64 %dst_size) { - call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 8, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 80, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %dst, i8 0, i64 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 80, i1 false) ret void } ; CHECK-LABEL: define void @test_align_min -; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 {{.*}}, i32 4, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 4 {{.*}}, i8 0, i64 {{.*}}, i1 false) define void @test_align_min(i8* %src, i8* %dst, i64 %dst_size) { - call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 8, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 36, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %dst, i8 0, i64 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 36, i1 false) ret void } ; CHECK-LABEL: define void @test_align_memcpy -; CHECK: call void @llvm.memset.p0i8.i64(i8* {{.*}}, i8 0, i64 {{.*}}, i32 8, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 8 {{.*}}, i8 0, i64 {{.*}}, i1 false) define void @test_align_memcpy(i8* %src, i8* %dst, i64 %dst_size) { - call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 80, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst, i8* align 8 %src, i64 80, i1 false) ret void } @@ -106,37 +106,37 @@ define void @test_align_memcpy(i8* %src, i8* %dst, i64 %dst_size) { ; CHECK: [[SIZEDIFF:%[0-9]+]] = sub i64 %dst_size, %src_size ; CHECK: [[SIZE:%[0-9]+]] = select i1 [[ULE]], i64 0, i64 [[SIZEDIFF]] ; CHECK: [[DST:%[0-9]+]] = getelementptr i8, i8* %dst, i64 %src_size -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[DST]], i8 %c, i64 [[SIZE]], i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[DST]], i8 %c, i64 [[SIZE]], i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false) ; CHECK-NEXT: ret void define void @test_non_i8_dst_type(i8* %src, i64 %src_size, i64* %dst_pi64, i64 %dst_size, i8 %c) { %dst = bitcast i64* %dst_pi64 to i8* - call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %src_size, i1 false) ret void } ; CHECK-LABEL: define void @test_different_dst -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src, i64 %src_size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src, i64 %src_size, i1 false) ; CHECK-NEXT: ret void define void @test_different_dst(i8* %dst2, i8* %src, i64 %src_size, i8* %dst, i64 %dst_size) { - call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src, i64 %src_size, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst, i8 0, i64 %dst_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src, i64 %src_size, i1 false) ret void } ; Make sure we also take into account dependencies on the destination. ; CHECK-LABEL: define i8 @test_intermediate_read -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 64, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 64, i1 false) ; CHECK-NEXT: %r = load i8, i8* %a -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 24, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 24, i1 false) ; CHECK-NEXT: ret i8 %r define i8 @test_intermediate_read(i8* %a, i8* %b) #0 { - call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 64, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %a, i8 0, i64 64, i1 false) %r = load i8, i8* %a - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 24, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 24, i1 false) ret i8 %r } @@ -146,23 +146,23 @@ define i8 @test_intermediate_read(i8* %a, i8* %b) #0 { ; CHECK-NEXT: %a = alloca %struct ; CHECK-NEXT: %a0 = getelementptr %struct, %struct* %a, i32 0, i32 0, i32 0 ; CHECK-NEXT: %a1 = getelementptr %struct, %struct* %a, i32 0, i32 1, i32 0 -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %a0, i8 0, i64 16, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %a0, i8 0, i64 16, i1 false) ; CHECK-NEXT: store i8 1, i8* %a1 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a0, i8* %b, i64 8, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a0, i8* %b, i64 8, i1 false) ; CHECK-NEXT: ret void define void @test_intermediate_write(i8* %b) #0 { %a = alloca %struct %a0 = getelementptr %struct, %struct* %a, i32 0, i32 0, i32 0 %a1 = getelementptr %struct, %struct* %a, i32 0, i32 1, i32 0 - call void @llvm.memset.p0i8.i64(i8* %a0, i8 0, i64 16, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %a0, i8 0, i64 16, i1 false) store i8 1, i8* %a1 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a0, i8* %b, i64 8, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a0, i8* %b, i64 8, i1 false) ret void } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) -declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) -declare void @llvm.memset.p0i8.i128(i8* nocapture, i8, i128, i32, i1) -declare void @llvm.memcpy.p0i8.p0i8.i128(i8* nocapture, i8* nocapture readonly, i128, i32, i1) +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) +declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) +declare void @llvm.memset.p0i8.i128(i8* nocapture, i8, i128, i1) +declare void @llvm.memcpy.p0i8.p0i8.i128(i8* nocapture, i8* nocapture readonly, i128, i1) diff --git a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll index 1c567042ce7..e36389a128f 100644 --- a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll +++ b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll @@ -3,99 +3,99 @@ target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128" ; CHECK-LABEL: define void @test( -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 128, i32 8, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %dst2, i8 %c, i64 128, i1 false) ; CHECK-NEXT: ret void define void @test(i8* %dst1, i8* %dst2, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %dst2, i8* align 8 %dst1, i64 128, i1 false) ret void } ; CHECK-LABEL: define void @test_smaller_memcpy( -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 100, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 100, i1 false) ; CHECK-NEXT: ret void define void @test_smaller_memcpy(i8* %dst1, i8* %dst2, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 100, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 100, i1 false) ret void } ; CHECK-LABEL: define void @test_smaller_memset( -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 100, i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 100, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false) ; CHECK-NEXT: ret void define void @test_smaller_memset(i8* %dst1, i8* %dst2, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 100, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 100, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false) ret void } ; CHECK-LABEL: define void @test_align_memset( -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 8, i1 false) -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 128, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %dst1, i8 %c, i64 128, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 128, i1 false) ; CHECK-NEXT: ret void define void @test_align_memset(i8* %dst1, i8* %dst2, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 8, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %dst1, i8 %c, i64 128, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false) ret void } ; CHECK-LABEL: define void @test_different_types( -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 8, i1 false) -; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %dst2, i8 %c, i32 100, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 %dst1, i8 %c, i64 128, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %dst2, i8 %c, i32 100, i1 false) ; CHECK-NEXT: ret void define void @test_different_types(i8* %dst1, i8* %dst2, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 8, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst2, i8* %dst1, i32 100, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %dst1, i8 %c, i64 128, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst2, i8* %dst1, i32 100, i1 false) ret void } ; CHECK-LABEL: define void @test_different_types_2( -; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %dst1, i8 %c, i32 128, i32 8, i1 false) -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 100, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 8 %dst1, i8 %c, i32 128, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst2, i8 %c, i64 100, i1 false) ; CHECK-NEXT: ret void define void @test_different_types_2(i8* %dst1, i8* %dst2, i8 %c) { - call void @llvm.memset.p0i8.i32(i8* %dst1, i8 %c, i32 128, i32 8, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 100, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* align 8 %dst1, i8 %c, i32 128, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 100, i1 false) ret void } ; CHECK-LABEL: define void @test_different_source_gep( -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) ; CHECK-NEXT: %p = getelementptr i8, i8* %dst1, i64 64 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %p, i64 64, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %p, i64 64, i1 false) ; CHECK-NEXT: ret void define void @test_different_source_gep(i8* %dst1, i8* %dst2, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) ; FIXME: We could optimize this as well. %p = getelementptr i8, i8* %dst1, i64 64 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %p, i64 64, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %p, i64 64, i1 false) ret void } ; CHECK-LABEL: define void @test_variable_size_1( -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 %dst1_size, i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 %dst1_size, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false) ; CHECK-NEXT: ret void define void @test_variable_size_1(i8* %dst1, i64 %dst1_size, i8* %dst2, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 %dst1_size, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 %dst1_size, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 128, i1 false) ret void } ; CHECK-LABEL: define void @test_variable_size_2( -; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 %dst2_size, i32 1, i1 false) +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 %dst2_size, i1 false) ; CHECK-NEXT: ret void define void @test_variable_size_2(i8* %dst1, i8* %dst2, i64 %dst2_size, i8 %c) { - call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 %dst2_size, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %dst1, i8 %c, i64 128, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %dst1, i64 %dst2_size, i1 false) ret void } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) -declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) +declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) diff --git a/llvm/test/Transforms/MemCpyOpt/pr29105.ll b/llvm/test/Transforms/MemCpyOpt/pr29105.ll index 03b176c4d24..e9e9b611aef 100644 --- a/llvm/test/Transforms/MemCpyOpt/pr29105.ll +++ b/llvm/test/Transforms/MemCpyOpt/pr29105.ll @@ -13,12 +13,12 @@ entry-block: %x.sroa.0.0..sroa_cast6 = bitcast [2048 x i64]* %x.sroa.0 to i8* call void @llvm.lifetime.start.p0i8(i64 16384, i8* %x.sroa.0.0..sroa_cast6) call void @llvm.lifetime.start.p0i8(i64 16384, i8* %0) - call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 16384, i32 8, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %x.sroa.0.0..sroa_cast6, i8* %0, i64 16384, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %0, i8 0, i64 16384, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %x.sroa.0.0..sroa_cast6, i8* align 8 %0, i64 16384, i1 false) call void @llvm.lifetime.end.p0i8(i64 16384, i8* %0) %1 = bitcast %Foo* %tmp2 to i8* call void @llvm.lifetime.start.p0i8(i64 16384, i8* %1) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %1, i8* %x.sroa.0.0..sroa_cast6, i64 16384, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %1, i8* align 8 %x.sroa.0.0..sroa_cast6, i64 16384, i1 false) call void @bar(%Foo* noalias nocapture nonnull dereferenceable(16384) %tmp2) call void @llvm.lifetime.end.p0i8(i64 16384, i8* %1) call void @llvm.lifetime.end.p0i8(i64 16384, i8* %x.sroa.0.0..sroa_cast6) @@ -27,13 +27,13 @@ entry-block: declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #1 -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #1 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #1 declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #1 declare void @bar(%Foo* noalias nocapture readonly dereferenceable(16384)) unnamed_addr #0 -declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i32, i1) #1 +declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1) #1 attributes #0 = { uwtable } attributes #1 = { argmemonly nounwind } diff --git a/llvm/test/Transforms/MemCpyOpt/profitable-memset.ll b/llvm/test/Transforms/MemCpyOpt/profitable-memset.ll index bbef1244ee3..649d2386f96 100644 --- a/llvm/test/Transforms/MemCpyOpt/profitable-memset.ll +++ b/llvm/test/Transforms/MemCpyOpt/profitable-memset.ll @@ -4,7 +4,7 @@ target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128" ; CHECK-LABEL: @foo( ; CHECK-NOT: store -; CHECK: call void @llvm.memset.p0i8.i64(i8* %2, i8 0, i64 8, i32 2, i1 false) +; CHECK: call void @llvm.memset.p0i8.i64(i8* align 2 %2, i8 0, i64 8, i1 false) define void @foo(i64* nocapture %P) { entry: diff --git a/llvm/test/Transforms/MemCpyOpt/smaller.ll b/llvm/test/Transforms/MemCpyOpt/smaller.ll index d0ec56e25dd..0c82b5201dc 100644 --- a/llvm/test/Transforms/MemCpyOpt/smaller.ll +++ b/llvm/test/Transforms/MemCpyOpt/smaller.ll @@ -5,7 +5,7 @@ ; Memcpyopt shouldn't optimize the second memcpy using the first ; because the first has a smaller size. -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp, i8* getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i32 16, i32 4, i1 false) +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %tmp, i8* align 4 getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i32 16, i1 false) target datalayout = "e-p:32:32:32" @@ -15,15 +15,15 @@ target datalayout = "e-p:32:32:32" @cell = external global %struct.s declare void @check(%struct.s* byval %p) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind define void @foo() nounwind { entry: %agg.tmp = alloca %struct.s, align 4 store i32 99, i32* getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 1), align 4 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i8* getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i32 0, i32 0), i32 11, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i8* align 1 getelementptr inbounds ([11 x i8], [11 x i8]* @.str, i32 0, i32 0), i32 11, i1 false) %tmp = getelementptr inbounds %struct.s, %struct.s* %agg.tmp, i32 0, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp, i8* getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i32 16, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %tmp, i8* align 4 getelementptr inbounds (%struct.s, %struct.s* @cell, i32 0, i32 0, i32 0), i32 16, i1 false) call void @check(%struct.s* byval %agg.tmp) ret void } diff --git a/llvm/test/Transforms/MemCpyOpt/sret.ll b/llvm/test/Transforms/MemCpyOpt/sret.ll index 34ba4c4d8bb..a99b52d5d6e 100644 --- a/llvm/test/Transforms/MemCpyOpt/sret.ll +++ b/llvm/test/Transforms/MemCpyOpt/sret.ll @@ -21,10 +21,10 @@ entry: call void @ccoshl(%0* noalias sret %memtmp, %0* byval align 8 %iz) nounwind %memtmp14 = bitcast %0* %memtmp to i8* %agg.result15 = bitcast %0* %agg.result to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %agg.result15, i8* %memtmp14, i32 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %agg.result15, i8* align 16 %memtmp14, i32 32, i1 false) ret void } declare void @ccoshl(%0* noalias nocapture sret, %0* byval) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind diff --git a/llvm/test/Transforms/MergeFunc/vector.ll b/llvm/test/Transforms/MergeFunc/vector.ll index ef1375311e6..db95ec742ba 100644 --- a/llvm/test/Transforms/MergeFunc/vector.ll +++ b/llvm/test/Transforms/MergeFunc/vector.ll @@ -59,7 +59,7 @@ declare void @_ZNSt6vectorIPvSaIS0_EE13_M_insert_auxEN9__gnu_cxx17__normal_itera declare void @_ZdlPv(i8*) nounwind -declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memmove.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind declare void @_ZSt17__throw_bad_allocv() noreturn diff --git a/llvm/test/Transforms/MetaRenamer/metarenamer.ll b/llvm/test/Transforms/MetaRenamer/metarenamer.ll index 7b527ae54cb..9cc7eb2a73f 100644 --- a/llvm/test/Transforms/MetaRenamer/metarenamer.ll +++ b/llvm/test/Transforms/MetaRenamer/metarenamer.ll @@ -35,11 +35,11 @@ define void @func_4_xxx(%struct.foo_xxx* sret %agg.result) nounwind uwtable ssp store double 4.000000e+00, double* %6, align 8 %7 = bitcast %struct.foo_xxx* %agg.result to i8* %8 = bitcast %struct.foo_xxx* %1 to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %7, i8* %8, i64 24, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %7, i8* align 8 %8, i64 24, i1 false) ret void } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind define i32 @func_5_xxx(i32 %arg_1_xxx, i32 %arg_2_xxx, i32 %arg_3_xxx, i32 %arg_4_xxx) nounwind uwtable ssp { %1 = alloca i32, align 4 diff --git a/llvm/test/Transforms/NewGVN/memory-handling.ll b/llvm/test/Transforms/NewGVN/memory-handling.ll index a0c4a998b8b..12e882bd089 100644 --- a/llvm/test/Transforms/NewGVN/memory-handling.ll +++ b/llvm/test/Transforms/NewGVN/memory-handling.ll @@ -20,9 +20,9 @@ declare i16** @__ctype_b_loc() local_unnamed_addr #1 ; Function Attrs: nounwind uwtable define void @BuildMask(i8* nocapture readonly) local_unnamed_addr #0 { - tail call void @llvm.memset.p0i8.i64(i8* bitcast ([26 x %struct.Letter]* @alPhrase to i8*), i8 0, i64 416, i32 16, i1 false) - tail call void @llvm.memset.p0i8.i64(i8* bitcast ([2 x i64]* @aqMainMask to i8*), i8 0, i64 16, i32 16, i1 false) - tail call void @llvm.memset.p0i8.i64(i8* bitcast ([2 x i64]* @aqMainSign to i8*), i8 0, i64 16, i32 16, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* align 16 bitcast ([26 x %struct.Letter]* @alPhrase to i8*), i8 0, i64 416, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* align 16 bitcast ([2 x i64]* @aqMainMask to i8*), i8 0, i64 16, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* align 16 bitcast ([2 x i64]* @aqMainSign to i8*), i8 0, i64 16, i1 false) br label %.sink.split .sink.split: ; preds = %14, %1 @@ -162,7 +162,7 @@ define void @BuildMask(i8* nocapture readonly) local_unnamed_addr #0 { } ; Function Attrs: argmemonly nounwind -declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i32, i1) #2 +declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1) #2 ; Function Attrs: inlinehint nounwind readonly uwtable declare i32 @tolower(i32) local_unnamed_addr #3 diff --git a/llvm/test/Transforms/NewGVN/nonescaping-malloc.ll b/llvm/test/Transforms/NewGVN/nonescaping-malloc.ll index 27d93e270d3..678211cf15e 100644 --- a/llvm/test/Transforms/NewGVN/nonescaping-malloc.ll +++ b/llvm/test/Transforms/NewGVN/nonescaping-malloc.ll @@ -83,7 +83,7 @@ bb.i.i: ; preds = %bb4.i _ZN4llvm14StringMapEntryIPvE6CreateINS_15MallocAllocatorES1_EEPS2_PKcS7_RT_T0_.exit.i: ; preds = %bb.i.i, %bb4.i %tmp.i18.i.i = getelementptr inbounds i8, i8* %tmp.i20.i.i, i64 16 %tmp15.i.i = zext i32 %tmp4.i.i to i64 - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp.i18.i.i, i8* %tmp41.i, i64 %tmp15.i.i, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp.i18.i.i, i8* %tmp41.i, i64 %tmp15.i.i, i1 false) %tmp.i18.sum.i.i = add i64 %tmp15.i.i, 16 %tmp17.i.i = getelementptr inbounds i8, i8* %tmp.i20.i.i, i64 %tmp.i18.sum.i.i store i8 0, i8* %tmp17.i.i, align 1 @@ -109,4 +109,4 @@ _ZN4llvm9StringMapIPvNS_15MallocAllocatorEE16GetOrCreateValueIS1_EERNS_14StringM ret %"struct.llvm::StringMapEntry<void*>"* %tmp10.i.i } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind diff --git a/llvm/test/Transforms/NewGVN/pr17732.ll b/llvm/test/Transforms/NewGVN/pr17732.ll index 6aee6ebeb06..48267518242 100644 --- a/llvm/test/Transforms/NewGVN/pr17732.ll +++ b/llvm/test/Transforms/NewGVN/pr17732.ll @@ -13,10 +13,10 @@ target triple = "x86_64-unknown-linux-gnu" define i32 @main() { entry: - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds (%struct.with_array, %struct.with_array* @array_with_zeroinit, i64 0, i32 0, i64 0), i8* getelementptr inbounds ({ [2 x i8], i32, i8, [3 x i8] }, { [2 x i8], i32, i8, [3 x i8] }* @main.obj_with_array, i64 0, i32 0, i64 0), i64 12, i32 4, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 getelementptr inbounds (%struct.with_array, %struct.with_array* @array_with_zeroinit, i64 0, i32 0, i64 0), i8* align 4 getelementptr inbounds ({ [2 x i8], i32, i8, [3 x i8] }, { [2 x i8], i32, i8, [3 x i8] }* @main.obj_with_array, i64 0, i32 0, i64 0), i64 12, i1 false) %0 = load i8, i8* getelementptr inbounds (%struct.with_array, %struct.with_array* @array_with_zeroinit, i64 0, i32 2), align 4 - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* getelementptr inbounds (%struct.with_vector, %struct.with_vector* @vector_with_zeroinit, i64 0, i32 0, i64 0), i8* getelementptr inbounds ({ <2 x i8>, i32, i8, [3 x i8] }, { <2 x i8>, i32, i8, [3 x i8] }* @main.obj_with_vector, i64 0, i32 0, i64 0), i64 12, i32 4, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 getelementptr inbounds (%struct.with_vector, %struct.with_vector* @vector_with_zeroinit, i64 0, i32 0, i64 0), i8* align 4 getelementptr inbounds ({ <2 x i8>, i32, i8, [3 x i8] }, { <2 x i8>, i32, i8, [3 x i8] }* @main.obj_with_vector, i64 0, i32 0, i64 0), i64 12, i1 false) %1 = load i8, i8* getelementptr inbounds (%struct.with_vector, %struct.with_vector* @vector_with_zeroinit, i64 0, i32 2), align 4 %conv0 = sext i8 %0 to i32 %conv1 = sext i8 %1 to i32 @@ -26,4 +26,4 @@ entry: ; CHECK: ret i32 1 } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i1) diff --git a/llvm/test/Transforms/NewGVN/rle.ll b/llvm/test/Transforms/NewGVN/rle.ll index 902abe979ea..f6e96ebd1b1 100644 --- a/llvm/test/Transforms/NewGVN/rle.ll +++ b/llvm/test/Transforms/NewGVN/rle.ll @@ -4,7 +4,7 @@ define signext i16 @memset_to_i16_local(i16* %A) nounwind ssp { entry: %conv = bitcast i16* %A to i8* - tail call void @llvm.memset.p0i8.i64(i8* %conv, i8 1, i64 200, i32 1, i1 false) + tail call void @llvm.memset.p0i8.i64(i8* %conv, i8 1, i64 200, i1 false) %arrayidx = getelementptr inbounds i16, i16* %A, i64 42 %tmp2 = load i16, i16* %arrayidx ret i16 %tmp2 @@ -20,7 +20,7 @@ entry: define float @memcpy_to_float_local(float* %A) nounwind ssp { entry: %conv = bitcast float* %A to i8* ; <i8*> [#uses=1] - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %conv, i8* bitcast ({i32, float, i32 }* @GCst to i8*), i64 12, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %conv, i8* bitcast ({i32, float, i32 }* @GCst to i8*), i64 12, i1 false) %arrayidx = getelementptr inbounds float, float* %A, i64 1 ; <float*> [#uses=1] %tmp2 = load float, float* %arrayidx ; <float> [#uses=1] ret float %tmp2 @@ -32,7 +32,7 @@ entry: define float @memcpy_to_float_local_as1(float* %A) nounwind ssp { entry: %conv = bitcast float* %A to i8* ; <i8*> [#uses=1] - tail call void @llvm.memcpy.p0i8.p1i8.i64(i8* %conv, i8 addrspace(1)* bitcast ({i32, float, i32 } addrspace(1)* @GCst_as1 to i8 addrspace(1)*), i64 12, i32 1, i1 false) + tail call void @llvm.memcpy.p0i8.p1i8.i64(i8* %conv, i8 addrspace(1)* bitcast ({i32, float, i32 } addrspace(1)* @GCst_as1 to i8 addrspace(1)*), i64 12, i1 false) %arrayidx = getelementptr inbounds float, float* %A, i64 1 ; <float*> [#uses=1] %tmp2 = load float, float* %arrayidx ; <float> [#uses=1] ret float %tmp2 @@ -46,14 +46,14 @@ define i32 @memset_to_load() nounwind readnone { entry: %x = alloca [256 x i32], align 4 ; <[256 x i32]*> [#uses=2] %tmp = bitcast [256 x i32]* %x to i8* ; <i8*> [#uses=1] - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 1024, i32 4, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 4 %tmp, i8 0, i64 1024, i1 false) %arraydecay = getelementptr inbounds [256 x i32], [256 x i32]* %x, i32 0, i32 0 ; <i32*> %tmp1 = load i32, i32* %arraydecay ; <i32> [#uses=1] ret i32 %tmp1 ; CHECK-LABEL: @memset_to_load( ; CHECK: ret i32 0 } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind -declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind +declare void @llvm.memcpy.p0i8.p1i8.i64(i8* nocapture, i8 addrspace(1)* nocapture, i64, i1) nounwind diff --git a/llvm/test/Transforms/ObjCARC/nested.ll b/llvm/test/Transforms/ObjCARC/nested.ll index cf14a1f9a66..b317cd80295 100644 --- a/llvm/test/Transforms/ObjCARC/nested.ll +++ b/llvm/test/Transforms/ObjCARC/nested.ll @@ -12,7 +12,7 @@ declare i8* @returner() declare i8* @objc_retainAutoreleasedReturnValue(i8*) declare i8* @objc_retain(i8*) declare void @objc_enumerationMutation(i8*) -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind declare i8* @objc_msgSend(i8*, i8*, ...) nonlazybind declare void @use(i8*) declare void @objc_release(i8*) @@ -35,7 +35,7 @@ entry: %items.ptr = alloca [16 x i8*], align 8 %0 = call i8* @objc_retain(i8* %a) nounwind %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %1 = call i8* @objc_retain(i8* %0) nounwind %tmp2 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %1, i8* %tmp2, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -100,7 +100,7 @@ entry: %call = call i8* @returner() %0 = call i8* @objc_retainAutoreleasedReturnValue(i8* %call) nounwind %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %1 = call i8* @objc_retain(i8* %0) nounwind %tmp2 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call3 = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %1, i8* %tmp2, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -165,7 +165,7 @@ entry: %tmp = load i8*, i8** @g, align 8 %0 = call i8* @objc_retain(i8* %tmp) nounwind %tmp2 = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp2, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp2, i8 0, i64 64, i1 false) %1 = call i8* @objc_retain(i8* %0) nounwind %tmp4 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %1, i8* %tmp4, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -230,7 +230,7 @@ entry: %call = call i8* @returner() %0 = call i8* @objc_retainAutoreleasedReturnValue(i8* %call) nounwind %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %1 = call i8* @objc_retain(i8* %0) nounwind %tmp2 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call3 = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %1, i8* %tmp2, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -296,7 +296,7 @@ entry: %call = call i8* @returner() %0 = call i8* @objc_retainAutoreleasedReturnValue(i8* %call) nounwind %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %1 = call i8* @objc_retain(i8* %0) nounwind %tmp2 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call3 = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %1, i8* %tmp2, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -365,7 +365,7 @@ entry: %0 = call i8* @objc_retainAutoreleasedReturnValue(i8* %call) nounwind call void @callee() %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %1 = call i8* @objc_retain(i8* %0) nounwind %tmp2 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call3 = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %1, i8* %tmp2, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -431,7 +431,7 @@ entry: %call = call i8* @returner() %0 = call i8* @objc_retainAutoreleasedReturnValue(i8* %call) nounwind %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %1 = call i8* @objc_retain(i8* %0) nounwind %tmp2 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call3 = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %1, i8* %tmp2, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -508,7 +508,7 @@ entry: %call1 = call i8* @returner() %1 = call i8* @objc_retainAutoreleasedReturnValue(i8* %call1) nounwind %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %2 = call i8* @objc_retain(i8* %0) nounwind %tmp3 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call4 = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %2, i8* %tmp3, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -575,7 +575,7 @@ entry: %call1 = call i8* @returner() %1 = call i8* @objc_retainAutoreleasedReturnValue(i8* %call1) nounwind %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %2 = call i8* @objc_retain(i8* %0) nounwind %tmp3 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call4 = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %2, i8* %tmp3, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -642,7 +642,7 @@ entry: %1 = call i8* @objc_retainAutoreleasedReturnValue(i8* %call1) nounwind call void @callee() %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %2 = call i8* @objc_retain(i8* %0) nounwind %tmp3 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call4 = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %2, i8* %tmp3, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) @@ -710,7 +710,7 @@ entry: %1 = call i8* @objc_retainAutoreleasedReturnValue(i8* %call1) nounwind call void @callee() %tmp = bitcast %struct.__objcFastEnumerationState* %state.ptr to i8* - call void @llvm.memset.p0i8.i64(i8* %tmp, i8 0, i64 64, i32 8, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 8 %tmp, i8 0, i64 64, i1 false) %2 = call i8* @objc_retain(i8* %0) nounwind %tmp3 = load i8*, i8** @"\01L_OBJC_SELECTOR_REFERENCES_", align 8 %call4 = call i64 bitcast (i8* (i8*, i8*, ...)* @objc_msgSend to i64 (i8*, i8*, %struct.__objcFastEnumerationState*, [16 x i8*]*, i64)*)(i8* %2, i8* %tmp3, %struct.__objcFastEnumerationState* %state.ptr, [16 x i8*]* %items.ptr, i64 16) diff --git a/llvm/test/Transforms/PGOProfile/memcpy.ll b/llvm/test/Transforms/PGOProfile/memcpy.ll index 9db4a4a2dd4..0a6c44b4374 100644 --- a/llvm/test/Transforms/PGOProfile/memcpy.ll +++ b/llvm/test/Transforms/PGOProfile/memcpy.ll @@ -24,7 +24,7 @@ for.cond1: for.body3: %conv = sext i32 %add to i64 ; CHECK: call void @__llvm_profile_instrument_range(i64 %conv, i8* bitcast ({ i64, i64, i64*, i8*, i8*, i32, [2 x i16] }* @__profd_foo to i8*), i32 0, i64 0, i64 8, i64 8192) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i1 false) %inc = add nsw i32 %j.0, 1 br label %for.cond1 @@ -32,4 +32,4 @@ for.end6: ret void } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) diff --git a/llvm/test/Transforms/PGOProfile/memop_clone.ll b/llvm/test/Transforms/PGOProfile/memop_clone.ll index 94ac92dd8a1..4b12e7c5b57 100644 --- a/llvm/test/Transforms/PGOProfile/memop_clone.ll +++ b/llvm/test/Transforms/PGOProfile/memop_clone.ll @@ -3,24 +3,24 @@ define i32 @test(i8* %a, i8* %b) !prof !1 { ; CHECK_LABEL: test ; CHECK: MemOP.Case.3: -; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %a, i32 3, i32 1, i1 false) +; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %a, i32 3, i1 false) ; CHECK: MemOP.Case.2: -; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %a, i32 2, i32 1, i1 false) +; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %a, i32 2, i1 false) ; CHECK: MemOP.Default: -; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %a, i32 undef, i32 1, i1 false) +; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %a, i32 undef, i1 false) ; CHECK: MemOP.Case.33: -; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* %b, i64 3, i32 1, i1 false) +; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* %b, i64 3, i1 false) ; CHECK MemOP.Case.24: -; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* %b, i64 2, i32 1, i1 false) +; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* %b, i64 2, i1 false) ; CHECK: MemOP.Default2: -; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* %b, i64 undef, i32 1, i1 false) - tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %a, i32 undef, i32 1, i1 false), !prof !2 - tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* %b, i64 undef, i32 1, i1 false), !prof !2 +; CHECK: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* %b, i64 undef, i1 false) + tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %a, i32 undef, i1 false), !prof !2 + tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* undef, i8* %b, i64 undef, i1 false), !prof !2 unreachable } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i32, i1) -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) !1 = !{!"function_entry_count", i64 5170} !2 = !{!"VP", i32 1, i64 2585, i64 3, i64 1802, i64 2, i64 783} diff --git a/llvm/test/Transforms/PGOProfile/memop_size_annotation.ll b/llvm/test/Transforms/PGOProfile/memop_size_annotation.ll index 5481d12b1af..4310d8ec9de 100644 --- a/llvm/test/Transforms/PGOProfile/memop_size_annotation.ll +++ b/llvm/test/Transforms/PGOProfile/memop_size_annotation.ll @@ -30,8 +30,8 @@ for.cond1: for.body3: %add = add nsw i32 %i.0, 1 %conv = sext i32 %add to i64 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false) -; MEMOP_ANNOTATION: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i1 false) +; MEMOP_ANNOTATION: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i1 false) ; MEMOP_ANNOTATION-SAME: !prof ![[MEMOP_VALUESITE:[0-9]+]] ; MEMOP_ANNOTATION9: ![[MEMOP_VALUESITE]] = !{!"VP", i32 1, i64 556, i64 1, i64 99, i64 2, i64 88, i64 3, i64 77, i64 9, i64 72, i64 4, i64 66, i64 5, i64 55, i64 6, i64 44, i64 7, i64 33, i64 8, i64 22} ; MEMOP_ANNOTATION4: ![[MEMOP_VALUESITE]] = !{!"VP", i32 1, i64 556, i64 1, i64 99, i64 2, i64 88, i64 3, i64 77, i64 9, i64 72} @@ -54,6 +54,6 @@ for.end6: declare void @llvm.lifetime.start(i64, i8* nocapture) -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) declare void @llvm.lifetime.end(i64, i8* nocapture) diff --git a/llvm/test/Transforms/PGOProfile/memop_size_from_strlen.ll b/llvm/test/Transforms/PGOProfile/memop_size_from_strlen.ll index 527f328b2d2..1d8509a0b0b 100644 --- a/llvm/test/Transforms/PGOProfile/memop_size_from_strlen.ll +++ b/llvm/test/Transforms/PGOProfile/memop_size_from_strlen.ll @@ -1,6 +1,6 @@ ; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture writeonly, i8* nocapture readonly, i32, i1) declare i32 @strlen(i8* nocapture) ; CHECK_LABEL: test @@ -9,6 +9,6 @@ declare i32 @strlen(i8* nocapture) define void @test(i8* %a, i8* %p) { %c = call i32 @strlen(i8* %p) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %p, i32 %c, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %p, i32 %c, i1 false) ret void } diff --git a/llvm/test/Transforms/PGOProfile/memop_size_opt.ll b/llvm/test/Transforms/PGOProfile/memop_size_opt.ll index fc5f41d40fb..4a2487a0b09 100644 --- a/llvm/test/Transforms/PGOProfile/memop_size_opt.ll +++ b/llvm/test/Transforms/PGOProfile/memop_size_opt.ll @@ -32,28 +32,28 @@ for.cond1: for.body3: %add = add nsw i32 %i.0, 1 %conv = sext i32 %add to i64 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof !30 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 %conv, i32 1, i1 false), !prof !31 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i1 false), !prof !30 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 %conv, i1 false), !prof !31 br label %for.inc ; MEMOP_OPT: switch i64 %conv, label %[[DEFAULT_LABEL:.*]] [ ; MEMOP_OPT: i64 1, label %[[CASE_1_LABEL:.*]] ; MEMOP_OPT: ], !prof [[SWITCH_BW:![0-9]+]] ; MEMOP_OPT: [[CASE_1_LABEL]]: -; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 1, i32 1, i1 false) +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 1, i1 false) ; MEMOP_OPT: br label %[[MERGE_LABEL:.*]] ; MEMOP_OPT: [[DEFAULT_LABEL]]: -; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof [[NEWVP:![0-9]+]] +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i1 false), !prof [[NEWVP:![0-9]+]] ; MEMOP_OPT: br label %[[MERGE_LABEL]] ; MEMOP_OPT: [[MERGE_LABEL]]: ; MEMOP_OPT: switch i64 %conv, label %[[DEFAULT_LABEL2:.*]] [ ; MEMOP_OPT: i64 1, label %[[CASE_1_LABEL2:.*]] ; MEMOP_OPT: ], !prof [[SWITCH_BW:![0-9]+]] ; MEMOP_OPT: [[CASE_1_LABEL2]]: -; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 1, i32 1, i1 false) +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 1, i1 false) ; MEMOP_OPT: br label %[[MERGE_LABEL2:.*]] ; MEMOP_OPT: [[DEFAULT_LABEL2]]: -; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 %conv, i32 1, i1 false), !prof [[NEWVP]] +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst2, i8* %src2, i64 %conv, i1 false), !prof [[NEWVP]] ; MEMOP_OPT: br label %[[MERGE_LABEL2]] ; MEMOP_OPT: [[MERGE_LABEL2]]: ; MEMOP_OPT: br label %for.inc @@ -116,7 +116,7 @@ for.end6: declare void @llvm.lifetime.start(i64, i8* nocapture) -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) declare void @llvm.lifetime.end(i64, i8* nocapture) diff --git a/llvm/test/Transforms/PGOProfile/memop_size_opt_zero.ll b/llvm/test/Transforms/PGOProfile/memop_size_opt_zero.ll index ede34f0de80..de48b622e46 100644 --- a/llvm/test/Transforms/PGOProfile/memop_size_opt_zero.ll +++ b/llvm/test/Transforms/PGOProfile/memop_size_opt_zero.ll @@ -7,13 +7,13 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" define void @foo(i8* %dst, i8* %src, i64 %conv) !prof !0 { - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof !1 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i1 false), !prof !1 ret void } -; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof !1 +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i1 false), !prof !1 !0 = !{!"function_entry_count", i64 1} !1 = !{!"VP", i32 1, i64 0, i64 1, i64 0, i64 2, i64 0, i64 3, i64 0, i64 9, i64 0, i64 4, i64 0, i64 5, i64 0, i64 6, i64 0, i64 7, i64 0, i64 8, i64 0} -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) diff --git a/llvm/test/Transforms/PlaceSafepoints/memset.ll b/llvm/test/Transforms/PlaceSafepoints/memset.ll index 7edca282292..41881f67580 100644 --- a/llvm/test/Transforms/PlaceSafepoints/memset.ll +++ b/llvm/test/Transforms/PlaceSafepoints/memset.ll @@ -5,13 +5,13 @@ define void @test(i32, i8 addrspace(1)* %ptr) gc "statepoint-example" { ; CHECK-NEXT: llvm.memset ; CHECK: do_safepoint ; CHECK: @foo - call void @llvm.memset.p1i8.i64(i8 addrspace(1)* %ptr, i8 0, i64 24, i32 8, i1 false) + call void @llvm.memset.p1i8.i64(i8 addrspace(1)* align 8 %ptr, i8 0, i64 24, i1 false) call void @foo() ret void } declare void @foo() -declare void @llvm.memset.p1i8.i64(i8 addrspace(1)*, i8, i64, i32, i1) +declare void @llvm.memset.p1i8.i64(i8 addrspace(1)*, i8, i64, i1) declare void @do_safepoint() define void @gc.safepoint_poll() { diff --git a/llvm/test/Transforms/SROA/address-spaces.ll b/llvm/test/Transforms/SROA/address-spaces.ll index a54a3afc79f..9cd9137833a 100644 --- a/llvm/test/Transforms/SROA/address-spaces.ll +++ b/llvm/test/Transforms/SROA/address-spaces.ll @@ -1,10 +1,10 @@ ; RUN: opt < %s -sroa -S | FileCheck %s target datalayout = "e-p:64:64:64-p1:16:16:16-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64" -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) -declare void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* nocapture, i8* nocapture readonly, i32, i32, i1) -declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture readonly, i32, i32, i1) -declare void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i1) +declare void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* nocapture, i8* nocapture readonly, i32, i1) +declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture readonly, i32, i1) +declare void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i1) ; Make sure an illegal bitcast isn't introduced @@ -16,9 +16,9 @@ define void @test_address_space_1_1(<2 x i64> addrspace(1)* %a, i16 addrspace(1) %aa = alloca <2 x i64>, align 16 %aptr = bitcast <2 x i64> addrspace(1)* %a to i8 addrspace(1)* %aaptr = bitcast <2 x i64>* %aa to i8* - call void @llvm.memcpy.p0i8.p1i8.i32(i8* %aaptr, i8 addrspace(1)* %aptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p0i8.p1i8.i32(i8* align 2 %aaptr, i8 addrspace(1)* align 2 %aptr, i32 16, i1 false) %bptr = bitcast i16 addrspace(1)* %b to i8 addrspace(1)* - call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* %bptr, i8* %aaptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false) ret void } @@ -30,9 +30,9 @@ define void @test_address_space_1_0(<2 x i64> addrspace(1)* %a, i16* %b) { %aa = alloca <2 x i64>, align 16 %aptr = bitcast <2 x i64> addrspace(1)* %a to i8 addrspace(1)* %aaptr = bitcast <2 x i64>* %aa to i8* - call void @llvm.memcpy.p0i8.p1i8.i32(i8* %aaptr, i8 addrspace(1)* %aptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p0i8.p1i8.i32(i8* align 2 %aaptr, i8 addrspace(1)* align 2 %aptr, i32 16, i1 false) %bptr = bitcast i16* %b to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %bptr, i8* %aaptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false) ret void } @@ -44,9 +44,9 @@ define void @test_address_space_0_1(<2 x i64>* %a, i16 addrspace(1)* %b) { %aa = alloca <2 x i64>, align 16 %aptr = bitcast <2 x i64>* %a to i8* %aaptr = bitcast <2 x i64>* %aa to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %aaptr, i8* %aptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %aaptr, i8* align 2 %aptr, i32 16, i1 false) %bptr = bitcast i16 addrspace(1)* %b to i8 addrspace(1)* - call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* %bptr, i8* %aaptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false) ret void } @@ -62,7 +62,7 @@ for.end: store [5 x i64] %in.coerce, [5 x i64]* %0, align 8 %scevgep9 = getelementptr %struct.struct_test_27.0.13, %struct.struct_test_27.0.13* %in, i32 0, i32 4, i32 0 %scevgep910 = bitcast i32* %scevgep9 to i8* - call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* undef, i8* %scevgep910, i32 16, i32 4, i1 false) + call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 4 undef, i8* align 4 %scevgep910, i32 16, i1 false) ret void } diff --git a/llvm/test/Transforms/SROA/alignment.ll b/llvm/test/Transforms/SROA/alignment.ll index 455d14246e5..dd0661374fd 100644 --- a/llvm/test/Transforms/SROA/alignment.ll +++ b/llvm/test/Transforms/SROA/alignment.ll @@ -1,7 +1,7 @@ ; RUN: opt < %s -sroa -S | FileCheck %s target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64" -declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i32(i8*, i8*, i32, i1) define void @test1({ i8, i8 }* %a, { i8, i8 }* %b) { ; CHECK-LABEL: @test1( @@ -23,8 +23,8 @@ entry: store i8 420, i8* %gep_alloca, align 16 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %gep_alloca, i8* %gep_a, i32 2, i32 16, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %gep_b, i8* %gep_alloca, i32 2, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %gep_alloca, i8* align 16 %gep_a, i32 2, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %gep_b, i8* align 16 %gep_alloca, i32 2, i1 false) ret void } @@ -57,9 +57,9 @@ entry: %aa = alloca <2 x i64>, align 16 %aptr = bitcast <2 x i64>* %a to i8* %aaptr = bitcast <2 x i64>* %aa to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %aaptr, i8* %aptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %aaptr, i8* align 2 %aptr, i32 16, i1 false) %bptr = bitcast i16* %b to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %bptr, i8* %aaptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %bptr, i8* align 2 %aaptr, i32 16, i1 false) ret void } @@ -77,10 +77,10 @@ entry: %a = alloca { i8*, i8*, i8* } %b = alloca { i8*, i8*, i8* } %a_raw = bitcast { i8*, i8*, i8* }* %a to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a_raw, i8* %x, i32 22, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %a_raw, i8* align 8 %x, i32 22, i1 false) %b_raw = bitcast { i8*, i8*, i8* }* %b to i8* %b_gep = getelementptr i8, i8* %b_raw, i32 6 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b_gep, i8* %x, i32 18, i32 2, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 2 %b_gep, i8* align 2 %x, i32 18, i1 false) ret void } @@ -155,7 +155,7 @@ entry: %raw2 = getelementptr inbounds [16 x i8], [16 x i8]* %a, i32 0, i32 8 %ptr2 = bitcast i8* %raw2 to double* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %raw1, i8* %out, i32 16, i32 0, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %raw1, i8* %out, i32 16, i1 false) ; CHECK: %[[val2:.*]] = load double, double* %{{.*}}, align 1 ; CHECK: %[[val1:.*]] = load double, double* %{{.*}}, align 1 @@ -165,7 +165,7 @@ entry: store double %val1, double* %ptr1, align 1 store double %val2, double* %ptr2, align 1 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %raw1, i32 16, i32 0, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %raw1, i32 16, i1 false) ; CHECK: store double %[[val1]], double* %{{.*}}, align 1 ; CHECK: store double %[[val2]], double* %{{.*}}, align 1 diff --git a/llvm/test/Transforms/SROA/alloca-address-space.ll b/llvm/test/Transforms/SROA/alloca-address-space.ll index 9d9f78f07ca..d28bc39e963 100644 --- a/llvm/test/Transforms/SROA/alloca-address-space.ll +++ b/llvm/test/Transforms/SROA/alloca-address-space.ll @@ -1,10 +1,10 @@ ; RUN: opt < %s -sroa -S | FileCheck %s target datalayout = "e-p:64:64:64-p1:16:16:16-p2:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64-A2" -declare void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* nocapture, i8 addrspace(2)* nocapture readonly, i32, i32, i1) -declare void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(2)* nocapture readonly, i32, i32, i1) -declare void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i32, i1) -declare void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i32, i1) +declare void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* nocapture, i8 addrspace(2)* nocapture readonly, i32, i1) +declare void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(2)* nocapture readonly, i32, i1) +declare void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i1) +declare void @llvm.memcpy.p1i8.p1i8.i32(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture readonly, i32, i1) @@ -16,9 +16,9 @@ define void @test_address_space_1_1(<2 x i64> addrspace(1)* %a, i16 addrspace(1) %aa = alloca <2 x i64>, align 16, addrspace(2) %aptr = bitcast <2 x i64> addrspace(1)* %a to i8 addrspace(1)* %aaptr = bitcast <2 x i64> addrspace(2)* %aa to i8 addrspace(2)* - call void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* %aaptr, i8 addrspace(1)* %aptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* align 2 %aaptr, i8 addrspace(1)* align 2 %aptr, i32 16, i1 false) %bptr = bitcast i16 addrspace(1)* %b to i8 addrspace(1)* - call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* %bptr, i8 addrspace(2)* %aaptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* align 2 %bptr, i8 addrspace(2)* align 2 %aaptr, i32 16, i1 false) ret void } @@ -30,9 +30,9 @@ define void @test_address_space_1_0(<2 x i64> addrspace(1)* %a, i16 addrspace(2) %aa = alloca <2 x i64>, align 16, addrspace(2) %aptr = bitcast <2 x i64> addrspace(1)* %a to i8 addrspace(1)* %aaptr = bitcast <2 x i64> addrspace(2)* %aa to i8 addrspace(2)* - call void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* %aaptr, i8 addrspace(1)* %aptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p2i8.p1i8.i32(i8 addrspace(2)* align 2 %aaptr, i8 addrspace(1)* align 2 %aptr, i32 16, i1 false) %bptr = bitcast i16 addrspace(2)* %b to i8 addrspace(2)* - call void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* %bptr, i8 addrspace(2)* %aaptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* align 2 %bptr, i8 addrspace(2)* align 2 %aaptr, i32 16, i1 false) ret void } @@ -44,9 +44,9 @@ define void @test_address_space_0_1(<2 x i64> addrspace(2)* %a, i16 addrspace(1) %aa = alloca <2 x i64>, align 16, addrspace(2) %aptr = bitcast <2 x i64> addrspace(2)* %a to i8 addrspace(2)* %aaptr = bitcast <2 x i64> addrspace(2)* %aa to i8 addrspace(2)* - call void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* %aaptr, i8 addrspace(2)* %aptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p2i8.p2i8.i32(i8 addrspace(2)* align 2 %aaptr, i8 addrspace(2)* align 2 %aptr, i32 16, i1 false) %bptr = bitcast i16 addrspace(1)* %b to i8 addrspace(1)* - call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* %bptr, i8 addrspace(2)* %aaptr, i32 16, i32 2, i1 false) + call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* align 2 %bptr, i8 addrspace(2)* align 2 %aaptr, i32 16, i1 false) ret void } @@ -61,7 +61,7 @@ for.end: store [5 x i64] %in.coerce, [5 x i64] addrspace(2)* %0, align 8 %scevgep9 = getelementptr %struct.struct_test_27.0.13, %struct.struct_test_27.0.13 addrspace(2)* %in, i32 0, i32 4, i32 0 %scevgep910 = bitcast i32 addrspace(2)* %scevgep9 to i8 addrspace(2)* - call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* undef, i8 addrspace(2)* %scevgep910, i32 16, i32 4, i1 false) + call void @llvm.memcpy.p1i8.p2i8.i32(i8 addrspace(1)* align 4 undef, i8 addrspace(2)* align 4 %scevgep910, i32 16, i1 false) ret void } diff --git a/llvm/test/Transforms/SROA/basictest.ll b/llvm/test/Transforms/SROA/basictest.ll index 8a30be9bf4f..948663ac3a1 100644 --- a/llvm/test/Transforms/SROA/basictest.ll +++ b/llvm/test/Transforms/SROA/basictest.ll @@ -80,31 +80,31 @@ entry: ; CHECK-NEXT: %[[test3_a7:.*]] = alloca [85 x i8] %b = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 300, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 300, i1 false) ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a1]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %src, i32 42 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %src, i32 42 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 42 ; CHECK-NEXT: %[[test3_r1:.*]] = load i8, i8* %[[gep]] ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 43 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [99 x i8], [99 x i8]* %[[test3_a2]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 99 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 99 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 142 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [16 x i8], [16 x i8]* %[[test3_a3]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 16 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 16 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 158 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a4]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 42 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 42 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 200 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 207 ; CHECK-NEXT: %[[test3_r2:.*]] = load i8, i8* %[[gep]] ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 208 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 215 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [85 x i8], [85 x i8]* %[[test3_a7]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 85 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 85 ; Clobber a single element of the array, this should be promotable. %c = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 42 @@ -244,59 +244,59 @@ entry: ; CHECK-NEXT: store i32 4, i32* %[[bitcast]] %overlap2.prefix = getelementptr i8, i8* %overlap2.1.1.i8, i64 -4 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.prefix, i8* %src, i32 8, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.prefix, i8* %src, i32 8, i1 false) ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a4]], i64 0, i64 39 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %src, i32 3 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %src, i32 3 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 3 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 5 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 5 ; Bridge between the overlapping areas - call void @llvm.memset.p0i8.i32(i8* %overlap2.1.2.i8, i8 42, i32 8, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* %overlap2.1.2.i8, i8 42, i32 8, i1 false) ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 2 -; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %[[gep]], i8 42, i32 5 +; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 %[[gep]], i8 42, i32 5 ; ...promoted i8 store... ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %[[gep]], i8 42, i32 2 +; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 %[[gep]], i8 42, i32 2 ; Entirely within the second overlap. - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.1.i8, i8* %src, i32 5, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.1.i8, i8* %src, i32 5, i1 false) ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 1 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep]], i8* %src, i32 5 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep]], i8* align 1 %src, i32 5 ; Trailing past the second overlap. - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.2.i8, i8* %src, i32 8, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.2.i8, i8* %src, i32 8, i1 false) ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 2 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep]], i8* %src, i32 5 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep]], i8* align 1 %src, i32 5 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 5 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [85 x i8], [85 x i8]* %[[test3_a7]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 3 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 3 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 300, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 300, i1 false) ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a1]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %[[gep]], i32 42 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %dst, i8* align 1 %[[gep]], i32 42 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 42 ; CHECK-NEXT: store i8 0, i8* %[[gep]] ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 43 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [99 x i8], [99 x i8]* %[[test3_a2]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 99 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 99 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 142 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [16 x i8], [16 x i8]* %[[test3_a3]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 16 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 16 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 158 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a4]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 42 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 42 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 200 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 207 ; CHECK-NEXT: store i8 42, i8* %[[gep]] ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 208 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 215 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [85 x i8], [85 x i8]* %[[test3_a7]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 85 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 85 ret void } @@ -315,9 +315,9 @@ entry: ; CHECK-NEXT: %[[test4_a6:.*]] = alloca [40 x i8] %b = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 100, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 100, i1 false) ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [20 x i8], [20 x i8]* %[[test4_a1]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep]], i8* %src, i32 20 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep]], i8* align 1 %src, i32 20 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 20 ; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16* ; CHECK-NEXT: %[[test4_r1:.*]] = load i16, i16* %[[bitcast]] @@ -325,10 +325,10 @@ entry: ; CHECK-NEXT: %[[test4_r2:.*]] = load i8, i8* %[[gep]] ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 23 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a2]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 30 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [10 x i8], [10 x i8]* %[[test4_a3]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 10 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 10 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 40 ; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16* ; CHECK-NEXT: %[[test4_r3:.*]] = load i16, i16* %[[bitcast]] @@ -336,7 +336,7 @@ entry: ; CHECK-NEXT: %[[test4_r4:.*]] = load i8, i8* %[[gep]] ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 43 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a4]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 50 ; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16* ; CHECK-NEXT: %[[test4_r5:.*]] = load i16, i16* %[[bitcast]] @@ -344,31 +344,31 @@ entry: ; CHECK-NEXT: %[[test4_r6:.*]] = load i8, i8* %[[gep]] ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 53 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a5]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 60 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [40 x i8], [40 x i8]* %[[test4_a6]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 40 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 40 %a.src.1 = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 20 %a.dst.1 = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 40 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.1, i32 10, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.1, i32 10, i1 false) ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a4]], i64 0, i64 0 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a2]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; Clobber a single element of the array, this should be promotable, and be deleted. %c = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 42 store i8 0, i8* %c %a.src.2 = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 50 - call void @llvm.memmove.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.2, i32 10, i32 1, i1 false) + call void @llvm.memmove.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.2, i32 10, i1 false) ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a4]], i64 0, i64 0 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a5]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 100, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 100, i1 false) ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [20 x i8], [20 x i8]* %[[test4_a1]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %[[gep]], i32 20 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %dst, i8* align 1 %[[gep]], i32 20 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 20 ; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16* ; CHECK-NEXT: store i16 %[[test4_r1]], i16* %[[bitcast]] @@ -376,10 +376,10 @@ entry: ; CHECK-NEXT: store i8 %[[test4_r2]], i8* %[[gep]] ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 23 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a2]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 30 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [10 x i8], [10 x i8]* %[[test4_a3]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 10 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 10 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 40 ; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16* ; CHECK-NEXT: store i16 %[[test4_r5]], i16* %[[bitcast]] @@ -387,7 +387,7 @@ entry: ; CHECK-NEXT: store i8 %[[test4_r6]], i8* %[[gep]] ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 43 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a4]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %dst, i64 50 ; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16* ; CHECK-NEXT: store i16 %[[test4_r5]], i16* %[[bitcast]] @@ -395,18 +395,18 @@ entry: ; CHECK-NEXT: store i8 %[[test4_r6]], i8* %[[gep]] ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 53 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test4_a5]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 7 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7 ; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds i8, i8* %dst, i64 60 ; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds [40 x i8], [40 x i8]* %[[test4_a6]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[gep_dst]], i8* %[[gep_src]], i32 40 +; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 40 ret void } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind -declare void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* nocapture, i8* nocapture, i32, i32, i1) nounwind -declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind -declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind define i16 @test5() { ; CHECK-LABEL: @test5( @@ -436,7 +436,7 @@ define i32 @test6() { entry: %a = alloca [4 x i8] %ptr = getelementptr [4 x i8], [4 x i8]* %a, i32 0, i32 0 - call void @llvm.memset.p0i8.i32(i8* %ptr, i8 42, i32 4, i32 1, i1 true) + call void @llvm.memset.p0i8.i32(i8* %ptr, i8 42, i32 4, i1 true) %iptr = bitcast i8* %ptr to i32* %val = load i32, i32* %iptr ret i32 %val @@ -456,8 +456,8 @@ define void @test7(i8* %src, i8* %dst) { entry: %a = alloca [4 x i8] %ptr = getelementptr [4 x i8], [4 x i8]* %a, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i32 1, i1 true) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i32 1, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i1 true) ret void } @@ -543,7 +543,7 @@ define %S2* @test10() { entry: %a = alloca [8 x i8] %ptr = getelementptr [8 x i8], [8 x i8]* %a, i32 0, i32 0 - call void @llvm.memset.p0i8.i32(i8* %ptr, i8 0, i32 8, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* %ptr, i8 0, i32 8, i1 false) %s2ptrptr = bitcast i8* %ptr to %S2** %s2ptr = load %S2*, %S2** %s2ptrptr ret %S2* %s2ptr @@ -743,10 +743,10 @@ define void @test16(i8* %src, i8* %dst) { entry: %a = alloca [3 x i8] %ptr = getelementptr [3 x i8], [3 x i8]* %a, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i1 false) %cast = bitcast i8* %ptr to i24* store i24 0, i24* %cast - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i1 false) ret void } @@ -763,8 +763,8 @@ define void @test17(i8* %src, i8* %dst) { entry: %a = alloca [3 x i8] %ptr = getelementptr [3 x i8], [3 x i8]* %a, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i32 1, i1 true) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i32 1, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i1 true) ret void } @@ -780,7 +780,7 @@ define void @test18(i8* %src, i8* %dst, i32 %size) { ; CHECK-NEXT: %[[agep1:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0 ; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[agep1]], i8* %src, i32 %size, ; CHECK-NEXT: %[[agep2:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0 -; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* %[[agep2]], i8 42, i32 %size, +; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 %[[agep2]], i8 42, i32 %size, ; CHECK-NEXT: %[[dstcast1:.*]] = bitcast i8* %dst to i32* ; CHECK-NEXT: store i32 42, i32* %[[dstcast1]] ; CHECK-NEXT: %[[dstgep1:.*]] = getelementptr inbounds i8, i8* %dst, i64 4 @@ -793,14 +793,14 @@ define void @test18(i8* %src, i8* %dst, i32 %size) { entry: %a = alloca [42 x i8] %ptr = getelementptr [42 x i8], [42 x i8]* %a, i32 0, i32 0 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 8, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 8, i1 false) %ptr2 = getelementptr [42 x i8], [42 x i8]* %a, i32 0, i32 8 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr2, i8* %src, i32 %size, i32 1, i1 false) - call void @llvm.memset.p0i8.i32(i8* %ptr2, i8 42, i32 %size, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr2, i8* %src, i32 %size, i1 false) + call void @llvm.memset.p0i8.i32(i8* %ptr2, i8 42, i32 %size, i1 false) %cast = bitcast i8* %ptr to i32* store i32 42, i32* %cast - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 8, i32 1, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr2, i32 %size, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr2, i32 %size, i1 false) ret void } @@ -819,7 +819,7 @@ entry: %a = alloca { i64, i8* } %cast1 = bitcast %opaque* %x to i8* %cast2 = bitcast { i64, i8* }* %a to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast2, i8* %cast1, i32 16, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast2, i8* %cast1, i32 16, i1 false) %gep = getelementptr inbounds { i64, i8* }, { i64, i8* }* %a, i32 0, i32 0 %val = load i64, i64* %gep ret i32 undef @@ -853,7 +853,7 @@ entry: ret i32 %sum2 } -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind define i8 @test21() { ; Test allocations and offsets which border on overflow of the int64_t used @@ -869,7 +869,7 @@ entry: store i8 255, i8* %gep0 %gep1 = getelementptr [2305843009213693951 x i8], [2305843009213693951 x i8]* %a, i64 0, i64 -9223372036854775807 %gep2 = getelementptr i8, i8* %gep1, i64 -1 - call void @llvm.memset.p0i8.i64(i8* %gep2, i8 0, i64 18446744073709551615, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %gep2, i8 0, i64 18446744073709551615, i1 false) %gep3 = getelementptr i8, i8* %gep1, i64 9223372036854775807 %gep4 = getelementptr i8, i8* %gep3, i64 9223372036854775807 %gep5 = getelementptr i8, i8* %gep4, i64 -6917529027641081857 @@ -894,7 +894,7 @@ define void @PR13916.1() { entry: %a = alloca i8 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 1, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a, i8* %a, i32 1, i1 false) %tmp2 = load i8, i8* %a ret void } @@ -914,7 +914,7 @@ entry: if.then: %tmp0 = bitcast %PR13916.struct* %a to i8* %tmp1 = bitcast %PR13916.struct* %a to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp0, i8* %tmp1, i32 1, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %tmp0, i8* %tmp1, i32 1, i1 false) br label %if.end if.end: @@ -992,7 +992,7 @@ entry: store %PR14034.list* undef, %PR14034.list** %prev %cast0 = bitcast %PR14034.struct* undef to i8* %cast1 = bitcast %PR14034.struct* %a to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast0, i8* %cast1, i32 12, i32 0, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast0, i8* %cast1, i32 12, i1 false) ret void } @@ -1065,15 +1065,15 @@ entry: ; Also use a memset to the middle 32-bits for fun. %X.sroa.0.2.raw_idx2.i = getelementptr inbounds i8, i8* %0, i32 2 - call void @llvm.memset.p0i8.i64(i8* %X.sroa.0.2.raw_idx2.i, i8 0, i64 4, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %X.sroa.0.2.raw_idx2.i, i8 0, i64 4, i1 false) ; Or a memset of the whole thing. - call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 8, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %0, i8 0, i64 8, i1 false) ; Write to the high 32-bits with a memcpy. %X.sroa.0.4.raw_idx4.i = getelementptr inbounds i8, i8* %0, i32 4 %d.raw = bitcast double* %d to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %X.sroa.0.4.raw_idx4.i, i8* %d.raw, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %X.sroa.0.4.raw_idx4.i, i8* %d.raw, i32 4, i1 false) ; Store to the high 32-bits... %X.sroa.0.4.cast5.i = bitcast i8* %X.sroa.0.4.raw_idx4.i to i32* @@ -1146,7 +1146,7 @@ entry: %cast1 = bitcast { [16 x i8 ] }* %gep to i8* %cast2 = bitcast { [16 x i8 ] }* %a to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast1, i8* %cast2, i32 16, i32 8, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %cast1, i8* align 8 %cast2, i32 16, i1 true) ret void ; CHECK: ret } @@ -1164,7 +1164,7 @@ entry: %cast1 = bitcast { [16 x i8 ] } addrspace(1)* %gep to i8 addrspace(1)* %cast2 = bitcast { [16 x i8 ] }* %a to i8* - call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* %cast1, i8* %cast2, i32 16, i32 8, i1 true) + call void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* align 8 %cast1, i8* align 8 %cast2, i32 16, i1 true) ret void ; CHECK: ret } @@ -1177,7 +1177,7 @@ define void @PR14465() { %stack = alloca [1048576 x i32], align 16 ; CHECK: alloca [1048576 x i32] %cast = bitcast [1048576 x i32]* %stack to i8* - call void @llvm.memset.p0i8.i64(i8* %cast, i8 -2, i64 4194304, i32 16, i1 false) + call void @llvm.memset.p0i8.i64(i8* align 16 %cast, i8 -2, i64 4194304, i1 false) ret void ; CHECK: ret } @@ -1206,7 +1206,7 @@ entry: ; CHECK-NEXT: {{.*}} = load i8, i8* %[[b]], align 8 %a.i8 = bitcast <{ i1 }>* %a to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.i8, i8* %b.i8, i32 1, i32 1, i1 false) nounwind + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.i8, i8* %b.i8, i32 1, i1 false) nounwind %bar = load i8, i8* %a.i8, align 1 %a.i1 = getelementptr inbounds <{ i1 }>, <{ i1 }>* %a, i32 0, i32 0 %baz = load i1, i1* %a.i1, align 1 @@ -1261,7 +1261,7 @@ entry: ; CHECK: alloca %a.i8 = bitcast i32* %a to i8* - call void @llvm.memset.p0i8.i32(i8* %a.i8, i8 0, i32 %x, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* %a.i8, i8 0, i32 %x, i1 false) %v = load i32, i32* %a ret i32 %v } @@ -1323,7 +1323,7 @@ bb1: end: %tmp.raw = bitcast [4 x i8]* %tmp to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %data, i8* %tmp.raw, i32 %size, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %data, i8* %tmp.raw, i32 %size, i1 false) ret void ; CHECK: ret void } @@ -1376,7 +1376,7 @@ define void @PR16651.1(i8* %a) { entry: %b = alloca i32, align 4 %b.cast = bitcast i32* %b to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b.cast, i8* %a, i32 4, i32 4, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %b.cast, i8* align 4 %a, i32 4, i1 true) %b.gep = getelementptr inbounds i8, i8* %b.cast, i32 2 load i8, i8* %b.gep, align 2 unreachable @@ -1413,7 +1413,7 @@ entry: %gep0 = getelementptr inbounds i32, i32* %a, i32 0 %cast1 = bitcast i32* %gep1 to i8* %cast0 = bitcast i32* %gep0 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast1, i8* %cast0, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast1, i8* %cast0, i32 4, i1 false) ret void } @@ -1424,7 +1424,7 @@ define void @PR18615() { entry: %f = alloca i8 %gep = getelementptr i8, i8* %f, i64 -1 - call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %gep, i32 1, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* undef, i8* %gep, i32 1, i1 false) ret void } @@ -1439,8 +1439,8 @@ define void @test24(i8* %src, i8* %dst) { entry: %a = alloca i64, align 16 %ptr = bitcast i64* %a to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 8, i32 1, i1 true) - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 8, i32 1, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 8, i1 true) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 8, i1 true) ret void } @@ -1663,12 +1663,12 @@ entry: %3 = load i64, i64* %1, align 8 store i64 %3, i64* %2, align 8 %4 = bitcast %struct.STest* %outData to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %4, i8* %0, i64 16, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %4, i8* align 4 %0, i64 16, i1 false) call void @llvm.lifetime.end.p0i8(i64 16, i8* %0) ret void } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind define void @PR27999() unnamed_addr { ; CHECK-LABEL: @PR27999( diff --git a/llvm/test/Transforms/SROA/big-endian.ll b/llvm/test/Transforms/SROA/big-endian.ll index fc4b8b28855..91165456038 100644 --- a/llvm/test/Transforms/SROA/big-endian.ll +++ b/llvm/test/Transforms/SROA/big-endian.ll @@ -226,7 +226,7 @@ entry: store i64 34494054408, i64* %a2 %tmp0 = bitcast { i32, i24 }* %a to i8* %tmp1 = bitcast i64* %a2 to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp0, i8* %tmp1, i64 8, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %tmp0, i8* align 4 %tmp1, i64 8, i1 false) ; CHECK: %[[LO_SHR:.*]] = lshr i64 34494054408, 32 ; CHECK: %[[LO_START:.*]] = trunc i64 %[[LO_SHR]] to i32 ; CHECK: %[[HI_START:.*]] = trunc i64 34494054408 to i32 @@ -249,4 +249,4 @@ entry: ; CHECK: ret void } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i1) diff --git a/llvm/test/Transforms/SROA/dbg-addr-diamond.ll b/llvm/test/Transforms/SROA/dbg-addr-diamond.ll index 132da991464..9ccb82e49a7 100644 --- a/llvm/test/Transforms/SROA/dbg-addr-diamond.ll +++ b/llvm/test/Transforms/SROA/dbg-addr-diamond.ll @@ -39,7 +39,7 @@ if.else: ; preds = %entry if.end: ; preds = %if.else, %if.then %1 = bitcast %struct.Pair* %p to i8*, !dbg !51 %2 = bitcast %struct.Pair* @pair to i8*, !dbg !51 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %2, i8* %1, i64 8, i32 4, i1 false), !dbg !51 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %2, i8* align 4 %1, i64 8, i1 false), !dbg !51 ret void } @@ -62,7 +62,7 @@ if.end: ; preds = %if.else, %if.then ; CHECK: ![[PVAR]] = !DILocalVariable(name: "p", {{.*}}) ; Function Attrs: argmemonly nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #2 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #2 ; Function Attrs: nounwind readnone speculatable declare void @llvm.dbg.addr(metadata, metadata, metadata) diff --git a/llvm/test/Transforms/SROA/mem-par-metadata-sroa.ll b/llvm/test/Transforms/SROA/mem-par-metadata-sroa.ll index ae5898ed550..32ea8f5732a 100644 --- a/llvm/test/Transforms/SROA/mem-par-metadata-sroa.ll +++ b/llvm/test/Transforms/SROA/mem-par-metadata-sroa.ll @@ -95,7 +95,7 @@ for.end: ; preds = %for.cond } ; Function Attrs: argmemonly nounwind -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #1 +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) #1 attributes #0 = { norecurse nounwind uwtable "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" } attributes #1 = { argmemonly nounwind } diff --git a/llvm/test/Transforms/SROA/preserve-nonnull.ll b/llvm/test/Transforms/SROA/preserve-nonnull.ll index a29da6dc2c3..d6f084fd749 100644 --- a/llvm/test/Transforms/SROA/preserve-nonnull.ll +++ b/llvm/test/Transforms/SROA/preserve-nonnull.ll @@ -3,7 +3,7 @@ ; Make sure that SROA doesn't lose nonnull metadata ; on loads from allocas that get optimized out. -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) ; Check that we do basic propagation of nonnull when rewriting. define i8* @propagate_nonnull(i32* %v) { @@ -37,7 +37,7 @@ entry: %buf = alloca float* %_arg_i8 = bitcast float** %arg to i8* %_buf_i8 = bitcast float** %buf to i8* - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %_buf_i8, i8* %_arg_i8, i64 8, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %_buf_i8, i8* align 8 %_arg_i8, i64 8, i1 false) %ret = load float*, float** %buf, align 8, !nonnull !0 ret float* %ret } diff --git a/llvm/test/Transforms/SROA/slice-order-independence.ll b/llvm/test/Transforms/SROA/slice-order-independence.ll index 7d57be6d81c..19e7143fd13 100644 --- a/llvm/test/Transforms/SROA/slice-order-independence.ll +++ b/llvm/test/Transforms/SROA/slice-order-independence.ll @@ -1,7 +1,7 @@ ; RUN: opt < %s -sroa -S | FileCheck %s target datalayout = "e-p:64:64:64-p1:16:16:16-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64" -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind ; Check that the chosen type for a split is independent from the order of ; slices even in case of types that are skipped because their width is not a @@ -12,7 +12,7 @@ define void @skipped_inttype_first({ i16*, i32 }*) { %arg = alloca { i16*, i32 }, align 8 %2 = bitcast { i16*, i32 }* %0 to i8* %3 = bitcast { i16*, i32 }* %arg to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %3, i8* %2, i32 16, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %3, i8* align 8 %2, i32 16, i1 false) %b = getelementptr inbounds { i16*, i32 }, { i16*, i32 }* %arg, i64 0, i32 0 %pb0 = bitcast i16** %b to i63* %b0 = load i63, i63* %pb0 @@ -27,7 +27,7 @@ define void @skipped_inttype_last({ i16*, i32 }*) { %arg = alloca { i16*, i32 }, align 8 %2 = bitcast { i16*, i32 }* %0 to i8* %3 = bitcast { i16*, i32 }* %arg to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %3, i8* %2, i32 16, i32 8, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %3, i8* align 8 %2, i32 16, i1 false) %b = getelementptr inbounds { i16*, i32 }, { i16*, i32 }* %arg, i64 0, i32 0 %pb1 = bitcast i16** %b to i8** %b1 = load i8*, i8** %pb1 diff --git a/llvm/test/Transforms/SROA/slice-width.ll b/llvm/test/Transforms/SROA/slice-width.ll index 6b6ab93dd0d..98ec1e97933 100644 --- a/llvm/test/Transforms/SROA/slice-width.ll +++ b/llvm/test/Transforms/SROA/slice-width.ll @@ -1,8 +1,8 @@ ; RUN: opt < %s -sroa -S | FileCheck %s target datalayout = "e-p:64:64:64-p1:16:16:16-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-f80:128-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64" -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind -declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind define void @no_split_on_non_byte_width(i32) { ; This tests that allocas are not split into slices that are not byte width multiple @@ -39,7 +39,7 @@ define void @memcpy_fp80_padding() { ; Copy from a global. %x_i8 = bitcast %union.Foo* %x to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %x_i8, i8* bitcast (%union.Foo* @foo_copy_source to i8*), i32 32, i32 16, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 16 %x_i8, i8* align 16 bitcast (%union.Foo* @foo_copy_source to i8*), i32 32, i1 false) ; Access a slice of the alloca to trigger SROA. %mid_p = getelementptr %union.Foo, %union.Foo* %x, i32 0, i32 1 @@ -58,7 +58,7 @@ define void @memset_fp80_padding() { ; Set to all ones. %x_i8 = bitcast %union.Foo* %x to i8* - call void @llvm.memset.p0i8.i32(i8* %x_i8, i8 -1, i32 32, i32 16, i1 false) + call void @llvm.memset.p0i8.i32(i8* align 16 %x_i8, i8 -1, i32 32, i1 false) ; Access a slice of the alloca to trigger SROA. %mid_p = getelementptr %union.Foo, %union.Foo* %x, i32 0, i32 1 @@ -68,7 +68,7 @@ define void @memset_fp80_padding() { } ; CHECK-LABEL: define void @memset_fp80_padding ; CHECK: alloca x86_fp80 -; CHECK: call void @llvm.memset.p0i8.i32(i8* %{{.*}}, i8 -1, i32 16, i32 16, i1 false) +; CHECK: call void @llvm.memset.p0i8.i32(i8* align 16 %{{.*}}, i8 -1, i32 16, i1 false) ; CHECK: store i64 -1, i64* @i64_sink %S.vec3float = type { float, float, float } @@ -85,7 +85,7 @@ entry: %tmp1 = alloca %S.vec3float, align 4 %0 = bitcast %S.vec3float* %tmp1 to i8* %1 = bitcast %S.vec3float* %x to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* %1, i32 12, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %0, i8* align 4 %1, i32 12, i1 false) ; The following block does nothing; but appears to confuse SROA %unused1 = bitcast %S.vec3float* %tmp1 to %U.vec3float* @@ -98,7 +98,7 @@ entry: %3 = bitcast %S.vec3float* %tmp1 to i8* ; CHECK: alloca ; CHECK-NOT: store <4 x float> - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %2, i8* %3, i32 12, i32 4, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %2, i8* align 4 %3, i32 12, i1 false) %result = call i32 @memcpy_vec3float_helper(%S.vec3float* %tmp2) ret i32 %result diff --git a/llvm/test/Transforms/SROA/vector-promotion.ll b/llvm/test/Transforms/SROA/vector-promotion.ll index 2d9b26b5309..0bf2d23a591 100644 --- a/llvm/test/Transforms/SROA/vector-promotion.ll +++ b/llvm/test/Transforms/SROA/vector-promotion.ll @@ -81,12 +81,12 @@ entry: ; CHECK-NOT: store %a.y.cast = bitcast <4 x i32>* %a.y to i8* - call void @llvm.memset.p0i8.i32(i8* %a.y.cast, i8 0, i32 16, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* %a.y.cast, i8 0, i32 16, i1 false) ; CHECK-NOT: memset %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2 %a.tmp1.cast = bitcast i32* %a.tmp1 to i8* - call void @llvm.memset.p0i8.i32(i8* %a.tmp1.cast, i8 -1, i32 4, i32 1, i1 false) + call void @llvm.memset.p0i8.i32(i8* %a.tmp1.cast, i8 -1, i32 4, i1 false) %tmp1 = load i32, i32* %a.tmp1 %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3 %tmp2 = load i32, i32* %a.tmp2 @@ -120,14 +120,14 @@ entry: %a.y.cast = bitcast <4 x i32>* %a.y to i8* %z.cast = bitcast <4 x i32>* %z to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.y.cast, i8* %z.cast, i32 16, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.y.cast, i8* %z.cast, i32 16, i1 false) ; CHECK-NOT: memcpy %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2 %a.tmp1.cast = bitcast i32* %a.tmp1 to i8* %z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2 %z.tmp1.cast = bitcast i32* %z.tmp1 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.tmp1.cast, i8* %z.tmp1.cast, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.tmp1.cast, i8* %z.tmp1.cast, i32 4, i1 false) %tmp1 = load i32, i32* %a.tmp1 %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3 %tmp2 = load i32, i32* %a.tmp2 @@ -150,7 +150,7 @@ entry: ; CHECK-NEXT: ret } -declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture, i32, i1) nounwind ; Same as test4 with a different sized address space pointer source. define i32 @test4_as1(<4 x i32> %x, <4 x i32> %y, <4 x i32> addrspace(1)* %z) { @@ -167,14 +167,14 @@ entry: %a.y.cast = bitcast <4 x i32>* %a.y to i8* %z.cast = bitcast <4 x i32> addrspace(1)* %z to i8 addrspace(1)* - call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.y.cast, i8 addrspace(1)* %z.cast, i32 16, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.y.cast, i8 addrspace(1)* %z.cast, i32 16, i1 false) ; CHECK-NOT: memcpy %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2 %a.tmp1.cast = bitcast i32* %a.tmp1 to i8* %z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %z, i16 0, i16 2 %z.tmp1.cast = bitcast i32 addrspace(1)* %z.tmp1 to i8 addrspace(1)* - call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.tmp1.cast, i8 addrspace(1)* %z.tmp1.cast, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.tmp1.cast, i8 addrspace(1)* %z.tmp1.cast, i32 4, i1 false) %tmp1 = load i32, i32* %a.tmp1 %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3 %tmp2 = load i32, i32* %a.tmp2 @@ -213,14 +213,14 @@ entry: %a.y.cast = bitcast <4 x i32>* %a.y to i8* %a.x.cast = bitcast <4 x i32>* %a.x to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.x.cast, i8* %a.y.cast, i32 16, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.x.cast, i8* %a.y.cast, i32 16, i1 false) ; CHECK-NOT: memcpy %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2 %a.tmp1.cast = bitcast i32* %a.tmp1 to i8* %z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2 %z.tmp1.cast = bitcast i32* %z.tmp1 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %z.tmp1.cast, i8* %a.tmp1.cast, i32 4, i32 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %z.tmp1.cast, i8* %a.tmp1.cast, i32 4, i1 false) %tmp1 = load i32, i32* %a.tmp1 %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3 %tmp2 = load i32, i32* %a.tmp2 @@ -242,8 +242,8 @@ entry: ; CHECK-NEXT: ret } -declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind -declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind +declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind +declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind define i64 @test6(<4 x i64> %x, <4 x i64> %y, i64 %n) { ; CHECK-LABEL: @test6( @@ -326,7 +326,7 @@ entry: ; CHECK-NEXT: ret <4 x i32> %[[ret]] } -declare void @llvm.memset.p0i32.i32(i32* nocapture, i32, i32, i32, i1) nounwind +declare void @llvm.memset.p0i32.i32(i32* nocapture, i32, i32, i1) nounwind define <4 x float> @test_subvec_memset() { ; CHECK-LABEL: @test_subvec_memset( @@ -336,23 +336,23 @@ entry: %a.gep0 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 0 %a.cast0 = bitcast float* %a.gep0 to i8* - call void @llvm.memset.p0i8.i32(i8* %a.cast0, i8 0, i32 8, i32 0, i1 false) + call void @llvm.memset.p0i8.i32(i8* %a.cast0, i8 0, i32 8, i1 false) ; CHECK-NOT: store ; CHECK: select <4 x i1> <i1 true, i1 true, i1 false, i1 false> %a.gep1 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 1 %a.cast1 = bitcast float* %a.gep1 to i8* - call void @llvm.memset.p0i8.i32(i8* %a.cast1, i8 1, i32 8, i32 0, i1 false) + call void @llvm.memset.p0i8.i32(i8* %a.cast1, i8 1, i32 8, i1 false) ; CHECK-NEXT: select <4 x i1> <i1 false, i1 true, i1 true, i1 false> %a.gep2 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 2 %a.cast2 = bitcast float* %a.gep2 to i8* - call void @llvm.memset.p0i8.i32(i8* %a.cast2, i8 3, i32 8, i32 0, i1 false) + call void @llvm.memset.p0i8.i32(i8* %a.cast2, i8 3, i32 8, i1 false) ; CHECK-NEXT: select <4 x i1> <i1 false, i1 false, i1 true, i1 true> %a.gep3 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 3 %a.cast3 = bitcast float* %a.gep3 to i8* - call void @llvm.memset.p0i8.i32(i8* %a.cast3, i8 7, i32 4, i32 0, i1 false) + call void @llvm.memset.p0i8.i32(i8* %a.cast3, i8 7, i32 4, i1 false) ; CHECK-NEXT: insertelement <4 x float> %ret = load <4 x float>, <4 x float>* %a @@ -369,7 +369,7 @@ entry: %a.gep0 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 0 %a.cast0 = bitcast float* %a.gep0 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast0, i8* %x, i32 8, i32 0, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast0, i8* %x, i32 8, i1 false) ; CHECK: %[[xptr:.*]] = bitcast i8* %x to <2 x float>* ; CHECK-NEXT: %[[x:.*]] = load <2 x float>, <2 x float>* %[[xptr]] ; CHECK-NEXT: %[[expand_x:.*]] = shufflevector <2 x float> %[[x]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef> @@ -377,7 +377,7 @@ entry: %a.gep1 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 1 %a.cast1 = bitcast float* %a.gep1 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast1, i8* %y, i32 8, i32 0, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast1, i8* %y, i32 8, i1 false) ; CHECK-NEXT: %[[yptr:.*]] = bitcast i8* %y to <2 x float>* ; CHECK-NEXT: %[[y:.*]] = load <2 x float>, <2 x float>* %[[yptr]] ; CHECK-NEXT: %[[expand_y:.*]] = shufflevector <2 x float> %[[y]], <2 x float> undef, <4 x i32> <i32 undef, i32 0, i32 1, i32 undef> @@ -385,7 +385,7 @@ entry: %a.gep2 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 2 %a.cast2 = bitcast float* %a.gep2 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast2, i8* %z, i32 8, i32 0, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast2, i8* %z, i32 8, i1 false) ; CHECK-NEXT: %[[zptr:.*]] = bitcast i8* %z to <2 x float>* ; CHECK-NEXT: %[[z:.*]] = load <2 x float>, <2 x float>* %[[zptr]] ; CHECK-NEXT: %[[expand_z:.*]] = shufflevector <2 x float> %[[z]], <2 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 1> @@ -393,12 +393,12 @@ entry: %a.gep3 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 3 %a.cast3 = bitcast float* %a.gep3 to i8* - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast3, i8* %f, i32 4, i32 0, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast3, i8* %f, i32 4, i1 false) ; CHECK-NEXT: %[[fptr:.*]] = bitcast i8* %f to float* ; CHECK-NEXT: %[[f:.*]] = load float, float* %[[fptr]] ; CHECK-NEXT: %[[insert_f:.*]] = insertelement <4 x float> - call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %a.cast2, i32 8, i32 0, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %a.cast2, i32 8, i1 false) ; CHECK-NEXT: %[[outptr:.*]] = bitcast i8* %out to <2 x float>* ; CHECK-NEXT: %[[extract_out:.*]] = shufflevector <4 x float> %[[insert_f]], <4 x float> undef, <2 x i32> <i32 2, i32 3> ; CHECK-NEXT: store <2 x float> %[[extract_out]], <2 x float>* %[[outptr]] diff --git a/llvm/test/Transforms/SafeStack/X86/byval.ll b/llvm/test/Transforms/SafeStack/X86/byval.ll index f9a06e54d2d..1bc5a298e78 100644 --- a/llvm/test/Transforms/SafeStack/X86/byval.ll +++ b/llvm/test/Transforms/SafeStack/X86/byval.ll @@ -26,7 +26,7 @@ entry: ; CHECK: store {{.*}} @__safestack_unsafe_stack_ptr ; CHECK: %[[B:.*]] = getelementptr i8, i8* %[[A]], i32 -400 ; CHECK: %[[C:.*]] = bitcast %struct.S* %zzz to i8* - ; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %[[B]], i8* %[[C]], i64 400, i32 8, i1 false) + ; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %[[B]], i8* align 8 %[[C]], i64 400, i1 false) ; CHECK: ret i32 %arrayidx = getelementptr inbounds %struct.S, %struct.S* %zzz, i64 0, i32 0, i64 %idx %0 = load i32, i32* %arrayidx, align 4 diff --git a/llvm/test/Transforms/SafeStack/X86/call.ll b/llvm/test/Transforms/SafeStack/X86/call.ll index 2d78bb1a689..a7bf9ae6e7e 100644 --- a/llvm/test/Transforms/SafeStack/X86/call.ll +++ b/llvm/test/Transforms/SafeStack/X86/call.ll @@ -30,7 +30,7 @@ entry: ; CHECK: ret void %q = alloca [10 x i8], align 1 %arraydecay = getelementptr inbounds [10 x i8], [10 x i8]* %q, i32 0, i32 0 - call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 1, i64 %len, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 1, i64 %len, i1 false) ret void } @@ -41,7 +41,7 @@ entry: ; CHECK: ret void %q = alloca [10 x i8], align 1 %arraydecay = getelementptr inbounds [10 x i8], [10 x i8]* %q, i32 0, i32 2 - call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 1, i64 7, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 1, i64 7, i1 false) ret void } @@ -52,7 +52,7 @@ entry: ; CHECK: ret void %q = alloca [10 x i8], align 1 %arraydecay = getelementptr inbounds [10 x i8], [10 x i8]* %q, i32 0, i32 7 - call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 1, i64 5, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 1, i64 5, i1 false) ret void } @@ -63,7 +63,7 @@ entry: ; CHECK: ret void %q = alloca [10 x i8], align 1 %arraydecay = getelementptr [10 x i8], [10 x i8]* %q, i32 0, i32 -1 - call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 1, i64 3, i32 1, i1 false) + call void @llvm.memset.p0i8.i64(i8* %arraydecay, i8 1, i64 3, i1 false) ret void } @@ -172,7 +172,7 @@ declare void @capture(i8* readnone) readnone declare void @readnone(i8* nocapture) readnone declare void @readnone0(i8* nocapture readnone, i8* nocapture) -declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind argmemonly +declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind argmemonly declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) nounwind argmemonly declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) nounwind argmemonly diff --git a/llvm/test/Transforms/SimplifyCFG/critedge-assume.ll b/llvm/test/Transforms/SimplifyCFG/critedge-assume.ll index bfeb65769de..42ce5a561cc 100644 --- a/llvm/test/Transforms/SimplifyCFG/critedge-assume.ll +++ b/llvm/test/Transforms/SimplifyCFG/critedge-assume.ll @@ -64,7 +64,7 @@ declare i32 @_ZNK1F5beginEv(%class.F*) declare i32 @_ZNK1F3endEv(%class.F*) -declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1) declare noalias nonnull i8* @_Znwm(i64) diff --git a/llvm/test/Transforms/Util/combine-alias-scope-metadata.ll b/llvm/test/Transforms/Util/combine-alias-scope-metadata.ll index fd0a3d5c5b9..f58e4f783b0 100644 --- a/llvm/test/Transforms/Util/combine-alias-scope-metadata.ll +++ b/llvm/test/Transforms/Util/combine-alias-scope-metadata.ll @@ -4,16 +4,16 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" define void @test(i8* noalias dereferenceable(1) %in, i8* noalias dereferenceable(1) %out) { %tmp = alloca i8 %tmp2 = alloca i8 -; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 1, i32 8, i1 false) - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp, i8* %in, i64 1, i32 8, i1 false), !alias.scope !4 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp2, i8* %tmp, i64 1, i32 8, i1 false), !alias.scope !5 +; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %out, i8* align 8 %in, i64 1, i1 false) + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %tmp, i8* align 8 %in, i64 1, i1 false), !alias.scope !4 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %tmp2, i8* align 8 %tmp, i64 1, i1 false), !alias.scope !5 - call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %tmp2, i64 1, i32 8, i1 false), !noalias !6 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 %out, i8* align 8 %tmp2, i64 1, i1 false), !noalias !6 ret void } -declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i32, i1) +declare void @llvm.memcpy.p0i8.p0i8.i64(i8*, i8*, i64, i1) !0 = !{!0} !1 = distinct !{!1, !0, !"in"} |
