diff options
Diffstat (limited to 'llvm/test')
3 files changed, 63 insertions, 3 deletions
diff --git a/llvm/test/CodeGen/X86/regalloc-reconcile-broken-hints.ll b/llvm/test/CodeGen/X86/regalloc-reconcile-broken-hints.ll index ba8ff1bc181..3bb14c4b1cd 100644 --- a/llvm/test/CodeGen/X86/regalloc-reconcile-broken-hints.ll +++ b/llvm/test/CodeGen/X86/regalloc-reconcile-broken-hints.ll @@ -1,4 +1,4 @@ -; RUN: llc < %s -o - -mtriple=x86_64-apple-macosx | FileCheck %s +; RUN: llc -lsr-filter-same-scaled-reg=false < %s -o - -mtriple=x86_64-apple-macosx | FileCheck %s ; Test case for the recoloring of broken hints. ; This is tricky to have something reasonably small to kick this optimization since ; it requires that spliting and spilling occur. diff --git a/llvm/test/Transforms/LoopStrengthReduce/2013-01-14-ReuseCast.ll b/llvm/test/Transforms/LoopStrengthReduce/2013-01-14-ReuseCast.ll index dcd068191e1..ea3f6077231 100644 --- a/llvm/test/Transforms/LoopStrengthReduce/2013-01-14-ReuseCast.ll +++ b/llvm/test/Transforms/LoopStrengthReduce/2013-01-14-ReuseCast.ll @@ -14,8 +14,8 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3 ; current LSR cost model. ; CHECK-NOT: = ptrtoint i8* undef to i64 ; CHECK: .lr.ph -; CHECK: [[TMP:%[^ ]+]] = add i64 %tmp5, 1 -; CHECK: sub i64 [[TMP]], %tmp6 +; CHECK: [[TMP:%[^ ]+]] = add i64 %tmp{{[0-9]+}}, -1 +; CHECK: sub i64 [[TMP]], %tmp{{[0-9]+}} ; CHECK: ret void define void @VerifyDiagnosticConsumerTest() unnamed_addr nounwind uwtable align 2 { bb: diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/lsr-filtering-scaledreg.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/lsr-filtering-scaledreg.ll new file mode 100644 index 00000000000..4ce6f1a79fb --- /dev/null +++ b/llvm/test/Transforms/LoopStrengthReduce/X86/lsr-filtering-scaledreg.ll @@ -0,0 +1,60 @@ +; RUN: opt < %s -loop-reduce -lsr-filter-same-scaled-reg=true -mtriple=x86_64-unknown-linux-gnu -S | FileCheck %s + +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" + +%struct.ham = type { i8, i8, [5 x i32], i64, i64, i64 } + +@global = external local_unnamed_addr global %struct.ham, align 8 + +define void @foo() local_unnamed_addr { +bb: + %tmp = load i64, i64* getelementptr inbounds (%struct.ham, %struct.ham* @global, i64 0, i32 3), align 8 + %tmp1 = and i64 %tmp, 1792 + %tmp2 = load i64, i64* getelementptr inbounds (%struct.ham, %struct.ham* @global, i64 0, i32 4), align 8 + %tmp3 = add i64 %tmp1, %tmp2 + %tmp4 = load i8*, i8** null, align 8 + %tmp5 = getelementptr inbounds i8, i8* %tmp4, i64 0 + %tmp6 = sub i64 0, %tmp3 + %tmp7 = getelementptr inbounds i8, i8* %tmp4, i64 %tmp6 + %tmp8 = inttoptr i64 0 to i8* + br label %bb9 + +; Without filtering non-optimal formulae with the same ScaledReg and Scale, the strategy +; to narrow LSR search space by picking winner reg will generate only one lsr.iv and +; unoptimal result. +; CHECK-LABEL: @foo( +; CHECK: bb9: +; CHECK-NEXT: = phi i8* +; CHECK-NEXT: = phi i8* + +bb9: ; preds = %bb12, %bb + %tmp10 = phi i8* [ %tmp7, %bb ], [ %tmp16, %bb12 ] + %tmp11 = phi i8* [ %tmp8, %bb ], [ %tmp17, %bb12 ] + br i1 false, label %bb18, label %bb12 + +bb12: ; preds = %bb9 + %tmp13 = getelementptr inbounds i8, i8* %tmp10, i64 8 + %tmp14 = bitcast i8* %tmp13 to i64* + %tmp15 = load i64, i64* %tmp14, align 1 + %tmp16 = getelementptr inbounds i8, i8* %tmp10, i64 16 + %tmp17 = getelementptr inbounds i8, i8* %tmp11, i64 16 + br label %bb9 + +bb18: ; preds = %bb9 + %tmp19 = icmp ugt i8* %tmp11, null + %tmp20 = getelementptr inbounds i8, i8* %tmp10, i64 8 + %tmp21 = getelementptr inbounds i8, i8* %tmp11, i64 8 + %tmp22 = select i1 %tmp19, i8* %tmp10, i8* %tmp20 + %tmp23 = select i1 %tmp19, i8* %tmp11, i8* %tmp21 + br label %bb24 + +bb24: ; preds = %bb24, %bb18 + %tmp25 = phi i8* [ %tmp27, %bb24 ], [ %tmp22, %bb18 ] + %tmp26 = phi i8* [ %tmp29, %bb24 ], [ %tmp23, %bb18 ] + %tmp27 = getelementptr inbounds i8, i8* %tmp25, i64 1 + %tmp28 = load i8, i8* %tmp25, align 1 + %tmp29 = getelementptr inbounds i8, i8* %tmp26, i64 1 + store i8 %tmp28, i8* %tmp26, align 1 + %tmp30 = icmp eq i8* %tmp29, %tmp5 + br label %bb24 +} |
