[MemCpyOpt] Turn memcpy from just-memset'd source into memset.

There's no point in copying around constants, so, when all else fails,
we can still transform memcpy of memset into two independent memsets.

To quote the example, we can turn:
  memset(dst1, c, dst1_size);
  memcpy(dst2, dst1, dst2_size);
into:
  memset(dst1, c, dst1_size);
  memset(dst2, c, dst2_size);
When dst2_size <= dst1_size.

Like r235232 for copy constructors, this can occur in move constructors.

Differential Revision: http://reviews.llvm.org/D9682

llvm-svn: 237506

3 files changed, 104 insertions, 2 deletions

diff --git a/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll b/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll
index a1f5ae19d24..4c3e3e86bf3 100644
--- a/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll
+++ b/llvm/test/Transforms/MemCpyOpt/callslot_deref.ll
@@ -17,10 +17,11 @@ define void @must_remove_memcpy(i8* noalias nocapture dereferenceable(4096) %dst
 }
 
 ; memset touch more bytes than those guaranteed to be dereferenceable
+; We can't remove the memcpy, but we can turn it into an independent memset.
 define void @must_not_remove_memcpy(i8* noalias nocapture dereferenceable(1024) %dst) {
 ; CHECK-LABEL: @must_not_remove_memcpy(
 ; CHECK: call void @llvm.memset.p0i8.i64
-; CHECK: call void @llvm.memcpy.p0i8.p0i8.i64
+; 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)
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 626317614c9..e3e57f09d88 100644
--- a/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll
+++ b/llvm/test/Transforms/MemCpyOpt/memcpy-to-memset-with-lifetimes.ll
@@ -40,7 +40,7 @@ entry-block:
 ; 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:         %[[sret_cast:[^=]+]] = bitcast [8 x i64]* %sret to i8*
-; CHECK:         call void @llvm.memcpy.p0i8.p0i8.i64(i8* %[[sret_cast]], i8* %[[a_cast]], i64 64
+; 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:         %[[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
diff --git a/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll
new file mode 100644
index 00000000000..1c567042ce7
--- /dev/null
+++ b/llvm/test/Transforms/MemCpyOpt/memset-memcpy-to-2x-memset.ll
@@ -0,0 +1,101 @@
+; RUN: opt -memcpyopt -S %s | FileCheck %s
+
+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: 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)
+  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: 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)
+  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: 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)
+  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: 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)
+  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: 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)
+  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: 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)
+  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: %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: 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)
+  ; 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)
+  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: 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)
+  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: 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)
+  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)