forked from OSchip/llvm-project
[MemCpyOpt] Don't generate zero-size memset
If a memset destination is overwritten by a memcpy and the sizes are exactly the same, then the memset is simply dead. We can directly drop it, instead of replacing it with a memset of zero size, which is particularly ugly for the case of a dynamic size.
This commit is contained in:
parent
dabd6abbcd
commit
9080444f33
|
@ -1172,6 +1172,13 @@ bool MemCpyOptPass::processMemSetMemCpyDependence(MemCpyInst *MemCpy,
|
|||
if (mayBeVisibleThroughUnwinding(Dest, MemSet, MemCpy))
|
||||
return false;
|
||||
|
||||
// If the sizes are the same, simply drop the memset instead of generating
|
||||
// a replacement with zero size.
|
||||
if (DestSize == SrcSize) {
|
||||
eraseInstruction(MemSet);
|
||||
return true;
|
||||
}
|
||||
|
||||
// By default, create an unaligned memset.
|
||||
unsigned Align = 1;
|
||||
// If Dest is aligned, and SrcSize is constant, use the minimum alignment
|
||||
|
|
|
@ -239,9 +239,7 @@ define void @test_missing_noalias(i8* %src, i64 %src_size, i8* %dst, i64 %dst_si
|
|||
|
||||
define void @test_same_const_size(i8* noalias %src, i8* noalias %dst, i8 %c) {
|
||||
; CHECK-LABEL: @test_same_const_size(
|
||||
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr i8, i8* [[DST:%.*]], i64 16
|
||||
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[TMP1]], i8 [[C:%.*]], i64 0, i1 false)
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[DST]], i8* [[SRC:%.*]], i64 16, i1 false)
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[DST:%.*]], i8* [[SRC:%.*]], i64 16, i1 false)
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 16, i1 false)
|
||||
|
@ -251,12 +249,7 @@ define void @test_same_const_size(i8* noalias %src, i8* noalias %dst, i8 %c) {
|
|||
|
||||
define void @test_same_dynamic_size(i8* noalias %src, i8* noalias %dst, i64 %size, i8 %c) {
|
||||
; CHECK-LABEL: @test_same_dynamic_size(
|
||||
; CHECK-NEXT: [[TMP1:%.*]] = icmp ule i64 [[SIZE:%.*]], [[SIZE]]
|
||||
; CHECK-NEXT: [[TMP2:%.*]] = sub i64 [[SIZE]], [[SIZE]]
|
||||
; CHECK-NEXT: [[TMP3:%.*]] = select i1 [[TMP1]], i64 0, i64 [[TMP2]]
|
||||
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr i8, i8* [[DST:%.*]], i64 [[SIZE]]
|
||||
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[TMP4]], i8 [[C:%.*]], i64 [[TMP3]], i1 false)
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[DST]], i8* [[SRC:%.*]], i64 [[SIZE]], i1 false)
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[DST:%.*]], i8* [[SRC:%.*]], i64 [[SIZE:%.*]], i1 false)
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
call void @llvm.memset.p0i8.i64(i8* %dst, i8 %c, i64 %size, i1 false)
|
||||
|
|
|
@ -40,8 +40,6 @@ define void @test2(i8* noalias %in) {
|
|||
; CHECK-LABEL: @test2(
|
||||
; CHECK-NEXT: entry:
|
||||
; CHECK-NEXT: [[CALL_I1_I:%.*]] = tail call i8* @get_ptr()
|
||||
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr i8, i8* [[CALL_I1_I]], i64 10
|
||||
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[TMP0]], i8 0, i64 0, i1 false)
|
||||
; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[CALL_I1_I]], i8* [[IN:%.*]], i64 10, i1 false)
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
|
@ -69,8 +67,6 @@ define void @test4(i32 %n, i8* noalias %ptr.0, i8* noalias %ptr.1, i32* %ptr.2)
|
|||
; CHECK-LABEL: @test4(
|
||||
; CHECK-NEXT: [[ELEM_I:%.*]] = getelementptr i8, i8* [[PTR_0:%.*]], i64 8
|
||||
; CHECK-NEXT: store i32 [[N:%.*]], i32* [[PTR_2:%.*]], align 8
|
||||
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr i8, i8* [[ELEM_I]], i64 10
|
||||
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[TMP1]], i8 0, i64 0, i1 false)
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[ELEM_I]], i8* [[PTR_1:%.*]], i64 10, i1 false)
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
|
|
Loading…
Reference in New Issue