a5c3b5748c
As discussed on https://github.com/llvm/llvm-project/issues/54682, MemorySSA currently has a bug when computing the clobber of calls that access loop-varying locations. I think a "proper" fix for this on the MemorySSA side might be non-trivial, but we can easily work around this in MemCpyOpt: Currently, MemCpyOpt uses a location-less getClobberingMemoryAccess() call to find a clobber on either the src or dest location, and then refines it for the src and dest clobber. This was intended as an optimization, as the location-less API is cached, while the location-affected APIs are not. However, I don't think this really makes a difference in practice, because I don't think anything will use the cached clobbers on those calls later anyway. On CTMark, this patch seems to be very mildly positive actually. So I think this is a reasonable way to avoid the problem for now, though MemorySSA should also get a fix. Differential Revision: https://reviews.llvm.org/D122911
43 lines
1.8 KiB
LLVM
43 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -memcpyopt < %s | FileCheck %s
|
|
|
|
; The memcpy here is *not* dead, because it reads memory written in a previous
|
|
; loop iteration.
|
|
|
|
define void @test(i1 %c, i8* nocapture noundef readonly %path, i8* noundef writeonly %name) {
|
|
; CHECK-LABEL: @test(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[TMP:%.*]] = alloca [260 x i8], align 16
|
|
; CHECK-NEXT: br label [[WHILE_BODY:%.*]]
|
|
; CHECK: while.body:
|
|
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[WHILE_BODY]] ], [ 259, [[ENTRY:%.*]] ]
|
|
; CHECK-NEXT: [[IV_NEXT]] = add nsw i64 [[IV]], -1
|
|
; CHECK-NEXT: [[TMP_IV:%.*]] = getelementptr inbounds [260 x i8], [260 x i8]* [[TMP]], i64 0, i64 [[IV]]
|
|
; CHECK-NEXT: store i8 42, i8* [[TMP_IV]], align 1
|
|
; CHECK-NEXT: br i1 [[C:%.*]], label [[WHILE_BODY]], label [[EXIT:%.*]]
|
|
; CHECK: exit:
|
|
; CHECK-NEXT: [[TMP_IV_1:%.*]] = getelementptr inbounds i8, i8* [[TMP_IV]], i64 1
|
|
; CHECK-NEXT: [[LEN:%.*]] = sub nsw i64 259, [[IV]]
|
|
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 [[NAME:%.*]], i8* nonnull align 1 [[TMP_IV_1]], i64 [[LEN]], i1 false)
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
%tmp = alloca [260 x i8], align 16
|
|
br label %while.body
|
|
|
|
while.body:
|
|
%iv = phi i64 [ %iv.next, %while.body ], [ 259, %entry ]
|
|
%iv.next = add nsw i64 %iv, -1
|
|
%tmp.iv = getelementptr inbounds [260 x i8], [260 x i8]* %tmp, i64 0, i64 %iv
|
|
store i8 42, i8* %tmp.iv, align 1
|
|
br i1 %c, label %while.body, label %exit
|
|
|
|
exit:
|
|
%tmp.iv.1 = getelementptr inbounds i8, i8* %tmp.iv, i64 1
|
|
%len = sub nsw i64 259, %iv
|
|
call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 1 %name, i8* nonnull align 1 %tmp.iv.1, i64 %len, i1 false)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* noalias nocapture writeonly %0, i8* noalias nocapture readonly %1, i64 %2, i1 immarg %3)
|