-
Notifications
You must be signed in to change notification settings - Fork 12.7k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
2 changed files
with
237 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,195 @@ | ||
| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4 | ||
| ; RUN: opt < %s -passes=memcpyopt -S -verify-memoryssa | FileCheck %s | ||
|
|
||
| %buf = type [9 x i8] | ||
|
|
||
| ; We can forward `memcpy` because the copy location are the same, | ||
| define void @forward_offset(ptr %dep_src) { | ||
| ; CHECK-LABEL: define void @forward_offset( | ||
| ; CHECK-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CHECK-NEXT: [[DEP_DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP_DEST]], ptr align 1 [[DEP_SRC]], i64 7, i1 false) | ||
| ; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 1 | ||
| ; CHECK-NEXT: [[DEP:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP]], ptr align 1 [[SRC]], i64 6, i1 false) | ||
| ; CHECK-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 1 %dep_src, i64 7, i1 false) | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 1 | ||
| %dest = getelementptr inbounds i8, ptr %dep_src, i64 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 6, i1 false) | ||
| ret void | ||
| } | ||
|
|
||
| ; We need to update the align value of the source of `memcpy` when forwarding. | ||
| define void @forward_offset_align(ptr %dep_src) { | ||
| ; CHECK-LABEL: define void @forward_offset_align( | ||
| ; CHECK-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CHECK-NEXT: [[DEP_DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP_DEST]], ptr align 4 [[DEP_SRC]], i64 9, i1 false) | ||
| ; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 3 | ||
| ; CHECK-NEXT: [[DEST:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 3 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEST]], ptr align 1 [[SRC]], i64 5, i1 false) | ||
| ; CHECK-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 4 %dep_src, i64 9, i1 false) | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 3 | ||
| %dest = getelementptr inbounds i8, ptr %dep_src, i64 3 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 5, i1 false) | ||
| ret void | ||
| } | ||
|
|
||
| ; We can change the align value to 2 when forwarding. | ||
| define void @forward_offset_align_2(ptr %dep_src) { | ||
| ; CHECK-LABEL: define void @forward_offset_align_2( | ||
| ; CHECK-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CHECK-NEXT: [[DEP_DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP_DEST]], ptr align 4 [[DEP_SRC]], i64 9, i1 false) | ||
| ; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 2 | ||
| ; CHECK-NEXT: [[DEP:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 2 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP]], ptr align 1 [[SRC]], i64 6, i1 false) | ||
| ; CHECK-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 4 %dep_src, i64 9, i1 false) | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 2 | ||
| %dest = getelementptr inbounds i8, ptr %dep_src, i64 2 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 6, i1 false) | ||
| ret void | ||
| } | ||
|
|
||
| ; We need to create a GEP instruction when forwarding. | ||
| define void @forward_offset_with_gep(ptr %dep_src) { | ||
| ; CHECK-LABEL: define void @forward_offset_with_gep( | ||
| ; CHECK-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CHECK-NEXT: [[DEP_DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP_DEST]], ptr align 1 [[DEP_SRC]], i64 7, i1 false) | ||
| ; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 1 | ||
| ; CHECK-NEXT: [[DEP1:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 2 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP1]], ptr align 1 [[SRC]], i64 6, i1 false) | ||
| ; CHECK-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 1 %dep_src, i64 7, i1 false) | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 1 | ||
| %dest = getelementptr inbounds i8, ptr %dep_src, i64 2 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 6, i1 false) | ||
| ret void | ||
| } | ||
|
|
||
| ; Make sure we pass the right parameters when calling `memcpy`. | ||
| define void @forward_offset_memcpy(ptr %dep_src) { | ||
| ; CHECK-LABEL: define void @forward_offset_memcpy( | ||
| ; CHECK-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CHECK-NEXT: [[DEP_DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: [[DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP_DEST]], ptr align 1 [[DEP_SRC]], i64 7, i1 false) | ||
| ; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEST]], ptr align 1 [[SRC]], i64 6, i1 false) | ||
| ; CHECK-NEXT: call void @use(ptr [[DEST]]) | ||
| ; CHECK-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| %dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 1 %dep_src, i64 7, i1 false) | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 6, i1 false) | ||
| call void @use(ptr %dest) | ||
| ret void | ||
| } | ||
|
|
||
| ; Make sure we pass the right parameters when calling `memcpy.inline`. | ||
| define void @forward_offset_memcpy_inline(ptr %dep_src) { | ||
| ; CHECK-LABEL: define void @forward_offset_memcpy_inline( | ||
| ; CHECK-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CHECK-NEXT: [[DEP_DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: [[DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP_DEST]], ptr align 1 [[DEP_SRC]], i64 7, i1 false) | ||
| ; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.inline.p0.p0.i64(ptr align 1 [[DEST]], ptr align 1 [[SRC]], i64 6, i1 false) | ||
| ; CHECK-NEXT: call void @use(ptr [[DEST]]) | ||
| ; CHECK-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| %dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 1 %dep_src, i64 7, i1 false) | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 1 | ||
| call void @llvm.memcpy.inline.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 6, i1 false) | ||
| call void @use(ptr %dest) | ||
| ret void | ||
| } | ||
|
|
||
| ; We cannot forward `memcpy` because it exceeds the size of `memcpy` it depends on. | ||
| define void @do_not_forward_oversize_offset(ptr %dep_src) { | ||
| ; CHECK-LABEL: define void @do_not_forward_oversize_offset( | ||
| ; CHECK-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CHECK-NEXT: [[DEP_DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP_DEST]], ptr align 1 [[DEP_SRC]], i64 6, i1 false) | ||
| ; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 1 | ||
| ; CHECK-NEXT: [[DEP:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP]], ptr align 1 [[SRC]], i64 6, i1 false) | ||
| ; CHECK-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 1 %dep_src, i64 6, i1 false) | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 1 | ||
| %dest = getelementptr inbounds i8, ptr %dep_src, i64 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 6, i1 false) | ||
| ret void | ||
| } | ||
|
|
||
| ; We can forward `memcpy` because the write operation does not corrupt the location to be copied. | ||
| define void @forward_offset_and_store(ptr %dep_src) { | ||
| ; CHECK-LABEL: define void @forward_offset_and_store( | ||
| ; CHECK-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CHECK-NEXT: [[DEP_DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP_DEST]], ptr align 1 [[DEP_SRC]], i64 7, i1 false) | ||
| ; CHECK-NEXT: store i8 1, ptr [[DEP_SRC]], align 1 | ||
| ; CHECK-NEXT: [[DEP_SRC_END:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 6 | ||
| ; CHECK-NEXT: store i8 1, ptr [[DEP_SRC_END]], align 1 | ||
| ; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 1 | ||
| ; CHECK-NEXT: [[DEP:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP]], ptr align 1 [[SRC]], i64 5, i1 false) | ||
| ; CHECK-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 1 %dep_src, i64 7, i1 false) | ||
| store i8 1, ptr %dep_src, align 1 | ||
| %dep_src_end = getelementptr inbounds i8, ptr %dep_src, i64 6 | ||
| store i8 1, ptr %dep_src_end, align 1 | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 1 | ||
| %dest = getelementptr inbounds i8, ptr %dep_src, i64 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 5, i1 false) | ||
| ret void | ||
| } | ||
|
|
||
| ; We cannot forward `memcpy` because the write operation alters the location to be copied. | ||
| ; Also, make sure we have removed the GEP instruction that was created temporarily. | ||
| define void @do_not_forward_offset_and_store(ptr %dep_src) { | ||
| ; CHECK-LABEL: define void @do_not_forward_offset_and_store( | ||
| ; CHECK-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CHECK-NEXT: [[DEP_DEST:%.*]] = alloca [9 x i8], align 1 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEP_DEST]], ptr align 1 [[DEP_SRC]], i64 7, i1 false) | ||
| ; CHECK-NEXT: [[DEP:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 1 | ||
| ; CHECK-NEXT: store i8 1, ptr [[DEP]], align 1 | ||
| ; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 1 | ||
| ; CHECK-NEXT: [[DEST:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 2 | ||
| ; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr align 1 [[DEST]], ptr align 1 [[SRC]], i64 5, i1 false) | ||
| ; CHECK-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 1 %dep_src, i64 7, i1 false) | ||
| %dep_src_offset = getelementptr inbounds i8, ptr %dep_src, i64 1 | ||
| store i8 1, ptr %dep_src_offset, align 1 | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 1 | ||
| %dest = getelementptr inbounds i8, ptr %dep_src, i64 2 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 5, i1 false) | ||
| ret void | ||
| } | ||
|
|
||
| declare void @use(ptr) | ||
|
|
||
| declare void @llvm.memcpy.p0.p0.i64(ptr nocapture, ptr nocapture, i64, i1) | ||
| declare void @llvm.memcpy.inline.p0.p0.i64(ptr nocapture, ptr nocapture, i64, i1) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,42 @@ | ||
| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4 | ||
| ; RUN: opt < %s -passes=memcpyopt,dse,instcombine -S -verify-memoryssa | FileCheck --check-prefix=CUSTOM %s | ||
| ; RUN: opt < %s -O2 -S | FileCheck --check-prefix=O2 %s | ||
|
|
||
| %buf = type [7 x i8] | ||
|
|
||
| ; Check that we eliminate all `memcpy` calls in this function. | ||
| define void @forward_offset_and_store(ptr %dep_src) { | ||
| ; CUSTOM-LABEL: define void @forward_offset_and_store( | ||
| ; CUSTOM-SAME: ptr [[DEP_SRC:%.*]]) { | ||
| ; CUSTOM-NEXT: [[DEP_DEST:%.*]] = alloca [7 x i8], align 1 | ||
| ; CUSTOM-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 1 dereferenceable(7) [[DEP_DEST]], ptr noundef nonnull align 1 dereferenceable(7) [[DEP_SRC]], i64 7, i1 false) | ||
| ; CUSTOM-NEXT: store i8 1, ptr [[DEP_SRC]], align 1 | ||
| ; CUSTOM-NEXT: [[DEP_SRC_END:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 6 | ||
| ; CUSTOM-NEXT: store i8 1, ptr [[DEP_SRC_END]], align 1 | ||
| ; CUSTOM-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 1 | ||
| ; CUSTOM-NEXT: [[DEST:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 1 | ||
| ; CUSTOM-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 1 dereferenceable(5) [[DEST]], ptr noundef nonnull align 1 dereferenceable(5) [[SRC]], i64 5, i1 false) | ||
| ; CUSTOM-NEXT: ret void | ||
| ; | ||
| ; O2-LABEL: define void @forward_offset_and_store( | ||
| ; O2-SAME: ptr nocapture [[DEP_SRC:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] { | ||
| ; O2-NEXT: [[DEP_DEST:%.*]] = alloca [7 x i8], align 1 | ||
| ; O2-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 1 dereferenceable(7) [[DEP_DEST]], ptr noundef nonnull align 1 dereferenceable(7) [[DEP_SRC]], i64 7, i1 false) | ||
| ; O2-NEXT: store i8 1, ptr [[DEP_SRC]], align 1 | ||
| ; O2-NEXT: [[DEP_SRC_END:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 6 | ||
| ; O2-NEXT: store i8 1, ptr [[DEP_SRC_END]], align 1 | ||
| ; O2-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[DEP_DEST]], i64 1 | ||
| ; O2-NEXT: [[DEST:%.*]] = getelementptr inbounds i8, ptr [[DEP_SRC]], i64 1 | ||
| ; O2-NEXT: call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 1 dereferenceable(5) [[DEST]], ptr noundef nonnull align 1 dereferenceable(5) [[SRC]], i64 5, i1 false) | ||
| ; O2-NEXT: ret void | ||
| ; | ||
| %dep_dest = alloca %buf, align 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dep_dest, ptr align 1 %dep_src, i64 7, i1 false) | ||
| store i8 1, ptr %dep_src, align 1 | ||
| %dep_src_end = getelementptr inbounds i8, ptr %dep_src, i64 6 | ||
| store i8 1, ptr %dep_src_end, align 1 | ||
| %src = getelementptr inbounds i8, ptr %dep_dest, i64 1 | ||
| %dest = getelementptr inbounds i8, ptr %dep_src, i64 1 | ||
| call void @llvm.memcpy.p0.p0.i64(ptr align 1 %dest, ptr align 1 %src, i64 5, i1 false) | ||
| ret void | ||
| } |