cd7ea4ea65
LAA currently adds memory locations with their original AATags to AST. However, scoped alias AATags may be valid only within one loop iteration, while LAA reasons across iterations. Fix this by determining which alias scopes are defined inside the loop, and drop AATags that reference these scopes. Fixes https://github.com/llvm/llvm-project/issues/79137.
79 lines
3.4 KiB
LLVM
79 lines
3.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: opt -S -O3 -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s
|
|
|
|
define internal void @acc(ptr noalias noundef %val, ptr noalias noundef %prev) {
|
|
entry:
|
|
%0 = load i8, ptr %prev, align 1
|
|
%conv = zext i8 %0 to i32
|
|
%1 = load i8, ptr %val, align 1
|
|
%conv1 = zext i8 %1 to i32
|
|
%add = add nsw i32 %conv1, %conv
|
|
%conv2 = trunc i32 %add to i8
|
|
store i8 %conv2, ptr %val, align 1
|
|
ret void
|
|
}
|
|
|
|
; This loop should not get vectorized.
|
|
define void @accsum(ptr noundef %vals, i64 noundef %num) #0 {
|
|
; CHECK-LABEL: define void @accsum(
|
|
; CHECK-SAME: ptr nocapture noundef [[VALS:%.*]], i64 noundef [[NUM:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[CMP1:%.*]] = icmp ugt i64 [[NUM]], 1
|
|
; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
|
|
; CHECK: for.body.preheader:
|
|
; CHECK-NEXT: [[LOAD_INITIAL:%.*]] = load i8, ptr [[VALS]], align 1
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[STORE_FORWARDED:%.*]] = phi i8 [ [[LOAD_INITIAL]], [[FOR_BODY_PREHEADER]] ], [ [[ADD_I:%.*]], [[FOR_BODY]] ]
|
|
; CHECK-NEXT: [[I_02:%.*]] = phi i64 [ 1, [[FOR_BODY_PREHEADER]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[VALS]], i64 [[I_02]]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = load i8, ptr [[ARRAYIDX]], align 1, !alias.scope [[META0:![0-9]+]], !noalias [[META3:![0-9]+]]
|
|
; CHECK-NEXT: [[ADD_I]] = add i8 [[TMP0]], [[STORE_FORWARDED]]
|
|
; CHECK-NEXT: store i8 [[ADD_I]], ptr [[ARRAYIDX]], align 1, !alias.scope [[META0]], !noalias [[META3]]
|
|
; CHECK-NEXT: [[INC]] = add nuw i64 [[I_02]], 1
|
|
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[NUM]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.inc, %entry
|
|
%i.0 = phi i64 [ 1, %entry ], [ %inc, %for.inc ]
|
|
%cmp = icmp ult i64 %i.0, %num
|
|
br i1 %cmp, label %for.body, label %for.cond.cleanup
|
|
|
|
for.cond.cleanup: ; preds = %for.cond
|
|
br label %for.end
|
|
|
|
for.body: ; preds = %for.cond
|
|
%arrayidx = getelementptr inbounds i8, ptr %vals, i64 %i.0
|
|
%sub = sub i64 %i.0, 1
|
|
%arrayidx1 = getelementptr inbounds i8, ptr %vals, i64 %sub
|
|
call void @acc(ptr noundef %arrayidx, ptr noundef %arrayidx1)
|
|
br label %for.inc
|
|
|
|
for.inc: ; preds = %for.body
|
|
%inc = add i64 %i.0, 1
|
|
br label %for.cond
|
|
|
|
for.end: ; preds = %for.cond.cleanup
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: nocallback nofree nosync nounwind willreturn memory(argmem: readwrite)
|
|
declare void @llvm.lifetime.start.p0(i64 immarg, ptr nocapture) #1
|
|
|
|
; Function Attrs: nocallback nofree nosync nounwind willreturn memory(argmem: readwrite)
|
|
declare void @llvm.lifetime.end.p0(i64 immarg, ptr nocapture) #1
|
|
|
|
attributes #0 = { "target-features"="+cmov,+cx8,+fxsr,+mmx,+sse,+sse2,+x87"}
|
|
;.
|
|
; CHECK: [[META0]] = !{[[META1:![0-9]+]]}
|
|
; CHECK: [[META1]] = distinct !{[[META1]], [[META2:![0-9]+]], !"acc: %val"}
|
|
; CHECK: [[META2]] = distinct !{[[META2]], !"acc"}
|
|
; CHECK: [[META3]] = !{[[META4:![0-9]+]]}
|
|
; CHECK: [[META4]] = distinct !{[[META4]], [[META2]], !"acc: %prev"}
|
|
;.
|