5ddf40fa78
If any extract is waiting to be erased, then bail out as this will distort the cost calculation and possibly lead to infinite loops. Fixes #129373
39 lines
1.8 KiB
LLVM
39 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=vector-combine -S -mtriple=x86_64-- -mattr=sse2 | FileCheck %s
|
|
; RUN: opt < %s -passes=vector-combine -S -mtriple=x86_64-- -mattr=avx2 | FileCheck %s
|
|
|
|
; infinite loop if we add the erased instructions to the work list in the wrong order.
|
|
define void @multiple_extract(ptr %p) {
|
|
; CHECK-LABEL: @multiple_extract(
|
|
; CHECK-NEXT: [[VP:%.*]] = load ptr, ptr [[P:%.*]], align 8
|
|
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds <2 x i32>, ptr [[VP]], i32 0, i64 0
|
|
; CHECK-NEXT: [[E0:%.*]] = load i32, ptr [[TMP1]], align 16
|
|
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds <2 x i32>, ptr [[VP]], i32 0, i64 1
|
|
; CHECK-NEXT: [[E1:%.*]] = load i32, ptr [[TMP2]], align 4
|
|
; CHECK-NEXT: store i32 [[E0]], ptr [[P]], align 4
|
|
; CHECK-NEXT: [[P1:%.*]] = getelementptr inbounds nuw i8, ptr [[P]], i64 4
|
|
; CHECK-NEXT: store i32 [[E1]], ptr [[P1]], align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%vp = load ptr, ptr %p, align 8
|
|
%v = load <2 x i32>, ptr %vp, align 16
|
|
%e0 = extractelement <2 x i32> %v, i64 0
|
|
%e1 = extractelement <2 x i32> %v, i64 1
|
|
store i32 %e0, ptr %p, align 4
|
|
%p1 = getelementptr inbounds nuw i8, ptr %p, i64 4
|
|
store i32 %e1, ptr %p1, align 4
|
|
ret void
|
|
}
|
|
|
|
; infinite loop if we fold an extract that is waiting to be erased
|
|
define void @unused_extract(ptr %p) {
|
|
; CHECK-LABEL: @unused_extract(
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%load = load <4 x float>, ptr %p, align 8
|
|
%shuffle0 = shufflevector <4 x float> zeroinitializer, <4 x float> %load, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
|
|
%shuffle1 = shufflevector <4 x float> %shuffle0, <4 x float> zeroinitializer, <4 x i32> <i32 0, i32 4, i32 poison, i32 poison>
|
|
%extract = extractelement <4 x float> %load, i64 1
|
|
ret void
|
|
}
|