maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[SLP] add fadd reduction test to show broken FMF propagation; NFC

This commit is contained in:
Sanjay Patel 2020-12-30 11:27:23 -05:00
parent 2016f2c8a7
commit 3567908d8c
1 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
llvm/test/Transforms/SLPVectorizer/X86/horizontal.ll
View File

@ -1766,4 +1766,39 @@ bb.1:
ret void
}
; FIXME: This is a miscompile.
; The FMF on the reduction should match the incoming insts.
define float @fadd_v4f32_fmf(float* %p) {
; CHECK-LABEL: @fadd_v4f32_fmf(
; CHECK-NEXT: [[P1:%.*]] = getelementptr inbounds float, float* [[P:%.*]], i64 1
; CHECK-NEXT: [[P2:%.*]] = getelementptr inbounds float, float* [[P]], i64 2
; CHECK-NEXT: [[P3:%.*]] = getelementptr inbounds float, float* [[P]], i64 3
; CHECK-NEXT: [[TMP1:%.*]] = bitcast float* [[P]] to <4 x float>*
; CHECK-NEXT: [[TMP2:%.*]] = load <4 x float>, <4 x float>* [[TMP1]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float -0.000000e+00, <4 x float> [[TMP2]])
; CHECK-NEXT: ret float [[TMP3]]
;
; STORE-LABEL: @fadd_v4f32_fmf(
; STORE-NEXT: [[P1:%.*]] = getelementptr inbounds float, float* [[P:%.*]], i64 1
; STORE-NEXT: [[P2:%.*]] = getelementptr inbounds float, float* [[P]], i64 2
; STORE-NEXT: [[P3:%.*]] = getelementptr inbounds float, float* [[P]], i64 3
; STORE-NEXT: [[TMP1:%.*]] = bitcast float* [[P]] to <4 x float>*
; STORE-NEXT: [[TMP2:%.*]] = load <4 x float>, <4 x float>* [[TMP1]], align 4
; STORE-NEXT: [[TMP3:%.*]] = call fast float @llvm.vector.reduce.fadd.v4f32(float -0.000000e+00, <4 x float> [[TMP2]])
; STORE-NEXT: ret float [[TMP3]]
;
%p1 = getelementptr inbounds float, float* %p, i64 1
%p2 = getelementptr inbounds float, float* %p, i64 2
%p3 = getelementptr inbounds float, float* %p, i64 3
%t0 = load float, float* %p, align 4
%t1 = load float, float* %p1, align 4
%t2 = load float, float* %p2, align 4
%t3 = load float, float* %p3, align 4
%add1 = fadd reassoc nsz float %t1, %t0
%add2 = fadd reassoc nsz float %t2, %add1
%add3 = fadd reassoc nsz float %t3, %add2
ret float %add3
}
declare i32 @__gxx_personality_v0(...)