48bc5b0a29
insertelement instructions. If the original vector has undef, not poison values, which are not rewritten by later insertelement instructions, need to transform shuffle with the undef vector, not a poison vector, and actual indices, not PoisonMaskElem, otherwise the transformation may produce more poisons output than the input.
28 lines
1.5 KiB
LLVM
28 lines
1.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -passes=slp-vectorizer -slp-threshold=0 < %s | FileCheck %s
|
|
|
|
define <4 x float> @simple_select(<4 x float> %a, <4 x float> %b, <4 x i32> %c) {
|
|
; CHECK-LABEL: @simple_select(
|
|
; CHECK-NEXT: [[TMP1:%.*]] = shufflevector <4 x i32> [[C:%.*]], <4 x i32> poison, <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[TMP2:%.*]] = icmp ne <2 x i32> [[TMP1]], zeroinitializer
|
|
; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x float> [[A:%.*]], <4 x float> poison, <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x float> [[B:%.*]], <4 x float> poison, <2 x i32> <i32 0, i32 1>
|
|
; CHECK-NEXT: [[TMP5:%.*]] = select <2 x i1> [[TMP2]], <2 x float> [[TMP3]], <2 x float> [[TMP4]]
|
|
; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x float> [[TMP5]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: ret <4 x float> [[TMP6]]
|
|
;
|
|
%c0 = extractelement <4 x i32> %c, i32 0
|
|
%c1 = extractelement <4 x i32> %c, i32 1
|
|
%a0 = extractelement <4 x float> %a, i32 0
|
|
%a1 = extractelement <4 x float> %a, i32 1
|
|
%b0 = extractelement <4 x float> %b, i32 0
|
|
%b1 = extractelement <4 x float> %b, i32 1
|
|
%cmp0 = icmp ne i32 %c0, 0
|
|
%cmp1 = icmp ne i32 %c1, 0
|
|
%s0 = select i1 %cmp0, float %a0, float %b0
|
|
%s1 = select i1 %cmp1, float %a1, float %b1
|
|
%ra = insertelement <4 x float> <float poison, float poison, float undef, float undef>, float %s0, i32 0
|
|
%rb = insertelement <4 x float> %ra, float %s1, i32 1
|
|
ret <4 x float> %rb
|
|
}
|