Page MenuHomePhabricator
Differential D114087 Diff 391342 llvm/test/Transforms/SLPVectorizer/X86/diamond_broadcast_extra_shuffle.ll

Changeset View

Standalone View

View Options

llvm/test/Transforms/SLPVectorizer/X86/diamond_broadcast_extra_shuffle.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -slp-vectorizer -S -mtriple=x86_64-unknown-linux -slp-threshold=-2 | FileCheck %s ; RUN: opt < %s -slp-vectorizer -S -mtriple=x86_64-unknown-linux -slp-threshold=-2 | FileCheck %s
define i32 @diamond_broadcast(i32* noalias nocapture %B, i32* noalias nocapture %A) { define i32 @diamond_broadcast(i32* noalias nocapture %B, i32* noalias nocapture %A) {
; CHECK-LABEL: @diamond_broadcast( ; CHECK-LABEL: @diamond_broadcast(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[A:%.*]], align 4 ; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[A:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1 ; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2 ; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[LD]], i32 0 ; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[LD]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer ; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[SHUFFLE1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 undef> ; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> [[SHUFFLE]], [[SHUFFLE]]
; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> [[SHUFFLE]], [[SHUFFLE1]]
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3 ; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>* ; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: ret i32 0 ; CHECK-NEXT: ret i32 0
; ;
entry: entry:
%ld = load i32, i32* %A, align 4 %ld = load i32, i32* %A, align 4
%mul = mul i32 %ld, %ld %mul = mul i32 %ld, %ld
Show All 12 Lines
define i32 @diamond_broadcast2(i32* noalias nocapture %B, i32* noalias nocapture %A) { define i32 @diamond_broadcast2(i32* noalias nocapture %B, i32* noalias nocapture %A) {
; CHECK-LABEL: @diamond_broadcast2( ; CHECK-LABEL: @diamond_broadcast2(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[A:%.*]], align 4 ; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[A:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1 ; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2 ; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[LD]], i32 0 ; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[LD]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 undef> ; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[SHUFFLE1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer ; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> [[SHUFFLE]], [[SHUFFLE]]
; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> [[SHUFFLE]], [[SHUFFLE1]]
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3 ; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>* ; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: ret i32 0 ; CHECK-NEXT: ret i32 0
; ;
entry: entry:
%ld = load i32, i32* %A, align 4 %ld = load i32, i32* %A, align 4
%mul = mul i32 %ld, %ld %mul = mul i32 %ld, %ld
Show All 12 Lines
define i32 @diamond_broadcast3(i32* noalias nocapture %B, i32* noalias nocapture %A) { define i32 @diamond_broadcast3(i32* noalias nocapture %B, i32* noalias nocapture %A) {
; CHECK-LABEL: @diamond_broadcast3( ; CHECK-LABEL: @diamond_broadcast3(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[A:%.*]], align 4 ; CHECK-NEXT: [[LD:%.*]] = load i32, i32* [[A:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1 ; CHECK-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2 ; CHECK-NEXT: [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 2
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[LD]], i32 0 ; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 [[LD]], i32 0
; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> <i32 0, i32 0, i32 0, i32 undef> ; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[SHUFFLE1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <4 x i32> <i32 0, i32 0, i32 undef, i32 0> ; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> [[SHUFFLE]], [[SHUFFLE]]
; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> [[SHUFFLE]], [[SHUFFLE1]]
; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3 ; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 3
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>* ; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[B]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4 ; CHECK-NEXT: store <4 x i32> [[TMP1]], <4 x i32>* [[TMP2]], align 4
; CHECK-NEXT: ret i32 0 ; CHECK-NEXT: ret i32 0
; ;
entry: entry:
%ld = load i32, i32* %A, align 4 %ld = load i32, i32* %A, align 4
%mul = mul i32 %ld, %ld %mul = mul i32 %ld, %ld
Show All 13 Lines