Page MenuHomePhabricator
Differential D29641 Diff 88731 test/Transforms/SLPVectorizer/X86/reduction_loads.ll

Changeset View

Standalone View

View Options

test/Transforms/SLPVectorizer/X86/reduction_loads.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-apple-macosx10.10.0 -mattr=+sse4.2 | FileCheck %s ; RUN: opt < %s -slp-vectorizer -S -mtriple=x86_64-apple-macosx10.10.0 -mattr=+sse4.2 | FileCheck %s
define i32 @test(i32* nocapture readonly %p) { define i32 @test(i32* nocapture readonly %p) {
; CHECK-LABEL: @test( ; CHECK-LABEL: @test(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds i32, i32* %p, i64 1 ; CHECK-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds i32, i32* %p, i64 2 ; CHECK-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 2
; CHECK-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds i32, i32* %p, i64 3 ; CHECK-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 3
; CHECK-NEXT: [[ARRAYIDX_4:%.*]] = getelementptr inbounds i32, i32* %p, i64 4 ; CHECK-NEXT: [[ARRAYIDX_4:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 4
; CHECK-NEXT: [[ARRAYIDX_5:%.*]] = getelementptr inbounds i32, i32* %p, i64 5 ; CHECK-NEXT: [[ARRAYIDX_5:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 5
; CHECK-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds i32, i32* %p, i64 6 ; CHECK-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 6
; CHECK-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds i32, i32* %p, i64 7 ; CHECK-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 7
; CHECK-NEXT: br label %for.body ; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body: ; CHECK: for.body:
; CHECK-NEXT: [[SUM:%.*]] = phi i32 [ 0, %entry ], [ %add.7, %for.body ] ; CHECK-NEXT: [[SUM:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD_7:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* %p to <8 x i32>* ; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[P]] to <8 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i32>, <8 x i32>* [[TMP0]], align 4 ; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i32>, <8 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = mul <8 x i32> <i32 42, i32 42, i32 42, i32 42, i32 42, i32 42, i32 42, i32 42>, [[TMP1]] ; CHECK-NEXT: [[TMP2:%.*]] = mul <8 x i32> <i32 42, i32 42, i32 42, i32 42, i32 42, i32 42, i32 42, i32 42>, [[TMP1]]
; CHECK-NEXT: [[ADD:%.*]] = add i32 undef, [[SUM]]
; CHECK-NEXT: [[ADD_1:%.*]] = add i32 undef, [[ADD]]
; CHECK-NEXT: [[ADD_2:%.*]] = add i32 undef, [[ADD_1]]
; CHECK-NEXT: [[ADD_3:%.*]] = add i32 undef, [[ADD_2]]
; CHECK-NEXT: [[ADD_4:%.*]] = add i32 undef, [[ADD_3]]
; CHECK-NEXT: [[ADD_5:%.*]] = add i32 undef, [[ADD_4]]
; CHECK-NEXT: [[ADD_6:%.*]] = add i32 undef, [[ADD_5]]
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef> ; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX:%.*]] = add <8 x i32> [[TMP2]], [[RDX_SHUF]] ; CHECK-NEXT: [[BIN_RDX:%.*]] = add <8 x i32> [[TMP2]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <8 x i32> [[BIN_RDX]], <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> ; CHECK-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <8 x i32> [[BIN_RDX]], <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX2:%.*]] = add <8 x i32> [[BIN_RDX]], [[RDX_SHUF1]] ; CHECK-NEXT: [[BIN_RDX2:%.*]] = add <8 x i32> [[BIN_RDX]], [[RDX_SHUF1]]
; CHECK-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <8 x i32> [[BIN_RDX2]], <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> ; CHECK-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <8 x i32> [[BIN_RDX2]], <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX4:%.*]] = add <8 x i32> [[BIN_RDX2]], [[RDX_SHUF3]] ; CHECK-NEXT: [[BIN_RDX4:%.*]] = add <8 x i32> [[BIN_RDX2]], [[RDX_SHUF3]]
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <8 x i32> [[BIN_RDX4]], i32 0 ; CHECK-NEXT: [[TMP3:%.*]] = extractelement <8 x i32> [[BIN_RDX4]], i32 0
; CHECK-NEXT: [[ADD_7:%.*]] = add i32 [[TMP4]], [[SUM]] ; CHECK-NEXT: [[ADD_7]] = add i32 [[TMP3]], [[SUM]]
; CHECK-NEXT: br i1 true, label %for.end, label %for.body ; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.end: ; CHECK: for.end:
; CHECK-NEXT: ret i32 [[ADD_7]] ; CHECK-NEXT: ret i32 [[ADD_7]]
; ;
entry: entry:
%arrayidx.1 = getelementptr inbounds i32, i32* %p, i64 1 %arrayidx.1 = getelementptr inbounds i32, i32* %p, i64 1
%arrayidx.2 = getelementptr inbounds i32, i32* %p, i64 2 %arrayidx.2 = getelementptr inbounds i32, i32* %p, i64 2
%arrayidx.3 = getelementptr inbounds i32, i32* %p, i64 3 %arrayidx.3 = getelementptr inbounds i32, i32* %p, i64 3
%arrayidx.4 = getelementptr inbounds i32, i32* %p, i64 4 %arrayidx.4 = getelementptr inbounds i32, i32* %p, i64 4
Show All 36 Lines