This is an archive of the discontinued LLVM Phabricator instance.

Differential D107106

[SLP]Do not consider deleted instruction as external users.
ClosedPublic

Authored by ABataev on Jul 29 2021, 2:31 PM.

Details

Reviewers
RKSimon
spatel
anton-afanasyev
dtemirbulatov
Commits
rGf4fb85481136: [SLP]Do not consider deleted instruction as external users.
Summary

If the instruction was previously deleted, it should not be treated as
an external user. This fixes cost estimation and removes dead
extractelement instructions.

Diff Detail

Unit TestsFailed

TimeTest
4,600 msx64 debian > libarcher.races::task-dependency.c
20 msx64 windows > flang-Unit.RuntimeGTest/_/FlangRuntimeTests_exe::Reductions.Logical

Event Timeline

ABataev created this revision.Jul 29 2021, 2:31 PM
Herald added a subscriber: hiraditya. · View Herald TranscriptJul 29 2021, 2:31 PM
ABataev requested review of this revision.Jul 29 2021, 2:31 PM
Herald added a project: Restricted Project. · View Herald TranscriptJul 29 2021, 2:31 PM
Harbormaster completed remote builds in B117049: Diff 362886.Jul 29 2021, 3:45 PM
dtemirbulatov accepted this revision.Jul 29 2021, 5:26 PM

LGTM.

This revision is now accepted and ready to land.Jul 29 2021, 5:26 PM
This revision was landed with ongoing or failed builds.Jul 30 2021, 5:38 AM
Closed by commit rGf4fb85481136: [SLP]Do not consider deleted instruction as external users. (authored by ABataev). · Explain Why
This revision was automatically updated to reflect the committed changes.
ABataev added a commit: rGf4fb85481136: [SLP]Do not consider deleted instruction as external users..

Revision Contents

PathSize
llvm/
lib/
Transforms/
Vectorize/
7 lines
test/
Transforms/
SLPVectorizer/
AArch64/
58 lines
SystemZ/
19 lines
X86/
2 lines
4 lines
16 lines
6 lines
69 lines

Diff 362886

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

  • This file is larger than 256 KB, so syntax highlighting is disabled by default.
Show First 20 Lines • Show All 2,936 Lines • ▼ Show 20 Lines for (int Lane = 0, LE = Entry->Scalars.size(); Lane != LE; ++Lane) {
} }
for (User *U : Scalar->users()) { for (User *U : Scalar->users()) {
LLVM_DEBUG(dbgs() << "SLP: Checking user:" << *U << ".\n"); LLVM_DEBUG(dbgs() << "SLP: Checking user:" << *U << ".\n");
Instruction *UserInst = dyn_cast<Instruction>(U); Instruction *UserInst = dyn_cast<Instruction>(U);
if (!UserInst) if (!UserInst)
continue; continue;
if (isDeleted(UserInst))
continue;
// Skip in-tree scalars that become vectors // Skip in-tree scalars that become vectors
if (TreeEntry *UseEntry = getTreeEntry(U)) { if (TreeEntry *UseEntry = getTreeEntry(U)) {
Value *UseScalar = UseEntry->Scalars[0]; Value *UseScalar = UseEntry->Scalars[0];
// Some in-tree scalars will remain as scalar in vectorized // Some in-tree scalars will remain as scalar in vectorized
// instructions. If that is the case, the one in Lane 0 will // instructions. If that is the case, the one in Lane 0 will
// be used. // be used.
if (UseScalar != U || if (UseScalar != U ||
UseEntry->State == TreeEntry::ScatterVectorize || UseEntry->State == TreeEntry::ScatterVectorize ||
▲ Show 20 Lines • Show All 3,351 Lines • ▼ Show 20 Lines
#ifndef NDEBUG #ifndef NDEBUG
Type *Ty = Scalar->getType(); Type *Ty = Scalar->getType();
if (!Ty->isVoidTy()) { if (!Ty->isVoidTy()) {
for (User *U : Scalar->users()) { for (User *U : Scalar->users()) {
LLVM_DEBUG(dbgs() << "SLP: \tvalidating user:" << *U << ".\n"); LLVM_DEBUG(dbgs() << "SLP: \tvalidating user:" << *U << ".\n");
// It is legal to delete users in the ignorelist. // It is legal to delete users in the ignorelist.
assert((getTreeEntry(U) || is_contained(UserIgnoreList, U)) && assert((getTreeEntry(U) || is_contained(UserIgnoreList, U) ||
(isa_and_nonnull<Instruction>(U) &&
isDeleted(cast<Instruction>(U)))) &&
"Deleting out-of-tree value"); "Deleting out-of-tree value");
} }
} }
#endif #endif
LLVM_DEBUG(dbgs() << "SLP: \tErasing scalar:" << *Scalar << ".\n"); LLVM_DEBUG(dbgs() << "SLP: \tErasing scalar:" << *Scalar << ".\n");
eraseInstruction(cast<Instruction>(Scalar)); eraseInstruction(cast<Instruction>(Scalar));
} }
} }
▲ Show 20 Lines • Show All 2,962 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/AArch64/gather-root.ll

Show All 22 Lines
; ;
; GATHER-LABEL: @PR28330( ; GATHER-LABEL: @PR28330(
; GATHER-NEXT: entry: ; GATHER-NEXT: entry:
; GATHER-NEXT: [[TMP0:%.*]] = load <8 x i8>, <8 x i8>* bitcast (i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1) to <8 x i8>*), align 1 ; GATHER-NEXT: [[TMP0:%.*]] = load <8 x i8>, <8 x i8>* bitcast (i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1) to <8 x i8>*), align 1
; GATHER-NEXT: [[TMP1:%.*]] = icmp eq <8 x i8> [[TMP0]], zeroinitializer ; GATHER-NEXT: [[TMP1:%.*]] = icmp eq <8 x i8> [[TMP0]], zeroinitializer
; GATHER-NEXT: br label [[FOR_BODY:%.*]] ; GATHER-NEXT: br label [[FOR_BODY:%.*]]
; GATHER: for.body: ; GATHER: for.body:
; GATHER-NEXT: [[P17:%.*]] = phi i32 [ [[OP_EXTRA:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ] ; GATHER-NEXT: [[P17:%.*]] = phi i32 [ [[OP_EXTRA:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
; GATHER-NEXT: [[TMP2:%.*]] = extractelement <8 x i1> [[TMP1]], i32 7 ; GATHER-NEXT: [[TMP2:%.*]] = select <8 x i1> [[TMP1]], <8 x i32> <i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720>, <8 x i32> <i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80>
; GATHER-NEXT: [[TMP3:%.*]] = select <8 x i1> [[TMP1]], <8 x i32> <i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720>, <8 x i32> <i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80> ; GATHER-NEXT: [[TMP3:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP2]])
; GATHER-NEXT: [[TMP4:%.*]] = extractelement <8 x i1> [[TMP1]], i32 6 ; GATHER-NEXT: [[OP_EXTRA]] = add i32 [[TMP3]], [[P17]]
; GATHER-NEXT: [[TMP5:%.*]] = extractelement <8 x i1> [[TMP1]], i32 5
; GATHER-NEXT: [[TMP6:%.*]] = extractelement <8 x i1> [[TMP1]], i32 4
; GATHER-NEXT: [[TMP7:%.*]] = extractelement <8 x i1> [[TMP1]], i32 3
; GATHER-NEXT: [[TMP8:%.*]] = extractelement <8 x i1> [[TMP1]], i32 2
; GATHER-NEXT: [[TMP9:%.*]] = extractelement <8 x i1> [[TMP1]], i32 1
; GATHER-NEXT: [[TMP10:%.*]] = extractelement <8 x i1> [[TMP1]], i32 0
; GATHER-NEXT: [[TMP11:%.*]] = extractelement <8 x i32> [[TMP3]], i32 0
; GATHER-NEXT: [[TMP12:%.*]] = extractelement <8 x i32> [[TMP3]], i32 1
; GATHER-NEXT: [[TMP13:%.*]] = extractelement <8 x i32> [[TMP3]], i32 2
; GATHER-NEXT: [[TMP14:%.*]] = extractelement <8 x i32> [[TMP3]], i32 3
; GATHER-NEXT: [[TMP15:%.*]] = extractelement <8 x i32> [[TMP3]], i32 4
; GATHER-NEXT: [[TMP16:%.*]] = extractelement <8 x i32> [[TMP3]], i32 5
; GATHER-NEXT: [[TMP17:%.*]] = extractelement <8 x i32> [[TMP3]], i32 6
; GATHER-NEXT: [[TMP18:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP3]])
; GATHER-NEXT: [[OP_EXTRA]] = add i32 [[TMP18]], [[P17]]
; GATHER-NEXT: [[TMP19:%.*]] = extractelement <8 x i32> [[TMP3]], i32 7
; GATHER-NEXT: br label [[FOR_BODY]] ; GATHER-NEXT: br label [[FOR_BODY]]
; ;
; MAX-COST-LABEL: @PR28330( ; MAX-COST-LABEL: @PR28330(
; MAX-COST-NEXT: entry: ; MAX-COST-NEXT: entry:
; MAX-COST-NEXT: [[P0:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1), align 1 ; MAX-COST-NEXT: [[P0:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1), align 1
; MAX-COST-NEXT: [[P1:%.*]] = icmp eq i8 [[P0]], 0 ; MAX-COST-NEXT: [[P1:%.*]] = icmp eq i8 [[P0]], 0
; MAX-COST-NEXT: [[P2:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 2), align 2 ; MAX-COST-NEXT: [[P2:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 2), align 2
; MAX-COST-NEXT: [[P3:%.*]] = icmp eq i8 [[P2]], 0 ; MAX-COST-NEXT: [[P3:%.*]] = icmp eq i8 [[P2]], 0
▲ Show 20 Lines • Show All 85 Lines • ▼ Show 20 Lines
; ;
; GATHER-LABEL: @PR32038( ; GATHER-LABEL: @PR32038(
; GATHER-NEXT: entry: ; GATHER-NEXT: entry:
; GATHER-NEXT: [[TMP0:%.*]] = load <8 x i8>, <8 x i8>* bitcast (i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1) to <8 x i8>*), align 1 ; GATHER-NEXT: [[TMP0:%.*]] = load <8 x i8>, <8 x i8>* bitcast (i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1) to <8 x i8>*), align 1
; GATHER-NEXT: [[TMP1:%.*]] = icmp eq <8 x i8> [[TMP0]], zeroinitializer ; GATHER-NEXT: [[TMP1:%.*]] = icmp eq <8 x i8> [[TMP0]], zeroinitializer
; GATHER-NEXT: br label [[FOR_BODY:%.*]] ; GATHER-NEXT: br label [[FOR_BODY:%.*]]
; GATHER: for.body: ; GATHER: for.body:
; GATHER-NEXT: [[P17:%.*]] = phi i32 [ [[OP_EXTRA:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ] ; GATHER-NEXT: [[P17:%.*]] = phi i32 [ [[OP_EXTRA:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
; GATHER-NEXT: [[TMP2:%.*]] = extractelement <8 x i1> [[TMP1]], i32 7 ; GATHER-NEXT: [[TMP2:%.*]] = select <8 x i1> [[TMP1]], <8 x i32> <i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720>, <8 x i32> <i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80>
; GATHER-NEXT: [[TMP3:%.*]] = select <8 x i1> [[TMP1]], <8 x i32> <i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720, i32 -720>, <8 x i32> <i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80, i32 -80> ; GATHER-NEXT: [[TMP3:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP2]])
; GATHER-NEXT: [[TMP4:%.*]] = extractelement <8 x i1> [[TMP1]], i32 6 ; GATHER-NEXT: [[OP_EXTRA]] = add i32 [[TMP3]], -5
; GATHER-NEXT: [[TMP5:%.*]] = extractelement <8 x i1> [[TMP1]], i32 5
; GATHER-NEXT: [[TMP6:%.*]] = extractelement <8 x i1> [[TMP1]], i32 4
; GATHER-NEXT: [[TMP7:%.*]] = extractelement <8 x i1> [[TMP1]], i32 3
; GATHER-NEXT: [[TMP8:%.*]] = extractelement <8 x i1> [[TMP1]], i32 2
; GATHER-NEXT: [[TMP9:%.*]] = extractelement <8 x i1> [[TMP1]], i32 1
; GATHER-NEXT: [[TMP10:%.*]] = extractelement <8 x i1> [[TMP1]], i32 0
; GATHER-NEXT: [[TMP11:%.*]] = extractelement <8 x i32> [[TMP3]], i32 0
; GATHER-NEXT: [[TMP12:%.*]] = extractelement <8 x i32> [[TMP3]], i32 1
; GATHER-NEXT: [[TMP13:%.*]] = extractelement <8 x i32> [[TMP3]], i32 2
; GATHER-NEXT: [[TMP14:%.*]] = extractelement <8 x i32> [[TMP3]], i32 3
; GATHER-NEXT: [[TMP15:%.*]] = extractelement <8 x i32> [[TMP3]], i32 4
; GATHER-NEXT: [[TMP16:%.*]] = extractelement <8 x i32> [[TMP3]], i32 5
; GATHER-NEXT: [[TMP17:%.*]] = extractelement <8 x i32> [[TMP3]], i32 6
; GATHER-NEXT: [[TMP18:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP3]])
; GATHER-NEXT: [[OP_EXTRA]] = add i32 [[TMP18]], -5
; GATHER-NEXT: [[TMP19:%.*]] = extractelement <8 x i32> [[TMP3]], i32 7
; GATHER-NEXT: br label [[FOR_BODY]] ; GATHER-NEXT: br label [[FOR_BODY]]
; ;
; MAX-COST-LABEL: @PR32038( ; MAX-COST-LABEL: @PR32038(
; MAX-COST-NEXT: entry: ; MAX-COST-NEXT: entry:
; MAX-COST-NEXT: [[TMP0:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1) to <4 x i8>*), align 1 ; MAX-COST-NEXT: [[TMP0:%.*]] = load <4 x i8>, <4 x i8>* bitcast (i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1) to <4 x i8>*), align 1
; MAX-COST-NEXT: [[TMP1:%.*]] = icmp eq <4 x i8> [[TMP0]], zeroinitializer ; MAX-COST-NEXT: [[TMP1:%.*]] = icmp eq <4 x i8> [[TMP0]], zeroinitializer
; MAX-COST-NEXT: [[P8:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 5), align 1 ; MAX-COST-NEXT: [[P8:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 5), align 1
; MAX-COST-NEXT: [[P9:%.*]] = icmp eq i8 [[P8]], 0 ; MAX-COST-NEXT: [[P9:%.*]] = icmp eq i8 [[P8]], 0
; MAX-COST-NEXT: [[P10:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 6), align 2 ; MAX-COST-NEXT: [[P10:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 6), align 2
; MAX-COST-NEXT: [[P11:%.*]] = icmp eq i8 [[P10]], 0 ; MAX-COST-NEXT: [[P11:%.*]] = icmp eq i8 [[P10]], 0
; MAX-COST-NEXT: [[P12:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 7), align 1 ; MAX-COST-NEXT: [[P12:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 7), align 1
; MAX-COST-NEXT: [[P13:%.*]] = icmp eq i8 [[P12]], 0 ; MAX-COST-NEXT: [[P13:%.*]] = icmp eq i8 [[P12]], 0
; MAX-COST-NEXT: [[P14:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 8), align 8 ; MAX-COST-NEXT: [[P14:%.*]] = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 8), align 8
; MAX-COST-NEXT: [[P15:%.*]] = icmp eq i8 [[P14]], 0 ; MAX-COST-NEXT: [[P15:%.*]] = icmp eq i8 [[P14]], 0
; MAX-COST-NEXT: br label [[FOR_BODY:%.*]] ; MAX-COST-NEXT: br label [[FOR_BODY:%.*]]
; MAX-COST: for.body: ; MAX-COST: for.body:
; MAX-COST-NEXT: [[P17:%.*]] = phi i32 [ [[P34:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ] ; MAX-COST-NEXT: [[P17:%.*]] = phi i32 [ [[P34:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
; MAX-COST-NEXT: [[TMP2:%.*]] = extractelement <4 x i1> [[TMP1]], i32 3 ; MAX-COST-NEXT: [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x i32> <i32 -720, i32 -720, i32 -720, i32 -720>, <4 x i32> <i32 -80, i32 -80, i32 -80, i32 -80>
; MAX-COST-NEXT: [[TMP3:%.*]] = select <4 x i1> [[TMP1]], <4 x i32> <i32 -720, i32 -720, i32 -720, i32 -720>, <4 x i32> <i32 -80, i32 -80, i32 -80, i32 -80>
; MAX-COST-NEXT: [[TMP4:%.*]] = extractelement <4 x i1> [[TMP1]], i32 2
; MAX-COST-NEXT: [[TMP5:%.*]] = extractelement <4 x i1> [[TMP1]], i32 1
; MAX-COST-NEXT: [[TMP6:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; MAX-COST-NEXT: [[P27:%.*]] = select i1 [[P9]], i32 -720, i32 -80 ; MAX-COST-NEXT: [[P27:%.*]] = select i1 [[P9]], i32 -720, i32 -80
; MAX-COST-NEXT: [[P29:%.*]] = select i1 [[P11]], i32 -720, i32 -80 ; MAX-COST-NEXT: [[P29:%.*]] = select i1 [[P11]], i32 -720, i32 -80
; MAX-COST-NEXT: [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP3]]) ; MAX-COST-NEXT: [[TMP3:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP2]])
; MAX-COST-NEXT: [[TMP8:%.*]] = add i32 [[TMP7]], [[P27]] ; MAX-COST-NEXT: [[TMP4:%.*]] = add i32 [[TMP3]], [[P27]]
; MAX-COST-NEXT: [[TMP9:%.*]] = add i32 [[TMP8]], [[P29]] ; MAX-COST-NEXT: [[TMP5:%.*]] = add i32 [[TMP4]], [[P29]]
; MAX-COST-NEXT: [[OP_EXTRA:%.*]] = add i32 [[TMP9]], -5 ; MAX-COST-NEXT: [[OP_EXTRA:%.*]] = add i32 [[TMP5]], -5
; MAX-COST-NEXT: [[P31:%.*]] = select i1 [[P13]], i32 -720, i32 -80 ; MAX-COST-NEXT: [[P31:%.*]] = select i1 [[P13]], i32 -720, i32 -80
; MAX-COST-NEXT: [[P32:%.*]] = add i32 [[OP_EXTRA]], [[P31]] ; MAX-COST-NEXT: [[P32:%.*]] = add i32 [[OP_EXTRA]], [[P31]]
; MAX-COST-NEXT: [[P33:%.*]] = select i1 [[P15]], i32 -720, i32 -80 ; MAX-COST-NEXT: [[P33:%.*]] = select i1 [[P15]], i32 -720, i32 -80
; MAX-COST-NEXT: [[P34]] = add i32 [[P32]], [[P33]] ; MAX-COST-NEXT: [[P34]] = add i32 [[P32]], [[P33]]
; MAX-COST-NEXT: br label [[FOR_BODY]] ; MAX-COST-NEXT: br label [[FOR_BODY]]
; ;
entry: entry:
%p0 = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1), align 1 %p0 = load i8, i8* getelementptr inbounds ([80 x i8], [80 x i8]* @a, i64 0, i64 1), align 1
Show All 37 Lines

llvm/test/Transforms/SLPVectorizer/SystemZ/pr34619.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 -mtriple=systemz-unknown -mcpu=z13 -slp-vectorizer -S < %s | FileCheck %s ; RUN: opt -mtriple=systemz-unknown -mcpu=z13 -slp-vectorizer -S < %s | FileCheck %s
@bar = external global [4 x [4 x i32]], align 4 @bar = external global [4 x [4 x i32]], align 4
@dct_luma = external global [4 x [4 x i32]], align 4 @dct_luma = external global [4 x [4 x i32]], align 4
define void @foo() local_unnamed_addr { define void @foo() local_unnamed_addr {
; CHECK-LABEL: @foo( ; CHECK-LABEL: @foo(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[ADD277:%.*]] = add nsw i32 undef, undef ; CHECK-NEXT: [[ADD277:%.*]] = add nsw i32 undef, undef
; CHECK-NEXT: store i32 [[ADD277]], i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 1), align 4 ; CHECK-NEXT: store i32 [[ADD277]], i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 1), align 4
; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 0), align 4 ; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 0), align 4
; CHECK-NEXT: [[ARRAYIDX372:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 0 ; CHECK-NEXT: [[ARRAYIDX372:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 0
; CHECK-NEXT: [[ARRAYIDX372_1:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 1 ; CHECK-NEXT: [[ARRAYIDX372_1:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 1
; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 2), align 4
; CHECK-NEXT: [[ARRAYIDX372_2:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 2 ; CHECK-NEXT: [[ARRAYIDX372_2:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 2
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 3), align 4 ; CHECK-NEXT: [[TMP1:%.*]] = load <2 x i32>, <2 x i32>* bitcast (i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 2) to <2 x i32>*), align 4
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x i32> poison, i32 [[TMP0]], i32 0 ; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> poison, i32 [[TMP0]], i32 0
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x i32> [[TMP3]], i32 [[ADD277]], i32 1 ; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[ADD277]], i32 1
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <4 x i32> [[TMP4]], i32 [[TMP1]], i32 2 ; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <4 x i32> [[TMP5]], i32 [[TMP2]], i32 3 ; CHECK-NEXT: [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> [[TMP4]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; CHECK-NEXT: [[TMP7:%.*]] = add nsw <4 x i32> poison, [[TMP6]] ; CHECK-NEXT: [[TMP6:%.*]] = add nsw <4 x i32> poison, [[TMP5]]
; CHECK-NEXT: [[TMP8:%.*]] = ashr <4 x i32> [[TMP7]], <i32 6, i32 6, i32 6, i32 6> ; CHECK-NEXT: [[TMP7:%.*]] = ashr <4 x i32> [[TMP6]], <i32 6, i32 6, i32 6, i32 6>
; CHECK-NEXT: [[ARRAYIDX372_3:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 3 ; CHECK-NEXT: [[ARRAYIDX372_3:%.*]] = getelementptr inbounds [4 x [4 x i32]], [4 x [4 x i32]]* @dct_luma, i64 0, i64 3, i64 3
; CHECK-NEXT: [[TMP9:%.*]] = bitcast i32* [[ARRAYIDX372]] to <4 x i32>* ; CHECK-NEXT: [[TMP8:%.*]] = bitcast i32* [[ARRAYIDX372]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[TMP8]], <4 x i32>* [[TMP9]], align 4 ; CHECK-NEXT: store <4 x i32> [[TMP7]], <4 x i32>* [[TMP8]], align 4
; CHECK-NEXT: unreachable ; CHECK-NEXT: unreachable
; ;
entry: entry:
%add277 = add nsw i32 undef, undef %add277 = add nsw i32 undef, undef
store i32 %add277, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 1), align 4 store i32 %add277, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 1), align 4
%0 = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 0), align 4 %0 = load i32, i32* getelementptr inbounds ([4 x [4 x i32]], [4 x [4 x i32]]* @bar, i64 0, i64 3, i64 0), align 4
%sub355 = add nsw i32 undef, %0 %sub355 = add nsw i32 undef, %0
%shr.i = ashr i32 %sub355, 6 %shr.i = ashr i32 %sub355, 6
Show All 18 Lines

llvm/test/Transforms/SLPVectorizer/X86/PR39774.ll

Show All 39 Lines
; CHECK-NEXT: [[OP_EXTRA25:%.*]] = and i32 [[OP_EXTRA24]], [[TMP0]] ; CHECK-NEXT: [[OP_EXTRA25:%.*]] = and i32 [[OP_EXTRA24]], [[TMP0]]
; CHECK-NEXT: [[OP_EXTRA26:%.*]] = and i32 [[OP_EXTRA25]], [[TMP0]] ; CHECK-NEXT: [[OP_EXTRA26:%.*]] = and i32 [[OP_EXTRA25]], [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x i32> <i32 poison, i32 14910>, i32 [[OP_EXTRA26]], i32 0 ; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x i32> <i32 poison, i32 14910>, i32 [[OP_EXTRA26]], i32 0
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP2]], i32 0 ; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[TMP2]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> [[TMP6]], i32 [[TMP2]], i32 1 ; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> [[TMP6]], i32 [[TMP2]], i32 1
; CHECK-NEXT: [[TMP8:%.*]] = and <2 x i32> [[TMP5]], [[TMP7]] ; CHECK-NEXT: [[TMP8:%.*]] = and <2 x i32> [[TMP5]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = add <2 x i32> [[TMP5]], [[TMP7]] ; CHECK-NEXT: [[TMP9:%.*]] = add <2 x i32> [[TMP5]], [[TMP7]]
; CHECK-NEXT: [[TMP10]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> [[TMP9]], <2 x i32> <i32 0, i32 3> ; CHECK-NEXT: [[TMP10]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> [[TMP9]], <2 x i32> <i32 0, i32 3>
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <2 x i32> [[TMP10]], i32 0
; CHECK-NEXT: [[TMP12:%.*]] = extractelement <2 x i32> [[TMP10]], i32 1
; CHECK-NEXT: br label [[LOOP]] ; CHECK-NEXT: br label [[LOOP]]
; ;
; FORCE_REDUCTION-LABEL: @Test( ; FORCE_REDUCTION-LABEL: @Test(
; FORCE_REDUCTION-NEXT: entry: ; FORCE_REDUCTION-NEXT: entry:
; FORCE_REDUCTION-NEXT: br label [[LOOP:%.*]] ; FORCE_REDUCTION-NEXT: br label [[LOOP:%.*]]
; FORCE_REDUCTION: loop: ; FORCE_REDUCTION: loop:
; FORCE_REDUCTION-NEXT: [[TMP1:%.*]] = phi <2 x i32> [ [[TMP12:%.*]], [[LOOP]] ], [ zeroinitializer, [[ENTRY:%.*]] ] ; FORCE_REDUCTION-NEXT: [[TMP1:%.*]] = phi <2 x i32> [ [[TMP12:%.*]], [[LOOP]] ], [ zeroinitializer, [[ENTRY:%.*]] ]
; FORCE_REDUCTION-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 1, i32 1> ; FORCE_REDUCTION-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 1, i32 1>
▲ Show 20 Lines • Show All 98 Lines • Show Last 20 Lines

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

Show First 20 Lines • Show All 351 Lines • ▼ Show 20 Lines
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <4 x float> [[TMP9]], float [[TMP5]], i32 3 ; CHECK-NEXT: [[TMP10:%.*]] = insertelement <4 x float> [[TMP9]], float [[TMP5]], i32 3
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x float> poison, float [[TMP1]], i32 0 ; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x float> poison, float [[TMP1]], i32 0
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef> ; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <4 x float> [[TMP11]], <4 x float> [[TMP12]], <4 x i32> <i32 0, i32 4, i32 5, i32 3> ; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <4 x float> [[TMP11]], <4 x float> [[TMP12]], <4 x i32> <i32 0, i32 4, i32 5, i32 3>
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <4 x float> [[TMP13]], float [[TMP6]], i32 3 ; CHECK-NEXT: [[TMP14:%.*]] = insertelement <4 x float> [[TMP13]], float [[TMP6]], i32 3
; CHECK-NEXT: [[TMP15:%.*]] = fadd <4 x float> [[TMP10]], [[TMP14]] ; CHECK-NEXT: [[TMP15:%.*]] = fadd <4 x float> [[TMP10]], [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = fsub <4 x float> [[TMP10]], [[TMP14]] ; CHECK-NEXT: [[TMP16:%.*]] = fsub <4 x float> [[TMP10]], [[TMP14]]
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <4 x float> [[TMP15]], <4 x float> [[TMP16]], <4 x i32> <i32 0, i32 5, i32 2, i32 7> ; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <4 x float> [[TMP15]], <4 x float> [[TMP16]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
; CHECK-NEXT: [[TMP18:%.*]] = extractelement <2 x float> [[TMP4]], i32 1
; CHECK-NEXT: [[TMP19:%.*]] = extractelement <2 x float> [[TMP3]], i32 1
; CHECK-NEXT: [[TMP20:%.*]] = extractelement <2 x float> [[TMP4]], i32 0
; CHECK-NEXT: [[TMP21:%.*]] = extractelement <2 x float> [[TMP3]], i32 0
; CHECK-NEXT: store <4 x float> [[TMP17]], <4 x float>* bitcast ([4 x float]* @fc to <4 x float>*), align 4 ; CHECK-NEXT: store <4 x float> [[TMP17]], <4 x float>* bitcast ([4 x float]* @fc to <4 x float>*), align 4
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
%1 = load float, float* getelementptr inbounds ([4 x float], [4 x float]* @fb, i32 0, i64 0), align 4 %1 = load float, float* getelementptr inbounds ([4 x float], [4 x float]* @fb, i32 0, i64 0), align 4
%2 = load float, float* getelementptr inbounds ([4 x float], [4 x float]* @fa, i32 0, i64 0), align 4 %2 = load float, float* getelementptr inbounds ([4 x float], [4 x float]* @fa, i32 0, i64 0), align 4
%3 = fadd float %1, %2 %3 = fadd float %1, %2
store float %3, float* getelementptr inbounds ([4 x float], [4 x float]* @fc, i32 0, i64 0), align 4 store float %3, float* getelementptr inbounds ([4 x float], [4 x float]* @fc, i32 0, i64 0), align 4
%4 = load float, float* getelementptr inbounds ([4 x float], [4 x float]* @fa, i32 0, i64 1), align 4 %4 = load float, float* getelementptr inbounds ([4 x float], [4 x float]* @fa, i32 0, i64 1), align 4
Show All 17 Lines

llvm/test/Transforms/SLPVectorizer/X86/horizontal-minmax.ll

Show First 20 Lines • Show All 839 Lines • ▼ Show 20 Lines
; THRESH-NEXT: [[TMP9:%.*]] = icmp sgt i32 [[TMP8]], [[TMP6]] ; THRESH-NEXT: [[TMP9:%.*]] = icmp sgt i32 [[TMP8]], [[TMP6]]
; THRESH-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], i32 [[TMP8]], i32 [[TMP6]] ; THRESH-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], i32 [[TMP8]], i32 [[TMP6]]
; THRESH-NEXT: [[TMP11:%.*]] = insertelement <2 x i32> poison, i32 [[TMP10]], i32 0 ; THRESH-NEXT: [[TMP11:%.*]] = insertelement <2 x i32> poison, i32 [[TMP10]], i32 0
; THRESH-NEXT: [[TMP12:%.*]] = insertelement <2 x i32> [[TMP11]], i32 [[TMP3]], i32 1 ; THRESH-NEXT: [[TMP12:%.*]] = insertelement <2 x i32> [[TMP11]], i32 [[TMP3]], i32 1
; THRESH-NEXT: [[TMP13:%.*]] = insertelement <2 x i32> poison, i32 [[TMP7]], i32 0 ; THRESH-NEXT: [[TMP13:%.*]] = insertelement <2 x i32> poison, i32 [[TMP7]], i32 0
; THRESH-NEXT: [[TMP14:%.*]] = insertelement <2 x i32> [[TMP13]], i32 [[TMP4]], i32 1 ; THRESH-NEXT: [[TMP14:%.*]] = insertelement <2 x i32> [[TMP13]], i32 [[TMP4]], i32 1
; THRESH-NEXT: [[TMP15:%.*]] = icmp sgt <2 x i32> [[TMP12]], [[TMP14]] ; THRESH-NEXT: [[TMP15:%.*]] = icmp sgt <2 x i32> [[TMP12]], [[TMP14]]
; THRESH-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP15]], <2 x i32> [[TMP12]], <2 x i32> [[TMP14]] ; THRESH-NEXT: [[TMP16:%.*]] = select <2 x i1> [[TMP15]], <2 x i32> [[TMP12]], <2 x i32> [[TMP14]]
; THRESH-NEXT: [[TMP17:%.*]] = extractelement <2 x i32> [[TMP16]], i32 1 ; THRESH-NEXT: [[TMP17:%.*]] = extractelement <2 x i32> [[TMP16]], i32 0
; THRESH-NEXT: [[TMP18:%.*]] = extractelement <2 x i32> [[TMP16]], i32 0 ; THRESH-NEXT: [[TMP18:%.*]] = extractelement <2 x i32> [[TMP16]], i32 1
; THRESH-NEXT: [[OP_EXTRA:%.*]] = icmp sgt i32 [[TMP18]], [[TMP17]] ; THRESH-NEXT: [[OP_EXTRA:%.*]] = icmp sgt i32 [[TMP17]], [[TMP18]]
; THRESH-NEXT: [[OP_EXTRA1:%.*]] = select i1 [[OP_EXTRA]], i32 [[TMP18]], i32 [[TMP17]] ; THRESH-NEXT: [[OP_EXTRA1:%.*]] = select i1 [[OP_EXTRA]], i32 [[TMP17]], i32 [[TMP18]]
; THRESH-NEXT: [[TMP19:%.*]] = extractelement <2 x i1> [[TMP15]], i32 1 ; THRESH-NEXT: [[TMP19:%.*]] = extractelement <2 x i1> [[TMP15]], i32 1
; THRESH-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 3, i32 4 ; THRESH-NEXT: [[TMP20:%.*]] = select i1 [[TMP19]], i32 3, i32 4
; THRESH-NEXT: store i32 [[TMP20]], i32* @var, align 8 ; THRESH-NEXT: store i32 [[TMP20]], i32* @var, align 8
; THRESH-NEXT: ret i32 [[OP_EXTRA1]] ; THRESH-NEXT: ret i32 [[OP_EXTRA1]]
; ;
%2 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16 %2 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
%3 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4 %3 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
%4 = icmp sgt i32 %2, %3 %4 = icmp sgt i32 %2, %3
▲ Show 20 Lines • Show All 168 Lines • ▼ Show 20 Lines
; THRESH-NEXT: [[TMP12:%.*]] = icmp sgt i32 [[TMP11]], [[TMP8]] ; THRESH-NEXT: [[TMP12:%.*]] = icmp sgt i32 [[TMP11]], [[TMP8]]
; THRESH-NEXT: [[TMP13:%.*]] = insertelement <2 x i1> poison, i1 [[TMP12]], i32 0 ; THRESH-NEXT: [[TMP13:%.*]] = insertelement <2 x i1> poison, i1 [[TMP12]], i32 0
; THRESH-NEXT: [[TMP14:%.*]] = insertelement <2 x i1> [[TMP13]], i1 [[TMP5]], i32 1 ; THRESH-NEXT: [[TMP14:%.*]] = insertelement <2 x i1> [[TMP13]], i1 [[TMP5]], i32 1
; THRESH-NEXT: [[TMP15:%.*]] = insertelement <2 x i32> poison, i32 [[TMP11]], i32 0 ; THRESH-NEXT: [[TMP15:%.*]] = insertelement <2 x i32> poison, i32 [[TMP11]], i32 0
; THRESH-NEXT: [[TMP16:%.*]] = insertelement <2 x i32> [[TMP15]], i32 [[TMP3]], i32 1 ; THRESH-NEXT: [[TMP16:%.*]] = insertelement <2 x i32> [[TMP15]], i32 [[TMP3]], i32 1
; THRESH-NEXT: [[TMP17:%.*]] = insertelement <2 x i32> poison, i32 [[TMP8]], i32 0 ; THRESH-NEXT: [[TMP17:%.*]] = insertelement <2 x i32> poison, i32 [[TMP8]], i32 0
; THRESH-NEXT: [[TMP18:%.*]] = insertelement <2 x i32> [[TMP17]], i32 [[TMP4]], i32 1 ; THRESH-NEXT: [[TMP18:%.*]] = insertelement <2 x i32> [[TMP17]], i32 [[TMP4]], i32 1
; THRESH-NEXT: [[TMP19:%.*]] = select <2 x i1> [[TMP14]], <2 x i32> [[TMP16]], <2 x i32> [[TMP18]] ; THRESH-NEXT: [[TMP19:%.*]] = select <2 x i1> [[TMP14]], <2 x i32> [[TMP16]], <2 x i32> [[TMP18]]
; THRESH-NEXT: [[TMP20:%.*]] = extractelement <2 x i32> [[TMP19]], i32 1 ; THRESH-NEXT: [[TMP20:%.*]] = extractelement <2 x i32> [[TMP19]], i32 0
; THRESH-NEXT: [[TMP21:%.*]] = extractelement <2 x i32> [[TMP19]], i32 0 ; THRESH-NEXT: [[TMP21:%.*]] = extractelement <2 x i32> [[TMP19]], i32 1
; THRESH-NEXT: [[OP_EXTRA:%.*]] = icmp sgt i32 [[TMP21]], [[TMP20]] ; THRESH-NEXT: [[OP_EXTRA:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
; THRESH-NEXT: [[OP_EXTRA1:%.*]] = select i1 [[OP_EXTRA]], i32 [[TMP21]], i32 [[TMP20]] ; THRESH-NEXT: [[OP_EXTRA1:%.*]] = select i1 [[OP_EXTRA]], i32 [[TMP20]], i32 [[TMP21]]
; THRESH-NEXT: ret i32 [[OP_EXTRA1]] ; THRESH-NEXT: ret i32 [[OP_EXTRA1]]
; ;
%2 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16 %2 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 0), align 16
%3 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4 %3 = load i32, i32* getelementptr inbounds ([32 x i32], [32 x i32]* @arr, i64 0, i64 1), align 4
%4 = icmp sgt i32 %2, %3 %4 = icmp sgt i32 %2, %3
br label %pp br label %pp
pp: pp:
▲ Show 20 Lines • Show All 315 Lines • Show Last 20 Lines

llvm/test/Transforms/SLPVectorizer/X86/ordering-bug.ll

Show All 22 Lines
; CHECK: while.end: ; CHECK: while.end:
; CHECK-NEXT: [[TMP6:%.*]] = phi <2 x i64> [ [[TMP0]], [[ENTRY:%.*]] ], [ [[TMP5]], [[WHILE_BODY_LR_PH]] ] ; CHECK-NEXT: [[TMP6:%.*]] = phi <2 x i64> [ [[TMP0]], [[ENTRY:%.*]] ], [ [[TMP5]], [[WHILE_BODY_LR_PH]] ]
; CHECK-NEXT: [[TMP7:%.*]] = load <2 x i64>, <2 x i64>* bitcast (%struct.a* @c to <2 x i64>*), align 8 ; CHECK-NEXT: [[TMP7:%.*]] = load <2 x i64>, <2 x i64>* bitcast (%struct.a* @c to <2 x i64>*), align 8
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x i64> [[TMP6]], i32 0 ; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x i64> [[TMP6]], i32 0
; CHECK-NEXT: [[ICMP_D0:%.*]] = icmp eq i64 [[TMP8]], 0 ; CHECK-NEXT: [[ICMP_D0:%.*]] = icmp eq i64 [[TMP8]], 0
; CHECK-NEXT: br i1 [[ICMP_D0]], label [[IF_END:%.*]], label [[IF_THEN:%.*]] ; CHECK-NEXT: br i1 [[ICMP_D0]], label [[IF_END:%.*]], label [[IF_THEN:%.*]]
; CHECK: if.then: ; CHECK: if.then:
; CHECK-NEXT: [[AND0_TMP:%.*]] = and i64 [[TMP8]], 8 ; CHECK-NEXT: [[AND0_TMP:%.*]] = and i64 [[TMP8]], 8
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <2 x i64> [[TMP6]], i32 1 ; CHECK-NEXT: [[TMP9:%.*]] = insertelement <2 x i64> poison, i64 [[AND0_TMP]], i32 0
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x i64> poison, i64 [[AND0_TMP]], i32 0 ; CHECK-NEXT: [[TMP10:%.*]] = extractelement <2 x i64> [[TMP6]], i32 1
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <2 x i64> [[TMP10]], i64 [[TMP9]], i32 1 ; CHECK-NEXT: [[TMP11:%.*]] = insertelement <2 x i64> [[TMP9]], i64 [[TMP10]], i32 1
; CHECK-NEXT: [[TMP12:%.*]] = and <2 x i64> [[TMP11]], [[TMP7]] ; CHECK-NEXT: [[TMP12:%.*]] = and <2 x i64> [[TMP11]], [[TMP7]]
; CHECK-NEXT: store <2 x i64> [[TMP12]], <2 x i64>* bitcast (%struct.a* @a to <2 x i64>*), align 8 ; CHECK-NEXT: store <2 x i64> [[TMP12]], <2 x i64>* bitcast (%struct.a* @a to <2 x i64>*), align 8
; CHECK-NEXT: br label [[IF_END]] ; CHECK-NEXT: br label [[IF_END]]
; CHECK: if.end: ; CHECK: if.end:
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
%a0 = load i64, i64* getelementptr inbounds (%struct.a, %struct.a* @a, i32 0, i32 0, i32 0), align 8 %a0 = load i64, i64* getelementptr inbounds (%struct.a, %struct.a* @a, i32 0, i32 0, i32 0), align 8
Show All 32 Lines

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

Show All 9 Lines
; CHECK-NEXT: br i1 undef, label [[IF_END50_I:%.*]], label [[IF_THEN22_I:%.*]] ; CHECK-NEXT: br i1 undef, label [[IF_END50_I:%.*]], label [[IF_THEN22_I:%.*]]
; CHECK: if.then22.i: ; CHECK: if.then22.i:
; CHECK-NEXT: [[SUB_I:%.*]] = add nsw i32 undef, -1 ; CHECK-NEXT: [[SUB_I:%.*]] = add nsw i32 undef, -1
; CHECK-NEXT: [[CONV31_I:%.*]] = and i32 undef, [[SUB_I]] ; CHECK-NEXT: [[CONV31_I:%.*]] = and i32 undef, [[SUB_I]]
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 0 ; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 0
; CHECK-NEXT: [[ARRAYIDX_I_I7_1_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 1 ; CHECK-NEXT: [[ARRAYIDX_I_I7_1_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 1
; CHECK-NEXT: [[ARRAYIDX_I_I7_2_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 2 ; CHECK-NEXT: [[ARRAYIDX_I_I7_2_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 2
; CHECK-NEXT: [[ARRAYIDX_I_I7_3_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 3 ; CHECK-NEXT: [[ARRAYIDX_I_I7_3_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 3
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> poison, i32 [[CONV31_I]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[CONV31_I]], i32 1
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[CONV31_I]], i32 2
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <4 x i32> [[TMP3]], i32 [[CONV31_I]], i32 3
; CHECK-NEXT: [[TMP5:%.*]] = lshr <4 x i32> [[TMP4]], <i32 1, i32 2, i32 3, i32 4>
; CHECK-NEXT: [[ARRAYIDX_I_I7_4_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 4 ; CHECK-NEXT: [[ARRAYIDX_I_I7_4_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 4
; CHECK-NEXT: [[SHR_4_I_I:%.*]] = lshr i32 [[CONV31_I]], 5
; CHECK-NEXT: [[ARRAYIDX_I_I7_5_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 5 ; CHECK-NEXT: [[ARRAYIDX_I_I7_5_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 5
; CHECK-NEXT: [[ARRAYIDX_I_I7_6_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 6 ; CHECK-NEXT: [[ARRAYIDX_I_I7_6_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 6
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x i32> poison, i32 [[CONV31_I]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> [[TMP6]], i32 [[CONV31_I]], i32 1
; CHECK-NEXT: [[TMP8:%.*]] = lshr <2 x i32> [[TMP7]], <i32 6, i32 7>
; CHECK-NEXT: [[ARRAYIDX_I_I7_7_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 7 ; CHECK-NEXT: [[ARRAYIDX_I_I7_7_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 7
; CHECK-NEXT: [[TMP1:%.*]] = insertelement <8 x i32> poison, i32 [[CONV31_I]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <8 x i32> [[TMP1]], i32 [[CONV31_I]], i32 1
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <8 x i32> [[TMP2]], i32 [[CONV31_I]], i32 2
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <8 x i32> [[TMP3]], i32 [[CONV31_I]], i32 3
; CHECK-NEXT: [[TMP5:%.*]] = insertelement <8 x i32> [[TMP4]], i32 [[CONV31_I]], i32 4
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <8 x i32> [[TMP5]], i32 [[CONV31_I]], i32 5
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <8 x i32> [[TMP6]], i32 [[CONV31_I]], i32 6
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <8 x i32> [[TMP7]], i32 [[CONV31_I]], i32 7
; CHECK-NEXT: [[TMP9:%.*]] = lshr <8 x i32> [[TMP8]], <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
; CHECK-NEXT: [[ARRAYIDX_I_I7_8_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 8 ; CHECK-NEXT: [[ARRAYIDX_I_I7_8_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 8
; CHECK-NEXT: [[ARRAYIDX_I_I7_9_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 9 ; CHECK-NEXT: [[ARRAYIDX_I_I7_9_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 9
; CHECK-NEXT: [[ARRAYIDX_I_I7_10_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 10 ; CHECK-NEXT: [[ARRAYIDX_I_I7_10_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 10
; CHECK-NEXT: [[TMP9:%.*]] = lshr <4 x i32> [[TMP4]], <i32 8, i32 9, i32 10, i32 11>
; CHECK-NEXT: [[ARRAYIDX_I_I7_11_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 11 ; CHECK-NEXT: [[ARRAYIDX_I_I7_11_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 11
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <4 x i32> poison, i32 [[CONV31_I]], i32 0
; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> [[TMP10]], i32 [[CONV31_I]], i32 1
; CHECK-NEXT: [[TMP12:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[CONV31_I]], i32 2
; CHECK-NEXT: [[TMP13:%.*]] = insertelement <4 x i32> [[TMP12]], i32 [[CONV31_I]], i32 3
; CHECK-NEXT: [[TMP14:%.*]] = lshr <4 x i32> [[TMP13]], <i32 9, i32 10, i32 11, i32 12>
; CHECK-NEXT: [[ARRAYIDX_I_I7_12_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 12 ; CHECK-NEXT: [[ARRAYIDX_I_I7_12_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 12
; CHECK-NEXT: [[SHR_12_I_I:%.*]] = lshr i32 [[CONV31_I]], 13
; CHECK-NEXT: [[ARRAYIDX_I_I7_13_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 13 ; CHECK-NEXT: [[ARRAYIDX_I_I7_13_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 13
; CHECK-NEXT: [[ARRAYIDX_I_I7_14_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 14 ; CHECK-NEXT: [[ARRAYIDX_I_I7_14_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 14
; CHECK-NEXT: [[TMP10:%.*]] = lshr <4 x i32> [[TMP4]], <i32 12, i32 13, i32 14, i32 15> ; CHECK-NEXT: [[TMP15:%.*]] = insertelement <2 x i32> poison, i32 [[CONV31_I]], i32 0
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x i32> [[TMP10]], i32 3 ; CHECK-NEXT: [[TMP16:%.*]] = insertelement <2 x i32> [[TMP15]], i32 [[CONV31_I]], i32 1
; CHECK-NEXT: [[TMP12:%.*]] = insertelement <16 x i32> poison, i32 [[SUB_I]], i32 0 ; CHECK-NEXT: [[TMP17:%.*]] = lshr <2 x i32> [[TMP16]], <i32 14, i32 15>
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> ; CHECK-NEXT: [[TMP18:%.*]] = insertelement <16 x i32> poison, i32 [[SUB_I]], i32 0
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <16 x i32> [[TMP12]], <16 x i32> [[TMP13]], <16 x i32> <i32 0, i32 16, i32 17, i32 18, i32 19, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> ; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <8 x i32> [[TMP9]], <8 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP15:%.*]] = insertelement <16 x i32> [[TMP14]], i32 [[SHR_4_I_I]], i32 5 ; CHECK-NEXT: [[TMP20:%.*]] = shufflevector <16 x i32> [[TMP18]], <16 x i32> [[TMP19]], <16 x i32> <i32 0, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <2 x i32> [[TMP8]], <2 x i32> poison, <16 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> ; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <4 x i32> [[TMP14]], <4 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <16 x i32> [[TMP15]], <16 x i32> [[TMP16]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 16, i32 17, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> ; CHECK-NEXT: [[TMP22:%.*]] = shufflevector <16 x i32> [[TMP20]], <16 x i32> [[TMP21]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 16, i32 17, i32 18, i32 19, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <4 x i32> [[TMP9]], <4 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> ; CHECK-NEXT: [[TMP23:%.*]] = insertelement <16 x i32> [[TMP22]], i32 [[SHR_12_I_I]], i32 13
; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <16 x i32> [[TMP17]], <16 x i32> [[TMP18]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15> ; CHECK-NEXT: [[TMP24:%.*]] = shufflevector <2 x i32> [[TMP17]], <2 x i32> poison, <16 x i32> <i32 0, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[TMP20:%.*]] = shufflevector <4 x i32> [[TMP10]], <4 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> ; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <16 x i32> [[TMP23]], <16 x i32> [[TMP24]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 16, i32 17>
; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <16 x i32> [[TMP19]], <16 x i32> [[TMP20]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19> ; CHECK-NEXT: [[TMP26:%.*]] = trunc <16 x i32> [[TMP25]] to <16 x i8>
; CHECK-NEXT: [[TMP22:%.*]] = trunc <16 x i32> [[TMP21]] to <16 x i8> ; CHECK-NEXT: [[TMP27:%.*]] = and <16 x i8> [[TMP26]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
; CHECK-NEXT: [[TMP23:%.*]] = extractelement <4 x i32> [[TMP10]], i32 2
; CHECK-NEXT: [[TMP24:%.*]] = extractelement <4 x i32> [[TMP10]], i32 1
; CHECK-NEXT: [[TMP25:%.*]] = extractelement <4 x i32> [[TMP10]], i32 0
; CHECK-NEXT: [[TMP26:%.*]] = extractelement <4 x i32> [[TMP9]], i32 3
; CHECK-NEXT: [[TMP27:%.*]] = extractelement <4 x i32> [[TMP9]], i32 2
; CHECK-NEXT: [[TMP28:%.*]] = extractelement <4 x i32> [[TMP9]], i32 1
; CHECK-NEXT: [[TMP29:%.*]] = extractelement <4 x i32> [[TMP9]], i32 0
; CHECK-NEXT: [[TMP30:%.*]] = extractelement <2 x i32> [[TMP8]], i32 1
; CHECK-NEXT: [[TMP31:%.*]] = extractelement <2 x i32> [[TMP8]], i32 0
; CHECK-NEXT: [[TMP32:%.*]] = extractelement <4 x i32> [[TMP5]], i32 3
; CHECK-NEXT: [[TMP33:%.*]] = extractelement <4 x i32> [[TMP5]], i32 2
; CHECK-NEXT: [[TMP34:%.*]] = extractelement <4 x i32> [[TMP5]], i32 1
; CHECK-NEXT: [[TMP35:%.*]] = extractelement <4 x i32> [[TMP5]], i32 0
; CHECK-NEXT: [[TMP36:%.*]] = and <16 x i8> [[TMP22]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
; CHECK-NEXT: [[ARRAYIDX_I_I7_15_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 15 ; CHECK-NEXT: [[ARRAYIDX_I_I7_15_I_I:%.*]] = getelementptr inbounds %"struct.std::array", %"struct.std::array"* undef, i64 0, i32 0, i64 15
; CHECK-NEXT: [[TMP37:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>* ; CHECK-NEXT: [[TMP28:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
; CHECK-NEXT: store <16 x i8> [[TMP36]], <16 x i8>* [[TMP37]], align 1 ; CHECK-NEXT: store <16 x i8> [[TMP27]], <16 x i8>* [[TMP28]], align 1
; CHECK-NEXT: unreachable ; CHECK-NEXT: unreachable
; CHECK: if.end50.i: ; CHECK: if.end50.i:
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
br i1 undef, label %if.end50.i, label %if.then22.i br i1 undef, label %if.end50.i, label %if.then22.i
if.then22.i: ; preds = %entry if.then22.i: ; preds = %entry
▲ Show 20 Lines • Show All 86 Lines • Show Last 20 Lines