This is an archive of the discontinued LLVM Phabricator instance.

Differential D107623

[AArch64] Correct sinking of shuffles to adds/subs
ClosedPublic

Authored by dmgreen on Aug 6 2021, 12:51 AM.

Details

Reviewers
TiehuZhang
fhahn
NickGuy
SjoerdMeijer
Commits
rG013030a0b213: [AArch64] Correct sinking of shuffles to adds/subs
Summary

This was checking extends as shuffles, where as we should be checking the operands. This helps sink the shuffles, creating more addl/subl instructions.

Diff Detail

Event Timeline

dmgreen created this revision.Aug 6 2021, 12:51 AM
Herald added subscribers: danielkiss, hiraditya, kristof.beyls. · View Herald TranscriptAug 6 2021, 12:51 AM
dmgreen requested review of this revision.Aug 6 2021, 12:51 AM
Herald added a project: Restricted Project. · View Herald TranscriptAug 6 2021, 12:51 AM
Harbormaster completed remote builds in B118327: Diff 364713.Aug 6 2021, 12:52 AM
dmgreen mentioned this in D107262: [CodeGenPrepare] The instruction to be sunk should be inserted before its user in a block.Aug 6 2021, 12:56 AM
dmgreen updated this revision to Diff 365141.Aug 9 2021, 3:39 AM

Update sink-free-instructions-inseltpoison.ll too.

Harbormaster completed remote builds in B118641: Diff 365141.Aug 9 2021, 3:40 AM
NickGuy accepted this revision.Aug 10 2021, 3:31 AM

LGTM

This revision is now accepted and ready to land.Aug 10 2021, 3:31 AM
This revision was landed with ongoing or failed builds.Aug 10 2021, 5:25 AM
Closed by commit rG013030a0b213: [AArch64] Correct sinking of shuffles to adds/subs (authored by dmgreen). · Explain Why
This revision was automatically updated to reflect the committed changes.
dmgreen added a commit: rG013030a0b213: [AArch64] Correct sinking of shuffles to adds/subs.

Revision Contents

PathSize
llvm/
lib/
Target/
AArch64/
2 lines
test/
Transforms/
CodeGenPrepare/
AArch64/
25 lines
25 lines

Diff 365446

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

  • This file is larger than 256 KB, so syntax highlighting is disabled by default.
Show First 20 Lines • Show All 11,640 Lines • ▼ Show 20 Linesbool AArch64TargetLowering::shouldSinkOperands(
case Instruction::Add: { case Instruction::Add: {
if (!areExtractExts(I->getOperand(0), I->getOperand(1))) if (!areExtractExts(I->getOperand(0), I->getOperand(1)))
return false; return false;
// If the exts' operands extract either the lower or upper elements, we // If the exts' operands extract either the lower or upper elements, we
// can sink them too. // can sink them too.
auto Ext1 = cast<Instruction>(I->getOperand(0)); auto Ext1 = cast<Instruction>(I->getOperand(0));
auto Ext2 = cast<Instruction>(I->getOperand(1)); auto Ext2 = cast<Instruction>(I->getOperand(1));
if (areExtractShuffleVectors(Ext1, Ext2)) { if (areExtractShuffleVectors(Ext1->getOperand(0), Ext2->getOperand(0))) {
Ops.push_back(&Ext1->getOperandUse(0)); Ops.push_back(&Ext1->getOperandUse(0));
Ops.push_back(&Ext2->getOperandUse(0)); Ops.push_back(&Ext2->getOperandUse(0));
} }
Ops.push_back(&I->getOperandUse(0)); Ops.push_back(&I->getOperandUse(0));
Ops.push_back(&I->getOperandUse(1)); Ops.push_back(&I->getOperandUse(1));
return true; return true;
▲ Show 20 Lines • Show All 7,215 Lines • Show Last 20 Lines

llvm/test/Transforms/CodeGenPrepare/AArch64/sink-free-instructions-inseltpoison.ll

Show First 20 Lines • Show All 148 Lines • ▼ Show 20 Linesif.else:
%vmull1 = tail call <8 x i16> @llvm.aarch64.neon.umull.v8i16(<8 x i8> %s3, <8 x i8> %s4) #3 %vmull1 = tail call <8 x i16> @llvm.aarch64.neon.umull.v8i16(<8 x i8> %s3, <8 x i8> %s4) #3
ret <8 x i16> %vmull1 ret <8 x i16> %vmull1
} }
; Both exts and their shufflevector operands can be sunk. ; Both exts and their shufflevector operands can be sunk.
define <8 x i16> @sink_shufflevector_ext_subadd(<16 x i8> %a, <16 x i8> %b) { define <8 x i16> @sink_shufflevector_ext_subadd(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: @sink_shufflevector_ext_subadd( ; CHECK-LABEL: @sink_shufflevector_ext_subadd(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[S1:%.*]] = shufflevector <16 x i8> [[A:%.*]], <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[S3:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: br i1 undef, label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]] ; CHECK-NEXT: br i1 undef, label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
; CHECK: if.then: ; CHECK: if.then:
; CHECK-NEXT: [[S2:%.*]] = shufflevector <16 x i8> [[B:%.*]], <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> ; CHECK-NEXT: [[S2:%.*]] = shufflevector <16 x i8> [[B:%.*]], <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[Z2:%.*]] = zext <8 x i8> [[S2]] to <8 x i16> ; CHECK-NEXT: [[Z2:%.*]] = zext <8 x i8> [[S2]] to <8 x i16>
; CHECK-NEXT: [[TMP0:%.*]] = zext <8 x i8> [[S1]] to <8 x i16> ; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <16 x i8> [[A:%.*]], <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[RES1:%.*]] = add <8 x i16> [[TMP0]], [[Z2]] ; CHECK-NEXT: [[TMP1:%.*]] = zext <8 x i8> [[TMP0]] to <8 x i16>
; CHECK-NEXT: [[RES1:%.*]] = add <8 x i16> [[TMP1]], [[Z2]]
; CHECK-NEXT: ret <8 x i16> [[RES1]] ; CHECK-NEXT: ret <8 x i16> [[RES1]]
; CHECK: if.else: ; CHECK: if.else:
; CHECK-NEXT: [[S4:%.*]] = shufflevector <16 x i8> [[B]], <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> ; CHECK-NEXT: [[S4:%.*]] = shufflevector <16 x i8> [[B]], <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[Z4:%.*]] = sext <8 x i8> [[S4]] to <8 x i16> ; CHECK-NEXT: [[Z4:%.*]] = sext <8 x i8> [[S4]] to <8 x i16>
; CHECK-NEXT: [[TMP1:%.*]] = sext <8 x i8> [[S3]] to <8 x i16> ; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[RES2:%.*]] = sub <8 x i16> [[TMP1]], [[Z4]] ; CHECK-NEXT: [[TMP3:%.*]] = sext <8 x i8> [[TMP2]] to <8 x i16>
; CHECK-NEXT: [[RES2:%.*]] = sub <8 x i16> [[TMP3]], [[Z4]]
; CHECK-NEXT: ret <8 x i16> [[RES2]] ; CHECK-NEXT: ret <8 x i16> [[RES2]]
; ;
entry: entry:
%s1 = shufflevector <16 x i8> %a, <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> %s1 = shufflevector <16 x i8> %a, <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%z1 = zext <8 x i8> %s1 to <8 x i16> %z1 = zext <8 x i8> %s1 to <8 x i16>
%s3 = shufflevector <16 x i8> %a, <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> %s3 = shufflevector <16 x i8> %a, <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%z3 = sext <8 x i8> %s3 to <8 x i16> %z3 = sext <8 x i8> %s3 to <8 x i16>
br i1 undef, label %if.then, label %if.else br i1 undef, label %if.then, label %if.else
Show All 13 Lines
declare void @user1(<8 x i16>) declare void @user1(<8 x i16>)
; Both exts and their shufflevector operands can be sunk. ; Both exts and their shufflevector operands can be sunk.
define <8 x i16> @sink_shufflevector_ext_subadd_multiuse(<16 x i8> %a, <16 x i8> %b) { define <8 x i16> @sink_shufflevector_ext_subadd_multiuse(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: @sink_shufflevector_ext_subadd_multiuse( ; CHECK-LABEL: @sink_shufflevector_ext_subadd_multiuse(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[S1:%.*]] = shufflevector <16 x i8> [[A:%.*]], <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> ; CHECK-NEXT: [[S3:%.*]] = shufflevector <16 x i8> [[A:%.*]], <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[S3:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[Z3:%.*]] = sext <8 x i8> [[S3]] to <8 x i16> ; CHECK-NEXT: [[Z3:%.*]] = sext <8 x i8> [[S3]] to <8 x i16>
; CHECK-NEXT: call void @user1(<8 x i16> [[Z3]]) ; CHECK-NEXT: call void @user1(<8 x i16> [[Z3]])
; CHECK-NEXT: br i1 undef, label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]] ; CHECK-NEXT: br i1 undef, label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
; CHECK: if.then: ; CHECK: if.then:
; CHECK-NEXT: [[S2:%.*]] = shufflevector <16 x i8> [[B:%.*]], <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> ; CHECK-NEXT: [[S2:%.*]] = shufflevector <16 x i8> [[B:%.*]], <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[Z2:%.*]] = zext <8 x i8> [[S2]] to <8 x i16> ; CHECK-NEXT: [[Z2:%.*]] = zext <8 x i8> [[S2]] to <8 x i16>
; CHECK-NEXT: [[TMP0:%.*]] = zext <8 x i8> [[S1]] to <8 x i16> ; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[RES1:%.*]] = add <8 x i16> [[TMP0]], [[Z2]] ; CHECK-NEXT: [[TMP1:%.*]] = zext <8 x i8> [[TMP0]] to <8 x i16>
; CHECK-NEXT: [[RES1:%.*]] = add <8 x i16> [[TMP1]], [[Z2]]
; CHECK-NEXT: ret <8 x i16> [[RES1]] ; CHECK-NEXT: ret <8 x i16> [[RES1]]
; CHECK: if.else: ; CHECK: if.else:
; CHECK-NEXT: [[S4:%.*]] = shufflevector <16 x i8> [[B]], <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> ; CHECK-NEXT: [[S4:%.*]] = shufflevector <16 x i8> [[B]], <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[Z4:%.*]] = sext <8 x i8> [[S4]] to <8 x i16> ; CHECK-NEXT: [[Z4:%.*]] = sext <8 x i8> [[S4]] to <8 x i16>
; CHECK-NEXT: [[TMP1:%.*]] = sext <8 x i8> [[S3]] to <8 x i16> ; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[RES2:%.*]] = sub <8 x i16> [[TMP1]], [[Z4]] ; CHECK-NEXT: [[TMP3:%.*]] = sext <8 x i8> [[TMP2]] to <8 x i16>
; CHECK-NEXT: [[RES2:%.*]] = sub <8 x i16> [[TMP3]], [[Z4]]
; CHECK-NEXT: ret <8 x i16> [[RES2]] ; CHECK-NEXT: ret <8 x i16> [[RES2]]
; ;
entry: entry:
%s1 = shufflevector <16 x i8> %a, <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> %s1 = shufflevector <16 x i8> %a, <16 x i8> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%z1 = zext <8 x i8> %s1 to <8 x i16> %z1 = zext <8 x i8> %s1 to <8 x i16>
%s3 = shufflevector <16 x i8> %a, <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> %s3 = shufflevector <16 x i8> %a, <16 x i8> poison, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%z3 = sext <8 x i8> %s3 to <8 x i16> %z3 = sext <8 x i8> %s3 to <8 x i16>
call void @user1(<8 x i16> %z3) call void @user1(<8 x i16> %z3)
▲ Show 20 Lines • Show All 51 Lines • Show Last 20 Lines

llvm/test/Transforms/CodeGenPrepare/AArch64/sink-free-instructions.ll

Show First 20 Lines • Show All 148 Lines • ▼ Show 20 Linesif.else:
%vmull1 = tail call <8 x i16> @llvm.aarch64.neon.umull.v8i16(<8 x i8> %s3, <8 x i8> %s4) #3 %vmull1 = tail call <8 x i16> @llvm.aarch64.neon.umull.v8i16(<8 x i8> %s3, <8 x i8> %s4) #3
ret <8 x i16> %vmull1 ret <8 x i16> %vmull1
} }
; Both exts and their shufflevector operands can be sunk. ; Both exts and their shufflevector operands can be sunk.
define <8 x i16> @sink_shufflevector_ext_subadd(<16 x i8> %a, <16 x i8> %b) { define <8 x i16> @sink_shufflevector_ext_subadd(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: @sink_shufflevector_ext_subadd( ; CHECK-LABEL: @sink_shufflevector_ext_subadd(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[S1:%.*]] = shufflevector <16 x i8> [[A:%.*]], <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[S3:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: br i1 undef, label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]] ; CHECK-NEXT: br i1 undef, label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
; CHECK: if.then: ; CHECK: if.then:
; CHECK-NEXT: [[S2:%.*]] = shufflevector <16 x i8> [[B:%.*]], <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> ; CHECK-NEXT: [[S2:%.*]] = shufflevector <16 x i8> [[B:%.*]], <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[Z2:%.*]] = zext <8 x i8> [[S2]] to <8 x i16> ; CHECK-NEXT: [[Z2:%.*]] = zext <8 x i8> [[S2]] to <8 x i16>
; CHECK-NEXT: [[TMP0:%.*]] = zext <8 x i8> [[S1]] to <8 x i16> ; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <16 x i8> [[A:%.*]], <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[RES1:%.*]] = add <8 x i16> [[TMP0]], [[Z2]] ; CHECK-NEXT: [[TMP1:%.*]] = zext <8 x i8> [[TMP0]] to <8 x i16>
; CHECK-NEXT: [[RES1:%.*]] = add <8 x i16> [[TMP1]], [[Z2]]
; CHECK-NEXT: ret <8 x i16> [[RES1]] ; CHECK-NEXT: ret <8 x i16> [[RES1]]
; CHECK: if.else: ; CHECK: if.else:
; CHECK-NEXT: [[S4:%.*]] = shufflevector <16 x i8> [[B]], <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> ; CHECK-NEXT: [[S4:%.*]] = shufflevector <16 x i8> [[B]], <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[Z4:%.*]] = sext <8 x i8> [[S4]] to <8 x i16> ; CHECK-NEXT: [[Z4:%.*]] = sext <8 x i8> [[S4]] to <8 x i16>
; CHECK-NEXT: [[TMP1:%.*]] = sext <8 x i8> [[S3]] to <8 x i16> ; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[RES2:%.*]] = sub <8 x i16> [[TMP1]], [[Z4]] ; CHECK-NEXT: [[TMP3:%.*]] = sext <8 x i8> [[TMP2]] to <8 x i16>
; CHECK-NEXT: [[RES2:%.*]] = sub <8 x i16> [[TMP3]], [[Z4]]
; CHECK-NEXT: ret <8 x i16> [[RES2]] ; CHECK-NEXT: ret <8 x i16> [[RES2]]
; ;
entry: entry:
%s1 = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> %s1 = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%z1 = zext <8 x i8> %s1 to <8 x i16> %z1 = zext <8 x i8> %s1 to <8 x i16>
%s3 = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> %s3 = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%z3 = sext <8 x i8> %s3 to <8 x i16> %z3 = sext <8 x i8> %s3 to <8 x i16>
br i1 undef, label %if.then, label %if.else br i1 undef, label %if.then, label %if.else
Show All 13 Lines
declare void @user1(<8 x i16>) declare void @user1(<8 x i16>)
; Both exts and their shufflevector operands can be sunk. ; Both exts and their shufflevector operands can be sunk.
define <8 x i16> @sink_shufflevector_ext_subadd_multiuse(<16 x i8> %a, <16 x i8> %b) { define <8 x i16> @sink_shufflevector_ext_subadd_multiuse(<16 x i8> %a, <16 x i8> %b) {
; CHECK-LABEL: @sink_shufflevector_ext_subadd_multiuse( ; CHECK-LABEL: @sink_shufflevector_ext_subadd_multiuse(
; CHECK-NEXT: entry: ; CHECK-NEXT: entry:
; CHECK-NEXT: [[S1:%.*]] = shufflevector <16 x i8> [[A:%.*]], <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> ; CHECK-NEXT: [[S3:%.*]] = shufflevector <16 x i8> [[A:%.*]], <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[S3:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[Z3:%.*]] = sext <8 x i8> [[S3]] to <8 x i16> ; CHECK-NEXT: [[Z3:%.*]] = sext <8 x i8> [[S3]] to <8 x i16>
; CHECK-NEXT: call void @user1(<8 x i16> [[Z3]]) ; CHECK-NEXT: call void @user1(<8 x i16> [[Z3]])
; CHECK-NEXT: br i1 undef, label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]] ; CHECK-NEXT: br i1 undef, label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
; CHECK: if.then: ; CHECK: if.then:
; CHECK-NEXT: [[S2:%.*]] = shufflevector <16 x i8> [[B:%.*]], <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> ; CHECK-NEXT: [[S2:%.*]] = shufflevector <16 x i8> [[B:%.*]], <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[Z2:%.*]] = zext <8 x i8> [[S2]] to <8 x i16> ; CHECK-NEXT: [[Z2:%.*]] = zext <8 x i8> [[S2]] to <8 x i16>
; CHECK-NEXT: [[TMP0:%.*]] = zext <8 x i8> [[S1]] to <8 x i16> ; CHECK-NEXT: [[TMP0:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[RES1:%.*]] = add <8 x i16> [[TMP0]], [[Z2]] ; CHECK-NEXT: [[TMP1:%.*]] = zext <8 x i8> [[TMP0]] to <8 x i16>
; CHECK-NEXT: [[RES1:%.*]] = add <8 x i16> [[TMP1]], [[Z2]]
; CHECK-NEXT: ret <8 x i16> [[RES1]] ; CHECK-NEXT: ret <8 x i16> [[RES1]]
; CHECK: if.else: ; CHECK: if.else:
; CHECK-NEXT: [[S4:%.*]] = shufflevector <16 x i8> [[B]], <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> ; CHECK-NEXT: [[S4:%.*]] = shufflevector <16 x i8> [[B]], <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[Z4:%.*]] = sext <8 x i8> [[S4]] to <8 x i16> ; CHECK-NEXT: [[Z4:%.*]] = sext <8 x i8> [[S4]] to <8 x i16>
; CHECK-NEXT: [[TMP1:%.*]] = sext <8 x i8> [[S3]] to <8 x i16> ; CHECK-NEXT: [[TMP2:%.*]] = shufflevector <16 x i8> [[A]], <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT: [[RES2:%.*]] = sub <8 x i16> [[TMP1]], [[Z4]] ; CHECK-NEXT: [[TMP3:%.*]] = sext <8 x i8> [[TMP2]] to <8 x i16>
; CHECK-NEXT: [[RES2:%.*]] = sub <8 x i16> [[TMP3]], [[Z4]]
; CHECK-NEXT: ret <8 x i16> [[RES2]] ; CHECK-NEXT: ret <8 x i16> [[RES2]]
; ;
entry: entry:
%s1 = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7> %s1 = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%z1 = zext <8 x i8> %s1 to <8 x i16> %z1 = zext <8 x i8> %s1 to <8 x i16>
%s3 = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15> %s3 = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%z3 = sext <8 x i8> %s3 to <8 x i16> %z3 = sext <8 x i8> %s3 to <8 x i16>
call void @user1(<8 x i16> %z3) call void @user1(<8 x i16> %z3)
▲ Show 20 Lines • Show All 51 Lines • Show Last 20 Lines