[GlobalISel][X86] Support vector type G_INSERT legalization/selection.

Summary:
Support vector type G_INSERT legalization/selection.
Split from https://reviews.llvm.org/D33665

Reviewers: qcolombet, t.p.northover, zvi, guyblank

Reviewed By: guyblank

Subscribers: guyblank, rovka, llvm-commits, kristof.beyls

Differential Revision: https://reviews.llvm.org/D33956

llvm-svn: 305989
This commit is contained in:
Igor Breger 2017-06-22 09:43:35 +00:00
parent b489e56ae2
commit 1c29be7e4f
6 changed files with 679 additions and 3 deletions

View File

@ -75,6 +75,12 @@ private:
bool selectUadde(MachineInstr &I, MachineRegisterInfo &MRI,
MachineFunction &MF) const;
bool selectCopy(MachineInstr &I, MachineRegisterInfo &MRI) const;
bool selectInsert(MachineInstr &I, MachineRegisterInfo &MRI,
MachineFunction &MF) const;
// emit insert subreg instruction and insert it before MachineInstr &I
bool emitInsertSubreg(unsigned DstReg, unsigned SrcReg, MachineInstr &I,
MachineRegisterInfo &MRI, MachineFunction &MF) const;
const TargetRegisterClass *getRegClass(LLT Ty, const RegisterBank &RB) const;
const TargetRegisterClass *getRegClass(LLT Ty, unsigned Reg,
@ -259,6 +265,8 @@ bool X86InstructionSelector::select(MachineInstr &I) const {
return true;
if (selectUadde(I, MRI, MF))
return true;
if (selectInsert(I, MRI, MF))
return true;
return false;
}
@ -703,6 +711,105 @@ bool X86InstructionSelector::selectUadde(MachineInstr &I,
return true;
}
bool X86InstructionSelector::emitInsertSubreg(unsigned DstReg, unsigned SrcReg,
MachineInstr &I,
MachineRegisterInfo &MRI,
MachineFunction &MF) const {
const LLT DstTy = MRI.getType(DstReg);
const LLT SrcTy = MRI.getType(SrcReg);
unsigned SubIdx = X86::NoSubRegister;
// TODO: support scalar types
if (!DstTy.isVector() || !SrcTy.isVector())
return false;
assert(SrcTy.getSizeInBits() < DstTy.getSizeInBits() &&
"Incorrect Src/Dst register size");
if (SrcTy.getSizeInBits() == 128)
SubIdx = X86::sub_xmm;
else if (SrcTy.getSizeInBits() == 256)
SubIdx = X86::sub_ymm;
else
return false;
const TargetRegisterClass *SrcRC = getRegClass(SrcTy, SrcReg, MRI);
const TargetRegisterClass *DstRC = getRegClass(DstTy, DstReg, MRI);
if (!RBI.constrainGenericRegister(SrcReg, *SrcRC, MRI) ||
!RBI.constrainGenericRegister(DstReg, *DstRC, MRI)) {
DEBUG(dbgs() << "Failed to constrain INSERT_SUBREG\n");
return false;
}
BuildMI(*I.getParent(), I, I.getDebugLoc(), TII.get(X86::COPY))
.addReg(DstReg, RegState::DefineNoRead, SubIdx)
.addReg(SrcReg);
return true;
}
bool X86InstructionSelector::selectInsert(MachineInstr &I,
MachineRegisterInfo &MRI,
MachineFunction &MF) const {
if (I.getOpcode() != TargetOpcode::G_INSERT)
return false;
const unsigned DstReg = I.getOperand(0).getReg();
const unsigned SrcReg = I.getOperand(1).getReg();
const unsigned InsertReg = I.getOperand(2).getReg();
int64_t Index = I.getOperand(3).getImm();
const LLT DstTy = MRI.getType(DstReg);
const LLT InsertRegTy = MRI.getType(InsertReg);
// Meanwile handle vector type only.
if (!DstTy.isVector())
return false;
if (Index % InsertRegTy.getSizeInBits() != 0)
return false; // Not insert subvector.
if (Index == 0 && MRI.getVRegDef(SrcReg)->isImplicitDef()) {
// Replace by subreg copy.
if (!emitInsertSubreg(DstReg, InsertReg, I, MRI, MF))
return false;
I.eraseFromParent();
return true;
}
bool HasAVX = STI.hasAVX();
bool HasAVX512 = STI.hasAVX512();
bool HasVLX = STI.hasVLX();
if (DstTy.getSizeInBits() == 256 && InsertRegTy.getSizeInBits() == 128) {
if (HasVLX)
I.setDesc(TII.get(X86::VINSERTF32x4Z256rr));
else if (HasAVX)
I.setDesc(TII.get(X86::VINSERTF128rr));
else
return false;
} else if (DstTy.getSizeInBits() == 512 && HasAVX512) {
if (InsertRegTy.getSizeInBits() == 128)
I.setDesc(TII.get(X86::VINSERTF32x4Zrr));
else if (InsertRegTy.getSizeInBits() == 256)
I.setDesc(TII.get(X86::VINSERTF64x4Zrr));
else
return false;
} else
return false;
// Convert to X86 VINSERT immediate.
Index = Index / InsertRegTy.getSizeInBits();
I.getOperand(3).setImm(Index);
return constrainSelectedInstRegOperands(I, TII, TRI, RBI);
}
InstructionSelector *
llvm::createX86InstructionSelector(const X86TargetMachine &TM,
X86Subtarget &Subtarget,

View File

@ -214,12 +214,24 @@ void X86LegalizerInfo::setLegalizerInfoAVX() {
if (!Subtarget.hasAVX())
return;
const LLT v16s8 = LLT::vector(16, 8);
const LLT v8s16 = LLT::vector(8, 16);
const LLT v4s32 = LLT::vector(4, 32);
const LLT v2s64 = LLT::vector(2, 64);
const LLT v32s8 = LLT::vector(32, 8);
const LLT v16s16 = LLT::vector(16, 16);
const LLT v8s32 = LLT::vector(8, 32);
const LLT v4s64 = LLT::vector(4, 64);
for (unsigned MemOp : {G_LOAD, G_STORE})
for (auto Ty : {v8s32, v4s64})
setAction({MemOp, Ty}, Legal);
for (auto Ty : {v32s8, v16s16, v8s32, v4s64})
setAction({G_INSERT, Ty}, Legal);
for (auto Ty : {v16s8, v8s16, v4s32, v2s64})
setAction({G_INSERT, 1, Ty}, Legal);
}
void X86LegalizerInfo::setLegalizerInfoAVX2() {
@ -243,6 +255,18 @@ void X86LegalizerInfo::setLegalizerInfoAVX512() {
if (!Subtarget.hasAVX512())
return;
const LLT v16s8 = LLT::vector(16, 8);
const LLT v8s16 = LLT::vector(8, 16);
const LLT v4s32 = LLT::vector(4, 32);
const LLT v2s64 = LLT::vector(2, 64);
const LLT v32s8 = LLT::vector(32, 8);
const LLT v16s16 = LLT::vector(16, 16);
const LLT v8s32 = LLT::vector(8, 32);
const LLT v4s64 = LLT::vector(4, 64);
const LLT v64s8 = LLT::vector(64, 8);
const LLT v32s16 = LLT::vector(32, 16);
const LLT v16s32 = LLT::vector(16, 32);
const LLT v8s64 = LLT::vector(8, 64);
@ -256,13 +280,15 @@ void X86LegalizerInfo::setLegalizerInfoAVX512() {
for (auto Ty : {v16s32, v8s64})
setAction({MemOp, Ty}, Legal);
for (auto Ty : {v64s8, v32s16, v16s32, v8s64})
setAction({G_INSERT, Ty}, Legal);
for (auto Ty : {v32s8, v16s16, v8s32, v4s64, v16s8, v8s16, v4s32, v2s64})
setAction({G_INSERT, 1, Ty}, Legal);
/************ VLX *******************/
if (!Subtarget.hasVLX())
return;
const LLT v4s32 = LLT::vector(4, 32);
const LLT v8s32 = LLT::vector(8, 32);
for (auto Ty : {v4s32, v8s32})
setAction({G_MUL, Ty}, Legal);
}

View File

@ -0,0 +1,33 @@
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx -global-isel -run-pass=legalizer -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f,+avx512vl -global-isel -run-pass=legalizer -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL
--- |
define void @test_insert_128() {
ret void
}
...
---
name: test_insert_128
# ALL-LABEL: name: test_insert_128
alignment: 4
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
# ALL: %0(<8 x s32>) = COPY %ymm0
# ALL-NEXT: %1(<4 x s32>) = COPY %xmm1
# ALL-NEXT: %2(<8 x s32>) = G_INSERT %0, %1(<4 x s32>), 0
# ALL-NEXT: %ymm0 = COPY %2(<8 x s32>)
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<8 x s32>) = COPY %ymm0
%1(<4 x s32>) = COPY %xmm1
%2(<8 x s32>) = G_INSERT %0(<8 x s32>), %1(<4 x s32>), 0
%ymm0 = COPY %2(<8 x s32>)
RET 0, implicit %ymm0
...

View File

@ -0,0 +1,63 @@
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f -global-isel -run-pass=legalizer -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL
--- |
define void @test_insert_128() {
ret void
}
define void @test_insert_256() {
ret void
}
...
---
name: test_insert_128
# ALL-LABEL: name: test_insert_128
alignment: 4
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
# ALL: %0(<16 x s32>) = COPY %zmm0
# ALL-NEXT: %1(<4 x s32>) = COPY %xmm1
# ALL-NEXT: %2(<16 x s32>) = G_INSERT %0, %1(<4 x s32>), 0
# ALL-NEXT: %ymm0 = COPY %2(<16 x s32>)
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %zmm0, %ymm1
%0(<16 x s32>) = COPY %zmm0
%1(<4 x s32>) = COPY %xmm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<4 x s32>), 0
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_256
# ALL-LABEL: name: test_insert_256
alignment: 4
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
# ALL: %0(<16 x s32>) = COPY %zmm0
# ALL-NEXT: %1(<8 x s32>) = COPY %ymm1
# ALL-NEXT: %2(<16 x s32>) = G_INSERT %0, %1(<8 x s32>), 0
# ALL-NEXT: %ymm0 = COPY %2(<16 x s32>)
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %zmm0, %ymm1
%0(<16 x s32>) = COPY %zmm0
%1(<8 x s32>) = COPY %ymm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<8 x s32>), 0
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...

View File

@ -0,0 +1,176 @@
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f,+avx512vl -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL
--- |
define void @test_insert_128_idx0() {
ret void
}
define void @test_insert_128_idx0_undef() {
ret void
}
define void @test_insert_128_idx1() {
ret void
}
define void @test_insert_128_idx1_undef() {
ret void
}
...
---
name: test_insert_128_idx0
# ALL-LABEL: name: test_insert_128_idx0
alignment: 4
legalized: true
regBankSelected: true
# AVX: registers:
# AVX-NEXT: - { id: 0, class: vr256, preferred-register: '' }
# AVX-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# AVX-NEXT: - { id: 2, class: vr256, preferred-register: '' }
#
# AVX512VL: registers:
# AVX512VL-NEXT: - { id: 0, class: vr256x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 2, class: vr256x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# AVX: %0 = COPY %ymm0
# AVX-NEXT: %1 = COPY %xmm1
# AVX-NEXT: %2 = VINSERTF128rr %0, %1, 0
# AVX-NEXT: %ymm0 = COPY %2
# AVX-NEXT: RET 0, implicit %ymm0
#
# AVX512VL: %0 = COPY %ymm0
# AVX512VL-NEXT: %1 = COPY %xmm1
# AVX512VL-NEXT: %2 = VINSERTF32x4Z256rr %0, %1, 0
# AVX512VL-NEXT: %ymm0 = COPY %2
# AVX512VL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<8 x s32>) = COPY %ymm0
%1(<4 x s32>) = COPY %xmm1
%2(<8 x s32>) = G_INSERT %0(<8 x s32>), %1(<4 x s32>), 0
%ymm0 = COPY %2(<8 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_128_idx0_undef
# ALL-LABEL: name: test_insert_128_idx0_undef
alignment: 4
legalized: true
regBankSelected: true
# AVX: registers:
# AVX-NEXT: - { id: 0, class: vecr, preferred-register: '' }
# AVX-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# AVX-NEXT: - { id: 2, class: vr256, preferred-register: '' }
#
# AVX512VL: registers:
# AVX512VL-NEXT: - { id: 0, class: vecr, preferred-register: '' }
# AVX512VL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 2, class: vr256x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# ALL: %1 = COPY %xmm1
# ALL-NEXT: undef %2.sub_xmm = COPY %1
# ALL-NEXT: %ymm0 = COPY %2
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<8 x s32>) = IMPLICIT_DEF
%1(<4 x s32>) = COPY %xmm1
%2(<8 x s32>) = G_INSERT %0(<8 x s32>), %1(<4 x s32>), 0
%ymm0 = COPY %2(<8 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_128_idx1
# ALL-LABEL: name: test_insert_128_idx1
alignment: 4
legalized: true
regBankSelected: true
# AVX: registers:
# AVX-NEXT: - { id: 0, class: vr256, preferred-register: '' }
# AVX-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# AVX-NEXT: - { id: 2, class: vr256, preferred-register: '' }
#
# AVX512VL: registers:
# AVX512VL-NEXT: - { id: 0, class: vr256x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 2, class: vr256x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# AVX: %0 = COPY %ymm0
# AVX-NEXT: %1 = COPY %xmm1
# AVX-NEXT: %2 = VINSERTF128rr %0, %1, 1
# AVX-NEXT: %ymm0 = COPY %2
# AVX-NEXT: RET 0, implicit %ymm0
#
# AVX512VL: %0 = COPY %ymm0
# AVX512VL-NEXT: %1 = COPY %xmm1
# AVX512VL-NEXT: %2 = VINSERTF32x4Z256rr %0, %1, 1
# AVX512VL-NEXT: %ymm0 = COPY %2
# AVX512VL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<8 x s32>) = COPY %ymm0
%1(<4 x s32>) = COPY %xmm1
%2(<8 x s32>) = G_INSERT %0(<8 x s32>), %1(<4 x s32>), 128
%ymm0 = COPY %2(<8 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_128_idx1_undef
# ALL-LABEL: name: test_insert_128_idx1_undef
alignment: 4
legalized: true
regBankSelected: true
# AVX: registers:
# AVX-NEXT: - { id: 0, class: vr256, preferred-register: '' }
# AVX-NEXT: - { id: 1, class: vr128, preferred-register: '' }
# AVX-NEXT: - { id: 2, class: vr256, preferred-register: '' }
#
# AVX512VL: registers:
# AVX512VL-NEXT: - { id: 0, class: vr256x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# AVX512VL-NEXT: - { id: 2, class: vr256x, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# AVX: %0 = IMPLICIT_DEF
# AVX-NEXT: %1 = COPY %xmm1
# AVX-NEXT: %2 = VINSERTF128rr %0, %1, 1
# AVX-NEXT: %ymm0 = COPY %2
# AVX-NEXT: RET 0, implicit %ymm0
#
# AVX512VL: %0 = IMPLICIT_DEF
# AVX512VL-NEXT: %1 = COPY %xmm1
# AVX512VL-NEXT: %2 = VINSERTF32x4Z256rr %0, %1, 1
# AVX512VL-NEXT: %ymm0 = COPY %2
# AVX512VL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<8 x s32>) = IMPLICIT_DEF
%1(<4 x s32>) = COPY %xmm1
%2(<8 x s32>) = G_INSERT %0(<8 x s32>), %1(<4 x s32>), 128
%ymm0 = COPY %2(<8 x s32>)
RET 0, implicit %ymm0
...

View File

@ -0,0 +1,271 @@
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f -global-isel -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=ALL
--- |
define void @test_insert_128_idx0() {
ret void
}
define void @test_insert_128_idx0_undef() {
ret void
}
define void @test_insert_128_idx1() {
ret void
}
define void @test_insert_128_idx1_undef() {
ret void
}
define void @test_insert_256_idx0() {
ret void
}
define void @test_insert_256_idx0_undef() {
ret void
}
define void @test_insert_256_idx1() {
ret void
}
define void @test_insert_256_idx1_undef() {
ret void
}
...
---
name: test_insert_128_idx0
# ALL-LABEL: name: test_insert_128_idx0
alignment: 4
legalized: true
regBankSelected: true
# ALL: registers:
# ALL-NEXT: - { id: 0, class: vr512, preferred-register: '' }
# ALL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# ALL-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# ALL: %0 = COPY %zmm0
# ALL-NEXT: %1 = COPY %xmm1
# ALL-NEXT: %2 = VINSERTF32x4Zrr %0, %1, 0
# ALL-NEXT: %ymm0 = COPY %2
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %zmm0, %ymm1
%0(<16 x s32>) = COPY %zmm0
%1(<4 x s32>) = COPY %xmm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<4 x s32>), 0
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_128_idx0_undef
# ALL-LABEL: name: test_insert_128_idx0_undef
alignment: 4
legalized: true
regBankSelected: true
# ALL: registers:
# ALL-NEXT: - { id: 0, class: vecr, preferred-register: '' }
# ALL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# ALL-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# ALL: %1 = COPY %xmm1
# ALL-NEXT: undef %2.sub_xmm = COPY %1
# ALL-NEXT: %ymm0 = COPY %2
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<16 x s32>) = IMPLICIT_DEF
%1(<4 x s32>) = COPY %xmm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<4 x s32>), 0
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_128_idx1
# ALL-LABEL: name: test_insert_128_idx1
alignment: 4
legalized: true
regBankSelected: true
# ALL: registers:
# ALL-NEXT: - { id: 0, class: vr512, preferred-register: '' }
# ALL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# ALL-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# ALL: %0 = COPY %zmm0
# ALL-NEXT: %1 = COPY %xmm1
# ALL-NEXT: %2 = VINSERTF32x4Zrr %0, %1, 1
# ALL-NEXT: %ymm0 = COPY %2
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<16 x s32>) = COPY %zmm0
%1(<4 x s32>) = COPY %xmm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<4 x s32>), 128
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_128_idx1_undef
# ALL-LABEL: name: test_insert_128_idx1_undef
alignment: 4
legalized: true
regBankSelected: true
# ALL: registers:
# ALL-NEXT: - { id: 0, class: vr512, preferred-register: '' }
# ALL-NEXT: - { id: 1, class: vr128x, preferred-register: '' }
# ALL-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# ALL: %0 = IMPLICIT_DEF
# ALL-NEXT: %1 = COPY %xmm1
# ALL-NEXT: %2 = VINSERTF32x4Zrr %0, %1, 1
# ALL-NEXT: %ymm0 = COPY %2
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<16 x s32>) = IMPLICIT_DEF
%1(<4 x s32>) = COPY %xmm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<4 x s32>), 128
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_256_idx0
# ALL-LABEL: name: test_insert_256_idx0
alignment: 4
legalized: true
regBankSelected: true
# ALL: registers:
# ALL-NEXT: - { id: 0, class: vr512, preferred-register: '' }
# ALL-NEXT: - { id: 1, class: vr256x, preferred-register: '' }
# ALL-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# ALL: %0 = COPY %zmm0
# ALL-NEXT: %1 = COPY %ymm1
# ALL-NEXT: %2 = VINSERTF64x4Zrr %0, %1, 0
# ALL-NEXT: %ymm0 = COPY %2
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %zmm0, %ymm1
%0(<16 x s32>) = COPY %zmm0
%1(<8 x s32>) = COPY %ymm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<8 x s32>), 0
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_256_idx0_undef
# ALL-LABEL: name: test_insert_256_idx0_undef
alignment: 4
legalized: true
regBankSelected: true
# ALL: registers:
# ALL-NEXT: - { id: 0, class: vecr, preferred-register: '' }
# ALL-NEXT: - { id: 1, class: vr256x, preferred-register: '' }
# ALL-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# ALL: %1 = COPY %ymm1
# ALL-NEXT: undef %2.sub_ymm = COPY %1
# ALL-NEXT: %ymm0 = COPY %2
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<16 x s32>) = IMPLICIT_DEF
%1(<8 x s32>) = COPY %ymm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<8 x s32>), 0
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_256_idx1
# ALL-LABEL: name: test_insert_256_idx1
alignment: 4
legalized: true
regBankSelected: true
# ALL: registers:
# ALL-NEXT: - { id: 0, class: vr512, preferred-register: '' }
# ALL-NEXT: - { id: 1, class: vr256x, preferred-register: '' }
# ALL-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# ALL: %0 = COPY %zmm0
# ALL-NEXT: %1 = COPY %ymm1
# ALL-NEXT: %2 = VINSERTF64x4Zrr %0, %1, 1
# ALL-NEXT: %ymm0 = COPY %2
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<16 x s32>) = COPY %zmm0
%1(<8 x s32>) = COPY %ymm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<8 x s32>), 256
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...
---
name: test_insert_256_idx1_undef
# ALL-LABEL: name: test_insert_256_idx1_undef
alignment: 4
legalized: true
regBankSelected: true
# ALL: registers:
# ALL-NEXT: - { id: 0, class: vr512, preferred-register: '' }
# ALL-NEXT: - { id: 1, class: vr256x, preferred-register: '' }
# ALL-NEXT: - { id: 2, class: vr512, preferred-register: '' }
registers:
- { id: 0, class: vecr }
- { id: 1, class: vecr }
- { id: 2, class: vecr }
# ALL: %0 = IMPLICIT_DEF
# ALL-NEXT: %1 = COPY %ymm1
# ALL-NEXT: %2 = VINSERTF64x4Zrr %0, %1, 1
# ALL-NEXT: %ymm0 = COPY %2
# ALL-NEXT: RET 0, implicit %ymm0
body: |
bb.1 (%ir-block.0):
liveins: %ymm0, %ymm1
%0(<16 x s32>) = IMPLICIT_DEF
%1(<8 x s32>) = COPY %ymm1
%2(<16 x s32>) = G_INSERT %0(<16 x s32>), %1(<8 x s32>), 256
%ymm0 = COPY %2(<16 x s32>)
RET 0, implicit %ymm0
...