maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

GlobalISel: Translate vector GEPs

This commit is contained in:
Matt Arsenault 2020-01-24 22:57:49 -05:00
parent 77e6bb3cba
commit 06d9230fef
3 changed files with 219 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
View File

@ -1049,10 +1049,6 @@ bool IRTranslator::translateCast(unsigned Opcode, const User &U,
bool IRTranslator::translateGetElementPtr(const User &U, bool IRTranslator::translateGetElementPtr(const User &U,
MachineIRBuilder &MIRBuilder) { MachineIRBuilder &MIRBuilder) {
// FIXME: support vector GEPs.
if (U.getType()->isVectorTy())
return false;
Value &Op0 = *U.getOperand(0); Value &Op0 = *U.getOperand(0);
Register BaseReg = getOrCreateVReg(Op0); Register BaseReg = getOrCreateVReg(Op0);
Type *PtrIRTy = Op0.getType(); Type *PtrIRTy = Op0.getType();
@ -1060,6 +1056,12 @@ bool IRTranslator::translateGetElementPtr(const User &U,
Type *OffsetIRTy = DL->getIntPtrType(PtrIRTy); Type *OffsetIRTy = DL->getIntPtrType(PtrIRTy);
LLT OffsetTy = getLLTForType(*OffsetIRTy, *DL); LLT OffsetTy = getLLTForType(*OffsetIRTy, *DL);
// Normalize Vector GEP - all scalar operands should be converted to the
// splat vector.
unsigned VectorWidth = 0;
if (auto *VT = dyn_cast<VectorType>(U.getType()))
VectorWidth = VT->getNumElements();
int64_t Offset = 0; int64_t Offset = 0;
for (gep_type_iterator GTI = gep_type_begin(&U), E = gep_type_end(&U); for (gep_type_iterator GTI = gep_type_begin(&U), E = gep_type_end(&U);
GTI != E; ++GTI) { GTI != E; ++GTI) {
@ -1079,7 +1081,6 @@ bool IRTranslator::translateGetElementPtr(const User &U,
} }
if (Offset != 0) { if (Offset != 0) {
LLT OffsetTy = getLLTForType(*OffsetIRTy, *DL);
auto OffsetMIB = MIRBuilder.buildConstant({OffsetTy}, Offset); auto OffsetMIB = MIRBuilder.buildConstant({OffsetTy}, Offset);
BaseReg = MIRBuilder.buildPtrAdd(PtrTy, BaseReg, OffsetMIB.getReg(0)) BaseReg = MIRBuilder.buildPtrAdd(PtrTy, BaseReg, OffsetMIB.getReg(0))
.getReg(0); .getReg(0);
@ -1087,8 +1088,15 @@ bool IRTranslator::translateGetElementPtr(const User &U,
} }
Register IdxReg = getOrCreateVReg(*Idx); Register IdxReg = getOrCreateVReg(*Idx);
if (MRI->getType(IdxReg) != OffsetTy) LLT IdxTy = MRI->getType(IdxReg);
if (IdxTy != OffsetTy) {
if (!IdxTy.isVector() && VectorWidth) {
IdxReg = MIRBuilder.buildSplatVector(
OffsetTy.changeElementType(IdxTy), IdxReg).getReg(0);
}
IdxReg = MIRBuilder.buildSExtOrTrunc(OffsetTy, IdxReg).getReg(0); IdxReg = MIRBuilder.buildSExtOrTrunc(OffsetTy, IdxReg).getReg(0);
}
// N = N + Idx * ElementSize; // N = N + Idx * ElementSize;
// Avoid doing it for ElementSize of 1. // Avoid doing it for ElementSize of 1.
@ -1107,7 +1115,7 @@ bool IRTranslator::translateGetElementPtr(const User &U,
if (Offset != 0) { if (Offset != 0) {
auto OffsetMIB = auto OffsetMIB =
MIRBuilder.buildConstant(getLLTForType(*OffsetIRTy, *DL), Offset); MIRBuilder.buildConstant(OffsetTy, Offset);
MIRBuilder.buildPtrAdd(getOrCreateVReg(U), BaseReg, OffsetMIB.getReg(0)); MIRBuilder.buildPtrAdd(getOrCreateVReg(U), BaseReg, OffsetMIB.getReg(0));
return true; return true;
} }

4
llvm/lib/CodeGen/GlobalISel/MachineIRBuilder.cpp
View File

@ -222,9 +222,9 @@ void MachineIRBuilder::validateShiftOp(const LLT &Res, const LLT &Op0,
MachineInstrBuilder MachineIRBuilder::buildPtrAdd(const DstOp &Res, MachineInstrBuilder MachineIRBuilder::buildPtrAdd(const DstOp &Res,
const SrcOp &Op0, const SrcOp &Op0,
const SrcOp &Op1) { const SrcOp &Op1) {
assert(Res.getLLTTy(*getMRI()).isPointer() && assert(Res.getLLTTy(*getMRI()).getScalarType().isPointer() &&
Res.getLLTTy(*getMRI()) == Op0.getLLTTy(*getMRI()) && "type mismatch"); Res.getLLTTy(*getMRI()) == Op0.getLLTTy(*getMRI()) && "type mismatch");
assert(Op1.getLLTTy(*getMRI()).isScalar() && "invalid offset type"); assert(Op1.getLLTTy(*getMRI()).getScalarType().isScalar() && "invalid offset type");
return buildInstr(TargetOpcode::G_PTR_ADD, {Res}, {Op0, Op1}); return buildInstr(TargetOpcode::G_PTR_ADD, {Res}, {Op0, Op1});
} }

202
llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-getelementptr.ll Normal file
View File

@ -0,0 +1,202 @@
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -stop-after=irtranslator -o - %s | FileCheck %s
; Test 64-bit pointer with 64-bit index
define <2 x i32 addrspace(1)*> @vector_gep_v2p1_index_v2i64(<2 x i32 addrspace(1)*> %ptr, <2 x i64> %idx) {
; CHECK-LABEL: name: vector_gep_v2p1_index_v2i64
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $sgpr30_sgpr31
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY $vgpr4
; CHECK: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr5
; CHECK: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr6
; CHECK: [[COPY7:%[0-9]+]]:_(s32) = COPY $vgpr7
; CHECK: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
; CHECK: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK: [[MV1:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p1>) = G_BUILD_VECTOR [[MV]](p1), [[MV1]](p1)
; CHECK: [[MV2:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY4]](s32), [[COPY5]](s32)
; CHECK: [[MV3:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY6]](s32), [[COPY7]](s32)
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[MV2]](s64), [[MV3]](s64)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 4
; CHECK: [[BUILD_VECTOR2:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[C]](s64), [[C]](s64)
; CHECK: [[MUL:%[0-9]+]]:_(<2 x s64>) = G_MUL [[BUILD_VECTOR2]], [[BUILD_VECTOR1]]
; CHECK: [[PTR_ADD:%[0-9]+]]:_(<2 x p1>) = G_PTR_ADD [[BUILD_VECTOR]], [[MUL]](<2 x s64>)
; CHECK: [[COPY9:%[0-9]+]]:_(<2 x p1>) = COPY [[PTR_ADD]](<2 x p1>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY9]](<2 x p1>)
; CHECK: $vgpr0 = COPY [[UV]](s32)
; CHECK: $vgpr1 = COPY [[UV1]](s32)
; CHECK: $vgpr2 = COPY [[UV2]](s32)
; CHECK: $vgpr3 = COPY [[UV3]](s32)
; CHECK: [[COPY10:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY8]]
; CHECK: S_SETPC_B64_return [[COPY10]], implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
%gep = getelementptr i32, <2 x i32 addrspace(1)*> %ptr, <2 x i64> %idx
ret <2 x i32 addrspace(1)*> %gep
}
; Test 32-bit pointer with 32-bit index
define <2 x i32 addrspace(3)*> @vector_gep_v2p3_index_v2i32(<2 x i32 addrspace(3)*> %ptr, <2 x i32> %idx) {
; CHECK-LABEL: name: vector_gep_v2p3_index_v2i32
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $sgpr30_sgpr31
; CHECK: [[COPY:%[0-9]+]]:_(p3) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(p3) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
; CHECK: [[COPY4:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p3>) = G_BUILD_VECTOR [[COPY]](p3), [[COPY1]](p3)
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[COPY2]](s32), [[COPY3]](s32)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 4
; CHECK: [[BUILD_VECTOR2:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[C]](s32), [[C]](s32)
; CHECK: [[MUL:%[0-9]+]]:_(<2 x s32>) = G_MUL [[BUILD_VECTOR2]], [[BUILD_VECTOR1]]
; CHECK: [[PTR_ADD:%[0-9]+]]:_(<2 x p3>) = G_PTR_ADD [[BUILD_VECTOR]], [[MUL]](<2 x s32>)
; CHECK: [[COPY5:%[0-9]+]]:_(<2 x p3>) = COPY [[PTR_ADD]](<2 x p3>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY5]](<2 x p3>)
; CHECK: $vgpr0 = COPY [[UV]](s32)
; CHECK: $vgpr1 = COPY [[UV1]](s32)
; CHECK: [[COPY6:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY4]]
; CHECK: S_SETPC_B64_return [[COPY6]], implicit $vgpr0, implicit $vgpr1
%gep = getelementptr i32, <2 x i32 addrspace(3)*> %ptr, <2 x i32> %idx
ret <2 x i32 addrspace(3)*> %gep
}
; Test 64-bit pointer with 32-bit index
define <2 x i32 addrspace(1)*> @vector_gep_v2p1_index_v2i32(<2 x i32 addrspace(1)*> %ptr, <2 x i32> %idx) {
; CHECK-LABEL: name: vector_gep_v2p1_index_v2i32
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $sgpr30_sgpr31
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY $vgpr4
; CHECK: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr5
; CHECK: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
; CHECK: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK: [[MV1:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p1>) = G_BUILD_VECTOR [[MV]](p1), [[MV1]](p1)
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[COPY4]](s32), [[COPY5]](s32)
; CHECK: [[SEXT:%[0-9]+]]:_(<2 x s64>) = G_SEXT [[BUILD_VECTOR1]](<2 x s32>)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 4
; CHECK: [[BUILD_VECTOR2:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[C]](s64), [[C]](s64)
; CHECK: [[MUL:%[0-9]+]]:_(<2 x s64>) = G_MUL [[BUILD_VECTOR2]], [[SEXT]]
; CHECK: [[PTR_ADD:%[0-9]+]]:_(<2 x p1>) = G_PTR_ADD [[BUILD_VECTOR]], [[MUL]](<2 x s64>)
; CHECK: [[COPY7:%[0-9]+]]:_(<2 x p1>) = COPY [[PTR_ADD]](<2 x p1>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY7]](<2 x p1>)
; CHECK: $vgpr0 = COPY [[UV]](s32)
; CHECK: $vgpr1 = COPY [[UV1]](s32)
; CHECK: $vgpr2 = COPY [[UV2]](s32)
; CHECK: $vgpr3 = COPY [[UV3]](s32)
; CHECK: [[COPY8:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY6]]
; CHECK: S_SETPC_B64_return [[COPY8]], implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
%gep = getelementptr i32, <2 x i32 addrspace(1)*> %ptr, <2 x i32> %idx
ret <2 x i32 addrspace(1)*> %gep
}
; Test 64-bit pointer with 64-bit scalar index
define <2 x i32 addrspace(1)*> @vector_gep_v2p1_index_i64(<2 x i32 addrspace(1)*> %ptr, i64 %idx) {
; CHECK-LABEL: name: vector_gep_v2p1_index_i64
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $sgpr30_sgpr31
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY $vgpr4
; CHECK: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr5
; CHECK: [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
; CHECK: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK: [[MV1:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p1>) = G_BUILD_VECTOR [[MV]](p1), [[MV1]](p1)
; CHECK: [[MV2:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY4]](s32), [[COPY5]](s32)
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[MV2]](s64), [[MV2]](s64)
; CHECK: [[COPY7:%[0-9]+]]:_(<2 x s64>) = COPY [[BUILD_VECTOR1]](<2 x s64>)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 4
; CHECK: [[BUILD_VECTOR2:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[C]](s64), [[C]](s64)
; CHECK: [[MUL:%[0-9]+]]:_(<2 x s64>) = G_MUL [[BUILD_VECTOR2]], [[COPY7]]
; CHECK: [[PTR_ADD:%[0-9]+]]:_(<2 x p1>) = G_PTR_ADD [[BUILD_VECTOR]], [[MUL]](<2 x s64>)
; CHECK: [[COPY8:%[0-9]+]]:_(<2 x p1>) = COPY [[PTR_ADD]](<2 x p1>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY8]](<2 x p1>)
; CHECK: $vgpr0 = COPY [[UV]](s32)
; CHECK: $vgpr1 = COPY [[UV1]](s32)
; CHECK: $vgpr2 = COPY [[UV2]](s32)
; CHECK: $vgpr3 = COPY [[UV3]](s32)
; CHECK: [[COPY9:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY6]]
; CHECK: S_SETPC_B64_return [[COPY9]], implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
%gep = getelementptr i32, <2 x i32 addrspace(1)*> %ptr, i64 %idx
ret <2 x i32 addrspace(1)*> %gep
}
; Test 64-bit pointer with 32-bit scalar index
define <2 x i32 addrspace(1)*> @vector_gep_v2p1_index_i32(<2 x i32 addrspace(1)*> %ptr, i32 %idx) {
; CHECK-LABEL: name: vector_gep_v2p1_index_i32
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $sgpr30_sgpr31
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY $vgpr4
; CHECK: [[COPY5:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
; CHECK: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK: [[MV1:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p1>) = G_BUILD_VECTOR [[MV]](p1), [[MV1]](p1)
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[COPY4]](s32), [[COPY4]](s32)
; CHECK: [[SEXT:%[0-9]+]]:_(<2 x s64>) = G_SEXT [[BUILD_VECTOR1]](<2 x s32>)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 4
; CHECK: [[BUILD_VECTOR2:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[C]](s64), [[C]](s64)
; CHECK: [[MUL:%[0-9]+]]:_(<2 x s64>) = G_MUL [[BUILD_VECTOR2]], [[SEXT]]
; CHECK: [[PTR_ADD:%[0-9]+]]:_(<2 x p1>) = G_PTR_ADD [[BUILD_VECTOR]], [[MUL]](<2 x s64>)
; CHECK: [[COPY6:%[0-9]+]]:_(<2 x p1>) = COPY [[PTR_ADD]](<2 x p1>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY6]](<2 x p1>)
; CHECK: $vgpr0 = COPY [[UV]](s32)
; CHECK: $vgpr1 = COPY [[UV1]](s32)
; CHECK: $vgpr2 = COPY [[UV2]](s32)
; CHECK: $vgpr3 = COPY [[UV3]](s32)
; CHECK: [[COPY7:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY5]]
; CHECK: S_SETPC_B64_return [[COPY7]], implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
%gep = getelementptr i32, <2 x i32 addrspace(1)*> %ptr, i32 %idx
ret <2 x i32 addrspace(1)*> %gep
}
; Test 64-bit pointer with 64-bit constant, non-splat
define <2 x i32 addrspace(1)*> @vector_gep_v2p1_index_v2i64_constant(<2 x i32 addrspace(1)*> %ptr, <2 x i64> %idx) {
; CHECK-LABEL: name: vector_gep_v2p1_index_v2i64_constant
; CHECK: bb.1 (%ir-block.0):
; CHECK: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $sgpr30_sgpr31
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY $vgpr4
; CHECK: [[COPY5:%[0-9]+]]:_(s32) = COPY $vgpr5
; CHECK: [[COPY6:%[0-9]+]]:_(s32) = COPY $vgpr6
; CHECK: [[COPY7:%[0-9]+]]:_(s32) = COPY $vgpr7
; CHECK: [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr30_sgpr31
; CHECK: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
; CHECK: [[MV1:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p1>) = G_BUILD_VECTOR [[MV]](p1), [[MV1]](p1)
; CHECK: [[MV2:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY4]](s32), [[COPY5]](s32)
; CHECK: [[MV3:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY6]](s32), [[COPY7]](s32)
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[MV2]](s64), [[MV3]](s64)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 1
; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 2
; CHECK: [[BUILD_VECTOR2:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[C]](s64), [[C1]](s64)
; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 4
; CHECK: [[BUILD_VECTOR3:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[C2]](s64), [[C2]](s64)
; CHECK: [[MUL:%[0-9]+]]:_(<2 x s64>) = G_MUL [[BUILD_VECTOR3]], [[BUILD_VECTOR2]]
; CHECK: [[PTR_ADD:%[0-9]+]]:_(<2 x p1>) = G_PTR_ADD [[BUILD_VECTOR]], [[MUL]](<2 x s64>)
; CHECK: [[COPY9:%[0-9]+]]:_(<2 x p1>) = COPY [[PTR_ADD]](<2 x p1>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY9]](<2 x p1>)
; CHECK: $vgpr0 = COPY [[UV]](s32)
; CHECK: $vgpr1 = COPY [[UV1]](s32)
; CHECK: $vgpr2 = COPY [[UV2]](s32)
; CHECK: $vgpr3 = COPY [[UV3]](s32)
; CHECK: [[COPY10:%[0-9]+]]:ccr_sgpr_64 = COPY [[COPY8]]
; CHECK: S_SETPC_B64_return [[COPY10]], implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3
%gep = getelementptr i32, <2 x i32 addrspace(1)*> %ptr, <2 x i64> <i64 1, i64 2>
ret <2 x i32 addrspace(1)*> %gep
}