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

GlobalISel: Fold out unmerge to scalars from concat_vector 

Removes illegal intermediate vectors if an operation was lowering to
concat_vectors, and the next operation is scalarized.

llvm-svn: 367081
This commit is contained in:
Matt Arsenault 2019-07-26 02:22:23 +00:00
parent 5c61015455
commit 51d795d941
3 changed files with 99 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
llvm/include/llvm/CodeGen/GlobalISel/LegalizationArtifactCombiner.h
View File

@ -203,14 +203,33 @@ public:
return false; return false;
} }
static unsigned getMergeOpcode(LLT OpTy, LLT DestTy) { static unsigned canFoldMergeOpcode(unsigned MergeOp, unsigned ConvertOp,
LLT OpTy, LLT DestTy) {
if (OpTy.isVector() && DestTy.isVector()) if (OpTy.isVector() && DestTy.isVector())
return TargetOpcode::G_CONCAT_VECTORS; return MergeOp == TargetOpcode::G_CONCAT_VECTORS;
if (OpTy.isVector() && !DestTy.isVector()) if (OpTy.isVector() && !DestTy.isVector()) {
return TargetOpcode::G_BUILD_VECTOR; if (MergeOp == TargetOpcode::G_BUILD_VECTOR)
return true;
return TargetOpcode::G_MERGE_VALUES; if (MergeOp == TargetOpcode::G_CONCAT_VECTORS) {
if (ConvertOp == 0)
return true;
const unsigned OpEltSize = OpTy.getElementType().getSizeInBits();
// Don't handle scalarization with a cast that isn't in the same
// direction as the vector cast. This could be handled, but it would
// require more intermediate unmerges.
if (ConvertOp == TargetOpcode::G_TRUNC)
return DestTy.getSizeInBits() <= OpEltSize;
return DestTy.getSizeInBits() >= OpEltSize;
}
return false;
}
return MergeOp == TargetOpcode::G_MERGE_VALUES;
} }
bool tryCombineMerges(MachineInstr &MI, bool tryCombineMerges(MachineInstr &MI,
@ -237,16 +256,14 @@ public:
MergeI = getDefIgnoringCopies(SrcDef->getOperand(1).getReg(), MRI); MergeI = getDefIgnoringCopies(SrcDef->getOperand(1).getReg(), MRI);
} }
// FIXME: Handle scalarizing concat_vectors (scalar result type with vector if (!MergeI || !canFoldMergeOpcode(MergeI->getOpcode(),
// source) ConvertOp, OpTy, DestTy))
unsigned MergingOpcode = getMergeOpcode(OpTy, DestTy);
if (!MergeI || MergeI->getOpcode() != MergingOpcode)
return false; return false;
const unsigned NumMergeRegs = MergeI->getNumOperands() - 1; const unsigned NumMergeRegs = MergeI->getNumOperands() - 1;
if (NumMergeRegs < NumDefs) { if (NumMergeRegs < NumDefs) {
if (ConvertOp != 0 || NumDefs % NumMergeRegs != 0) if (NumDefs % NumMergeRegs != 0)
return false; return false;
Builder.setInstr(MI); Builder.setInstr(MI);
@ -264,7 +281,22 @@ public:
++j, ++DefIdx) ++j, ++DefIdx)
DstRegs.push_back(MI.getOperand(DefIdx).getReg()); DstRegs.push_back(MI.getOperand(DefIdx).getReg());
Builder.buildUnmerge(DstRegs, MergeI->getOperand(Idx + 1).getReg()); if (ConvertOp) {
SmallVector<Register, 2> TmpRegs;
// This is a vector that is being scalarized and casted. Extract to
// the element type, and do the conversion on the scalars.
LLT MergeEltTy
= MRI.getType(MergeI->getOperand(0).getReg()).getElementType();
for (unsigned j = 0; j < NumMergeRegs; ++j)
TmpRegs.push_back(MRI.createGenericVirtualRegister(MergeEltTy));
Builder.buildUnmerge(TmpRegs, MergeI->getOperand(Idx + 1).getReg());
for (unsigned j = 0; j < NumMergeRegs; ++j)
Builder.buildInstr(ConvertOp, {DstRegs[j]}, {TmpRegs[j]});
} else {
Builder.buildUnmerge(DstRegs, MergeI->getOperand(Idx + 1).getReg());
}
} }
} else if (NumMergeRegs > NumDefs) { } else if (NumMergeRegs > NumDefs) {

92
llvm/test/CodeGen/AMDGPU/GlobalISel/artifact-combiner-unmerge-values.mir
View File

@ -225,17 +225,25 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s1_trunc_v4s1_of_concat_vectors_v4s32_v2s32 ; CHECK-LABEL: name: test_unmerge_values_s1_trunc_v4s1_of_concat_vectors_v4s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>) ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: [[TRUNC:%[0-9]+]]:_(<4 x s1>) = G_TRUNC [[CONCAT_VECTORS]](<4 x s32>) ; CHECK: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; CHECK: [[UV:%[0-9]+]]:_(s1), [[UV1:%[0-9]+]]:_(s1), [[UV2:%[0-9]+]]:_(s1), [[UV3:%[0-9]+]]:_(s1) = G_UNMERGE_VALUES [[TRUNC]](<4 x s1>) ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
; CHECK: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[UV]](s1) ; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[UV]](s32)
; CHECK: [[SEXT1:%[0-9]+]]:_(s32) = G_SEXT [[UV1]](s1) ; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C]](s32)
; CHECK: [[SEXT2:%[0-9]+]]:_(s32) = G_SEXT [[UV2]](s1) ; CHECK: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C]](s32)
; CHECK: [[SEXT3:%[0-9]+]]:_(s32) = G_SEXT [[UV3]](s1) ; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[UV1]](s32)
; CHECK: $vgpr0 = COPY [[SEXT]](s32) ; CHECK: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[COPY3]], [[C]](s32)
; CHECK: $vgpr1 = COPY [[SEXT1]](s32) ; CHECK: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[SHL1]], [[C]](s32)
; CHECK: $vgpr2 = COPY [[SEXT2]](s32) ; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY [[UV2]](s32)
; CHECK: $vgpr3 = COPY [[SEXT3]](s32) ; CHECK: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[COPY4]], [[C]](s32)
; CHECK: [[ASHR2:%[0-9]+]]:_(s32) = G_ASHR [[SHL2]], [[C]](s32)
; CHECK: [[COPY5:%[0-9]+]]:_(s32) = COPY [[UV3]](s32)
; CHECK: [[SHL3:%[0-9]+]]:_(s32) = G_SHL [[COPY5]], [[C]](s32)
; CHECK: [[ASHR3:%[0-9]+]]:_(s32) = G_ASHR [[SHL3]], [[C]](s32)
; CHECK: $vgpr0 = COPY [[ASHR]](s32)
; CHECK: $vgpr1 = COPY [[ASHR1]](s32)
; CHECK: $vgpr2 = COPY [[ASHR2]](s32)
; CHECK: $vgpr3 = COPY [[ASHR3]](s32)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1 %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3 %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1 %2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1
@ -258,8 +266,8 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s16_of_concat_vectors_v2s16_v2s16 ; CHECK-LABEL: name: test_unmerge_values_s16_of_concat_vectors_v2s16_v2s16
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[COPY]](<2 x s16>), [[COPY1]](<2 x s16>) ; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](<2 x s16>)
; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<4 x s16>) ; CHECK: [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY1]](<2 x s16>)
; CHECK: S_ENDPGM 0, implicit [[UV]](s16), implicit [[UV1]](s16), implicit [[UV2]](s16), implicit [[UV3]](s16) ; CHECK: S_ENDPGM 0, implicit [[UV]](s16), implicit [[UV1]](s16), implicit [[UV2]](s16), implicit [[UV3]](s16)
%0:_(<2 x s16>) = COPY $vgpr0 %0:_(<2 x s16>) = COPY $vgpr0
%1:_(<2 x s16>) = COPY $vgpr1 %1:_(<2 x s16>) = COPY $vgpr1
@ -275,8 +283,8 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s32_of_concat_vectors_v2s32_v2s32 ; CHECK-LABEL: name: test_unmerge_values_s32_of_concat_vectors_v2s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr1_vgpr2 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr1_vgpr2
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>) ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<4 x s32>) ; CHECK: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; CHECK: S_ENDPGM 0, implicit [[UV]](s32), implicit [[UV1]](s32), implicit [[UV2]](s32), implicit [[UV3]](s32) ; CHECK: S_ENDPGM 0, implicit [[UV]](s32), implicit [[UV1]](s32), implicit [[UV2]](s32), implicit [[UV3]](s32)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1 %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr1_vgpr2 %1:_(<2 x s32>) = COPY $vgpr1_vgpr2
@ -292,8 +300,8 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s32_of_concat_vectors_v2s64_v2s64 ; CHECK-LABEL: name: test_unmerge_values_s32_of_concat_vectors_v2s64_v2s64
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s64>) = G_CONCAT_VECTORS [[COPY]](<2 x s64>), [[COPY1]](<2 x s64>) ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<4 x s64>) ; CHECK: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
; CHECK: S_ENDPGM 0, implicit [[UV]](s32), implicit [[UV1]](s32), implicit [[UV2]](s32), implicit [[UV3]](s32), implicit [[UV4]](s32), implicit [[UV5]](s32), implicit [[UV6]](s32), implicit [[UV7]](s32) ; CHECK: S_ENDPGM 0, implicit [[UV]](s32), implicit [[UV1]](s32), implicit [[UV2]](s32), implicit [[UV3]](s32), implicit [[UV4]](s32), implicit [[UV5]](s32), implicit [[UV6]](s32), implicit [[UV7]](s32)
%0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 %0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 %1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
@ -309,10 +317,13 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s32_of_trunc_concat_vectors_v2s64_v2s64 ; CHECK-LABEL: name: test_unmerge_values_s32_of_trunc_concat_vectors_v2s64_v2s64
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s64>) = G_CONCAT_VECTORS [[COPY]](<2 x s64>), [[COPY1]](<2 x s64>) ; CHECK: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
; CHECK: [[TRUNC:%[0-9]+]]:_(<4 x s32>) = G_TRUNC [[CONCAT_VECTORS]](<4 x s64>) ; CHECK: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[UV]](s64)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[TRUNC]](<4 x s32>) ; CHECK: [[TRUNC1:%[0-9]+]]:_(s32) = G_TRUNC [[UV1]](s64)
; CHECK: S_ENDPGM 0, implicit [[UV]](s32), implicit [[UV1]](s32), implicit [[UV2]](s32), implicit [[UV3]](s32) ; CHECK: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
; CHECK: [[TRUNC2:%[0-9]+]]:_(s32) = G_TRUNC [[UV2]](s64)
; CHECK: [[TRUNC3:%[0-9]+]]:_(s32) = G_TRUNC [[UV3]](s64)
; CHECK: S_ENDPGM 0, implicit [[TRUNC]](s32), implicit [[TRUNC1]](s32), implicit [[TRUNC2]](s32), implicit [[TRUNC3]](s32)
%0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 %0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 %1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
%2:_(<4 x s64>) = G_CONCAT_VECTORS %0, %1 %2:_(<4 x s64>) = G_CONCAT_VECTORS %0, %1
@ -328,15 +339,13 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s64_of_sext_concat_vectors_v2s32_v2s32 ; CHECK-LABEL: name: test_unmerge_values_s64_of_sext_concat_vectors_v2s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>) ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<4 x s32>)
; CHECK: [[SEXT:%[0-9]+]]:_(s64) = G_SEXT [[UV]](s32) ; CHECK: [[SEXT:%[0-9]+]]:_(s64) = G_SEXT [[UV]](s32)
; CHECK: [[SEXT1:%[0-9]+]]:_(s64) = G_SEXT [[UV1]](s32) ; CHECK: [[SEXT1:%[0-9]+]]:_(s64) = G_SEXT [[UV1]](s32)
; CHECK: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; CHECK: [[SEXT2:%[0-9]+]]:_(s64) = G_SEXT [[UV2]](s32) ; CHECK: [[SEXT2:%[0-9]+]]:_(s64) = G_SEXT [[UV2]](s32)
; CHECK: [[SEXT3:%[0-9]+]]:_(s64) = G_SEXT [[UV3]](s32) ; CHECK: [[SEXT3:%[0-9]+]]:_(s64) = G_SEXT [[UV3]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s64>) = G_BUILD_VECTOR [[SEXT]](s64), [[SEXT1]](s64), [[SEXT2]](s64), [[SEXT3]](s64) ; CHECK: S_ENDPGM 0, implicit [[SEXT]](s64), implicit [[SEXT1]](s64), implicit [[SEXT2]](s64), implicit [[SEXT3]](s64)
; CHECK: [[UV4:%[0-9]+]]:_(s64), [[UV5:%[0-9]+]]:_(s64), [[UV6:%[0-9]+]]:_(s64), [[UV7:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<4 x s64>)
; CHECK: S_ENDPGM 0, implicit [[UV4]](s64), implicit [[UV5]](s64), implicit [[UV6]](s64), implicit [[UV7]](s64)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1 %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3 %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1 %2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1
@ -352,15 +361,13 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s64_of_zext_concat_vectors_v2s32_v2s32 ; CHECK-LABEL: name: test_unmerge_values_s64_of_zext_concat_vectors_v2s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>) ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<4 x s32>)
; CHECK: [[ZEXT:%[0-9]+]]:_(s64) = G_ZEXT [[UV]](s32) ; CHECK: [[ZEXT:%[0-9]+]]:_(s64) = G_ZEXT [[UV]](s32)
; CHECK: [[ZEXT1:%[0-9]+]]:_(s64) = G_ZEXT [[UV1]](s32) ; CHECK: [[ZEXT1:%[0-9]+]]:_(s64) = G_ZEXT [[UV1]](s32)
; CHECK: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; CHECK: [[ZEXT2:%[0-9]+]]:_(s64) = G_ZEXT [[UV2]](s32) ; CHECK: [[ZEXT2:%[0-9]+]]:_(s64) = G_ZEXT [[UV2]](s32)
; CHECK: [[ZEXT3:%[0-9]+]]:_(s64) = G_ZEXT [[UV3]](s32) ; CHECK: [[ZEXT3:%[0-9]+]]:_(s64) = G_ZEXT [[UV3]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s64>) = G_BUILD_VECTOR [[ZEXT]](s64), [[ZEXT1]](s64), [[ZEXT2]](s64), [[ZEXT3]](s64) ; CHECK: S_ENDPGM 0, implicit [[ZEXT]](s64), implicit [[ZEXT1]](s64), implicit [[ZEXT2]](s64), implicit [[ZEXT3]](s64)
; CHECK: [[UV4:%[0-9]+]]:_(s64), [[UV5:%[0-9]+]]:_(s64), [[UV6:%[0-9]+]]:_(s64), [[UV7:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<4 x s64>)
; CHECK: S_ENDPGM 0, implicit [[UV4]](s64), implicit [[UV5]](s64), implicit [[UV6]](s64), implicit [[UV7]](s64)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1 %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3 %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1 %2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1
@ -376,15 +383,13 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s64_of_anyext_concat_vectors_v2s32_v2s32 ; CHECK-LABEL: name: test_unmerge_values_s64_of_anyext_concat_vectors_v2s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>) ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<4 x s32>)
; CHECK: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[UV]](s32) ; CHECK: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[UV]](s32)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[UV1]](s32) ; CHECK: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[UV1]](s32)
; CHECK: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; CHECK: [[ANYEXT2:%[0-9]+]]:_(s64) = G_ANYEXT [[UV2]](s32) ; CHECK: [[ANYEXT2:%[0-9]+]]:_(s64) = G_ANYEXT [[UV2]](s32)
; CHECK: [[ANYEXT3:%[0-9]+]]:_(s64) = G_ANYEXT [[UV3]](s32) ; CHECK: [[ANYEXT3:%[0-9]+]]:_(s64) = G_ANYEXT [[UV3]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s64>) = G_BUILD_VECTOR [[ANYEXT]](s64), [[ANYEXT1]](s64), [[ANYEXT2]](s64), [[ANYEXT3]](s64) ; CHECK: S_ENDPGM 0, implicit [[ANYEXT]](s64), implicit [[ANYEXT1]](s64), implicit [[ANYEXT2]](s64), implicit [[ANYEXT3]](s64)
; CHECK: [[UV4:%[0-9]+]]:_(s64), [[UV5:%[0-9]+]]:_(s64), [[UV6:%[0-9]+]]:_(s64), [[UV7:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[BUILD_VECTOR]](<4 x s64>)
; CHECK: S_ENDPGM 0, implicit [[UV4]](s64), implicit [[UV5]](s64), implicit [[UV6]](s64), implicit [[UV7]](s64)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1 %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3 %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1 %2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1
@ -400,10 +405,13 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s8_of_trunc_v4s16_concat_vectors_v2s32_v2s32 ; CHECK-LABEL: name: test_unmerge_values_s8_of_trunc_v4s16_concat_vectors_v2s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>) ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: [[TRUNC:%[0-9]+]]:_(<4 x s16>) = G_TRUNC [[CONCAT_VECTORS]](<4 x s32>) ; CHECK: [[TRUNC:%[0-9]+]]:_(s8) = G_TRUNC [[UV]](s32)
; CHECK: [[UV:%[0-9]+]]:_(s8), [[UV1:%[0-9]+]]:_(s8), [[UV2:%[0-9]+]]:_(s8), [[UV3:%[0-9]+]]:_(s8), [[UV4:%[0-9]+]]:_(s8), [[UV5:%[0-9]+]]:_(s8), [[UV6:%[0-9]+]]:_(s8), [[UV7:%[0-9]+]]:_(s8) = G_UNMERGE_VALUES [[TRUNC]](<4 x s16>) ; CHECK: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[UV1]](s32)
; CHECK: S_ENDPGM 0, implicit [[UV]](s8), implicit [[UV1]](s8), implicit [[UV2]](s8), implicit [[UV3]](s8), implicit [[UV4]](s8), implicit [[UV5]](s8), implicit [[UV6]](s8), implicit [[UV7]](s8) ; CHECK: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; CHECK: [[TRUNC2:%[0-9]+]]:_(s8) = G_TRUNC [[UV2]](s32)
; CHECK: [[TRUNC3:%[0-9]+]]:_(s8) = G_TRUNC [[UV3]](s32)
; CHECK: S_ENDPGM 0, implicit [[TRUNC]](s8), implicit [[TRUNC1]](s8), implicit %6:_(s8), implicit %7:_(s8), implicit [[TRUNC2]](s8), implicit [[TRUNC3]](s8), implicit %10:_(s8), implicit %11:_(s8)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1 %0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3 %1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1 %2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1
@ -419,8 +427,8 @@ body: |
; CHECK-LABEL: name: test_unmerge_values_s16_of_anyext_v4s64_concat_vectors_v2s32_v2s32 ; CHECK-LABEL: name: test_unmerge_values_s16_of_anyext_v4s64_concat_vectors_v2s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1 ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3 ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>) ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<4 x s32>) ; CHECK: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; CHECK: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[UV]](s32) ; CHECK: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[UV]](s32)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[UV1]](s32) ; CHECK: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[UV1]](s32)
; CHECK: [[ANYEXT2:%[0-9]+]]:_(s64) = G_ANYEXT [[UV2]](s32) ; CHECK: [[ANYEXT2:%[0-9]+]]:_(s64) = G_ANYEXT [[UV2]](s32)

11
llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-phi.mir
View File

@ -523,7 +523,6 @@ body: |
; CHECK: liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4 ; CHECK: liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4
; CHECK: [[DEF:%[0-9]+]]:_(<16 x s32>) = G_IMPLICIT_DEF ; CHECK: [[DEF:%[0-9]+]]:_(<16 x s32>) = G_IMPLICIT_DEF
; CHECK: [[DEF1:%[0-9]+]]:_(<16 x s32>) = G_IMPLICIT_DEF ; CHECK: [[DEF1:%[0-9]+]]:_(<16 x s32>) = G_IMPLICIT_DEF
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<32 x s32>) = G_CONCAT_VECTORS [[DEF]](<16 x s32>), [[DEF1]](<16 x s32>)
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr4 ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr4
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0 ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[COPY]](s32), [[C]] ; CHECK: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[COPY]](s32), [[C]]
@ -531,8 +530,10 @@ body: |
; CHECK: G_BR %bb.2 ; CHECK: G_BR %bb.2
; CHECK: bb.1: ; CHECK: bb.1:
; CHECK: successors: %bb.2(0x80000000) ; CHECK: successors: %bb.2(0x80000000)
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32), [[UV12:%[0-9]+]]:_(s32), [[UV13:%[0-9]+]]:_(s32), [[UV14:%[0-9]+]]:_(s32), [[UV15:%[0-9]+]]:_(s32), [[UV16:%[0-9]+]]:_(s32), [[UV17:%[0-9]+]]:_(s32), [[UV18:%[0-9]+]]:_(s32), [[UV19:%[0-9]+]]:_(s32), [[UV20:%[0-9]+]]:_(s32), [[UV21:%[0-9]+]]:_(s32), [[UV22:%[0-9]+]]:_(s32), [[UV23:%[0-9]+]]:_(s32), [[UV24:%[0-9]+]]:_(s32), [[UV25:%[0-9]+]]:_(s32), [[UV26:%[0-9]+]]:_(s32), [[UV27:%[0-9]+]]:_(s32), [[UV28:%[0-9]+]]:_(s32), [[UV29:%[0-9]+]]:_(s32), [[UV30:%[0-9]+]]:_(s32), [[UV31:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<32 x s32>) ; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32), [[UV12:%[0-9]+]]:_(s32), [[UV13:%[0-9]+]]:_(s32), [[UV14:%[0-9]+]]:_(s32), [[UV15:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[DEF]](<16 x s32>)
; CHECK: [[UV32:%[0-9]+]]:_(s32), [[UV33:%[0-9]+]]:_(s32), [[UV34:%[0-9]+]]:_(s32), [[UV35:%[0-9]+]]:_(s32), [[UV36:%[0-9]+]]:_(s32), [[UV37:%[0-9]+]]:_(s32), [[UV38:%[0-9]+]]:_(s32), [[UV39:%[0-9]+]]:_(s32), [[UV40:%[0-9]+]]:_(s32), [[UV41:%[0-9]+]]:_(s32), [[UV42:%[0-9]+]]:_(s32), [[UV43:%[0-9]+]]:_(s32), [[UV44:%[0-9]+]]:_(s32), [[UV45:%[0-9]+]]:_(s32), [[UV46:%[0-9]+]]:_(s32), [[UV47:%[0-9]+]]:_(s32), [[UV48:%[0-9]+]]:_(s32), [[UV49:%[0-9]+]]:_(s32), [[UV50:%[0-9]+]]:_(s32), [[UV51:%[0-9]+]]:_(s32), [[UV52:%[0-9]+]]:_(s32), [[UV53:%[0-9]+]]:_(s32), [[UV54:%[0-9]+]]:_(s32), [[UV55:%[0-9]+]]:_(s32), [[UV56:%[0-9]+]]:_(s32), [[UV57:%[0-9]+]]:_(s32), [[UV58:%[0-9]+]]:_(s32), [[UV59:%[0-9]+]]:_(s32), [[UV60:%[0-9]+]]:_(s32), [[UV61:%[0-9]+]]:_(s32), [[UV62:%[0-9]+]]:_(s32), [[UV63:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[CONCAT_VECTORS]](<32 x s32>) ; CHECK: [[UV16:%[0-9]+]]:_(s32), [[UV17:%[0-9]+]]:_(s32), [[UV18:%[0-9]+]]:_(s32), [[UV19:%[0-9]+]]:_(s32), [[UV20:%[0-9]+]]:_(s32), [[UV21:%[0-9]+]]:_(s32), [[UV22:%[0-9]+]]:_(s32), [[UV23:%[0-9]+]]:_(s32), [[UV24:%[0-9]+]]:_(s32), [[UV25:%[0-9]+]]:_(s32), [[UV26:%[0-9]+]]:_(s32), [[UV27:%[0-9]+]]:_(s32), [[UV28:%[0-9]+]]:_(s32), [[UV29:%[0-9]+]]:_(s32), [[UV30:%[0-9]+]]:_(s32), [[UV31:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[DEF1]](<16 x s32>)
; CHECK: [[UV32:%[0-9]+]]:_(s32), [[UV33:%[0-9]+]]:_(s32), [[UV34:%[0-9]+]]:_(s32), [[UV35:%[0-9]+]]:_(s32), [[UV36:%[0-9]+]]:_(s32), [[UV37:%[0-9]+]]:_(s32), [[UV38:%[0-9]+]]:_(s32), [[UV39:%[0-9]+]]:_(s32), [[UV40:%[0-9]+]]:_(s32), [[UV41:%[0-9]+]]:_(s32), [[UV42:%[0-9]+]]:_(s32), [[UV43:%[0-9]+]]:_(s32), [[UV44:%[0-9]+]]:_(s32), [[UV45:%[0-9]+]]:_(s32), [[UV46:%[0-9]+]]:_(s32), [[UV47:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[DEF]](<16 x s32>)
; CHECK: [[UV48:%[0-9]+]]:_(s32), [[UV49:%[0-9]+]]:_(s32), [[UV50:%[0-9]+]]:_(s32), [[UV51:%[0-9]+]]:_(s32), [[UV52:%[0-9]+]]:_(s32), [[UV53:%[0-9]+]]:_(s32), [[UV54:%[0-9]+]]:_(s32), [[UV55:%[0-9]+]]:_(s32), [[UV56:%[0-9]+]]:_(s32), [[UV57:%[0-9]+]]:_(s32), [[UV58:%[0-9]+]]:_(s32), [[UV59:%[0-9]+]]:_(s32), [[UV60:%[0-9]+]]:_(s32), [[UV61:%[0-9]+]]:_(s32), [[UV62:%[0-9]+]]:_(s32), [[UV63:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[DEF1]](<16 x s32>)
; CHECK: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[UV]], [[UV32]] ; CHECK: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[UV]], [[UV32]]
; CHECK: [[ADD1:%[0-9]+]]:_(s32) = G_ADD [[UV1]], [[UV33]] ; CHECK: [[ADD1:%[0-9]+]]:_(s32) = G_ADD [[UV1]], [[UV33]]
; CHECK: [[ADD2:%[0-9]+]]:_(s32) = G_ADD [[UV2]], [[UV34]] ; CHECK: [[ADD2:%[0-9]+]]:_(s32) = G_ADD [[UV2]], [[UV34]]
@ -571,8 +572,8 @@ body: |
; CHECK: bb.2: ; CHECK: bb.2:
; CHECK: [[PHI:%[0-9]+]]:_(<16 x s32>) = G_PHI [[DEF]](<16 x s32>), %bb.0, [[UV64]](<16 x s32>), %bb.1 ; CHECK: [[PHI:%[0-9]+]]:_(<16 x s32>) = G_PHI [[DEF]](<16 x s32>), %bb.0, [[UV64]](<16 x s32>), %bb.1
; CHECK: [[PHI1:%[0-9]+]]:_(<16 x s32>) = G_PHI [[DEF1]](<16 x s32>), %bb.0, [[UV65]](<16 x s32>), %bb.1 ; CHECK: [[PHI1:%[0-9]+]]:_(<16 x s32>) = G_PHI [[DEF1]](<16 x s32>), %bb.0, [[UV65]](<16 x s32>), %bb.1
; CHECK: [[CONCAT_VECTORS1:%[0-9]+]]:_(<32 x s32>) = G_CONCAT_VECTORS [[PHI]](<16 x s32>), [[PHI1]](<16 x s32>) ; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<32 x s32>) = G_CONCAT_VECTORS [[PHI]](<16 x s32>), [[PHI1]](<16 x s32>)
; CHECK: S_SETPC_B64 undef $sgpr30_sgpr31, implicit [[CONCAT_VECTORS1]](<32 x s32>) ; CHECK: S_SETPC_B64 undef $sgpr30_sgpr31, implicit [[CONCAT_VECTORS]](<32 x s32>)
bb.0: bb.0:
successors: %bb.1, %bb.2 successors: %bb.1, %bb.2
liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4 liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4