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

GlobalISel: Partially implement lower for G_INSERT 

llvm-svn: 373946
This commit is contained in:
Matt Arsenault 2019-10-07 19:13:27 +00:00
parent 1237aa2996
commit 4bcdcad91b
4 changed files with 193 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
View File

@ -231,6 +231,7 @@ public:
LegalizeResult lowerShuffleVector(MachineInstr &MI);
LegalizeResult lowerDynStackAlloc(MachineInstr &MI);
LegalizeResult lowerExtract(MachineInstr &MI);
LegalizeResult lowerInsert(MachineInstr &MI);
private:
MachineRegisterInfo &MRI;

41
llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
View File

@ -2249,6 +2249,8 @@ LegalizerHelper::lower(MachineInstr &MI, unsigned TypeIdx, LLT Ty) {
return lowerDynStackAlloc(MI);
case G_EXTRACT:
return lowerExtract(MI);
case G_INSERT:
return lowerInsert(MI);
}
}
@ -4134,3 +4136,42 @@ LegalizerHelper::lowerExtract(MachineInstr &MI) {
return UnableToLegalize;
}
LegalizerHelper::LegalizeResult LegalizerHelper::lowerInsert(MachineInstr &MI) {
Register Dst = MI.getOperand(0).getReg();
Register Src = MI.getOperand(1).getReg();
Register InsertSrc = MI.getOperand(2).getReg();
uint64_t Offset = MI.getOperand(3).getImm();
LLT DstTy = MRI.getType(Src);
LLT InsertTy = MRI.getType(InsertSrc);
if (InsertTy.isScalar() &&
(DstTy.isScalar() ||
(DstTy.isVector() && DstTy.getElementType() == InsertTy))) {
LLT IntDstTy = DstTy;
if (!DstTy.isScalar()) {
IntDstTy = LLT::scalar(DstTy.getSizeInBits());
Src = MIRBuilder.buildBitcast(IntDstTy, Src).getReg(0);
}
Register ExtInsSrc = MIRBuilder.buildZExt(IntDstTy, InsertSrc).getReg(0);
if (Offset != 0) {
auto ShiftAmt = MIRBuilder.buildConstant(IntDstTy, Offset);
ExtInsSrc = MIRBuilder.buildShl(IntDstTy, ExtInsSrc, ShiftAmt).getReg(0);
}
APInt MaskVal = ~APInt::getBitsSet(DstTy.getSizeInBits(), Offset,
InsertTy.getSizeInBits());
auto Mask = MIRBuilder.buildConstant(IntDstTy, MaskVal);
auto MaskedSrc = MIRBuilder.buildAnd(IntDstTy, Src, Mask);
auto Or = MIRBuilder.buildOr(IntDstTy, MaskedSrc, ExtInsSrc);
MIRBuilder.buildBitcast(Dst, Or);
MI.eraseFromParent();
return Legalized;
}
return UnableToLegalize;
}

10
llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
View File

@ -912,13 +912,9 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_,
unsigned LitTyIdx = Op == G_EXTRACT ? 0 : 1;
// FIXME: Doesn't handle extract of illegal sizes.
auto &Builder = getActionDefinitionsBuilder(Op);
// FIXME: Cleanup when G_INSERT lowering implemented.
if (Op == G_EXTRACT)
Builder.lowerIf(all(typeIs(LitTyIdx, S16), sizeIs(BigTyIdx, 32)));
Builder
getActionDefinitionsBuilder(Op)
.lowerIf(all(typeIs(LitTyIdx, S16), sizeIs(BigTyIdx, 32)))
// FIXME: Multiples of 16 should not be legal.
.legalIf([=](const LegalityQuery &Query) {
const LLT BigTy = Query.Types[BigTyIdx];
const LLT LitTy = Query.Types[LitTyIdx];

154
llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-insert.mir
View File

@ -762,15 +762,48 @@ body: |
; CHECK-LABEL: name: test_insert_v2s16_s16_offset0
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; CHECK: [[INSERT:%[0-9]+]]:_(<2 x s16>) = G_INSERT [[COPY]], [[TRUNC]](s16), 0
; CHECK: $vgpr0 = COPY [[INSERT]](<2 x s16>)
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 -65536
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[BITCAST]], [[C1]]
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND1]], [[AND]]
; CHECK: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
; CHECK: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %1
%3:_(<2 x s16>) = G_INSERT %0, %2, 0
$vgpr0 = COPY %3
...
---
name: test_insert_v2s16_s16_offset1
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: test_insert_v2s16_s16_offset1
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
; CHECK: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 -65535
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[BITCAST]], [[C2]]
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND1]], [[SHL]]
; CHECK: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
; CHECK: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %1
%3:_(<2 x s16>) = G_INSERT %0, %2, 1
$vgpr0 = COPY %3
...
---
name: test_insert_v2s16_s16_offset16
body: |
@ -780,9 +813,17 @@ body: |
; CHECK-LABEL: name: test_insert_v2s16_s16_offset16
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; CHECK: [[INSERT:%[0-9]+]]:_(<2 x s16>) = G_INSERT [[COPY]], [[TRUNC]](s16), 16
; CHECK: $vgpr0 = COPY [[INSERT]](<2 x s16>)
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
; CHECK: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[BITCAST]], [[C2]]
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND1]], [[SHL]]
; CHECK: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
; CHECK: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %1
@ -1247,3 +1288,104 @@ body: |
%3:_(s64) = G_INSERT %0, %2, 48
$vgpr0_vgpr1 = COPY %3
...
---
name: test_insert_s32_s16_offset0
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: test_insert_s32_s16_offset0
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 -65536
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY1]], [[C1]]
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND1]], [[AND]]
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[OR]](s32)
; CHECK: $vgpr0 = COPY [[BITCAST]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %1
%3:_(s32) = G_INSERT %1, %2, 0
$vgpr0 = COPY %3
...
---
name: test_insert_s32_s16_offset1
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: test_insert_s32_s16_offset1
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
; CHECK: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 -65535
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY1]], [[C2]]
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND1]], [[SHL]]
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[OR]](s32)
; CHECK: $vgpr0 = COPY [[BITCAST]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %1
%3:_(s32) = G_INSERT %1, %2, 1
$vgpr0 = COPY %3
...
---
name: test_insert_s32_s16_offset8
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: test_insert_s32_s16_offset8
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
; CHECK: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 -65281
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY1]], [[C2]]
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND1]], [[SHL]]
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[OR]](s32)
; CHECK: $vgpr0 = COPY [[BITCAST]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %1
%3:_(s32) = G_INSERT %1, %2, 8
$vgpr0 = COPY %3
...
---
name: test_insert_s32_s16_offset16
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: test_insert_s32_s16_offset16
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C1]](s32)
; CHECK: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY1]], [[C2]]
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND1]], [[SHL]]
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[OR]](s32)
; CHECK: $vgpr0 = COPY [[BITCAST]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %1
%3:_(s32) = G_INSERT %1, %2, 16
$vgpr0 = COPY %3
...