intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-02-04 20:00:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

[GlobalISel] Extend CombinerHelper::matchConstantOp() to match constant splat vectors.

Browse Source 
This allows the "x op 0 -> x" fold to optimize vector constant RHSs.

Differential Revision: https://reviews.llvm.org/D110802
This commit is contained in:
Amara Emerson
2021-09-30 00:20:56 -07:00
parent fdcbb540fc
commit ca8316b704
3 changed files with 40 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
View File

@@ -2340,9 +2340,9 @@ bool CombinerHelper::matchEqualDefs(const MachineOperand &MOP1,
bool CombinerHelper::matchConstantOp(const MachineOperand &MOP, int64_t C) {
if (!MOP.isReg())
return false;
// MIPatternMatch doesn't let us look through G_ZEXT etc.
auto ValAndVReg = getIConstantVRegValWithLookThrough(MOP.getReg(), MRI);
return ValAndVReg && ValAndVReg->Value == C;
auto *MI = MRI.getVRegDef(MOP.getReg());
auto MaybeCst = isConstantOrConstantSplatVector(*MI, MRI);
return MaybeCst.hasValue() && MaybeCst->getSExtValue() == C;
}
bool CombinerHelper::replaceSingleDefInstWithOperand(MachineInstr &MI,

18
llvm/test/CodeGen/AArch64/GlobalISel/combine-mul.mir
View File

@@ -31,15 +31,12 @@ machineFunctionInfo: {}
body: |
bb.0:
liveins: $q0
; Currently not implemented.
; CHECK-LABEL: name: mul_vector_by_zero
; CHECK: liveins: $q0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[C]](s32), [[C]](s32), [[C]](s32), [[C]](s32)
; CHECK-NEXT: [[MUL:%[0-9]+]]:_(<4 x s32>) = G_MUL [[COPY]], [[BUILD_VECTOR]]
; CHECK-NEXT: $q0 = COPY [[MUL]](<4 x s32>)
; CHECK-NEXT: $q0 = COPY [[BUILD_VECTOR]](<4 x s32>)
%0:_(<4 x s32>) = COPY $q0
%1:_(s32) = G_CONSTANT i32 0
%2:_(<4 x s32>) = G_BUILD_VECTOR %1(s32), %1(s32), %1(s32), %1(s32)
@@ -76,15 +73,11 @@ machineFunctionInfo: {}
body: |
bb.0:
liveins: $q0
; Currently not implemented.
; CHECK-LABEL: name: mul_vector_by_one
; CHECK: liveins: $q0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[C]](s32), [[C]](s32), [[C]](s32), [[C]](s32)
; CHECK-NEXT: [[MUL:%[0-9]+]]:_(<4 x s32>) = G_MUL [[COPY]], [[BUILD_VECTOR]]
; CHECK-NEXT: $q0 = COPY [[MUL]](<4 x s32>)
; CHECK-NEXT: $q0 = COPY [[COPY]](<4 x s32>)
%0:_(<4 x s32>) = COPY $q0
%1:_(s32) = G_CONSTANT i32 1
%2:_(<4 x s32>) = G_BUILD_VECTOR %1(s32), %1(s32), %1(s32), %1(s32)
@@ -123,15 +116,14 @@ machineFunctionInfo: {}
body: |
bb.0:
liveins: $q0
; Currently not implemented.
; CHECK-LABEL: name: mul_vector_by_neg_one
; CHECK: liveins: $q0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
; CHECK-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[C]](s32), [[C]](s32), [[C]](s32), [[C]](s32)
; CHECK-NEXT: [[MUL:%[0-9]+]]:_(<4 x s32>) = G_MUL [[COPY]], [[BUILD_VECTOR]]
; CHECK-NEXT: $q0 = COPY [[MUL]](<4 x s32>)
; CHECK-NEXT: [[SUB:%[0-9]+]]:_(<4 x s32>) = G_SUB [[BUILD_VECTOR]], [[COPY]]
; CHECK-NEXT: $q0 = COPY [[SUB]](<4 x s32>)
%0:_(<4 x s32>) = COPY $q0
%1:_(s32) = G_CONSTANT i32 -1
%2:_(<4 x s32>) = G_BUILD_VECTOR %1(s32), %1(s32), %1(s32), %1(s32)

32
llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-trivial-arith.mir
View File

@@ -378,3 +378,35 @@ body: |
$w0 = COPY %rot(s32)
RET_ReallyLR implicit $w0
...
---
name: lshr_of_vec_zero
body: |
bb.1:
liveins: $q0
; CHECK-LABEL: name: lshr_of_vec_zero
; CHECK: [[COPY:%[0-9]+]]:_(<8 x s16>) = COPY $q0
; CHECK-NEXT: $q0 = COPY [[COPY]](<8 x s16>)
; CHECK-NEXT: RET_ReallyLR implicit $q0
%0:_(<8 x s16>) = COPY $q0
%5:_(s16) = G_CONSTANT i16 0
%zero_vec:_(<8 x s16>) = G_BUILD_VECTOR %5(s16), %5(s16), %5(s16), %5(s16), %5(s16), %5(s16), %5(s16), %5(s16)
%shift:_(<8 x s16>) = G_LSHR %0, %zero_vec(<8 x s16>)
$q0 = COPY %shift(<8 x s16>)
RET_ReallyLR implicit $q0
...
---
name: ptradd_of_vec_zero
body: |
bb.1:
liveins: $q0
; CHECK-LABEL: name: ptradd_of_vec_zero
; CHECK: [[COPY:%[0-9]+]]:_(<2 x p0>) = COPY $q0
; CHECK-NEXT: $q0 = COPY [[COPY]](<2 x p0>)
; CHECK-NEXT: RET_ReallyLR implicit $q0
%0:_(<2 x p0>) = COPY $q0
%5:_(s64) = G_CONSTANT i64 0
%zero_vec:_(<2 x s64>) = G_BUILD_VECTOR %5(s64), %5(s64)
%ptr:_(<2 x p0>) = G_PTR_ADD %0, %zero_vec(<2 x s64>)
$q0 = COPY %ptr(<2 x p0>)
RET_ReallyLR implicit $q0
...