[AArch64][GlobalISel] Make <8 x s16> for G_INSERT_VECTOR_ELT legal.

This commit is contained in:
Amara Emerson 2020-09-24 13:06:03 -07:00
parent 6f10998ad8
commit ade6fa46f9
3 changed files with 107 additions and 5 deletions

View File

@ -597,11 +597,7 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
.minScalarOrElt(0, s8); // Worst case, we need at least s8.
getActionDefinitionsBuilder(G_INSERT_VECTOR_ELT)
.legalIf([=](const LegalityQuery &Query) {
const LLT &VecTy = Query.Types[0];
// TODO: Support s8 and s16
return VecTy == v2s32 || VecTy == v4s32 || VecTy == v2s64;
});
.legalIf(typeInSet(0, {v8s16, v2s32, v4s32, v2s64}));
getActionDefinitionsBuilder(G_BUILD_VECTOR)
.legalFor({{v8s8, s8},

View File

@ -0,0 +1,79 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=aarch64-linux-gnu -O0 -run-pass=legalizer %s -o - -global-isel-abort=1 | FileCheck %s
---
name: v8s16
body: |
bb.0:
liveins: $q0
; CHECK-LABEL: name: v8s16
; CHECK: [[COPY:%[0-9]+]]:_(<8 x s16>) = COPY $q0
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK: %val:_(s16) = G_CONSTANT i16 42
; CHECK: [[IVEC:%[0-9]+]]:_(<8 x s16>) = G_INSERT_VECTOR_ELT [[COPY]], %val(s16), [[C]](s32)
; CHECK: $q0 = COPY [[IVEC]](<8 x s16>)
; CHECK: RET_ReallyLR
%0:_(<8 x s16>) = COPY $q0
%1:_(s32) = G_CONSTANT i32 1
%val:_(s16) = G_CONSTANT i16 42
%2:_(<8 x s16>) = G_INSERT_VECTOR_ELT %0(<8 x s16>), %val(s16), %1(s32)
$q0 = COPY %2(<8 x s16>)
RET_ReallyLR
...
---
name: v2s32
body: |
bb.0:
liveins: $q0
; CHECK-LABEL: name: v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $d0
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK: %val:_(s32) = G_CONSTANT i32 42
; CHECK: [[IVEC:%[0-9]+]]:_(<2 x s32>) = G_INSERT_VECTOR_ELT [[COPY]], %val(s32), [[C]](s32)
; CHECK: $d0 = COPY [[IVEC]](<2 x s32>)
; CHECK: RET_ReallyLR
%0:_(<2 x s32>) = COPY $d0
%1:_(s32) = G_CONSTANT i32 1
%val:_(s32) = G_CONSTANT i32 42
%2:_(<2 x s32>) = G_INSERT_VECTOR_ELT %0(<2 x s32>), %val(s32), %1(s32)
$d0 = COPY %2(<2 x s32>)
RET_ReallyLR
...
---
name: v4s32
body: |
bb.0:
liveins: $q0
; CHECK-LABEL: name: v4s32
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK: %val:_(s32) = G_CONSTANT i32 42
; CHECK: [[IVEC:%[0-9]+]]:_(<4 x s32>) = G_INSERT_VECTOR_ELT [[COPY]], %val(s32), [[C]](s32)
; CHECK: $q0 = COPY [[IVEC]](<4 x s32>)
; CHECK: RET_ReallyLR
%0:_(<4 x s32>) = COPY $q0
%1:_(s32) = G_CONSTANT i32 1
%val:_(s32) = G_CONSTANT i32 42
%2:_(<4 x s32>) = G_INSERT_VECTOR_ELT %0(<4 x s32>), %val(s32), %1(s32)
$q0 = COPY %2(<4 x s32>)
RET_ReallyLR
...
---
name: v2s64
body: |
bb.0:
liveins: $q0
; CHECK-LABEL: name: v2s64
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK: %val:_(s64) = G_CONSTANT i64 42
; CHECK: [[IVEC:%[0-9]+]]:_(<2 x s64>) = G_INSERT_VECTOR_ELT [[COPY]], %val(s64), [[C]](s32)
; CHECK: $q0 = COPY [[IVEC]](<2 x s64>)
; CHECK: RET_ReallyLR
%0:_(<2 x s64>) = COPY $q0
%1:_(s32) = G_CONSTANT i32 1
%val:_(s64) = G_CONSTANT i64 42
%2:_(<2 x s64>) = G_INSERT_VECTOR_ELT %0(<2 x s64>), %val(s64), %1(s32)
$q0 = COPY %2(<2 x s64>)
RET_ReallyLR
...

View File

@ -1,6 +1,33 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -verify-machineinstrs -mtriple aarch64-unknown-unknown -run-pass=instruction-select %s -o - | FileCheck %s
---
name: v8s16_fpr
alignment: 4
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.0:
liveins: $q1, $h0
; CHECK-LABEL: name: v8s16_fpr
; CHECK: liveins: $q1, $h0
; CHECK: [[COPY:%[0-9]+]]:fpr16 = COPY $h0
; CHECK: [[COPY1:%[0-9]+]]:fpr128 = COPY $q1
; CHECK: [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
; CHECK: [[INSERT_SUBREG:%[0-9]+]]:fpr128 = INSERT_SUBREG [[DEF]], [[COPY]], %subreg.hsub
; CHECK: [[INSvi16lane:%[0-9]+]]:fpr128 = INSvi16lane [[COPY1]], 1, [[INSERT_SUBREG]], 0
; CHECK: $q0 = COPY [[INSvi16lane]]
; CHECK: RET_ReallyLR implicit $q0
%0:fpr(s16) = COPY $h0
%1:fpr(<8 x s16>) = COPY $q1
%3:gpr(s32) = G_CONSTANT i32 1
%2:fpr(<8 x s16>) = G_INSERT_VECTOR_ELT %1, %0(s16), %3(s32)
$q0 = COPY %2(<8 x s16>)
RET_ReallyLR implicit $q0
...
---
name: v4s32_fpr
alignment: 4
legalized: true