forked from OSchip/llvm-project
173 lines
6.1 KiB
YAML
173 lines
6.1 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -mtriple=aarch64-- -run-pass=instruction-select -O1 -verify-machineinstrs %s -o - | FileCheck %s
|
|
---
|
|
name: splat_4xi32
|
|
alignment: 2
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.1.entry:
|
|
liveins: $w0
|
|
|
|
; CHECK-LABEL: name: splat_4xi32
|
|
; CHECK: liveins: $w0
|
|
; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
|
|
; CHECK: [[DUPv4i32gpr:%[0-9]+]]:fpr128 = DUPv4i32gpr [[COPY]]
|
|
; CHECK: $q0 = COPY [[DUPv4i32gpr]]
|
|
; CHECK: RET_ReallyLR implicit $q0
|
|
%0:gpr(s32) = COPY $w0
|
|
%2:fpr(<4 x s32>) = G_IMPLICIT_DEF
|
|
%3:gpr(s32) = G_CONSTANT i32 0
|
|
%5:fpr(<4 x s32>) = G_BUILD_VECTOR %3(s32), %3(s32), %3(s32), %3(s32)
|
|
%1:fpr(<4 x s32>) = G_INSERT_VECTOR_ELT %2, %0(s32), %3(s32)
|
|
%4:fpr(<4 x s32>) = G_SHUFFLE_VECTOR %1(<4 x s32>), %2, %5(<4 x s32>)
|
|
$q0 = COPY %4(<4 x s32>)
|
|
RET_ReallyLR implicit $q0
|
|
|
|
...
|
|
---
|
|
name: splat_2xi64
|
|
alignment: 2
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.1.entry:
|
|
liveins: $x0
|
|
|
|
; CHECK-LABEL: name: splat_2xi64
|
|
; CHECK: liveins: $x0
|
|
; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
|
|
; CHECK: [[DUPv2i64gpr:%[0-9]+]]:fpr128 = DUPv2i64gpr [[COPY]]
|
|
; CHECK: $q0 = COPY [[DUPv2i64gpr]]
|
|
; CHECK: RET_ReallyLR implicit $q0
|
|
%0:gpr(s64) = COPY $x0
|
|
%2:fpr(<2 x s64>) = G_IMPLICIT_DEF
|
|
%3:gpr(s32) = G_CONSTANT i32 0
|
|
%5:fpr(<2 x s32>) = G_BUILD_VECTOR %3(s32), %3(s32)
|
|
%1:fpr(<2 x s64>) = G_INSERT_VECTOR_ELT %2, %0(s64), %3(s32)
|
|
%4:fpr(<2 x s64>) = G_SHUFFLE_VECTOR %1(<2 x s64>), %2, %5(<2 x s32>)
|
|
$q0 = COPY %4(<2 x s64>)
|
|
RET_ReallyLR implicit $q0
|
|
|
|
...
|
|
---
|
|
name: splat_4xf32
|
|
alignment: 2
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.1.entry:
|
|
liveins: $s0
|
|
|
|
; CHECK-LABEL: name: splat_4xf32
|
|
; CHECK: liveins: $s0
|
|
; CHECK: [[COPY:%[0-9]+]]:fpr32 = COPY $s0
|
|
; CHECK: [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
|
|
; CHECK: [[INSERT_SUBREG:%[0-9]+]]:fpr128 = INSERT_SUBREG [[DEF]], [[COPY]], %subreg.ssub
|
|
; CHECK: [[DUPv4i32lane:%[0-9]+]]:fpr128 = DUPv4i32lane [[INSERT_SUBREG]], 0
|
|
; CHECK: $q0 = COPY [[DUPv4i32lane]]
|
|
; CHECK: RET_ReallyLR implicit $q0
|
|
%0:fpr(s32) = COPY $s0
|
|
%2:fpr(<4 x s32>) = G_IMPLICIT_DEF
|
|
%3:gpr(s32) = G_CONSTANT i32 0
|
|
%5:fpr(<4 x s32>) = G_BUILD_VECTOR %3(s32), %3(s32), %3(s32), %3(s32)
|
|
%1:fpr(<4 x s32>) = G_INSERT_VECTOR_ELT %2, %0(s32), %3(s32)
|
|
%4:fpr(<4 x s32>) = G_SHUFFLE_VECTOR %1(<4 x s32>), %2, %5(<4 x s32>)
|
|
$q0 = COPY %4(<4 x s32>)
|
|
RET_ReallyLR implicit $q0
|
|
|
|
...
|
|
---
|
|
name: splat_2xf64
|
|
alignment: 2
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.1.entry:
|
|
liveins: $d0
|
|
|
|
; CHECK-LABEL: name: splat_2xf64
|
|
; CHECK: liveins: $d0
|
|
; CHECK: [[COPY:%[0-9]+]]:fpr64 = COPY $d0
|
|
; CHECK: [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
|
|
; CHECK: [[INSERT_SUBREG:%[0-9]+]]:fpr128 = INSERT_SUBREG [[DEF]], [[COPY]], %subreg.dsub
|
|
; CHECK: [[DUPv2i64lane:%[0-9]+]]:fpr128 = DUPv2i64lane [[INSERT_SUBREG]], 0
|
|
; CHECK: $q0 = COPY [[DUPv2i64lane]]
|
|
; CHECK: RET_ReallyLR implicit $q0
|
|
%0:fpr(s64) = COPY $d0
|
|
%2:fpr(<2 x s64>) = G_IMPLICIT_DEF
|
|
%3:gpr(s32) = G_CONSTANT i32 0
|
|
%5:fpr(<2 x s32>) = G_BUILD_VECTOR %3(s32), %3(s32)
|
|
%1:fpr(<2 x s64>) = G_INSERT_VECTOR_ELT %2, %0(s64), %3(s32)
|
|
%4:fpr(<2 x s64>) = G_SHUFFLE_VECTOR %1(<2 x s64>), %2, %5(<2 x s32>)
|
|
$q0 = COPY %4(<2 x s64>)
|
|
RET_ReallyLR implicit $q0
|
|
|
|
...
|
|
---
|
|
name: splat_2xf64_copies
|
|
alignment: 2
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.1.entry:
|
|
liveins: $d0
|
|
|
|
; This test is exactly the same as splat_2xf64, except it adds two copies.
|
|
; These copies shouldn't get in the way of matching the dup pattern.
|
|
; CHECK-LABEL: name: splat_2xf64_copies
|
|
; CHECK: liveins: $d0
|
|
; CHECK: [[COPY:%[0-9]+]]:fpr64 = COPY $d0
|
|
; CHECK: [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
|
|
; CHECK: [[INSERT_SUBREG:%[0-9]+]]:fpr128 = INSERT_SUBREG [[DEF]], [[COPY]], %subreg.dsub
|
|
; CHECK: [[DUPv2i64lane:%[0-9]+]]:fpr128 = DUPv2i64lane [[INSERT_SUBREG]], 0
|
|
; CHECK: $q0 = COPY [[DUPv2i64lane]]
|
|
; CHECK: RET_ReallyLR implicit $q0
|
|
%0:fpr(s64) = COPY $d0
|
|
%2:fpr(<2 x s64>) = G_IMPLICIT_DEF
|
|
%6:fpr(<2 x s64>) = COPY %2
|
|
%3:gpr(s32) = G_CONSTANT i32 0
|
|
%5:fpr(<2 x s32>) = G_BUILD_VECTOR %3(s32), %3(s32)
|
|
%1:fpr(<2 x s64>) = G_INSERT_VECTOR_ELT %6, %0(s64), %3(s32)
|
|
%7:fpr(<2 x s64>) = COPY %1
|
|
%4:fpr(<2 x s64>) = G_SHUFFLE_VECTOR %7(<2 x s64>), %2, %5(<2 x s32>)
|
|
$q0 = COPY %4(<2 x s64>)
|
|
RET_ReallyLR implicit $q0
|
|
|
|
...
|
|
---
|
|
name: not_all_zeros
|
|
alignment: 2
|
|
legalized: true
|
|
regBankSelected: true
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.1.entry:
|
|
liveins: $x0
|
|
; Make sure that we don't do the optimization when it's not all zeroes.
|
|
; CHECK-LABEL: name: not_all_zeros
|
|
; CHECK: liveins: $x0
|
|
; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
|
|
; CHECK: [[DEF:%[0-9]+]]:fpr128 = IMPLICIT_DEF
|
|
; CHECK: [[INSvi64gpr:%[0-9]+]]:fpr128 = INSvi64gpr [[DEF]], 0, [[COPY]]
|
|
; CHECK: [[ADRP:%[0-9]+]]:gpr64common = ADRP target-flags(aarch64-page) %const.0
|
|
; CHECK: [[LDRQui:%[0-9]+]]:fpr128 = LDRQui [[ADRP]], target-flags(aarch64-pageoff, aarch64-nc) %const.0
|
|
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:qq = REG_SEQUENCE [[INSvi64gpr]], %subreg.qsub0, [[DEF]], %subreg.qsub1
|
|
; CHECK: [[TBLv16i8Two:%[0-9]+]]:fpr128 = TBLv16i8Two [[REG_SEQUENCE]], [[LDRQui]]
|
|
; CHECK: $q0 = COPY [[TBLv16i8Two]]
|
|
; CHECK: RET_ReallyLR implicit $q0
|
|
%0:gpr(s64) = COPY $x0
|
|
%2:fpr(<2 x s64>) = G_IMPLICIT_DEF
|
|
%3:gpr(s32) = G_CONSTANT i32 0
|
|
%6:gpr(s32) = G_CONSTANT i32 1
|
|
%5:fpr(<2 x s32>) = G_BUILD_VECTOR %3(s32), %6(s32)
|
|
%1:fpr(<2 x s64>) = G_INSERT_VECTOR_ELT %2, %0(s64), %3(s32)
|
|
%4:fpr(<2 x s64>) = G_SHUFFLE_VECTOR %1(<2 x s64>), %2, %5(<2 x s32>)
|
|
$q0 = COPY %4(<2 x s64>)
|
|
RET_ReallyLR implicit $q0
|