llvm-project/llvm/test/CodeGen/AArch64/GlobalISel/legalize-fexp2.mir

253 lines
13 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -verify-machineinstrs -mtriple aarch64--- \
# RUN: -run-pass=legalizer -mattr=+fullfp16 -global-isel %s -o - \
# RUN: | FileCheck %s
...
---
name: test_v4f16.exp2
alignment: 4
tracksRegLiveness: true
body: |
bb.0:
liveins: $d0
; CHECK-LABEL: name: test_v4f16.exp2
; CHECK: liveins: $d0
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $d0
; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
; CHECK: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[UV]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY1]](s32)
; CHECK: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[UV1]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT1]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY2]](s32)
; CHECK: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[UV2]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT2]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY3]](s32)
; CHECK: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[UV3]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT3]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC3:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY4]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[FPTRUNC]](s16), [[FPTRUNC1]](s16), [[FPTRUNC2]](s16), [[FPTRUNC3]](s16)
; CHECK: $d0 = COPY [[BUILD_VECTOR]](<4 x s16>)
; CHECK: RET_ReallyLR implicit $d0
%0:_(<4 x s16>) = COPY $d0
%1:_(<4 x s16>) = G_FEXP2 %0
$d0 = COPY %1(<4 x s16>)
RET_ReallyLR implicit $d0
...
---
name: test_v8f16.exp2
alignment: 4
tracksRegLiveness: true
body: |
bb.0:
liveins: $q0
; CHECK-LABEL: name: test_v8f16.exp2
; CHECK: liveins: $q0
; CHECK: [[COPY:%[0-9]+]]:_(<8 x s16>) = COPY $q0
; CHECK: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16), [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16), [[UV6:%[0-9]+]]:_(s16), [[UV7:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](<8 x s16>)
; CHECK: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[UV]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY1]](s32)
; CHECK: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[UV1]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT1]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY2]](s32)
; CHECK: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[UV2]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT2]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY3]](s32)
; CHECK: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[UV3]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT3]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC3:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY4]](s32)
; CHECK: [[FPEXT4:%[0-9]+]]:_(s32) = G_FPEXT [[UV4]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT4]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY5:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC4:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY5]](s32)
; CHECK: [[FPEXT5:%[0-9]+]]:_(s32) = G_FPEXT [[UV5]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT5]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY6:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC5:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY6]](s32)
; CHECK: [[FPEXT6:%[0-9]+]]:_(s32) = G_FPEXT [[UV6]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT6]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY7:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC6:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY7]](s32)
; CHECK: [[FPEXT7:%[0-9]+]]:_(s32) = G_FPEXT [[UV7]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT7]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY8:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC7:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY8]](s32)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<8 x s16>) = G_BUILD_VECTOR [[FPTRUNC]](s16), [[FPTRUNC1]](s16), [[FPTRUNC2]](s16), [[FPTRUNC3]](s16), [[FPTRUNC4]](s16), [[FPTRUNC5]](s16), [[FPTRUNC6]](s16), [[FPTRUNC7]](s16)
; CHECK: $q0 = COPY [[BUILD_VECTOR]](<8 x s16>)
; CHECK: RET_ReallyLR implicit $q0
%0:_(<8 x s16>) = COPY $q0
%1:_(<8 x s16>) = G_FEXP2 %0
$q0 = COPY %1(<8 x s16>)
RET_ReallyLR implicit $q0
...
---
name: test_v2f32.exp2
alignment: 4
tracksRegLiveness: true
body: |
bb.0:
liveins: $d0
; CHECK-LABEL: name: test_v2f32.exp2
; CHECK: liveins: $d0
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $d0
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[UV]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[UV1]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[COPY1]](s32), [[COPY2]](s32)
; CHECK: $d0 = COPY [[BUILD_VECTOR]](<2 x s32>)
; CHECK: RET_ReallyLR implicit $d0
%0:_(<2 x s32>) = COPY $d0
%1:_(<2 x s32>) = G_FEXP2 %0
$d0 = COPY %1(<2 x s32>)
RET_ReallyLR implicit $d0
...
---
name: test_v4f32.exp2
alignment: 4
tracksRegLiveness: true
body: |
bb.0:
liveins: $q0
; CHECK-LABEL: name: test_v4f32.exp2
; CHECK: liveins: $q0
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $q0
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[UV]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[UV1]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[UV2]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[UV3]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[COPY1]](s32), [[COPY2]](s32), [[COPY3]](s32), [[COPY4]](s32)
; CHECK: $q0 = COPY [[BUILD_VECTOR]](<4 x s32>)
; CHECK: RET_ReallyLR implicit $q0
%0:_(<4 x s32>) = COPY $q0
%1:_(<4 x s32>) = G_FEXP2 %0
$q0 = COPY %1(<4 x s32>)
RET_ReallyLR implicit $q0
...
---
name: test_v2f64.exp2
alignment: 4
tracksRegLiveness: true
body: |
bb.0:
liveins: $q0
; CHECK-LABEL: name: test_v2f64.exp2
; CHECK: liveins: $q0
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
; CHECK: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $d0 = COPY [[UV]](s64)
; CHECK: BL &exp2, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $d0, implicit-def $d0
; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $d0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $d0 = COPY [[UV1]](s64)
; CHECK: BL &exp2, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $d0, implicit-def $d0
; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY $d0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[COPY1]](s64), [[COPY2]](s64)
; CHECK: $q0 = COPY [[BUILD_VECTOR]](<2 x s64>)
; CHECK: RET_ReallyLR implicit $q0
%0:_(<2 x s64>) = COPY $q0
%1:_(<2 x s64>) = G_FEXP2 %0
$q0 = COPY %1(<2 x s64>)
RET_ReallyLR implicit $q0
...
---
name: test_exp2_half
alignment: 4
tracksRegLiveness: true
body: |
bb.0:
liveins: $h0
; CHECK-LABEL: name: test_exp2_half
; CHECK: liveins: $h0
; CHECK: [[COPY:%[0-9]+]]:_(s16) = COPY $h0
; CHECK: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[COPY]](s16)
; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def $sp, implicit $sp
; CHECK: $s0 = COPY [[FPEXT]](s32)
; CHECK: BL &exp2f, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit $s0, implicit-def $s0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $s0
; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sp, implicit $sp
; CHECK: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[COPY1]](s32)
; CHECK: $h0 = COPY [[FPTRUNC]](s16)
; CHECK: RET_ReallyLR implicit $h0
%0:_(s16) = COPY $h0
%1:_(s16) = G_FEXP2 %0
$h0 = COPY %1(s16)
RET_ReallyLR implicit $h0