llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-fcmp.mir

154 lines
6.4 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -O0 -march=amdgcn -mcpu=fiji -run-pass=legalizer %s -o - | FileCheck %s
---
name: test_fcmp_s32
body: |
bb.0.entry:
liveins: $vgpr0
; CHECK-LABEL: name: test_fcmp_s32
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[FCMP:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[C]](s32), [[COPY]]
; CHECK: [[SELECT:%[0-9]+]]:_(s32) = G_SELECT [[FCMP]](s1), [[C]], [[COPY]]
; CHECK: $vgpr0 = COPY [[SELECT]](s32)
%0:_(s32) = G_CONSTANT i32 0
%1:_(s32) = COPY $vgpr0
%2:_(s1) = G_FCMP floatpred(oeq), %0, %1
%3:_(s32) = G_SELECT %2, %0, %1
$vgpr0 = COPY %3
...
---
name: test_fcmp_s64
body: |
bb.0.entry:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_fcmp_s64
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[FCMP:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[C]](s64), [[COPY]]
; CHECK: [[SELECT:%[0-9]+]]:_(s64) = G_SELECT [[FCMP]](s1), [[C]], [[COPY]]
; CHECK: $vgpr0_vgpr1 = COPY [[SELECT]](s64)
%0:_(s64) = G_CONSTANT i64 0
%1:_(s64) = COPY $vgpr0_vgpr1
%2:_(s1) = G_FCMP floatpred(oeq), %0, %1
%3:_(s64) = G_SELECT %2, %0, %1
$vgpr0_vgpr1 = COPY %3
...
---
name: test_fcmp_s16
body: |
bb.0.entry:
liveins: $vgpr0
; CHECK-LABEL: name: test_fcmp_s16
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[C]](s32)
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
; CHECK: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
; CHECK: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
; CHECK: [[FCMP:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[FPEXT]](s32), [[FPEXT1]]
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY [[C]](s32)
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
; CHECK: [[SELECT:%[0-9]+]]:_(s32) = G_SELECT [[FCMP]](s1), [[COPY1]], [[COPY2]]
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[SELECT]](s32)
; CHECK: $vgpr0 = COPY [[COPY3]](s32)
%0:_(s16) = G_CONSTANT i16 0
%1:_(s32) = COPY $vgpr0
%2:_(s16) = G_TRUNC %1
%3:_(s1) = G_FCMP floatpred(oeq), %0, %2
%4:_(s16) = G_SELECT %3, %0, %2
%5:_(s32) = G_ANYEXT %4
$vgpr0 = COPY %5
...
---
name: test_fcmp_v2s32
body: |
bb.0.entry:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_fcmp_v2s32
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: [[FCMP:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[C]](s32), [[UV]]
; CHECK: [[FCMP1:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[C]](s32), [[UV1]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s1>) = G_BUILD_VECTOR [[FCMP]](s1), [[FCMP1]](s1)
; CHECK: S_NOP 0, implicit [[BUILD_VECTOR]](<2 x s1>)
%0:_(s32) = G_CONSTANT i32 0
%1:_(<2 x s32>) = G_BUILD_VECTOR %0, %0
%2:_(<2 x s32>) = COPY $vgpr0_vgpr1
%3:_(<2 x s1>) = G_FCMP floatpred(oeq), %1, %2
S_NOP 0, implicit %3
...
---
name: test_fcmp_v2s32_flags
body: |
bb.0.entry:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_fcmp_v2s32_flags
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: %8:_(s1) = nnan G_FCMP floatpred(oeq), [[C]](s32), [[UV]]
; CHECK: %9:_(s1) = nnan G_FCMP floatpred(oeq), [[C]](s32), [[UV1]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s1>) = G_BUILD_VECTOR %8(s1), %9(s1)
; CHECK: S_NOP 0, implicit [[BUILD_VECTOR]](<2 x s1>)
%0:_(s32) = G_CONSTANT i32 0
%1:_(<2 x s32>) = G_BUILD_VECTOR %0, %0
%2:_(<2 x s32>) = COPY $vgpr0_vgpr1
%3:_(<2 x s1>) = nnan G_FCMP floatpred(oeq), %1, %2
S_NOP 0, implicit %3
...
---
name: test_fcmp_v3s32
body: |
bb.0.entry:
liveins: $vgpr0_vgpr1_vgpr2
; CHECK-LABEL: name: test_fcmp_v3s32
; CHECK: [[DEF:%[0-9]+]]:_(<3 x s32>) = G_IMPLICIT_DEF
; CHECK: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[DEF]](<3 x s32>)
; CHECK: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; CHECK: [[FCMP:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[UV]](s32), [[UV3]]
; CHECK: [[FCMP1:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[UV1]](s32), [[UV4]]
; CHECK: [[FCMP2:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[UV2]](s32), [[UV5]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s1>) = G_BUILD_VECTOR [[FCMP]](s1), [[FCMP1]](s1), [[FCMP2]](s1)
; CHECK: S_NOP 0, implicit [[BUILD_VECTOR]](<3 x s1>)
%0:_(<3 x s32>) = G_IMPLICIT_DEF
%1:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
%2:_(<3 x s1>) = G_FCMP floatpred(oeq), %0, %1
S_NOP 0, implicit %2
...
---
name: test_fcmp_v4s32
body: |
bb.0.entry:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK-LABEL: name: test_fcmp_v4s32
; CHECK: [[DEF:%[0-9]+]]:_(p1) = G_IMPLICIT_DEF
; CHECK: [[LOAD:%[0-9]+]]:_(<4 x s32>) = G_LOAD [[DEF]](p1) :: (volatile load 16)
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[LOAD]](<4 x s32>)
; CHECK: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; CHECK: [[FCMP:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[UV]](s32), [[UV4]]
; CHECK: [[FCMP1:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[UV1]](s32), [[UV5]]
; CHECK: [[FCMP2:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[UV2]](s32), [[UV6]]
; CHECK: [[FCMP3:%[0-9]+]]:_(s1) = G_FCMP floatpred(oeq), [[UV3]](s32), [[UV7]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s1>) = G_BUILD_VECTOR [[FCMP]](s1), [[FCMP1]](s1), [[FCMP2]](s1), [[FCMP3]](s1)
; CHECK: S_NOP 0, implicit [[BUILD_VECTOR]](<4 x s1>)
%0:_(p1) = G_IMPLICIT_DEF
%1:_(<4 x s32>) = G_LOAD %0 :: (volatile load 16)
%2:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%3:_(<4 x s1>) = G_FCMP floatpred(oeq) , %1, %2
S_NOP 0, implicit %3
...