maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-trunc.mir

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

216 lines
8.1 KiB
Plaintext
Raw Normal View History

AMDGPU/GlobalISel: Make G_TRUNC legal This is required to be legal. I'm not sure how we were getting away without defining any rules for it.
2020-01-22 09:22:57 +08:00
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -run-pass=legalizer -global-isel-abort=0 -o - %s | FileCheck %s
---
name: test_trunc_s64_to_s32
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_trunc_s64_to_s32
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[TRUNC:%[0-9]+]]:_(s32) = G_TRUNC [[COPY]](s64)
; CHECK: $vgpr0 = COPY [[TRUNC]](s32)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(s32) = G_TRUNC %0
$vgpr0 = COPY %1
...
---
name: test_trunc_s64_to_s16
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_trunc_s64_to_s16
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s64)
; CHECK: S_ENDPGM 0, implicit [[TRUNC]](s16)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(s16) = G_TRUNC %0
S_ENDPGM 0, implicit %1
...
---
name: test_trunc_v2s32_to_v2s16
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_trunc_v2s32_to_v2s16
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[TRUNC:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[COPY]](<2 x s32>)
; CHECK: $vgpr0 = COPY [[TRUNC]](<2 x s16>)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s16>) = G_TRUNC %0
$vgpr0 = COPY %1
...
GlobalISel: Implement fewerElementsVector for G_TRUNC Extend fewerElementsVectorBasic to handle operands with different element types.
2020-02-16 09:24:36 +08:00
---
name: test_trunc_v3s32_to_v3s16
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2
; CHECK-LABEL: name: test_trunc_v3s32_to_v3s16
; 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 [[COPY]](<3 x s32>)
; CHECK: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[UV]](s32), [[UV1]](s32)
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[UV2]](s32), [[DEF]](s32)
; CHECK: [[TRUNC:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[BUILD_VECTOR]](<2 x s32>)
; CHECK: [[TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[BUILD_VECTOR1]](<2 x s32>)
; CHECK: [[DEF1:%[0-9]+]]:_(<2 x s16>) = G_IMPLICIT_DEF
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<6 x s16>) = G_CONCAT_VECTORS [[TRUNC]](<2 x s16>), [[TRUNC1]](<2 x s16>), [[DEF1]](<2 x s16>)
; CHECK: [[EXTRACT:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[CONCAT_VECTORS]](<6 x s16>), 0
; CHECK: [[DEF2:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; CHECK: [[INSERT:%[0-9]+]]:_(<4 x s16>) = G_INSERT [[DEF2]], [[EXTRACT]](<3 x s16>), 0
; CHECK: [[UV3:%[0-9]+]]:_(<2 x s16>), [[UV4:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[INSERT]](<4 x s16>)
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
; CHECK: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; CHECK: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
; CHECK: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV4]](<2 x s16>)
; CHECK: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
; CHECK: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
; CHECK: S_ENDPGM 0, implicit [[TRUNC2]](s16), implicit [[TRUNC3]](s16), implicit [[TRUNC4]](s16)
%0:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
%1:_(<3 x s16>) = G_TRUNC %0
%2:_(s16), %3:_(s16), %4:_(s16) = G_UNMERGE_VALUES %1
S_ENDPGM 0, implicit %2, implicit %3, implicit %4
...
AMDGPU/GlobalISel: Make G_TRUNC legal This is required to be legal. I'm not sure how we were getting away without defining any rules for it.
2020-01-22 09:22:57 +08:00
---
name: test_trunc_v4s32_to_v4s16
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK-LABEL: name: test_trunc_v4s32_to_v4s16
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
GlobalISel: Implement fewerElementsVector for G_TRUNC Extend fewerElementsVectorBasic to handle operands with different element types.
2020-02-16 09:24:36 +08:00
; CHECK: [[UV:%[0-9]+]]:_(<2 x s32>), [[UV1:%[0-9]+]]:_(<2 x s32>) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; CHECK: [[TRUNC:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[UV]](<2 x s32>)
; CHECK: [[TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[UV1]](<2 x s32>)
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[TRUNC]](<2 x s16>), [[TRUNC1]](<2 x s16>)
; CHECK: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
AMDGPU/GlobalISel: Make G_TRUNC legal This is required to be legal. I'm not sure how we were getting away without defining any rules for it.
2020-01-22 09:22:57 +08:00
%0:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<4 x s16>) = G_TRUNC %0
$vgpr0_vgpr1 = COPY %1
...
GlobalISel: Implement fewerElementsVector for G_TRUNC Extend fewerElementsVectorBasic to handle operands with different element types.
2020-02-16 09:24:36 +08:00
---
name: test_trunc_v8s32_to_v8s16
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
; CHECK-LABEL: name: test_trunc_v8s32_to_v8s16
; CHECK: [[COPY:%[0-9]+]]:_(<8 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
; CHECK: [[UV:%[0-9]+]]:_(<2 x s32>), [[UV1:%[0-9]+]]:_(<2 x s32>), [[UV2:%[0-9]+]]:_(<2 x s32>), [[UV3:%[0-9]+]]:_(<2 x s32>) = G_UNMERGE_VALUES [[COPY]](<8 x s32>)
; CHECK: [[TRUNC:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[UV]](<2 x s32>)
; CHECK: [[TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[UV1]](<2 x s32>)
; CHECK: [[TRUNC2:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[UV2]](<2 x s32>)
; CHECK: [[TRUNC3:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[UV3]](<2 x s32>)
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s16>) = G_CONCAT_VECTORS [[TRUNC]](<2 x s16>), [[TRUNC1]](<2 x s16>), [[TRUNC2]](<2 x s16>), [[TRUNC3]](<2 x s16>)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[CONCAT_VECTORS]](<8 x s16>)
%0:_(<8 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
%1:_(<8 x s16>) = G_TRUNC %0
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %1
...
---
name: test_trunc_v2s64_to_v2s16
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK-LABEL: name: test_trunc_v2s64_to_v2s16
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[TRUNC:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[COPY]](<2 x s64>)
; CHECK: $vgpr0 = COPY [[TRUNC]](<2 x s16>)
%0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<2 x s16>) = G_TRUNC %0
$vgpr0 = COPY %1
...
---
name: test_trunc_v4s64_to_v4s16
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
; CHECK-LABEL: name: test_trunc_v4s64_to_v4s16
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
; CHECK: [[UV:%[0-9]+]]:_(<2 x s64>), [[UV1:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[COPY]](<4 x s64>)
; CHECK: [[TRUNC:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[UV]](<2 x s64>)
; CHECK: [[TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_TRUNC [[UV1]](<2 x s64>)
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[TRUNC]](<2 x s16>), [[TRUNC1]](<2 x s16>)
; CHECK: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
%0:_(<4 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
%1:_(<4 x s16>) = G_TRUNC %0
$vgpr0_vgpr1 = COPY %1
...
AMDGPU/GlobalISel: Make G_TRUNC legal This is required to be legal. I'm not sure how we were getting away without defining any rules for it.
2020-01-22 09:22:57 +08:00
---
name: test_trunc_s64_to_s1
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_trunc_s64_to_s1
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[TRUNC:%[0-9]+]]:_(s1) = G_TRUNC [[COPY]](s64)
; CHECK: S_ENDPGM 0, implicit [[TRUNC]](s1)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(s1) = G_TRUNC %0
S_ENDPGM 0, implicit %1
...
---
name: test_trunc_s32_to_s1
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: test_trunc_s32_to_s1
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[TRUNC:%[0-9]+]]:_(s1) = G_TRUNC [[COPY]](s32)
; CHECK: S_ENDPGM 0, implicit [[TRUNC]](s1)
%0:_(s32) = COPY $vgpr0
%1:_(s1) = G_TRUNC %0
S_ENDPGM 0, implicit %1
...
---
name: test_trunc_s16_to_s1
body: |
bb.0:
liveins: $vgpr0
; CHECK-LABEL: name: test_trunc_s16_to_s1
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
; CHECK: [[TRUNC1:%[0-9]+]]:_(s1) = G_TRUNC [[TRUNC]](s16)
; CHECK: S_ENDPGM 0, implicit [[TRUNC1]](s1)
%0:_(s32) = COPY $vgpr0
%1:_(s16) = G_TRUNC %0
%2:_(s1) = G_TRUNC %1
S_ENDPGM 0, implicit %2
...
---
name: test_trunc_v4s32_to_v4s1
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK-LABEL: name: test_trunc_v4s32_to_v4s1
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[TRUNC:%[0-9]+]]:_(<4 x s1>) = G_TRUNC [[COPY]](<4 x s32>)
; CHECK: S_ENDPGM 0, implicit [[TRUNC]](<4 x s1>)
%0:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<4 x s1>) = G_TRUNC %0
S_ENDPGM 0, implicit %1
...