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-smin.mir

447 lines
23 KiB
Plaintext
Raw Normal View History

AMDGPU/GlobalISel: Legality for integer min/max llvm-svn: 361519
2019-05-24 01:58:48 +08:00
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
AMDGPU/GlobalISel: Fix legality for G_BUILD_VECTOR llvm-svn: 365575
2019-07-10 06:48:04 +08:00
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=SI %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=VI %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=GFX9 %s
AMDGPU/GlobalISel: Legality for integer min/max llvm-svn: 361519
2019-05-24 01:58:48 +08:00
---
name: test_smin_s32
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; SI-LABEL: name: test_smin_s32
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; SI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[COPY]], [[COPY1]]
; SI: $vgpr0 = COPY [[SMIN]](s32)
; VI-LABEL: name: test_smin_s32
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; VI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[COPY]], [[COPY1]]
; VI: $vgpr0 = COPY [[SMIN]](s32)
; GFX9-LABEL: name: test_smin_s32
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[COPY]], [[COPY1]]
; GFX9: $vgpr0 = COPY [[SMIN]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = G_SMIN %0, %1
$vgpr0 = COPY %2
...
---
name: test_smin_s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; SI-LABEL: name: test_smin_s16
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; SI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; SI: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
; SI: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C]](s32)
; SI: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C]](s32)
; SI: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; SI: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[COPY3]], [[C]](s32)
; SI: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[SHL1]], [[C]](s32)
; SI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[ASHR]], [[ASHR1]]
; SI: [[COPY4:%[0-9]+]]:_(s32) = COPY [[SMIN]](s32)
; SI: $vgpr0 = COPY [[COPY4]](s32)
; VI-LABEL: name: test_smin_s16
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
; VI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; VI: [[SMIN:%[0-9]+]]:_(s16) = G_SMIN [[TRUNC]], [[TRUNC1]]
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SMIN]](s16)
; VI: $vgpr0 = COPY [[ANYEXT]](s32)
; GFX9-LABEL: name: test_smin_s16
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; GFX9: [[SMIN:%[0-9]+]]:_(s16) = G_SMIN [[TRUNC]], [[TRUNC1]]
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SMIN]](s16)
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %0
%3:_(s16) = G_TRUNC %1
%4:_(s16) = G_SMIN %2, %3
%5:_(s32) = G_ANYEXT %4
$vgpr0 = COPY %5
...
---
name: test_smin_s8
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; SI-LABEL: name: test_smin_s8
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; SI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
; SI: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
; SI: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C]](s32)
; SI: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C]](s32)
; SI: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; SI: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[COPY3]], [[C]](s32)
; SI: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[SHL1]], [[C]](s32)
; SI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[ASHR]], [[ASHR1]]
; SI: [[COPY4:%[0-9]+]]:_(s32) = COPY [[SMIN]](s32)
; SI: $vgpr0 = COPY [[COPY4]](s32)
; VI-LABEL: name: test_smin_s8
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; VI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[C]](s32)
; VI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
; VI: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC1]], [[TRUNC]](s16)
; VI: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[TRUNC]](s16)
; VI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; VI: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[TRUNC2]], [[TRUNC]](s16)
; VI: [[ASHR1:%[0-9]+]]:_(s16) = G_ASHR [[SHL1]], [[TRUNC]](s16)
; VI: [[SMIN:%[0-9]+]]:_(s16) = G_SMIN [[ASHR]], [[ASHR1]]
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SMIN]](s16)
; VI: $vgpr0 = COPY [[ANYEXT]](s32)
; GFX9-LABEL: name: test_smin_s8
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[C]](s32)
; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC1]], [[TRUNC]](s16)
; GFX9: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[TRUNC]](s16)
; GFX9: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; GFX9: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[TRUNC2]], [[TRUNC]](s16)
; GFX9: [[ASHR1:%[0-9]+]]:_(s16) = G_ASHR [[SHL1]], [[TRUNC]](s16)
; GFX9: [[SMIN:%[0-9]+]]:_(s16) = G_SMIN [[ASHR]], [[ASHR1]]
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SMIN]](s16)
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s8) = G_TRUNC %0
%3:_(s8) = G_TRUNC %1
%4:_(s8) = G_SMIN %2, %3
%5:_(s32) = G_ANYEXT %4
$vgpr0 = COPY %5
...
---
name: test_smin_s17
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; SI-LABEL: name: test_smin_s17
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; SI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 15
; SI: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
; SI: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C]](s32)
; SI: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C]](s32)
; SI: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; SI: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[COPY3]], [[C]](s32)
; SI: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[SHL1]], [[C]](s32)
; SI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[ASHR]], [[ASHR1]]
; SI: [[COPY4:%[0-9]+]]:_(s32) = COPY [[SMIN]](s32)
; SI: $vgpr0 = COPY [[COPY4]](s32)
; VI-LABEL: name: test_smin_s17
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; VI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 15
; VI: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
; VI: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C]](s32)
; VI: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C]](s32)
; VI: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; VI: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[COPY3]], [[C]](s32)
; VI: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[SHL1]], [[C]](s32)
; VI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[ASHR]], [[ASHR1]]
; VI: [[COPY4:%[0-9]+]]:_(s32) = COPY [[SMIN]](s32)
; VI: $vgpr0 = COPY [[COPY4]](s32)
; GFX9-LABEL: name: test_smin_s17
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 15
; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
; GFX9: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C]](s32)
; GFX9: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C]](s32)
; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
; GFX9: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[COPY3]], [[C]](s32)
; GFX9: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[SHL1]], [[C]](s32)
; GFX9: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[ASHR]], [[ASHR1]]
; GFX9: [[COPY4:%[0-9]+]]:_(s32) = COPY [[SMIN]](s32)
; GFX9: $vgpr0 = COPY [[COPY4]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s17) = G_TRUNC %0
%3:_(s17) = G_TRUNC %1
%4:_(s17) = G_SMIN %2, %3
%5:_(s32) = G_ANYEXT %4
$vgpr0 = COPY %5
...
---
name: test_smin_v2s32
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; SI-LABEL: name: test_smin_v2s32
; SI: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; SI: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; SI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; SI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; SI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[UV]], [[UV2]]
; SI: [[SMIN1:%[0-9]+]]:_(s32) = G_SMIN [[UV1]], [[UV3]]
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SMIN]](s32), [[SMIN1]](s32)
; SI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; VI-LABEL: name: test_smin_v2s32
; VI: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; VI: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; VI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; VI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; VI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[UV]], [[UV2]]
; VI: [[SMIN1:%[0-9]+]]:_(s32) = G_SMIN [[UV1]], [[UV3]]
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SMIN]](s32), [[SMIN1]](s32)
; VI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX9-LABEL: name: test_smin_v2s32
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX9: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[UV]], [[UV2]]
; GFX9: [[SMIN1:%[0-9]+]]:_(s32) = G_SMIN [[UV1]], [[UV3]]
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SMIN]](s32), [[SMIN1]](s32)
; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<2 x s32>) = G_SMIN %0, %1
$vgpr0_vgpr1 = COPY %2
...
---
name: test_smin_v3s32
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2, $vgpr3_vgpr4_vgpr5
; SI-LABEL: name: test_smin_v3s32
; SI: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; SI: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; SI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; SI: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; SI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[UV]], [[UV3]]
; SI: [[SMIN1:%[0-9]+]]:_(s32) = G_SMIN [[UV1]], [[UV4]]
; SI: [[SMIN2:%[0-9]+]]:_(s32) = G_SMIN [[UV2]], [[UV5]]
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[SMIN]](s32), [[SMIN1]](s32), [[SMIN2]](s32)
; SI: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
; VI-LABEL: name: test_smin_v3s32
; VI: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; VI: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; VI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; VI: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; VI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[UV]], [[UV3]]
; VI: [[SMIN1:%[0-9]+]]:_(s32) = G_SMIN [[UV1]], [[UV4]]
; VI: [[SMIN2:%[0-9]+]]:_(s32) = G_SMIN [[UV2]], [[UV5]]
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[SMIN]](s32), [[SMIN1]](s32), [[SMIN2]](s32)
; VI: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
; GFX9-LABEL: name: test_smin_v3s32
; GFX9: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; GFX9: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; GFX9: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; GFX9: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[UV]], [[UV3]]
; GFX9: [[SMIN1:%[0-9]+]]:_(s32) = G_SMIN [[UV1]], [[UV4]]
; GFX9: [[SMIN2:%[0-9]+]]:_(s32) = G_SMIN [[UV2]], [[UV5]]
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[SMIN]](s32), [[SMIN1]](s32), [[SMIN2]](s32)
; GFX9: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
%0:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
%1:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
%2:_(<3 x s32>) = G_SMIN %0, %1
$vgpr0_vgpr1_vgpr2 = COPY %2
...
---
name: test_smin_v2s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; SI-LABEL: name: test_smin_v2s16
; SI: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; SI: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
GlobalISel: Lower scalarizing unmerge of a vector to shifts AMDGPU sometimes has legal s16 and <2 x s16> operations, but all registers are really 32-bit. An unmerge destination really should ben widened to a 32-bit register. If widening a scalarizing vector with a target size that matches the vector size, bitcast to integer and extract the relevant bits with shifts. I'm not sure if this is the right place for this. This could arguably be part of widenScalar for the result. I also have a growing feeling that we're missing a bitcast legalize action. llvm-svn: 367604
2019-08-02 03:10:05 +08:00
; SI: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
; SI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; SI: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; SI: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
; SI: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
; SI: [[COPY2:%[0-9]+]]:_(s32) = COPY [[BITCAST]](s32)
; SI: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[COPY2]], [[C]](s32)
; SI: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[SHL]], [[C]](s32)
; SI: [[COPY3:%[0-9]+]]:_(s32) = COPY [[BITCAST1]](s32)
; SI: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[COPY3]], [[C]](s32)
; SI: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[SHL1]], [[C]](s32)
; SI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[ASHR]], [[ASHR1]]
AMDGPU/GlobalISel: Legality for integer min/max llvm-svn: 361519
2019-05-24 01:58:48 +08:00
; SI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[SMIN]](s32)
GlobalISel: Lower scalarizing unmerge of a vector to shifts AMDGPU sometimes has legal s16 and <2 x s16> operations, but all registers are really 32-bit. An unmerge destination really should ben widened to a 32-bit register. If widening a scalarizing vector with a target size that matches the vector size, bitcast to integer and extract the relevant bits with shifts. I'm not sure if this is the right place for this. This could arguably be part of widenScalar for the result. I also have a growing feeling that we're missing a bitcast legalize action. llvm-svn: 367604
2019-08-02 03:10:05 +08:00
; SI: [[COPY4:%[0-9]+]]:_(s32) = COPY [[LSHR]](s32)
; SI: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[COPY4]], [[C]](s32)
; SI: [[ASHR2:%[0-9]+]]:_(s32) = G_ASHR [[SHL2]], [[C]](s32)
; SI: [[COPY5:%[0-9]+]]:_(s32) = COPY [[LSHR1]](s32)
; SI: [[SHL3:%[0-9]+]]:_(s32) = G_SHL [[COPY5]], [[C]](s32)
; SI: [[ASHR3:%[0-9]+]]:_(s32) = G_ASHR [[SHL3]], [[C]](s32)
; SI: [[SMIN1:%[0-9]+]]:_(s32) = G_SMIN [[ASHR2]], [[ASHR3]]
AMDGPU/GlobalISel: Legality for integer min/max llvm-svn: 361519
2019-05-24 01:58:48 +08:00
; SI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[SMIN1]](s32)
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16)
; SI: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
; VI-LABEL: name: test_smin_v2s16
; VI: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; VI: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
GlobalISel: Lower scalarizing unmerge of a vector to shifts AMDGPU sometimes has legal s16 and <2 x s16> operations, but all registers are really 32-bit. An unmerge destination really should ben widened to a 32-bit register. If widening a scalarizing vector with a target size that matches the vector size, bitcast to integer and extract the relevant bits with shifts. I'm not sure if this is the right place for this. This could arguably be part of widenScalar for the result. I also have a growing feeling that we're missing a bitcast legalize action. llvm-svn: 367604
2019-08-02 03:10:05 +08:00
; VI: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
; VI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; VI: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; VI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
; VI: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
; VI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
; VI: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
; VI: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
; VI: [[SMIN:%[0-9]+]]:_(s16) = G_SMIN [[TRUNC]], [[TRUNC2]]
; VI: [[SMIN1:%[0-9]+]]:_(s16) = G_SMIN [[TRUNC1]], [[TRUNC3]]
AMDGPU/GlobalISel: Legality for integer min/max llvm-svn: 361519
2019-05-24 01:58:48 +08:00
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR [[SMIN]](s16), [[SMIN1]](s16)
; VI: $vgpr0 = COPY [[BUILD_VECTOR]](<2 x s16>)
; GFX9-LABEL: name: test_smin_v2s16
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
; GFX9: [[SMIN:%[0-9]+]]:_(<2 x s16>) = G_SMIN [[COPY]], [[COPY1]]
; GFX9: $vgpr0 = COPY [[SMIN]](<2 x s16>)
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(<2 x s16>) = COPY $vgpr1
%2:_(<2 x s16>) = G_SMIN %0, %1
$vgpr0 = COPY %2
...
---
name: test_smin_v3s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; SI-LABEL: name: test_smin_v3s16
; SI: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; SI: [[EXTRACT:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[DEF]](<4 x s16>), 0
; SI: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; SI: [[EXTRACT1:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[DEF1]](<4 x s16>), 0
; SI: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[EXTRACT]](<3 x s16>)
; SI: [[UV3:%[0-9]+]]:_(s16), [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[EXTRACT1]](<3 x s16>)
; SI: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[UV]](s16)
; SI: [[SEXT1:%[0-9]+]]:_(s32) = G_SEXT [[UV3]](s16)
; SI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[SEXT]], [[SEXT1]]
; SI: [[SEXT2:%[0-9]+]]:_(s32) = G_SEXT [[UV1]](s16)
; SI: [[SEXT3:%[0-9]+]]:_(s32) = G_SEXT [[UV4]](s16)
; SI: [[SMIN1:%[0-9]+]]:_(s32) = G_SMIN [[SEXT2]], [[SEXT3]]
; SI: [[SEXT4:%[0-9]+]]:_(s32) = G_SEXT [[UV2]](s16)
; SI: [[SEXT5:%[0-9]+]]:_(s32) = G_SEXT [[UV5]](s16)
; SI: [[SMIN2:%[0-9]+]]:_(s32) = G_SMIN [[SEXT4]], [[SEXT5]]
AMDGPU/GlobalISel: Fix legality for G_BUILD_VECTOR llvm-svn: 365575
2019-07-10 06:48:04 +08:00
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY [[SMIN]](s32)
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY [[SMIN1]](s32)
; SI: [[COPY2:%[0-9]+]]:_(s32) = COPY [[SMIN2]](s32)
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[COPY]](s32), [[COPY1]](s32), [[COPY2]](s32)
; SI: [[TRUNC:%[0-9]+]]:_(<3 x s16>) = G_TRUNC [[BUILD_VECTOR]](<3 x s32>)
; SI: S_NOP 0, implicit [[TRUNC]](<3 x s16>)
AMDGPU/GlobalISel: Legality for integer min/max llvm-svn: 361519
2019-05-24 01:58:48 +08:00
; VI-LABEL: name: test_smin_v3s16
; VI: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; VI: [[EXTRACT:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[DEF]](<4 x s16>), 0
; VI: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; VI: [[EXTRACT1:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[DEF1]](<4 x s16>), 0
; VI: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[EXTRACT]](<3 x s16>)
; VI: [[UV3:%[0-9]+]]:_(s16), [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[EXTRACT1]](<3 x s16>)
; VI: [[SMIN:%[0-9]+]]:_(s16) = G_SMIN [[UV]], [[UV3]]
; VI: [[SMIN1:%[0-9]+]]:_(s16) = G_SMIN [[UV1]], [[UV4]]
; VI: [[SMIN2:%[0-9]+]]:_(s16) = G_SMIN [[UV2]], [[UV5]]
AMDGPU/GlobalISel: Fix legality for G_BUILD_VECTOR llvm-svn: 365575
2019-07-10 06:48:04 +08:00
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SMIN]](s16)
; VI: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[SMIN1]](s16)
; VI: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[SMIN2]](s16)
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[ANYEXT]](s32), [[ANYEXT1]](s32), [[ANYEXT2]](s32)
; VI: [[TRUNC:%[0-9]+]]:_(<3 x s16>) = G_TRUNC [[BUILD_VECTOR]](<3 x s32>)
; VI: S_NOP 0, implicit [[TRUNC]](<3 x s16>)
AMDGPU/GlobalISel: Legality for integer min/max llvm-svn: 361519
2019-05-24 01:58:48 +08:00
; GFX9-LABEL: name: test_smin_v3s16
; GFX9: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; GFX9: [[EXTRACT:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[DEF]](<4 x s16>), 0
; GFX9: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; GFX9: [[EXTRACT1:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[DEF1]](<4 x s16>), 0
; GFX9: [[DEF2:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; GFX9: [[INSERT:%[0-9]+]]:_(<4 x s16>) = G_INSERT [[DEF2]], [[EXTRACT]](<3 x s16>), 0
; GFX9: [[DEF3:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; GFX9: [[INSERT1:%[0-9]+]]:_(<4 x s16>) = G_INSERT [[DEF3]], [[EXTRACT1]](<3 x s16>), 0
; GFX9: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[INSERT]](<4 x s16>)
; GFX9: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[INSERT1]](<4 x s16>)
; GFX9: [[SMIN:%[0-9]+]]:_(<2 x s16>) = G_SMIN [[UV]], [[UV2]]
; GFX9: [[SMIN1:%[0-9]+]]:_(<2 x s16>) = G_SMIN [[UV1]], [[UV3]]
; GFX9: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[SMIN]](<2 x s16>), [[SMIN1]](<2 x s16>)
; GFX9: [[EXTRACT2:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[CONCAT_VECTORS]](<4 x s16>), 0
; GFX9: S_NOP 0, implicit [[EXTRACT2]](<3 x s16>)
%0:_(<3 x s16>) = G_IMPLICIT_DEF
%1:_(<3 x s16>) = G_IMPLICIT_DEF
%2:_(<3 x s16>) = G_SMIN %0, %1
S_NOP 0, implicit %2
...
---
name: test_smin_v4s16
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; SI-LABEL: name: test_smin_v4s16
; SI: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
; SI: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
; SI: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
; SI: [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16), [[UV6:%[0-9]+]]:_(s16), [[UV7:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
; SI: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[UV]](s16)
; SI: [[SEXT1:%[0-9]+]]:_(s32) = G_SEXT [[UV4]](s16)
; SI: [[SMIN:%[0-9]+]]:_(s32) = G_SMIN [[SEXT]], [[SEXT1]]
; SI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[SMIN]](s32)
; SI: [[SEXT2:%[0-9]+]]:_(s32) = G_SEXT [[UV1]](s16)
; SI: [[SEXT3:%[0-9]+]]:_(s32) = G_SEXT [[UV5]](s16)
; SI: [[SMIN1:%[0-9]+]]:_(s32) = G_SMIN [[SEXT2]], [[SEXT3]]
; SI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[SMIN1]](s32)
; SI: [[SEXT4:%[0-9]+]]:_(s32) = G_SEXT [[UV2]](s16)
; SI: [[SEXT5:%[0-9]+]]:_(s32) = G_SEXT [[UV6]](s16)
; SI: [[SMIN2:%[0-9]+]]:_(s32) = G_SMIN [[SEXT4]], [[SEXT5]]
; SI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[SMIN2]](s32)
; SI: [[SEXT6:%[0-9]+]]:_(s32) = G_SEXT [[UV3]](s16)
; SI: [[SEXT7:%[0-9]+]]:_(s32) = G_SEXT [[UV7]](s16)
; SI: [[SMIN3:%[0-9]+]]:_(s32) = G_SMIN [[SEXT6]], [[SEXT7]]
; SI: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[SMIN3]](s32)
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16), [[TRUNC2]](s16), [[TRUNC3]](s16)
; SI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<4 x s16>)
; VI-LABEL: name: test_smin_v4s16
; VI: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
; VI: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
; VI: [[UV:%[0-9]+]]:_(s16), [[UV1:%[0-9]+]]:_(s16), [[UV2:%[0-9]+]]:_(s16), [[UV3:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
; VI: [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16), [[UV6:%[0-9]+]]:_(s16), [[UV7:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
; VI: [[SMIN:%[0-9]+]]:_(s16) = G_SMIN [[UV]], [[UV4]]
; VI: [[SMIN1:%[0-9]+]]:_(s16) = G_SMIN [[UV1]], [[UV5]]
; VI: [[SMIN2:%[0-9]+]]:_(s16) = G_SMIN [[UV2]], [[UV6]]
; VI: [[SMIN3:%[0-9]+]]:_(s16) = G_SMIN [[UV3]], [[UV7]]
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[SMIN]](s16), [[SMIN1]](s16), [[SMIN2]](s16), [[SMIN3]](s16)
; VI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<4 x s16>)
; GFX9-LABEL: name: test_smin_v4s16
; GFX9: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
; GFX9: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
; GFX9: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
; GFX9: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
; GFX9: [[SMIN:%[0-9]+]]:_(<2 x s16>) = G_SMIN [[UV]], [[UV2]]
; GFX9: [[SMIN1:%[0-9]+]]:_(<2 x s16>) = G_SMIN [[UV1]], [[UV3]]
; GFX9: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[SMIN]](<2 x s16>), [[SMIN1]](<2 x s16>)
; GFX9: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
%2:_(<4 x s16>) = G_SMIN %0, %1
$vgpr0_vgpr1 = COPY %2
...