maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU/GlobalISel: Legalize concat_vectors 

llvm-svn: 350598
This commit is contained in:
Matt Arsenault 2019-01-08 01:30:02 +00:00
parent 376f2ef2f0
commit a1515d2d33
2 changed files with 141 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
View File

@ -38,6 +38,8 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST,
const LLT S512 = LLT::scalar(512);
const LLT V2S16 = LLT::vector(2, 16);
const LLT V4S16 = LLT::vector(4, 16);
const LLT V8S16 = LLT::vector(8, 16);
const LLT V2S32 = LLT::vector(2, 32);
const LLT V3S32 = LLT::vector(3, 32);
@ -279,6 +281,16 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST,
.clampNumElements(0, V2S64, V8S64)
.minScalarSameAs(1, 0);
// TODO: Support any combination of v2s32
getActionDefinitionsBuilder(G_CONCAT_VECTORS)
.legalFor({{V4S32, V2S32},
{V8S32, V2S32},
{V8S32, V4S32},
{V4S64, V2S64},
{V4S16, V2S16},
{V8S16, V2S16},
{V8S16, V4S16}});
// Merge/Unmerge
for (unsigned Op : {G_MERGE_VALUES, G_UNMERGE_VALUES}) {
unsigned BigTyIdx = Op == G_MERGE_VALUES ? 0 : 1;

129
llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-concat-vectors.mir Normal file
View File

@ -0,0 +1,129 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -O0 -run-pass=legalizer %s -o - | FileCheck %s
---
name: concat_vectors_v2s32_v2s32
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; CHECK-LABEL: name: concat_vectors_v2s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[CONCAT_VECTORS]](<4 x s32>)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<4 x s32>) = G_CONCAT_VECTORS %0, %1
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2
...
---
name: concat_vectors_v2s16_v2s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: concat_vectors_v2s16_v2s16
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[COPY]](<2 x s16>), [[COPY1]](<2 x s16>)
; CHECK: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(<2 x s16>) = COPY $vgpr1
%2:_(<4 x s16>) = G_CONCAT_VECTORS %0, %1
$vgpr0_vgpr1 = COPY %2
...
---
name: concat_vectors_v2s16_v2s16_v2s16_v2s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
; CHECK-LABEL: name: concat_vectors_v2s16_v2s16_v2s16_v2s16
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
; CHECK: [[COPY2:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr2
; CHECK: [[COPY3:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr3
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s16>) = G_CONCAT_VECTORS [[COPY]](<2 x s16>), [[COPY1]](<2 x s16>), [[COPY2]](<2 x s16>), [[COPY3]](<2 x s16>)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[CONCAT_VECTORS]](<8 x s16>)
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(<2 x s16>) = COPY $vgpr1
%2:_(<2 x s16>) = COPY $vgpr2
%3:_(<2 x s16>) = COPY $vgpr3
%4:_(<8 x s16>) = G_CONCAT_VECTORS %0, %1, %2, %3
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %4
...
---
name: concat_vectors_v4s16_v4s16
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; CHECK-LABEL: name: concat_vectors_v4s16_v4s16
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s16>) = G_CONCAT_VECTORS [[COPY]](<4 x s16>), [[COPY1]](<4 x s16>)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[CONCAT_VECTORS]](<8 x s16>)
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
%2:_(<8 x s16>) = G_CONCAT_VECTORS %0, %1
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2
...
---
name: concat_vectors_v4s32_v4s32
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7
; CHECK-LABEL: name: concat_vectors_v4s32_v4s32
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s32>) = G_CONCAT_VECTORS [[COPY]](<4 x s32>), [[COPY1]](<4 x s32>)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[CONCAT_VECTORS]](<8 x s32>)
%0:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3,
%1:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
%2:_(<8 x s32>) = G_CONCAT_VECTORS %0, %1
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY %2
...
---
name: concat_vectors_v2s32_v2s32_v2s32_v2s32
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5, $vgpr6_vgpr7
; CHECK-LABEL: name: concat_vectors_v2s32_v2s32_v2s32_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; CHECK: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; CHECK: [[COPY3:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr6_vgpr7
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s32>) = G_CONCAT_VECTORS [[COPY]](<2 x s32>), [[COPY1]](<2 x s32>), [[COPY2]](<2 x s32>), [[COPY3]](<2 x s32>)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[CONCAT_VECTORS]](<8 x s32>)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<2 x s32>) = COPY $vgpr4_vgpr5
%3:_(<2 x s32>) = COPY $vgpr6_vgpr7
%4:_(<8 x s32>) = G_CONCAT_VECTORS %0, %1, %2, %3
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY %4
...
---
name: concat_vectors_v2s64_v2s64
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7
; CHECK-LABEL: name: concat_vectors_v2s64_v2s64
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s64>) = G_CONCAT_VECTORS [[COPY]](<2 x s64>), [[COPY1]](<2 x s64>)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[CONCAT_VECTORS]](<4 x s64>)
%0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
%2:_(<4 x s64>) = G_CONCAT_VECTORS %0, %1
$vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY %2
...