9e9907f1cf
Similar to 806761a762.
For IR files without a target triple, -mtriple= specifies the full
target triple while -march= merely sets the architecture part of the
default target triple, leaving a target triple which may not make sense,
e.g. amdgpu-apple-darwin.
Therefore, -march= is error-prone and not recommended for tests without
a target triple. The issue has been benign as we recognize
$unknown-apple-darwin as ELF instead of rejecting it outrightly.
This patch changes AMDGPU tests to not rely on the default
OS/environment components. Tests that need fixes are not changed:
```
LLVM :: CodeGen/AMDGPU/fabs.f64.ll
LLVM :: CodeGen/AMDGPU/fabs.ll
LLVM :: CodeGen/AMDGPU/floor.ll
LLVM :: CodeGen/AMDGPU/fneg-fabs.f64.ll
LLVM :: CodeGen/AMDGPU/fneg-fabs.ll
LLVM :: CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll
LLVM :: CodeGen/AMDGPU/schedule-if-2.ll
```
120 lines
4.9 KiB
YAML
120 lines
4.9 KiB
YAML
# RUN: llc -mtriple=amdgcn -mcpu=gfx940 -verify-machineinstrs -run-pass si-insert-waitcnts -o - %s | FileCheck -check-prefix=GCN %s
|
|
|
|
# GCN-LABEL: name: buffer_load_dword_lds_ds_read
|
|
# GCN: BUFFER_LOAD_DWORD_LDS_IDXEN
|
|
# GCN-NEXT: S_WAITCNT 3952
|
|
# vmcnt(0)
|
|
# GCN-NEXT: DS_READ_B32_gfx9
|
|
---
|
|
name: buffer_load_dword_lds_ds_read
|
|
body: |
|
|
bb.0:
|
|
$m0 = S_MOV_B32 0
|
|
BUFFER_LOAD_DWORD_LDS_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 4, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(1) undef` + 4), (store (s32) into `ptr addrspace(3) undef` + 4)
|
|
$vgpr0 = DS_READ_B32_gfx9 $vgpr1, 0, 0, implicit $m0, implicit $exec :: (load (s32) from `ptr addrspace(3) undef`)
|
|
S_ENDPGM 0
|
|
|
|
...
|
|
|
|
# GCN-LABEL: name: buffer_load_dword_lds_vmcnt_1
|
|
# GCN: BUFFER_LOAD_DWORD_LDS_IDXEN
|
|
# GCN-NEXT: BUFFER_LOAD_DWORD_IDXEN
|
|
# GCN-NEXT: S_WAITCNT 3953
|
|
# vmcnt(1)
|
|
# GCN-NEXT: DS_READ_B32_gfx9
|
|
---
|
|
name: buffer_load_dword_lds_vmcnt_1
|
|
body: |
|
|
bb.0:
|
|
$m0 = S_MOV_B32 0
|
|
BUFFER_LOAD_DWORD_LDS_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 4, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(1) undef`), (store (s32) into `ptr addrspace(3) undef`)
|
|
$vgpr10 = BUFFER_LOAD_DWORD_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 4, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(1) undef`)
|
|
$vgpr0 = DS_READ_B32_gfx9 $vgpr1, 0, 0, implicit $m0, implicit $exec :: (load (s32) from `ptr addrspace(3) undef`)
|
|
S_ENDPGM 0
|
|
|
|
...
|
|
|
|
# GCN-LABEL: name: buffer_load_dword_lds_flat_read
|
|
# GCN: BUFFER_LOAD_DWORD_LDS_IDXEN
|
|
# GCN-NEXT: S_WAITCNT 3952
|
|
# vmcnt(0)
|
|
# GCN-NEXT: FLAT_LOAD_DWORD
|
|
---
|
|
name: buffer_load_dword_lds_flat_read
|
|
body: |
|
|
bb.0:
|
|
$m0 = S_MOV_B32 0
|
|
BUFFER_LOAD_DWORD_LDS_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 4, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(1) undef`), (store (s32) into `ptr addrspace(3) undef`)
|
|
$vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr undef`)
|
|
|
|
S_ENDPGM 0
|
|
|
|
...
|
|
|
|
# GCN-LABEL: name: global_load_lds_dword_ds_read
|
|
# GCN: GLOBAL_LOAD_LDS_DWORD
|
|
# GCN-NEXT: S_WAITCNT 3952
|
|
# vmcnt(0)
|
|
# GCN-NEXT: DS_READ_B32_gfx9
|
|
---
|
|
name: global_load_lds_dword_ds_read
|
|
body: |
|
|
bb.0:
|
|
$m0 = S_MOV_B32 0
|
|
GLOBAL_LOAD_LDS_DWORD $vgpr0_vgpr1, 4, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(1) undef` + 4), (store (s32) into `ptr addrspace(3) undef` + 4)
|
|
$vgpr0 = DS_READ_B32_gfx9 $vgpr1, 0, 0, implicit $m0, implicit $exec :: (load (s32) from `ptr addrspace(3) undef`)
|
|
S_ENDPGM 0
|
|
|
|
...
|
|
|
|
# GCN-LABEL: name: scratch_load_lds_dword_ds_read
|
|
# GCN: SCRATCH_LOAD_LDS_DWORD
|
|
# GCN-NEXT: S_WAITCNT 3952
|
|
# vmcnt(0)
|
|
# GCN-NEXT: DS_READ_B32_gfx9
|
|
---
|
|
name: scratch_load_lds_dword_ds_read
|
|
body: |
|
|
bb.0:
|
|
$m0 = S_MOV_B32 0
|
|
SCRATCH_LOAD_LDS_DWORD $vgpr0, 4, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(5) undef` + 4), (store (s32) into `ptr addrspace(3) undef` + 4)
|
|
$vgpr0 = DS_READ_B32_gfx9 $vgpr1, 0, 0, implicit $m0, implicit $exec :: (load (s32) from `ptr addrspace(3) undef`)
|
|
S_ENDPGM 0
|
|
|
|
...
|
|
|
|
# GCN-LABEL: name: buffer_store_lds_dword_ds_read
|
|
# GCN: BUFFER_STORE_LDS_DWORD
|
|
# GCN-NEXT: DS_READ_B32_gfx9
|
|
---
|
|
name: buffer_store_lds_dword_ds_read
|
|
body: |
|
|
bb.0:
|
|
$m0 = S_MOV_B32 0
|
|
BUFFER_STORE_LDS_DWORD $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 4, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(3) undef` + 4), (store (s32) into `ptr addrspace(1) undef` + 4)
|
|
$vgpr0 = DS_READ_B32_gfx9 $vgpr1, 0, 0, implicit $m0, implicit $exec :: (load (s32) from `ptr addrspace(3) undef`)
|
|
S_ENDPGM 0
|
|
|
|
...
|
|
|
|
# No need to wait before load from VMEM to LDS.
|
|
# GCN-LABEL: name: series_of_buffer_load_dword_lds_ds_read
|
|
# GCN: BUFFER_LOAD_DWORD_LDS_IDXEN
|
|
# GCN-NEXT: BUFFER_LOAD_DWORD_LDS_IDXEN
|
|
# GCN-NEXT: BUFFER_LOAD_DWORD_LDS_IDXEN
|
|
# GCN-NEXT: S_WAITCNT 3952
|
|
# vmcnt(0)
|
|
# GCN-NEXT: DS_READ_B32_gfx9
|
|
---
|
|
name: series_of_buffer_load_dword_lds_ds_read
|
|
body: |
|
|
bb.0:
|
|
$m0 = S_MOV_B32 0
|
|
BUFFER_LOAD_DWORD_LDS_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 0, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(1) undef`), (store (s32) into `ptr addrspace(3) undef`)
|
|
BUFFER_LOAD_DWORD_LDS_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 4, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(1) undef` + 4), (store (s32) into `ptr addrspace(3) undef` + 4)
|
|
BUFFER_LOAD_DWORD_LDS_IDXEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4, 8, 0, 0, implicit $exec, implicit $m0 :: (load (s32) from `ptr addrspace(1) undef` + 8), (store (s32) into `ptr addrspace(3) undef` + 8)
|
|
$vgpr0 = DS_READ_B32_gfx9 $vgpr1, 0, 0, implicit $m0, implicit $exec :: (load (s32) from `ptr addrspace(3) undef`)
|
|
S_ENDPGM 0
|
|
|
|
...
|