9e9907f1cf
Similar to 806761a7629df268c8aed49657aeccffa6bca449. 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 ```
33 lines
1016 B
YAML
33 lines
1016 B
YAML
# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -run-pass=si-peephole-sdwa -verify-machineinstrs -o - %s | FileCheck -check-prefix=GCN %s
|
|
|
|
# Do not fold stack objects into SDWA.
|
|
|
|
---
|
|
# GCN-LABEL: name: sdwa_stack_object_src0
|
|
# GCN: V_ADD_U32_e64 %stack.0, killed %1
|
|
name: sdwa_stack_object_src0
|
|
stack:
|
|
- { id: 0, type: default, offset: 0, size: 32, alignment: 4, stack-id: default }
|
|
body: |
|
|
bb.0:
|
|
%0:vgpr_32 = IMPLICIT_DEF
|
|
%1:vgpr_32 = V_AND_B32_e32 255, %0, implicit $exec
|
|
%2:vgpr_32 = V_ADD_U32_e64 %stack.0, killed %1, 0, implicit $exec
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|
|
---
|
|
name: sdwa_stack_object_src1
|
|
# GCN-LABEL: name: sdwa_stack_object_src1
|
|
# GCN: V_ADD_U32_e64 killed %1, %stack.0
|
|
stack:
|
|
- { id: 0, type: default, offset: 0, size: 32, alignment: 4, stack-id: default }
|
|
body: |
|
|
bb.0:
|
|
%0:vgpr_32 = IMPLICIT_DEF
|
|
%1:vgpr_32 = V_AND_B32_e32 255, %0, implicit $exec
|
|
%2:vgpr_32 = V_ADD_U32_e64 killed %1, %stack.0, 0, implicit $exec
|
|
S_ENDPGM 0, implicit %2
|
|
|
|
...
|