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
```
20 lines
1.1 KiB
YAML
20 lines
1.1 KiB
YAML
# RUN: llc -mtriple=amdgcn -mcpu=tonga %s -start-before detect-dead-lanes -stop-before machine-scheduler -verify-machineinstrs -o - | FileCheck -check-prefix=GCN %s
|
|
# RUN: llc -mtriple=amdgcn -mcpu=tonga %s -start-before detect-dead-lanes -stop-before machine-scheduler -verify-machineinstrs -early-live-intervals -o - | FileCheck -check-prefix=GCN %s
|
|
|
|
# GCN-LABEL: name: dead_lane
|
|
# GCN: bb.0:
|
|
# GCN-NEXT: %5:vgpr_32 = nofpexcept V_MAC_F32_e32 undef %1:vgpr_32, undef %1:vgpr_32, undef %5, implicit $mode, implicit $exec
|
|
# GCN-NEXT: FLAT_STORE_DWORD undef %4:vreg_64, %5,
|
|
---
|
|
name: dead_lane
|
|
tracksRegLiveness: true
|
|
body: |
|
|
bb.0:
|
|
%1:vgpr_32 = nofpexcept V_MAC_F32_e32 undef %0:vgpr_32, undef %0:vgpr_32, undef %0:vgpr_32, implicit $mode, implicit $exec
|
|
%2:vgpr_32 = nofpexcept V_MAC_F32_e32 undef %0:vgpr_32, undef %0:vgpr_32, undef %0:vgpr_32, implicit $mode, implicit $exec
|
|
%3:vreg_64 = REG_SEQUENCE %1:vgpr_32, %subreg.sub0, %2:vgpr_32, %subreg.sub1
|
|
FLAT_STORE_DWORD undef %4:vreg_64, %3.sub0, 0, 0, implicit $exec, implicit $flat_scr
|
|
S_ENDPGM 0
|
|
|
|
...
|