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
```
19 lines
593 B
LLVM
19 lines
593 B
LLVM
; RUN: llc -mtriple=amdgcn -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
declare float @llvm.amdgcn.fdiv.fast(float, float) #0
|
|
|
|
; CHECK-LABEL: {{^}}test_fdiv_fast:
|
|
; CHECK: v_cndmask_b32_e32 v{{[0-9]+}}, 1.0, v{{[0-9]+}}, vcc
|
|
; CHECK: v_mul_f32_e32
|
|
; CHECK: v_rcp_f32_e32
|
|
; CHECK: v_mul_f32_e32
|
|
; CHECK: v_mul_f32_e32
|
|
define amdgpu_kernel void @test_fdiv_fast(ptr addrspace(1) %out, float %a, float %b) #1 {
|
|
%fdiv = call float @llvm.amdgcn.fdiv.fast(float %a, float %b)
|
|
store float %fdiv, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone }
|
|
attributes #1 = { nounwind }
|