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
```
12 lines
526 B
LLVM
12 lines
526 B
LLVM
; RUN: llc -mtriple=r600 -mcpu=redwood -verify-machineinstrs < %s
|
|
|
|
declare float @llvm.r600.dot4(<4 x float>, <4 x float>) nounwind readnone
|
|
|
|
define amdgpu_kernel void @test_dp4(ptr addrspace(1) %out, ptr addrspace(1) %a, ptr addrspace(1) %b) nounwind {
|
|
%src0 = load <4 x float>, ptr addrspace(1) %a, align 16
|
|
%src1 = load <4 x float>, ptr addrspace(1) %b, align 16
|
|
%dp4 = call float @llvm.r600.dot4(<4 x float> %src0, <4 x float> %src1) nounwind readnone
|
|
store float %dp4, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|