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
```
18 lines
656 B
LLVM
18 lines
656 B
LLVM
;RUN: llc < %s -mtriple=r600 -mcpu=redwood | FileCheck %s
|
|
|
|
;CHECK: MULADD_IEEE * {{T[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
|
|
define amdgpu_ps void @test(<4 x float> inreg %reg0) {
|
|
%r0 = extractelement <4 x float> %reg0, i32 0
|
|
%r1 = extractelement <4 x float> %reg0, i32 1
|
|
%r2 = extractelement <4 x float> %reg0, i32 2
|
|
%r3 = fmul float %r0, %r1
|
|
%r4 = fadd float %r3, %r2
|
|
%vec = insertelement <4 x float> undef, float %r4, i32 0
|
|
call void @llvm.r600.store.swizzle(<4 x float> %vec, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
declare float @fabs(float ) readnone
|
|
declare void @llvm.r600.store.swizzle(<4 x float>, i32, i32)
|