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 ```
15 lines
735 B
LLVM
15 lines
735 B
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; Check that write mask is 0xf.
|
|
|
|
; GCN-LABEL: {{^}}sample_2d_vectorized_use:
|
|
; GCN: image_sample v[{{[0-9:]+}}], v[{{[0-9:]+}}], s[{{[0-9:]+}}], s[{{[0-9:]+}}] dmask:0xf
|
|
define amdgpu_ps <4 x float> @sample_2d_vectorized_use(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s, float %t, <4 x float> %a) {
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32 15, float %s, float %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%r = fadd <4 x float> %v, %a
|
|
ret <4 x float> %r
|
|
}
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32)
|