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
```
23 lines
895 B
LLVM
23 lines
895 B
LLVM
; RUN: llc -mtriple=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
|
|
|
|
declare i32 @llvm.amdgcn.mbcnt.lo(i32, i32) #0
|
|
declare i32 @llvm.amdgcn.mbcnt.hi(i32, i32) #0
|
|
|
|
; SI-LABEL: {{^}}test_array_ptr_calc:
|
|
; SI-DAG: v_mul_u32_u24
|
|
; SI-DAG: v_mul_hi_u32_u24
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @test_array_ptr_calc(ptr addrspace(1) noalias %out, ptr addrspace(1) noalias %inA, ptr addrspace(1) noalias %inB) {
|
|
%mbcnt.lo = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0)
|
|
%tid = call i32 @llvm.amdgcn.mbcnt.hi(i32 -1, i32 %mbcnt.lo)
|
|
%a_ptr = getelementptr [1025 x i32], ptr addrspace(1) %inA, i32 %tid, i32 0
|
|
%b_ptr = getelementptr i32, ptr addrspace(1) %inB, i32 %tid
|
|
%a = load i32, ptr addrspace(1) %a_ptr
|
|
%b = load i32, ptr addrspace(1) %b_ptr
|
|
%result = add i32 %a, %b
|
|
store i32 %result, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone }
|