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
```
27 lines
541 B
LLVM
27 lines
541 B
LLVM
; RUN: llc -mtriple=amdgcn -O0 -o - %s | FileCheck %s
|
|
|
|
; CHECK-LABEL: non_uniform_loop
|
|
; CHECK: s_endpgm
|
|
define amdgpu_kernel void @non_uniform_loop(ptr addrspace(1) %array) {
|
|
entry:
|
|
%w = tail call i32 @llvm.amdgcn.workitem.id.x()
|
|
br label %for.cond
|
|
|
|
for.cond:
|
|
%i = phi i32 [0, %entry], [%i.next, %for.inc]
|
|
%cmp = icmp ult i32 %i, %w
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
br label %for.inc
|
|
|
|
for.inc:
|
|
%i.next = add i32 %i, 1
|
|
br label %for.cond
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x()
|