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
```
40 lines
1.6 KiB
LLVM
40 lines
1.6 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck --check-prefixes=GCN,GCN-FMF,GCN-SAFE %s
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
|
|
|
|
; Test that the -enable-no-signed-zeros-fp-math flag works
|
|
|
|
; GCN-LABEL: {{^}}fneg_fsub_f32_fmf:
|
|
; GCN: v_sub_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
|
|
; GCN-FMF-NOT: xor
|
|
define amdgpu_kernel void @fneg_fsub_f32_fmf(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%add = add i32 %tid, 1
|
|
%gep = getelementptr float, ptr addrspace(1) %in, i32 %tid
|
|
%b_ptr = getelementptr float, ptr addrspace(1) %in, i32 %add
|
|
%a = load float, ptr addrspace(1) %gep, align 4
|
|
%b = load float, ptr addrspace(1) %b_ptr, align 4
|
|
%result = fsub fast float %a, %b
|
|
%neg.result = fsub fast float -0.0, %result
|
|
store float %neg.result, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}fneg_fsub_f32_safe:
|
|
; GCN: v_sub_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
|
|
; GCN-SAFE: v_xor_b32_e32 v{{[0-9]+}}, 0x80000000, [[SUB]]
|
|
define amdgpu_kernel void @fneg_fsub_f32_safe(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%add = add i32 %tid, 1
|
|
%gep = getelementptr float, ptr addrspace(1) %in, i32 %tid
|
|
%b_ptr = getelementptr float, ptr addrspace(1) %in, i32 %add
|
|
%a = load float, ptr addrspace(1) %gep, align 4
|
|
%b = load float, ptr addrspace(1) %b_ptr, align 4
|
|
%result = fsub float %a, %b
|
|
%neg.result = fsub float -0.0, %result
|
|
store float %neg.result, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|