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
```
19 lines
604 B
LLVM
19 lines
604 B
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
|
|
|
|
declare half @llvm.amdgcn.sin.f16(half %a)
|
|
|
|
; GCN-LABEL: {{^}}sin_f16
|
|
; GCN: buffer_load_ushort v[[A_F16:[0-9]+]]
|
|
; VI: v_sin_f16_e32 v[[R_F16:[0-9]+]], v[[A_F16]]
|
|
; GCN: buffer_store_short v[[R_F16]]
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @sin_f16(
|
|
ptr addrspace(1) %r,
|
|
ptr addrspace(1) %a) {
|
|
entry:
|
|
%a.val = load half, ptr addrspace(1) %a
|
|
%r.val = call half @llvm.amdgcn.sin.f16(half %a.val)
|
|
store half %r.val, ptr addrspace(1) %r
|
|
ret void
|
|
}
|