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
826 B
LLVM
19 lines
826 B
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}truncstore_arg_v16i32_to_v16i8:
|
|
; SI: buffer_store_dwordx4
|
|
define amdgpu_kernel void @truncstore_arg_v16i32_to_v16i8(ptr addrspace(1) %out, <16 x i32> %in) {
|
|
%trunc = trunc <16 x i32> %in to <16 x i8>
|
|
store <16 x i8> %trunc, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}truncstore_arg_v16i64_to_v16i8:
|
|
; SI: buffer_store_dwordx4
|
|
define amdgpu_kernel void @truncstore_arg_v16i64_to_v16i8(ptr addrspace(1) %out, <16 x i64> %in) {
|
|
%trunc = trunc <16 x i64> %in to <16 x i8>
|
|
store <16 x i8> %trunc, ptr addrspace(1) %out
|
|
ret void
|
|
}
|