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
561 B
LLVM
19 lines
561 B
LLVM
; RUN: opt -mtriple=amdgcn-- -codegenprepare -S < %s | FileCheck -check-prefix=OPT %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=SI-LLC %s
|
|
|
|
; OPT-LABEL: @test(
|
|
; OPT: mul nsw i32
|
|
; OPT-NEXT: sext
|
|
|
|
; SI-LLC-LABEL: {{^}}test:
|
|
; SI-LLC: s_mul_i32
|
|
; SI-LLC-NOT: mul
|
|
define amdgpu_kernel void @test(ptr addrspace(1) nocapture readonly %in, i32 %a, i8 %b) {
|
|
entry:
|
|
%0 = mul nsw i32 %a, 3
|
|
%1 = sext i32 %0 to i64
|
|
%2 = getelementptr i8, ptr addrspace(1) %in, i64 %1
|
|
store i8 %b, ptr addrspace(1) %2
|
|
ret void
|
|
}
|