Fangrui Song 9e9907f1cf
[AMDGPU,test] Change llc -march= to -mtriple= (#75982)
Similar to 806761a7629df268c8aed49657aeccffa6bca449.

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
```
2024-01-16 21:54:58 -08:00

27 lines
782 B
LLVM

; RUN: llc < %s -mtriple=r600 -mcpu=redwood | FileCheck %s
; CHECK: {{^}}bfe_def:
; CHECK: BFE_UINT
define amdgpu_kernel void @bfe_def(ptr addrspace(1) %out, i32 %x) {
entry:
%0 = lshr i32 %x, 5
%1 = and i32 %0, 15 ; 0xf
store i32 %1, ptr addrspace(1) %out
ret void
}
; This program could be implemented using a BFE_UINT instruction, however
; since the lshr constant + number of bits in the mask is >= 32, it can also be
; implmented with a LSHR instruction, which is better, because LSHR has less
; operands and requires less constants.
; CHECK: {{^}}bfe_shift:
; CHECK-NOT: BFE_UINT
define amdgpu_kernel void @bfe_shift(ptr addrspace(1) %out, i32 %x) {
entry:
%0 = lshr i32 %x, 16
%1 = and i32 %0, 65535 ; 0xffff
store i32 %1, ptr addrspace(1) %out
ret void
}