Files
clang-p2996/llvm/test/CodeGen/AMDGPU/ffloor.ll
Fangrui Song 9e9907f1cf [AMDGPU,test] Change llc -march= to -mtriple= (#75982)
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
```
2024-01-16 21:54:58 -08:00

50 lines
1.5 KiB
LLVM

; RUN: llc -mtriple=amdgcn -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
; RUN: llc -mtriple=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
; FUNC-LABEL: {{^}}floor_f32:
; SI: v_floor_f32_e32
; R600: FLOOR
define amdgpu_kernel void @floor_f32(ptr addrspace(1) %out, float %in) {
%tmp = call float @llvm.floor.f32(float %in) #0
store float %tmp, ptr addrspace(1) %out
ret void
}
; FUNC-LABEL: {{^}}floor_v2f32:
; SI: v_floor_f32_e32
; SI: v_floor_f32_e32
define amdgpu_kernel void @floor_v2f32(ptr addrspace(1) %out, <2 x float> %in) {
%tmp = call <2 x float> @llvm.floor.v2f32(<2 x float> %in) #0
store <2 x float> %tmp, ptr addrspace(1) %out
ret void
}
; FUNC-LABEL: {{^}}floor_v4f32:
; SI: v_floor_f32_e32
; SI: v_floor_f32_e32
; SI: v_floor_f32_e32
; SI: v_floor_f32_e32
; R600: FLOOR
; R600: FLOOR
; R600: FLOOR
; R600: FLOOR
define amdgpu_kernel void @floor_v4f32(ptr addrspace(1) %out, <4 x float> %in) {
%tmp = call <4 x float> @llvm.floor.v4f32(<4 x float> %in) #0
store <4 x float> %tmp, ptr addrspace(1) %out
ret void
}
; Function Attrs: nounwind readonly
declare float @llvm.floor.f32(float) #0
; Function Attrs: nounwind readonly
declare <2 x float> @llvm.floor.v2f32(<2 x float>) #0
; Function Attrs: nounwind readonly
declare <4 x float> @llvm.floor.v4f32(<4 x float>) #0
attributes #0 = { nounwind readnone }