9e9907f1cf
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 ```
40 lines
1.2 KiB
LLVM
40 lines
1.2 KiB
LLVM
; RUN: llc < %s -mtriple=amdgcn | FileCheck %s -check-prefix=SI -check-prefix=FUNC
|
|
; RUN: llc < %s -mtriple=amdgcn -mcpu=tonga | FileCheck %s -check-prefix=SI -check-prefix=FUNC
|
|
; RUN: llc < %s -mtriple=r600 -mcpu=redwood | FileCheck %s -check-prefix=EG -check-prefix=FUNC
|
|
|
|
;FUNC-LABEL: test
|
|
;EG: MULADD_IEEE *
|
|
;EG: FRACT *
|
|
;EG: ADD *
|
|
;EG: COS * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
;EG-NOT: COS
|
|
;SI: v_cos_f32
|
|
;SI-NOT: v_cos_f32
|
|
|
|
define amdgpu_kernel void @test(ptr addrspace(1) %out, float %x) #1 {
|
|
%cos = call float @llvm.cos.f32(float %x)
|
|
store float %cos, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
;FUNC-LABEL: testv
|
|
;EG: COS * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
;EG: COS * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
;EG: COS * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
;EG: COS * T{{[0-9]+\.[XYZW], PV\.[XYZW]}}
|
|
;EG-NOT: COS
|
|
;SI: v_cos_f32
|
|
;SI: v_cos_f32
|
|
;SI: v_cos_f32
|
|
;SI: v_cos_f32
|
|
;SI-NOT: v_cos_f32
|
|
|
|
define amdgpu_kernel void @testv(ptr addrspace(1) %out, <4 x float> inreg %vx) #1 {
|
|
%cos = call <4 x float> @llvm.cos.v4f32(<4 x float> %vx)
|
|
store <4 x float> %cos, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.cos.f32(float) readnone
|
|
declare <4 x float> @llvm.cos.v4f32(<4 x float>) readnone
|