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
```
31 lines
1.2 KiB
LLVM
31 lines
1.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck %s
|
|
|
|
declare double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr nocapture, double) #8
|
|
|
|
define protected amdgpu_kernel void @IllegalGEPConst(i32 %a, ptr addrspace(1) %b, double %c) {
|
|
; CHECK-LABEL: IllegalGEPConst:
|
|
; CHECK: ; %bb.0: ; %entry
|
|
; CHECK-NEXT: s_load_dword s2, s[0:1], 0x24
|
|
; CHECK-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x2c
|
|
; CHECK-NEXT: v_mov_b32_e32 v2, 0
|
|
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
|
|
; CHECK-NEXT: s_ashr_i32 s3, s2, 31
|
|
; CHECK-NEXT: s_lshl_b64 s[0:1], s[2:3], 3
|
|
; CHECK-NEXT: s_add_u32 s0, s4, s0
|
|
; CHECK-NEXT: v_mov_b32_e32 v0, s6
|
|
; CHECK-NEXT: v_mov_b32_e32 v1, s7
|
|
; CHECK-NEXT: s_addc_u32 s1, s5, s1
|
|
; CHECK-NEXT: global_atomic_add_f64 v2, v[0:1], s[0:1] offset:-8
|
|
; CHECK-NEXT: s_endpgm
|
|
entry:
|
|
%i = add nsw i32 %a, -1
|
|
%i.2 = sext i32 %i to i64
|
|
%i.3 = getelementptr inbounds double, ptr addrspace(1) %b, i64 %i.2
|
|
%i.4 = addrspacecast ptr addrspace(1) %i.3 to ptr
|
|
%i.5 = tail call contract double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr %i.4, double %c) #8
|
|
ret void
|
|
}
|
|
|
|
attributes #8 = { argmemonly mustprogress nounwind willreturn "target-cpu"="gfx90a" }
|