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
1.3 KiB
LLVM
31 lines
1.3 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx908 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; Check that we do not use AGPRs for v32i32 type
|
|
|
|
; GCN-LABEL: {{^}}test_v1024:
|
|
; GCN-NOT: v_accvgpr
|
|
; GCN-COUNT-8: global_store_dwordx4
|
|
; GCN-NOT: v_accvgpr
|
|
define amdgpu_kernel void @test_v1024(i1 %c0) {
|
|
entry:
|
|
%alloca = alloca <32 x i32>, align 16, addrspace(5)
|
|
call void @llvm.memset.p5.i32(ptr addrspace(5) %alloca, i8 0, i32 128, i1 false)
|
|
br i1 %c0, label %if.then.i.i, label %if.else.i
|
|
|
|
if.then.i.i: ; preds = %entry
|
|
call void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) align 16 %alloca, ptr addrspace(5) align 4 undef, i64 128, i1 false)
|
|
br label %if.then.i62.i
|
|
|
|
if.else.i: ; preds = %entry
|
|
br label %if.then.i62.i
|
|
|
|
if.then.i62.i: ; preds = %if.else.i, %if.then.i.i
|
|
call void @llvm.memcpy.p1.p5.i64(ptr addrspace(1) align 4 undef, ptr addrspace(5) align 16 %alloca, i64 128, i1 false)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.memset.p5.i32(ptr addrspace(5) nocapture readonly, i8, i32, i1 immarg)
|
|
declare void @llvm.memcpy.p5.p5.i64(ptr addrspace(5) nocapture writeonly, ptr addrspace(5) nocapture readonly, i64, i1 immarg)
|
|
|
|
declare void @llvm.memcpy.p1.p5.i64(ptr addrspace(1) nocapture writeonly, ptr addrspace(5) nocapture readonly, i64, i1 immarg)
|