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
```
34 lines
1.4 KiB
LLVM
34 lines
1.4 KiB
LLVM
; RUN: llc -mtriple=amdgcn -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
; Test for a bug where DAGCombiner::ReassociateOps() was creating adds
|
|
; with offset in the first operand and base pointers in the second.
|
|
|
|
; CHECK-LABEL: {{^}}store_same_base_ptr:
|
|
; CHECK: buffer_store_dword v{{[0-9]+}}, [[VADDR:v\[[0-9]+:[0-9]+\]]], [[SADDR:s\[[0-9]+:[0-9]+\]]]
|
|
; CHECK: buffer_store_dword v{{[0-9]+}}, [[VADDR]], [[SADDR]]
|
|
; CHECK: buffer_store_dword v{{[0-9]+}}, [[VADDR]], [[SADDR]]
|
|
; CHECK: buffer_store_dword v{{[0-9]+}}, [[VADDR]], [[SADDR]]
|
|
|
|
define amdgpu_kernel void @store_same_base_ptr(ptr addrspace(1) %out) {
|
|
entry:
|
|
%id = call i32 @llvm.amdgcn.workitem.id.x() #0
|
|
%offset = sext i32 %id to i64
|
|
%offset0 = add i64 %offset, 1027
|
|
%ptr0 = getelementptr i32, ptr addrspace(1) %out, i64 %offset0
|
|
store volatile i32 3, ptr addrspace(1) %ptr0
|
|
%offset1 = add i64 %offset, 1026
|
|
%ptr1 = getelementptr i32, ptr addrspace(1) %out, i64 %offset1
|
|
store volatile i32 2, ptr addrspace(1) %ptr1
|
|
%offset2 = add i64 %offset, 1025
|
|
%ptr2 = getelementptr i32, ptr addrspace(1) %out, i64 %offset2
|
|
store volatile i32 1, ptr addrspace(1) %ptr2
|
|
%offset3 = add i64 %offset, 1024
|
|
%ptr3 = getelementptr i32, ptr addrspace(1) %out, i64 %offset3
|
|
store volatile i32 0, ptr addrspace(1) %ptr3
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #0
|
|
|
|
attributes #0 = { nounwind readnone }
|