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
```
26 lines
760 B
LLVM
26 lines
760 B
LLVM
; RUN: llc -mtriple=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: @bfe_uniform
|
|
; GCN: s_bfe_u32 s{{[0-9]+}}, s{{[0-9]+}}, 0x40010
|
|
define amdgpu_kernel void @bfe_uniform(i32 %val, ptr addrspace(1) %out) {
|
|
%hibits = lshr i32 %val, 16
|
|
%masked = and i32 %hibits, 15
|
|
store i32 %masked, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: @bfe_divergent
|
|
; GCN: v_bfe_u32 v{{[0-9]+}}, v{{[0-9]+}}, 16, 4
|
|
define amdgpu_kernel void @bfe_divergent(i32 %val, ptr addrspace(1) %out) {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%divergent = add i32 %val, %tid
|
|
%hibits = lshr i32 %divergent, 16
|
|
%masked = and i32 %hibits, 15
|
|
store i32 %masked, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x()
|
|
|