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
```
52 lines
1.5 KiB
LLVM
52 lines
1.5 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10 %s
|
|
|
|
; GCN-LABEL: {{^}}add_var_var_i1:
|
|
; GFX9: s_xor_b64
|
|
; GFX10: s_xor_b32
|
|
define amdgpu_kernel void @add_var_var_i1(ptr addrspace(1) %out, ptr addrspace(1) %in0, ptr addrspace(1) %in1) {
|
|
%a = load volatile i1, ptr addrspace(1) %in0
|
|
%b = load volatile i1, ptr addrspace(1) %in1
|
|
%add = add i1 %a, %b
|
|
store i1 %add, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}add_var_imm_i1:
|
|
; GFX9: s_not_b64
|
|
; GFX10: s_not_b32
|
|
define amdgpu_kernel void @add_var_imm_i1(ptr addrspace(1) %out, ptr addrspace(1) %in) {
|
|
%a = load volatile i1, ptr addrspace(1) %in
|
|
%add = add i1 %a, 1
|
|
store i1 %add, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}add_i1_cf:
|
|
; GCN: ; %endif
|
|
; GFX9: s_not_b64
|
|
; GFX10: s_not_b32
|
|
define amdgpu_kernel void @add_i1_cf(ptr addrspace(1) %out, ptr addrspace(1) %a, ptr addrspace(1) %b) {
|
|
entry:
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%d_cmp = icmp ult i32 %tid, 16
|
|
br i1 %d_cmp, label %if, label %else
|
|
|
|
if:
|
|
%0 = load volatile i1, ptr addrspace(1) %a
|
|
br label %endif
|
|
|
|
else:
|
|
%1 = load volatile i1, ptr addrspace(1) %b
|
|
br label %endif
|
|
|
|
endif:
|
|
%2 = phi i1 [%0, %if], [%1, %else]
|
|
%3 = add i1 %2, -1
|
|
store i1 %3, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x()
|