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
```
37 lines
865 B
LLVM
37 lines
865 B
LLVM
; RUN: llc < %s -mtriple=r600 -mcpu=cayman | FileCheck %s
|
|
|
|
; CHECK-LABEL: {{^}}main:
|
|
; CHECK: LOOP_START_DX10
|
|
; CHECK: ALU_PUSH_BEFORE
|
|
; CHECK: LOOP_START_DX10
|
|
; CHECK: PUSH
|
|
; CHECK-NOT: ALU_PUSH_BEFORE
|
|
; CHECK: END_LOOP
|
|
; CHECK: END_LOOP
|
|
define amdgpu_ps void @main (<4 x float> inreg %reg0) {
|
|
entry:
|
|
br label %outer_loop
|
|
|
|
outer_loop:
|
|
%cnt = phi i32 [0, %entry], [%cnt_incr, %inner_loop]
|
|
%cond = icmp eq i32 %cnt, 16
|
|
br i1 %cond, label %outer_loop_body, label %exit
|
|
|
|
outer_loop_body:
|
|
%cnt_incr = add i32 %cnt, 1
|
|
br label %inner_loop
|
|
|
|
inner_loop:
|
|
%cnt2 = phi i32 [0, %outer_loop_body], [%cnt2_incr, %inner_loop_body]
|
|
%n = load volatile i32, ptr addrspace(1) undef
|
|
%cond2 = icmp slt i32 %cnt2, %n
|
|
br i1 %cond2, label %inner_loop_body, label %outer_loop
|
|
|
|
inner_loop_body:
|
|
%cnt2_incr = add i32 %cnt2, 1
|
|
br label %inner_loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|