9e9907f1cf
Similar to 806761a7629df268c8aed49657aeccffa6bca449. 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 ```
30 lines
825 B
LLVM
30 lines
825 B
LLVM
; RUN: opt -passes=loop-unroll -unroll-threshold=2000 -S < %s | llc -mtriple=r600 -mcpu=cypress | FileCheck %s
|
|
; REQUIRES: asserts
|
|
|
|
; CHECK: {{^}}alu_limits:
|
|
; CHECK: CF_END
|
|
|
|
%struct.foo = type {i32, i32, i32}
|
|
|
|
define amdgpu_kernel void @alu_limits(ptr addrspace(1) %out, ptr addrspace(5) %in, i32 %offset) {
|
|
entry:
|
|
%ptr = getelementptr inbounds %struct.foo, ptr addrspace(5) %in, i32 1, i32 2
|
|
%x = load i32, ptr addrspace(5) %ptr, align 4
|
|
br label %loop
|
|
loop:
|
|
%i = phi i32 [ 100, %entry ], [ %nexti, %loop ]
|
|
%val = phi i32 [ 1, %entry ], [ %nextval, %loop ]
|
|
|
|
%nexti = sub i32 %i, 1
|
|
|
|
%y = xor i32 %x, %i
|
|
%nextval = mul i32 %val, %y
|
|
|
|
%cond = icmp ne i32 %nexti, 0
|
|
br i1 %cond, label %loop, label %end
|
|
end:
|
|
%out_val = add i32 %nextval, 4
|
|
store i32 %out_val, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|