mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 20:43:44 +02:00
dd9ab77318
Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
23 lines
914 B
LLVM
23 lines
914 B
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
|
|
|
|
declare i32 @llvm.amdgcn.mbcnt.lo(i32, i32) #0
|
|
declare i32 @llvm.amdgcn.mbcnt.hi(i32, i32) #0
|
|
|
|
; SI-LABEL: {{^}}test_array_ptr_calc:
|
|
; SI-DAG: v_mul_lo_i32
|
|
; SI-DAG: v_mul_hi_i32
|
|
; SI: s_endpgm
|
|
define amdgpu_kernel void @test_array_ptr_calc(i32 addrspace(1)* noalias %out, [1025 x i32] addrspace(1)* noalias %inA, i32 addrspace(1)* noalias %inB) {
|
|
%mbcnt.lo = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0)
|
|
%tid = call i32 @llvm.amdgcn.mbcnt.hi(i32 -1, i32 %mbcnt.lo)
|
|
%a_ptr = getelementptr [1025 x i32], [1025 x i32] addrspace(1)* %inA, i32 %tid, i32 0
|
|
%b_ptr = getelementptr i32, i32 addrspace(1)* %inB, i32 %tid
|
|
%a = load i32, i32 addrspace(1)* %a_ptr
|
|
%b = load i32, i32 addrspace(1)* %b_ptr
|
|
%result = add i32 %a, %b
|
|
store i32 %result, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind readnone }
|