mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-24 05:23:45 +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
39 lines
1.8 KiB
LLVM
39 lines
1.8 KiB
LLVM
; RUN: llc -O0 -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=+promote-alloca < %s | FileCheck -check-prefix=NOOPTS -check-prefix=ALL %s
|
|
; RUN: llc -O1 -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=+promote-alloca < %s | FileCheck -check-prefix=OPTS -check-prefix=ALL %s
|
|
|
|
; ALL-LABEL: {{^}}promote_alloca_i32_array_array:
|
|
; NOOPTS: workgroup_group_segment_byte_size = 0{{$}}
|
|
; NOOPTS-NOT ds_write
|
|
; OPTS: ds_write
|
|
define amdgpu_kernel void @promote_alloca_i32_array_array(i32 addrspace(1)* %out, i32 %index) #0 {
|
|
entry:
|
|
%alloca = alloca [2 x [2 x i32]]
|
|
%gep0 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 0
|
|
%gep1 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 1
|
|
store i32 0, i32* %gep0
|
|
store i32 1, i32* %gep1
|
|
%gep2 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 %index
|
|
%load = load i32, i32* %gep2
|
|
store i32 %load, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; ALL-LABEL: {{^}}optnone_promote_alloca_i32_array_array:
|
|
; ALL: workgroup_group_segment_byte_size = 0{{$}}
|
|
; ALL-NOT ds_write
|
|
define amdgpu_kernel void @optnone_promote_alloca_i32_array_array(i32 addrspace(1)* %out, i32 %index) #1 {
|
|
entry:
|
|
%alloca = alloca [2 x [2 x i32]]
|
|
%gep0 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 0
|
|
%gep1 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 1
|
|
store i32 0, i32* %gep0
|
|
store i32 1, i32* %gep1
|
|
%gep2 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 %index
|
|
%load = load i32, i32* %gep2
|
|
store i32 %load, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind "amdgpu-flat-work-group-size"="64,64" }
|
|
attributes #1 = { nounwind optnone noinline "amdgpu-flat-work-group-size"="64,64" }
|