mirror of
https://github.com/RPCSX/llvm.git
synced 2024-11-23 19:59:57 +00:00
d706d030af
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). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@298444 91177308-0d34-0410-b5e6-96231b3b80d8
19 lines
610 B
LLVM
19 lines
610 B
LLVM
; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
|
|
|
|
declare half @llvm.amdgcn.rcp.f16(half %a)
|
|
|
|
; GCN-LABEL: {{^}}rcp_f16
|
|
; GCN: buffer_load_ushort v[[A_F16:[0-9]+]]
|
|
; VI: v_rcp_f16_e32 v[[R_F16:[0-9]+]], v[[A_F16]]
|
|
; GCN: buffer_store_short v[[R_F16]]
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @rcp_f16(
|
|
half addrspace(1)* %r,
|
|
half addrspace(1)* %a) {
|
|
entry:
|
|
%a.val = load half, half addrspace(1)* %a
|
|
%r.val = call half @llvm.amdgcn.rcp.f16(half %a.val)
|
|
store half %r.val, half addrspace(1)* %r
|
|
ret void
|
|
}
|