llvm-diff shows there is no change to amdgcn--amdhsa.bc. Similar to how cl_khr_fp64 and cl_khr_fp16 implementations are put in a same file for math built-ins, this PR do the same to atom_* built-ins. The main motivation is to prevent that two files with same base name implementats different built-ins. In a follow-up PR, I'd like to relax libclc_configure_lib_source to only compare filename instead of path for overriding, since in our downstream the same category of built-ins, e.g. math, are organized in several different folders.
45 lines
1.6 KiB
Common Lisp
45 lines
1.6 KiB
Common Lisp
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include <clc/atomic/atom_min.h>
|
|
|
|
#ifdef cl_khr_global_int32_extended_atomics
|
|
#define __CLC_ATOMIC_OP min
|
|
#define __CLC_ATOMIC_ADDRESS_SPACE global
|
|
#include "atom_int32_binary.inc"
|
|
#endif // cl_khr_global_int32_extended_atomics
|
|
|
|
#ifdef cl_khr_local_int32_extended_atomics
|
|
#define __CLC_ATOMIC_OP min
|
|
#define __CLC_ATOMIC_ADDRESS_SPACE local
|
|
#include "atom_int32_binary.inc"
|
|
#endif // cl_khr_local_int32_extended_atomics
|
|
|
|
#ifdef cl_khr_int64_extended_atomics
|
|
|
|
unsigned long __clc__sync_fetch_and_min_local_8(volatile local long *, long);
|
|
unsigned long __clc__sync_fetch_and_min_global_8(volatile global long *, long);
|
|
unsigned long __clc__sync_fetch_and_umin_local_8(volatile local unsigned long *,
|
|
unsigned long);
|
|
unsigned long
|
|
__clc__sync_fetch_and_umin_global_8(volatile global unsigned long *,
|
|
unsigned long);
|
|
|
|
#define IMPL(AS, TYPE, OP) \
|
|
_CLC_OVERLOAD _CLC_DEF TYPE atom_min(volatile AS TYPE *p, TYPE val) { \
|
|
return __clc__sync_fetch_and_##OP##_##AS##_8(p, val); \
|
|
}
|
|
|
|
IMPL(global, long, min)
|
|
IMPL(global, unsigned long, umin)
|
|
IMPL(local, long, min)
|
|
IMPL(local, unsigned long, umin)
|
|
#undef IMPL
|
|
|
|
#endif // cl_khr_int64_extended_atomics
|