b474c3f69e
This commit moves the various vload and vstore builtins (including vload_half, vloada_half, etc.) to the CLC library. This is almost entirely a code move and does not make any attempt to clean up or optimize the definitions of these builtins. There is no change to any of the targets' builtin libraries, except that the vstore helper rounding functions are now internalized. Cleanups can come in future work. The new CLC declarations and new OpenCL wrappers show how these CLC implementations could be defined more simply. The builtins could probably also be vectorized in future work; right now all of the 'half' versions for both vload and vstore are essentially scalarized.
78 lines
3.1 KiB
C++
78 lines
3.1 KiB
C++
//===----------------------------------------------------------------------===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#define CLC_VSTORE_TY __CLC_XCONCAT(less_aligned_, __CLC_GENTYPE)
|
|
#define CLC_VSTORE_NAME(x) \
|
|
__CLC_XCONCAT(__CLC_XCONCAT(x, vstore), __CLC_VECSIZE)
|
|
#define CLC_VSTORE_HALF_NAME(x, y) \
|
|
__CLC_XCONCAT(__CLC_XCONCAT(__CLC_XCONCAT(x, vstore_half), __CLC_VECSIZE), y)
|
|
#define CLC_VSTOREA_HALF_NAME(x, y) \
|
|
__CLC_XCONCAT(__CLC_XCONCAT(__CLC_XCONCAT(x, vstorea_half), __CLC_VECSIZE), y)
|
|
|
|
#ifndef __CLC_SCALAR
|
|
|
|
#define CLC_VSTORE_DEF(ADDRSPACE) \
|
|
_CLC_OVERLOAD _CLC_DEF void CLC_VSTORE_NAME()( \
|
|
CLC_VSTORE_TY data, size_t offset, ADDRSPACE __CLC_SCALAR_GENTYPE *p) { \
|
|
return CLC_VSTORE_NAME(__clc_)(data, offset, p); \
|
|
}
|
|
|
|
CLC_VSTORE_DEF(__private)
|
|
CLC_VSTORE_DEF(__local)
|
|
CLC_VSTORE_DEF(__global)
|
|
|
|
#if _CLC_DISTINCT_GENERIC_AS_SUPPORTED
|
|
CLC_VSTORE_DEF(__generic)
|
|
#endif
|
|
|
|
#undef CLC_VSTORE_DEF
|
|
|
|
#endif // __CLC_SCALAR
|
|
|
|
// vstore_half and vstorea_half are available even if cl_khr_fp16 is
|
|
// unavailable.
|
|
#ifdef __CLC_FPSIZE
|
|
#if __CLC_FPSIZE == 32 || __CLC_FPSIZE == 64
|
|
|
|
#define CLC_VSTORE_HALF_DEF(ADDRSPACE, SUFFIX) \
|
|
_CLC_OVERLOAD _CLC_DEF void CLC_VSTORE_HALF_NAME(, SUFFIX)( \
|
|
CLC_VSTORE_TY data, size_t offset, ADDRSPACE half *p) { \
|
|
CLC_VSTORE_HALF_NAME(__clc_, SUFFIX)(data, offset, p); \
|
|
} \
|
|
\
|
|
_CLC_OVERLOAD _CLC_DEF void CLC_VSTOREA_HALF_NAME(, SUFFIX)( \
|
|
CLC_VSTORE_TY data, size_t offset, ADDRSPACE half *p) { \
|
|
CLC_VSTOREA_HALF_NAME(__clc_, SUFFIX)(data, offset, p); \
|
|
}
|
|
|
|
#define CLC_VSTORE_HALF_DEF_ALL_MODES(ADDRSPACE) \
|
|
CLC_VSTORE_HALF_DEF(ADDRSPACE, ) \
|
|
CLC_VSTORE_HALF_DEF(ADDRSPACE, _rtz) \
|
|
CLC_VSTORE_HALF_DEF(ADDRSPACE, _rtn) \
|
|
CLC_VSTORE_HALF_DEF(ADDRSPACE, _rtp) \
|
|
CLC_VSTORE_HALF_DEF(ADDRSPACE, _rte)
|
|
|
|
CLC_VSTORE_HALF_DEF_ALL_MODES(__private)
|
|
CLC_VSTORE_HALF_DEF_ALL_MODES(__local)
|
|
CLC_VSTORE_HALF_DEF_ALL_MODES(__global)
|
|
|
|
#if _CLC_DISTINCT_GENERIC_AS_SUPPORTED
|
|
CLC_VSTORE_HALF_DEF_ALL_MODES(__generic)
|
|
#endif
|
|
|
|
#undef CLC_VSTORE_HALF_DEF
|
|
#undef CLC_VSTORE_HALF_DEF_ALL_MODES
|
|
|
|
#endif
|
|
#endif
|
|
|
|
#undef CLC_VSTORE_TY
|
|
#undef CLC_VSTORE_NAME
|
|
#undef CLC_VSTORE_HALF_NAME
|
|
#undef CLC_VSTOREA_HALF_NAME
|