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.
72 lines
2.5 KiB
C++
72 lines
2.5 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_VLOAD_NAME(x) __CLC_XCONCAT(__CLC_XCONCAT(x, vload), __CLC_VECSIZE)
|
|
#define CLC_VLOAD_HALF_NAME(x) \
|
|
__CLC_XCONCAT(__CLC_XCONCAT(x, vload_half), __CLC_VECSIZE)
|
|
#define CLC_VLOADA_HALF_NAME(x) \
|
|
__CLC_XCONCAT(__CLC_XCONCAT(x, vloada_half), __CLC_VECSIZE)
|
|
|
|
#ifndef __CLC_SCALAR
|
|
|
|
#define CLC_VLOAD_TY __CLC_XCONCAT(less_aligned_, __CLC_GENTYPE)
|
|
|
|
#define VLOAD_DEF(ADDRSPACE) \
|
|
_CLC_OVERLOAD _CLC_DEF CLC_VLOAD_TY CLC_VLOAD_NAME()( \
|
|
size_t offset, const ADDRSPACE __CLC_SCALAR_GENTYPE *x) { \
|
|
return CLC_VLOAD_NAME(__clc_)(offset, x); \
|
|
}
|
|
|
|
VLOAD_DEF(__private)
|
|
VLOAD_DEF(__local)
|
|
VLOAD_DEF(__constant)
|
|
VLOAD_DEF(__global)
|
|
|
|
#if _CLC_DISTINCT_GENERIC_AS_SUPPORTED
|
|
VLOAD_DEF(__generic)
|
|
#endif
|
|
|
|
#undef VLOAD_DEF
|
|
#undef CLC_VLOAD_TY
|
|
|
|
#endif
|
|
|
|
// vload_half and vloada_half are available even if cl_khr_fp16 is unavailable.
|
|
// Declare these functions when working on float types, which we know are
|
|
// always available.
|
|
#ifdef __CLC_FPSIZE
|
|
#if __CLC_FPSIZE == 32
|
|
|
|
#define VLOAD_HALF_DEF(ADDRSPACE) \
|
|
_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE CLC_VLOAD_HALF_NAME()( \
|
|
size_t offset, const ADDRSPACE half *mem) { \
|
|
return CLC_VLOAD_HALF_NAME(__clc_)(offset, mem); \
|
|
} \
|
|
\
|
|
_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE CLC_VLOADA_HALF_NAME()( \
|
|
size_t offset, const ADDRSPACE half *mem) { \
|
|
return CLC_VLOADA_HALF_NAME(__clc_)(offset, mem); \
|
|
}
|
|
|
|
VLOAD_HALF_DEF(__private)
|
|
VLOAD_HALF_DEF(__local)
|
|
VLOAD_HALF_DEF(__constant)
|
|
VLOAD_HALF_DEF(__global)
|
|
|
|
#if _CLC_DISTINCT_GENERIC_AS_SUPPORTED
|
|
VLOAD_HALF_DEF(__generic)
|
|
#endif
|
|
|
|
#undef VLOAD_HALF_DEF
|
|
#endif
|
|
#endif
|
|
|
|
#undef CLC_VLOAD_NAME
|
|
#undef CLC_VLOAD_HALF_NAME
|
|
#undef CLC_VLOADA_HALF_NAME
|