338dee0742
With this PR, if we have customized implementation for scalar or vector length = 2, we don't need to write new macros, e.g. https://github.com/intel/llvm/blob/fb18321705f6/libclc/clc/include/clc/clcmacro.h#L15 Undef __HALF_ONLY, __FLOAT_ONLY and __DOUBLE_ONLY at the end of clc/include/clc/math/gentype.inc llvm-diff shows no change to nvptx64--nvidiacl.bc and amdgcn--amdhsa.bc
28 lines
820 B
Common Lisp
28 lines
820 B
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/clcmacro.h>
|
|
#include <clc/internal/clc.h>
|
|
#include <clc/math/tables.h>
|
|
|
|
#ifdef cl_khr_fp64
|
|
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
|
|
#endif // cl_khr_fp64
|
|
|
|
#ifdef cl_khr_fp16
|
|
#pragma OPENCL EXTENSION cl_khr_fp16 : enable
|
|
#endif // cl_khr_fp16
|
|
|
|
#define COMPILING_LOG2
|
|
#include "clc_log_base.h"
|
|
#undef COMPILING_LOG2
|
|
|
|
#define FUNCTION __clc_log2
|
|
#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
|
|
#include <clc/math/gentype.inc>
|