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
45 lines
1.1 KiB
Common Lisp
45 lines
1.1 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/clcmacro.h>
|
|
#include <clc/float/definitions.h>
|
|
#include <clc/internal/clc.h>
|
|
#include <clc/math/clc_log2.h>
|
|
|
|
/*
|
|
*log(x) = log2(x) * (1/log2(e))
|
|
*/
|
|
|
|
_CLC_OVERLOAD _CLC_DEF float __clc_log(float x) {
|
|
return __clc_log2(x) * (1.0f / M_LOG2E_F);
|
|
}
|
|
|
|
#ifdef cl_khr_fp64
|
|
|
|
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
|
|
|
|
_CLC_OVERLOAD _CLC_DEF double __clc_log(double x) {
|
|
return __clc_log2(x) * (1.0 / M_LOG2E);
|
|
}
|
|
|
|
#endif // cl_khr_fp64
|
|
|
|
#ifdef cl_khr_fp16
|
|
|
|
#pragma OPENCL EXTENSION cl_khr_fp16 : enable
|
|
|
|
_CLC_OVERLOAD _CLC_DEF half __clc_log(half x) {
|
|
return (half)__clc_log2((float)x) * (1.0h / M_LOG2E_H);
|
|
}
|
|
|
|
#endif // cl_khr_fp16
|
|
|
|
#define FUNCTION __clc_log
|
|
#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
|
|
#include <clc/math/gentype.inc>
|