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
20 lines
678 B
Common Lisp
20 lines
678 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>
|
|
|
|
_CLC_OVERLOAD _CLC_DEF float __clc_native_rsqrt(float x) {
|
|
return __builtin_r600_recipsqrt_ieeef(x);
|
|
}
|
|
|
|
#define __FLOAT_ONLY
|
|
#define FUNCTION __clc_native_rsqrt
|
|
#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
|
|
#include <clc/math/gentype.inc>
|