82912fd620
This commit bulk-updates the libclc license headers to the current Apache-2.0 WITH LLVM-exception license in situations where they were previously attributed to AMD - and occasionally under an additional single individual contributor - under an MIT license. AMD signed the LLVM relicensing agreement and so agreed for their past contributions under the new LLVM license. The LLVM project also has had a long-standing, unwritten, policy of not adding copyright notices to source code. This policy was recently written up [1]. This commit therefore also removes these copyright notices at the same time. Note that there are outstanding copyright notices attributed to others - and many files missing copyright headers - which will be dealt with in future work. [1] https://llvm.org/docs/DeveloperPolicy.html#embedded-copyright-or-contributed-by-statements
73 lines
1.7 KiB
Common Lisp
73 lines
1.7 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 "sincos_helpers.h"
|
|
#include <clc/clc.h>
|
|
#include <clc/clcmacro.h>
|
|
#include <clc/math/math.h>
|
|
|
|
_CLC_OVERLOAD _CLC_DEF float sin(float x)
|
|
{
|
|
int ix = as_int(x);
|
|
int ax = ix & 0x7fffffff;
|
|
float dx = as_float(ax);
|
|
|
|
float r0, r1;
|
|
int regn = __clc_argReductionS(&r0, &r1, dx);
|
|
|
|
float ss = __clc_sinf_piby4(r0, r1);
|
|
float cc = __clc_cosf_piby4(r0, r1);
|
|
|
|
float s = (regn & 1) != 0 ? cc : ss;
|
|
s = as_float(as_int(s) ^ ((regn > 1) << 31) ^ (ix ^ ax));
|
|
|
|
s = ax >= PINFBITPATT_SP32 ? as_float(QNANBITPATT_SP32) : s;
|
|
|
|
//Subnormals
|
|
s = x == 0.0f ? x : s;
|
|
|
|
return s;
|
|
}
|
|
|
|
_CLC_UNARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, float, sin, float);
|
|
|
|
#ifdef cl_khr_fp64
|
|
|
|
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
|
|
|
|
_CLC_OVERLOAD _CLC_DEF double sin(double x) {
|
|
double y = fabs(x);
|
|
|
|
double r, rr;
|
|
int regn;
|
|
|
|
if (y < 0x1.0p+47)
|
|
__clc_remainder_piby2_medium(y, &r, &rr, ®n);
|
|
else
|
|
__clc_remainder_piby2_large(y, &r, &rr, ®n);
|
|
|
|
double2 sc = __clc_sincos_piby4(r, rr);
|
|
|
|
int2 s = as_int2(regn & 1 ? sc.hi : sc.lo);
|
|
s.hi ^= ((regn > 1) << 31) ^ ((x < 0.0) << 31);
|
|
|
|
return isinf(x) | isnan(x) ? as_double(QNANBITPATT_DP64) : as_double(s);
|
|
}
|
|
|
|
_CLC_UNARY_VECTORIZE(_CLC_OVERLOAD _CLC_DEF, double, sin, double);
|
|
|
|
#endif
|
|
|
|
#ifdef cl_khr_fp16
|
|
|
|
#pragma OPENCL EXTENSION cl_khr_fp16 : enable
|
|
|
|
_CLC_DEFINE_UNARY_BUILTIN_FP16(sin)
|
|
|
|
#endif
|