mirror of
git://sourceware.org/git/newlib-cygwin.git
synced 2025-01-23 23:47:22 +08:00
e18743072b
This implements a set of vectorized math routines to be used by the compiler auto-vectorizer. Versions for vectors with 2 lanes up to 64 lanes (in powers of 2) are provided. These routines are based on the scalar versions of the math routines in libm/common, libm/math and libm/mathfp. They make extensive use of the GCC C vector extensions and GCN-specific builtins in GCC.
60 lines
2.1 KiB
C
60 lines
2.1 KiB
C
/*
|
|
* Copyright 2023 Siemens
|
|
*
|
|
* The authors hereby grant permission to use, copy, modify, distribute,
|
|
* and license this software and its documentation for any purpose, provided
|
|
* that existing copyright notices are retained in all copies and that this
|
|
* notice is included verbatim in any distributions. No written agreement,
|
|
* license, or royalty fee is required for any of the authorized uses.
|
|
* Modifications to this software may be copyrighted by their authors
|
|
* and need not follow the licensing terms described here, provided that
|
|
* the new terms are clearly indicated on the first page of each file where
|
|
* they apply.
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 1994-2009 Red Hat, Inc. All rights reserved.
|
|
*
|
|
* This copyrighted material is made available to anyone wishing to use,
|
|
* modify, copy, or redistribute it subject to the terms and conditions
|
|
* of the BSD License. This program is distributed in the hope that
|
|
* it will be useful, but WITHOUT ANY WARRANTY expressed or implied,
|
|
* including the implied warranties of MERCHANTABILITY or FITNESS FOR
|
|
* A PARTICULAR PURPOSE. A copy of this license is available at
|
|
* http://www.opensource.org/licenses. Any Red Hat trademarks that are
|
|
* incorporated in the source code or documentation are not subject to
|
|
* the BSD License and may only be used or replicated with the express
|
|
* permission of Red Hat, Inc.
|
|
*/
|
|
|
|
/* Based on newlib/libm/mathfp/sf_numtest.c in Newlib. */
|
|
|
|
#include "amdgcnmach.h"
|
|
|
|
v64si
|
|
v64sf_numtestf (v64sf x)
|
|
{
|
|
// Explicitly create mask for internal function.
|
|
v64si __mask = VECTOR_INIT (-1);
|
|
FUNCTION_INIT (v64si);
|
|
|
|
v64si wx;
|
|
GET_FLOAT_WORD (wx, x, NO_COND);
|
|
v64si exp = (wx & 0x7f800000) >> 23;
|
|
|
|
/* Check for a zero input. */
|
|
VECTOR_RETURN (VECTOR_INIT (0), x == 0.0);
|
|
|
|
/* Check for not a number or infinity. */
|
|
VECTOR_IF (exp == 0xff, cond)
|
|
VECTOR_RETURN (VECTOR_MERGE (VECTOR_INIT (NAN), VECTOR_INIT (INF),
|
|
wx & 0x7fffff),
|
|
cond);
|
|
/* Otherwise it's a finite value. */
|
|
VECTOR_ELSE (cond)
|
|
VECTOR_RETURN (VECTOR_INIT (NUM), cond);
|
|
VECTOR_ENDIF
|
|
|
|
FUNCTION_RETURN;
|
|
}
|