| 1 |
148 |
jeremybenn |
/* -------------------------------------------------------------- */
|
| 2 |
|
|
/* (C)Copyright 2001,2008, */
|
| 3 |
|
|
/* International Business Machines Corporation, */
|
| 4 |
|
|
/* Sony Computer Entertainment, Incorporated, */
|
| 5 |
|
|
/* Toshiba Corporation, */
|
| 6 |
|
|
/* */
|
| 7 |
|
|
/* All Rights Reserved. */
|
| 8 |
|
|
/* */
|
| 9 |
|
|
/* Redistribution and use in source and binary forms, with or */
|
| 10 |
|
|
/* without modification, are permitted provided that the */
|
| 11 |
|
|
/* following conditions are met: */
|
| 12 |
|
|
/* */
|
| 13 |
|
|
/* - Redistributions of source code must retain the above copyright*/
|
| 14 |
|
|
/* notice, this list of conditions and the following disclaimer. */
|
| 15 |
|
|
/* */
|
| 16 |
|
|
/* - Redistributions in binary form must reproduce the above */
|
| 17 |
|
|
/* copyright notice, this list of conditions and the following */
|
| 18 |
|
|
/* disclaimer in the documentation and/or other materials */
|
| 19 |
|
|
/* provided with the distribution. */
|
| 20 |
|
|
/* */
|
| 21 |
|
|
/* - Neither the name of IBM Corporation nor the names of its */
|
| 22 |
|
|
/* contributors may be used to endorse or promote products */
|
| 23 |
|
|
/* derived from this software without specific prior written */
|
| 24 |
|
|
/* permission. */
|
| 25 |
|
|
/* */
|
| 26 |
|
|
/* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND */
|
| 27 |
|
|
/* CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, */
|
| 28 |
|
|
/* INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF */
|
| 29 |
|
|
/* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE */
|
| 30 |
|
|
/* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR */
|
| 31 |
|
|
/* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, */
|
| 32 |
|
|
/* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT */
|
| 33 |
|
|
/* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; */
|
| 34 |
|
|
/* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) */
|
| 35 |
|
|
/* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN */
|
| 36 |
|
|
/* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR */
|
| 37 |
|
|
/* OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, */
|
| 38 |
|
|
/* EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */
|
| 39 |
|
|
/* -------------------------------------------------------------- */
|
| 40 |
|
|
/* PROLOG END TAG zYx */
|
| 41 |
|
|
#ifdef __SPU__
|
| 42 |
|
|
|
| 43 |
|
|
#ifndef _LDEXPD2_H_
|
| 44 |
|
|
#define _LDEXPD2_H_ 1
|
| 45 |
|
|
|
| 46 |
|
|
#include <spu_intrinsics.h>
|
| 47 |
|
|
|
| 48 |
|
|
/*
|
| 49 |
|
|
* FUNCTION
|
| 50 |
|
|
* vector double _ldexpd2(vector double x, vector signed long long exp)
|
| 51 |
|
|
*
|
| 52 |
|
|
* DESCRIPTION
|
| 53 |
|
|
* The _ldexpd2 function Computes x * 2^exp for each of the two elements
|
| 54 |
|
|
* of x using the corresponding elements of exp.
|
| 55 |
|
|
*
|
| 56 |
|
|
*/
|
| 57 |
|
|
static __inline vector double _ldexpd2(vector double x, vector signed long long llexp)
|
| 58 |
|
|
{
|
| 59 |
|
|
vec_uchar16 odd_to_even = ((vec_uchar16) { 4,5,6,7, 0x80,0x80,0x80,0x80,
|
| 60 |
|
|
12,13,14,15, 0x80,0x80,0x80,0x80 });
|
| 61 |
|
|
vec_int4 exp;
|
| 62 |
|
|
vec_int4 e1, e2;
|
| 63 |
|
|
vec_int4 min = spu_splats(-2044);
|
| 64 |
|
|
vec_int4 max = spu_splats(2046);
|
| 65 |
|
|
vec_uint4 cmp_min, cmp_max;
|
| 66 |
|
|
vec_uint4 shift = (vec_uint4) { 20, 32, 20, 32 };
|
| 67 |
|
|
vec_double2 f1, f2;
|
| 68 |
|
|
vec_double2 out;
|
| 69 |
|
|
|
| 70 |
|
|
exp = (vec_int4)spu_shuffle(llexp, llexp, odd_to_even);
|
| 71 |
|
|
|
| 72 |
|
|
/* Clamp the specified exponent to the range -2044 to 2046.
|
| 73 |
|
|
*/
|
| 74 |
|
|
|
| 75 |
|
|
cmp_min = spu_cmpgt(exp, min);
|
| 76 |
|
|
cmp_max = spu_cmpgt(exp, max);
|
| 77 |
|
|
exp = spu_sel(min, exp, cmp_min);
|
| 78 |
|
|
exp = spu_sel(exp, max, cmp_max);
|
| 79 |
|
|
|
| 80 |
|
|
/* Generate the factors f1 = 2^e1 and f2 = 2^e2
|
| 81 |
|
|
*/
|
| 82 |
|
|
e1 = spu_rlmaska(exp, -1);
|
| 83 |
|
|
e2 = spu_sub(exp, e1);
|
| 84 |
|
|
|
| 85 |
|
|
f1 = (vec_double2)spu_sl(spu_add(e1, 1023), shift);
|
| 86 |
|
|
f2 = (vec_double2)spu_sl(spu_add(e2, 1023), shift);
|
| 87 |
|
|
|
| 88 |
|
|
/* Compute the product x * 2^e1 * 2^e2
|
| 89 |
|
|
*/
|
| 90 |
|
|
out = spu_mul(spu_mul(x, f1), f2);
|
| 91 |
|
|
|
| 92 |
|
|
return (out);
|
| 93 |
|
|
}
|
| 94 |
|
|
|
| 95 |
|
|
#endif /* _LDEXPD2_H_ */
|
| 96 |
|
|
#endif /* __SPU__ */
|
| 97 |
|
|
|
