[444] | 1 | /* |
---|
| 2 | (C) Copyright 2001,2006, |
---|
| 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 without |
---|
| 10 | modification, are permitted provided that the following conditions are met: |
---|
| 11 | |
---|
| 12 | * Redistributions of source code must retain the above copyright notice, |
---|
| 13 | this list of conditions and the following disclaimer. |
---|
| 14 | * Redistributions in binary form must reproduce the above copyright |
---|
| 15 | notice, this list of conditions and the following disclaimer in the |
---|
| 16 | documentation and/or other materials provided with the distribution. |
---|
| 17 | * Neither the names of the copyright holders nor the names of their |
---|
| 18 | contributors may be used to endorse or promote products derived from this |
---|
| 19 | software without specific prior written permission. |
---|
| 20 | |
---|
| 21 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS |
---|
| 22 | IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED |
---|
| 23 | TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A |
---|
| 24 | PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER |
---|
| 25 | OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, |
---|
| 26 | EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
---|
| 27 | PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR |
---|
| 28 | PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF |
---|
| 29 | LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING |
---|
| 30 | NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS |
---|
| 31 | SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
---|
| 32 | */ |
---|
| 33 | #ifndef _ROUND_H_ |
---|
| 34 | #define _ROUND_H_ 1 |
---|
| 35 | |
---|
| 36 | #include <spu_intrinsics.h> |
---|
| 37 | #include "headers/vec_literal.h" |
---|
| 38 | |
---|
| 39 | /* Round the input to the nearest integer, rounding halfway |
---|
| 40 | * cases away from zero. |
---|
| 41 | */ |
---|
| 42 | static __inline double _round(double x) |
---|
| 43 | { |
---|
| 44 | vec_uchar16 splat_hi = VEC_LITERAL(vec_uchar16, 0,1,2,3,0,1,2,3, 8,9,10,11, 8,9,10,11); |
---|
| 45 | vec_int4 exp, shift; |
---|
| 46 | vec_uint4 sign = VEC_LITERAL(vec_uint4, 0x80000000, 0, 0x80000000, 0); |
---|
| 47 | vec_uint4 or_mask, and_mask, mask, addend; |
---|
| 48 | vec_double2 in, in_hi, out; |
---|
| 49 | |
---|
| 50 | in = spu_promote(x, 0); |
---|
| 51 | |
---|
| 52 | /* Add 0.5 (fixed precision to eliminate rounding issues) |
---|
| 53 | */ |
---|
| 54 | in_hi = spu_shuffle(in, in, splat_hi); |
---|
| 55 | exp = spu_and(spu_rlmask((vec_int4)in_hi, -20), 0x7FF); |
---|
| 56 | |
---|
| 57 | shift = spu_sub(VEC_LITERAL(vec_int4, 1022, 1043, 1022, 1043), exp); |
---|
| 58 | |
---|
| 59 | addend = spu_and(spu_rlmask(VEC_LITERAL(vec_uint4, 0x100000, 0x80000000, |
---|
| 60 | 0x100000, 0x80000000), shift), |
---|
| 61 | spu_cmpgt((vec_uint4)spu_add(shift, -1), -33)); |
---|
| 62 | |
---|
| 63 | in = (vec_double2)spu_addx((vec_uint4)in, addend, |
---|
| 64 | spu_rlqwbyte(spu_genc((vec_uint4)in, addend), 4)); |
---|
| 65 | |
---|
| 66 | /* Truncate the result. |
---|
| 67 | */ |
---|
| 68 | in_hi = spu_shuffle(in, in, splat_hi); |
---|
| 69 | exp = spu_and(spu_rlmask((vec_int4)in_hi, -20), 0x7FF); |
---|
| 70 | |
---|
| 71 | shift = spu_sub(VEC_LITERAL(vec_int4, 1023, 1043, 1023, 1043), exp); |
---|
| 72 | or_mask = spu_andc(spu_cmpgt(shift, 0), sign); |
---|
| 73 | |
---|
| 74 | |
---|
| 75 | and_mask = spu_rlmask(VEC_LITERAL(vec_uint4, 0xFFFFF, -1, 0xFFFFF, -1), |
---|
| 76 | shift); |
---|
| 77 | mask = spu_or(spu_and(and_mask, spu_cmpgt(shift, -31)), or_mask); |
---|
| 78 | |
---|
| 79 | /* Apply the mask and return the result. |
---|
| 80 | */ |
---|
| 81 | out = spu_andc(in, (vec_double2)(mask)); |
---|
| 82 | |
---|
| 83 | return (spu_extract(out, 0)); |
---|
| 84 | } |
---|
| 85 | #endif /* _ROUND_H_ */ |
---|