Alexandre Lision | 8af73cb | 2013-12-10 14:11:20 -0500 | [diff] [blame^] | 1 | /* Copyright (C) 2004 Jean-Marc Valin */ |
| 2 | /** |
| 3 | @file cb_search_sse.h |
| 4 | @brief Fixed codebook functions (SSE version) |
| 5 | */ |
| 6 | /* |
| 7 | Redistribution and use in source and binary forms, with or without |
| 8 | modification, are permitted provided that the following conditions |
| 9 | are met: |
| 10 | |
| 11 | - Redistributions of source code must retain the above copyright |
| 12 | notice, this list of conditions and the following disclaimer. |
| 13 | |
| 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 | |
| 18 | - Neither the name of the Xiph.org Foundation nor the names of its |
| 19 | contributors may be used to endorse or promote products derived from |
| 20 | this software without specific prior written permission. |
| 21 | |
| 22 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
| 23 | ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
| 24 | LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
| 25 | A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR |
| 26 | CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, |
| 27 | EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
| 28 | PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR |
| 29 | PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF |
| 30 | LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING |
| 31 | NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS |
| 32 | SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 33 | */ |
| 34 | |
| 35 | #include <xmmintrin.h> |
| 36 | |
| 37 | static inline void _spx_mm_getr_ps (__m128 U, float *__Z, float *__Y, float *__X, float *__W) |
| 38 | { |
| 39 | union { |
| 40 | float __a[4]; |
| 41 | __m128 __v; |
| 42 | } __u; |
| 43 | |
| 44 | __u.__v = U; |
| 45 | |
| 46 | *__Z = __u.__a[0]; |
| 47 | *__Y = __u.__a[1]; |
| 48 | *__X = __u.__a[2]; |
| 49 | *__W = __u.__a[3]; |
| 50 | |
| 51 | } |
| 52 | |
| 53 | #define OVERRIDE_COMPUTE_WEIGHTED_CODEBOOK |
| 54 | static void compute_weighted_codebook(const signed char *shape_cb, const spx_sig_t *_r, float *resp, __m128 *resp2, __m128 *E, int shape_cb_size, int subvect_size, char *stack) |
| 55 | { |
| 56 | int i, j, k; |
| 57 | __m128 resj, EE; |
| 58 | VARDECL(__m128 *r); |
| 59 | VARDECL(__m128 *shape); |
| 60 | ALLOC(r, subvect_size, __m128); |
| 61 | ALLOC(shape, subvect_size, __m128); |
| 62 | for(j=0;j<subvect_size;j++) |
| 63 | r[j] = _mm_load_ps1(_r+j); |
| 64 | for (i=0;i<shape_cb_size;i+=4) |
| 65 | { |
| 66 | float *_res = resp+i*subvect_size; |
| 67 | const signed char *_shape = shape_cb+i*subvect_size; |
| 68 | EE = _mm_setzero_ps(); |
| 69 | for(j=0;j<subvect_size;j++) |
| 70 | { |
| 71 | shape[j] = _mm_setr_ps(0.03125*_shape[j], 0.03125*_shape[subvect_size+j], 0.03125*_shape[2*subvect_size+j], 0.03125*_shape[3*subvect_size+j]); |
| 72 | } |
| 73 | for(j=0;j<subvect_size;j++) |
| 74 | { |
| 75 | resj = _mm_setzero_ps(); |
| 76 | for (k=0;k<=j;k++) |
| 77 | resj = _mm_add_ps(resj, _mm_mul_ps(shape[k],r[j-k])); |
| 78 | _spx_mm_getr_ps(resj, _res+j, _res+subvect_size+j, _res+2*subvect_size+j, _res+3*subvect_size+j); |
| 79 | *resp2++ = resj; |
| 80 | EE = _mm_add_ps(EE, _mm_mul_ps(resj, resj)); |
| 81 | } |
| 82 | E[i>>2] = EE; |
| 83 | } |
| 84 | } |