aacpsdsp_init.c 3.2 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172
  1. /*
  2. * SIMD optimized MPEG-4 Parametric Stereo decoding functions
  3. *
  4. * This file is part of FFmpeg.
  5. *
  6. * FFmpeg is free software; you can redistribute it and/or
  7. * modify it under the terms of the GNU Lesser General Public
  8. * License as published by the Free Software Foundation; either
  9. * version 2.1 of the License, or (at your option) any later version.
  10. *
  11. * FFmpeg is distributed in the hope that it will be useful,
  12. * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13. * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  14. * Lesser General Public License for more details.
  15. *
  16. * You should have received a copy of the GNU Lesser General Public
  17. * License along with FFmpeg; if not, write to the Free Software
  18. * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  19. */
  20. #include <stddef.h>
  21. #include "config.h"
  22. #include "libavutil/x86/cpu.h"
  23. #include "libavutil/attributes.h"
  24. #include "libavcodec/aacpsdsp.h"
  25. void ff_ps_add_squares_sse (float *dst, const float (*src)[2], int n);
  26. void ff_ps_add_squares_sse3 (float *dst, const float (*src)[2], int n);
  27. void ff_ps_mul_pair_single_sse (float (*dst)[2], float (*src0)[2],
  28. float *src1, int n);
  29. void ff_ps_hybrid_analysis_sse (float (*out)[2], float (*in)[2],
  30. const float (*filter)[8][2],
  31. ptrdiff_t stride, int n);
  32. void ff_ps_hybrid_analysis_sse3(float (*out)[2], float (*in)[2],
  33. const float (*filter)[8][2],
  34. ptrdiff_t stride, int n);
  35. void ff_ps_stereo_interpolate_sse3(float (*l)[2], float (*r)[2],
  36. float h[2][4], float h_step[2][4],
  37. int len);
  38. void ff_ps_stereo_interpolate_ipdopd_sse3(float (*l)[2], float (*r)[2],
  39. float h[2][4], float h_step[2][4],
  40. int len);
  41. void ff_ps_hybrid_synthesis_deint_sse(float out[2][38][64], float (*in)[32][2],
  42. int i, int len);
  43. void ff_ps_hybrid_synthesis_deint_sse4(float out[2][38][64], float (*in)[32][2],
  44. int i, int len);
  45. void ff_ps_hybrid_analysis_ileave_sse(float (*out)[32][2], float L[2][38][64],
  46. int i, int len);
  47. av_cold void ff_psdsp_init_x86(PSDSPContext *s)
  48. {
  49. int cpu_flags = av_get_cpu_flags();
  50. if (EXTERNAL_SSE(cpu_flags)) {
  51. s->add_squares = ff_ps_add_squares_sse;
  52. s->mul_pair_single = ff_ps_mul_pair_single_sse;
  53. s->hybrid_analysis_ileave = ff_ps_hybrid_analysis_ileave_sse;
  54. s->hybrid_synthesis_deint = ff_ps_hybrid_synthesis_deint_sse;
  55. s->hybrid_analysis = ff_ps_hybrid_analysis_sse;
  56. }
  57. if (EXTERNAL_SSE3(cpu_flags)) {
  58. s->add_squares = ff_ps_add_squares_sse3;
  59. s->stereo_interpolate[0] = ff_ps_stereo_interpolate_sse3;
  60. s->stereo_interpolate[1] = ff_ps_stereo_interpolate_ipdopd_sse3;
  61. s->hybrid_analysis = ff_ps_hybrid_analysis_sse3;
  62. }
  63. if (EXTERNAL_SSE4(cpu_flags)) {
  64. s->hybrid_synthesis_deint = ff_ps_hybrid_synthesis_deint_sse4;
  65. }
  66. }