diff options
| author | Ronald S. Bultje <rsbultje@gmail.com> | 2015-10-06 11:42:03 -0400 |
|---|---|---|
| committer | Ronald S. Bultje <rsbultje@gmail.com> | 2015-10-13 11:05:58 -0400 |
| commit | f76423d0975dae4bb2513e6b20be2a7803fd7019 (patch) | |
| tree | 4c00cf0d8d442551625e1ccb32883728c6750465 /libavcodec/x86/vp9dsp_init_16bpp_template.c | |
| parent | 6b579cf547a75a0cbda5cb7f10eab9ca07522b0a (diff) | |
vp9: add x86 simd (sse2/ssse3) for iadst4 10bpp functions.
Diffstat (limited to 'libavcodec/x86/vp9dsp_init_16bpp_template.c')
| -rw-r--r-- | libavcodec/x86/vp9dsp_init_16bpp_template.c | 21 |
1 files changed, 18 insertions, 3 deletions
diff --git a/libavcodec/x86/vp9dsp_init_16bpp_template.c b/libavcodec/x86/vp9dsp_init_16bpp_template.c index 6e12af3d3d..93fc684bf9 100644 --- a/libavcodec/x86/vp9dsp_init_16bpp_template.c +++ b/libavcodec/x86/vp9dsp_init_16bpp_template.c @@ -126,8 +126,11 @@ decl_ipred_fns(tm, BPC, mmxext, sse2); decl_itxfm_func(iwht, iwht, 4, BPC, mmxext); #if BPC == 10 -decl_itxfm_func(idct, idct, 4, BPC, mmxext); -decl_itxfm_func(idct, idct, 4, BPC, ssse3); +decl_itxfm_func(idct, idct, 4, BPC, mmxext); +decl_itxfm_func(idct, iadst, 4, BPC, sse2); +decl_itxfm_func(iadst, idct, 4, BPC, sse2); +decl_itxfm_func(iadst, iadst, 4, BPC, sse2); +decl_itxfm_funcs(4, BPC, ssse3); #endif #endif /* HAVE_YASM */ @@ -169,6 +172,11 @@ av_cold void INIT_FUNC(VP9DSPContext *dsp, int bitexact) init_itx_func(idx, ADST_DCT, typea, typeb, size, bpp, opt); \ init_itx_func(idx, DCT_ADST, typea, typeb, size, bpp, opt); \ init_itx_func(idx, ADST_ADST, typea, typeb, size, bpp, opt) +#define init_itx_funcs(idx, size, bpp, opt) \ + init_itx_func(idx, DCT_DCT, idct, idct, size, bpp, opt); \ + init_itx_func(idx, ADST_DCT, idct, iadst, size, bpp, opt); \ + init_itx_func(idx, DCT_ADST, iadst, idct, size, bpp, opt); \ + init_itx_func(idx, ADST_ADST, iadst, iadst, size, bpp, opt); \ if (EXTERNAL_MMXEXT(cpu_flags)) { init_ipred_func(tm, TM_VP8, 4, BPC, mmxext); @@ -185,13 +193,20 @@ av_cold void INIT_FUNC(VP9DSPContext *dsp, int bitexact) init_subpel3(1, avg, BPC, sse2); init_lpf_funcs(BPC, sse2); init_8_16_32_ipred_funcs(tm, TM_VP8, BPC, sse2); +#if BPC == 10 + if (!bitexact) { + init_itx_func(TX_4X4, ADST_DCT, idct, iadst, 4, 10, sse2); + init_itx_func(TX_4X4, DCT_ADST, iadst, idct, 4, 10, sse2); + init_itx_func(TX_4X4, ADST_ADST, iadst, iadst, 4, 10, sse2); + } +#endif } if (EXTERNAL_SSSE3(cpu_flags)) { init_lpf_funcs(BPC, ssse3); #if BPC == 10 if (!bitexact) { - init_itx_func(TX_4X4, DCT_DCT, idct, idct, 4, 10, ssse3); + init_itx_funcs(TX_4X4, 4, BPC, ssse3); } #endif } |