[FFmpeg-devel] [PATCH 07/11] avcodec/mips: loongson optimize h264qpel with mmi v2

Michael Niedermayer michael at niedermayer.cc
Tue May 24 21:09:50 CEST 2016


On Tue, May 17, 2016 at 03:08:13PM +0800, 周晓勇 wrote:
> avcodec/mips/h264qpel_mmi: Version 2 of the optimizations for loongson mmi
>     
>     1. no longer use the register names directly and optimized code format
>     2. to be compatible with O32, specify type of address variable with mips_reg and handle the address variable with PTR_ operator
>     3. temporarily annotated func put_(avg_)h264_qpel16_hv_lowpass_mmi and related funcs which couldn't pass fate testing in O32 ABI
>     4. use uld and mtc1 to workaround cpu 3A2000 gslwlc1 bug (gslwlc1 instruction extension bug in O32 ABI)
>     5. put_pixels_ an avg_pixels_ functions use hpeldsp optimizations instead
> 
> 
> 
> 
> 
> 
> 
> 
> 在 2016-05-13 18:05:51,"周晓勇" <ipfootball at 126.com> 写道:
> 
> From 151ccd1cefff1887b58166113e65893bcc2e724d Mon Sep 17 00:00:00 2001
> From: Zhou Xiaoyong <zhouxiaoyong at loongson.cn>
> Date: Thu, 12 May 2016 10:46:09 +0800
> Subject: [PATCH 07/11] avcodec/mips: loongson optimize h264qpel with mmi v2
> 
> 
> ---
>  libavcodec/mips/h264qpel_init_mips.c |   28 +
>  libavcodec/mips/h264qpel_mmi.c       | 3823 ++++++++++++++++++++--------------
>  2 files changed, 2252 insertions(+), 1599 deletions(-)
> 
> 
> diff --git a/libavcodec/mips/h264qpel_init_mips.c b/libavcodec/mips/h264qpel_init_mips.c
> index 92219f8..d97e9cc 100644
> --- a/libavcodec/mips/h264qpel_init_mips.c
> +++ b/libavcodec/mips/h264qpel_init_mips.c
> @@ -133,38 +133,52 @@ static av_cold void h264qpel_init_msa(H264QpelContext *c, int bit_depth)
>  static av_cold void h264qpel_init_mmi(H264QpelContext *c, int bit_depth)
>  {
>      if (8 == bit_depth) {
> +        //FIXME put_h264_qpel16_hv_lowpass_mmi
>          c->put_h264_qpel_pixels_tab[0][0] = ff_put_h264_qpel16_mc00_mmi;
>          c->put_h264_qpel_pixels_tab[0][1] = ff_put_h264_qpel16_mc10_mmi;
>          c->put_h264_qpel_pixels_tab[0][2] = ff_put_h264_qpel16_mc20_mmi;
>          c->put_h264_qpel_pixels_tab[0][3] = ff_put_h264_qpel16_mc30_mmi;
>          c->put_h264_qpel_pixels_tab[0][4] = ff_put_h264_qpel16_mc01_mmi;
>          c->put_h264_qpel_pixels_tab[0][5] = ff_put_h264_qpel16_mc11_mmi;
> +#if 0
>          c->put_h264_qpel_pixels_tab[0][6] = ff_put_h264_qpel16_mc21_mmi;
> +#endif
>          c->put_h264_qpel_pixels_tab[0][7] = ff_put_h264_qpel16_mc31_mmi;
>          c->put_h264_qpel_pixels_tab[0][8] = ff_put_h264_qpel16_mc02_mmi;
> +#if 0
>          c->put_h264_qpel_pixels_tab[0][9] = ff_put_h264_qpel16_mc12_mmi;
>          c->put_h264_qpel_pixels_tab[0][10] = ff_put_h264_qpel16_mc22_mmi;
>          c->put_h264_qpel_pixels_tab[0][11] = ff_put_h264_qpel16_mc32_mmi;
> +#endif
>          c->put_h264_qpel_pixels_tab[0][12] = ff_put_h264_qpel16_mc03_mmi;
>          c->put_h264_qpel_pixels_tab[0][13] = ff_put_h264_qpel16_mc13_mmi;
> +#if 0
>          c->put_h264_qpel_pixels_tab[0][14] = ff_put_h264_qpel16_mc23_mmi;
> +#endif
>          c->put_h264_qpel_pixels_tab[0][15] = ff_put_h264_qpel16_mc33_mmi;
>  
> +        //FIXME put_h264_qpel16_hv_lowpass_mmi
>          c->put_h264_qpel_pixels_tab[1][0] = ff_put_h264_qpel8_mc00_mmi;
>          c->put_h264_qpel_pixels_tab[1][1] = ff_put_h264_qpel8_mc10_mmi;
>          c->put_h264_qpel_pixels_tab[1][2] = ff_put_h264_qpel8_mc20_mmi;
>          c->put_h264_qpel_pixels_tab[1][3] = ff_put_h264_qpel8_mc30_mmi;
>          c->put_h264_qpel_pixels_tab[1][4] = ff_put_h264_qpel8_mc01_mmi;
>          c->put_h264_qpel_pixels_tab[1][5] = ff_put_h264_qpel8_mc11_mmi;
> +#if 0
>          c->put_h264_qpel_pixels_tab[1][6] = ff_put_h264_qpel8_mc21_mmi;
> +#endif
>          c->put_h264_qpel_pixels_tab[1][7] = ff_put_h264_qpel8_mc31_mmi;
>          c->put_h264_qpel_pixels_tab[1][8] = ff_put_h264_qpel8_mc02_mmi;
> +#if 0
>          c->put_h264_qpel_pixels_tab[1][9] = ff_put_h264_qpel8_mc12_mmi;
>          c->put_h264_qpel_pixels_tab[1][10] = ff_put_h264_qpel8_mc22_mmi;
>          c->put_h264_qpel_pixels_tab[1][11] = ff_put_h264_qpel8_mc32_mmi;
> +#endif
>          c->put_h264_qpel_pixels_tab[1][12] = ff_put_h264_qpel8_mc03_mmi;
>          c->put_h264_qpel_pixels_tab[1][13] = ff_put_h264_qpel8_mc13_mmi;
> +#if 0
>          c->put_h264_qpel_pixels_tab[1][14] = ff_put_h264_qpel8_mc23_mmi;
> +#endif
>          c->put_h264_qpel_pixels_tab[1][15] = ff_put_h264_qpel8_mc33_mmi;
>  
>          c->put_h264_qpel_pixels_tab[2][0] = ff_put_h264_qpel4_mc00_mmi;
> @@ -184,38 +198,52 @@ static av_cold void h264qpel_init_mmi(H264QpelContext *c, int bit_depth)
>          c->put_h264_qpel_pixels_tab[2][14] = ff_put_h264_qpel4_mc23_mmi;
>          c->put_h264_qpel_pixels_tab[2][15] = ff_put_h264_qpel4_mc33_mmi;
>  
> +        //FIXME avg_h264_qpel16_hv_lowpass_mmi
>          c->avg_h264_qpel_pixels_tab[0][0] = ff_avg_h264_qpel16_mc00_mmi;
>          c->avg_h264_qpel_pixels_tab[0][1] = ff_avg_h264_qpel16_mc10_mmi;
>          c->avg_h264_qpel_pixels_tab[0][2] = ff_avg_h264_qpel16_mc20_mmi;
>          c->avg_h264_qpel_pixels_tab[0][3] = ff_avg_h264_qpel16_mc30_mmi;
>          c->avg_h264_qpel_pixels_tab[0][4] = ff_avg_h264_qpel16_mc01_mmi;
>          c->avg_h264_qpel_pixels_tab[0][5] = ff_avg_h264_qpel16_mc11_mmi;
> +#if 0
>          c->avg_h264_qpel_pixels_tab[0][6] = ff_avg_h264_qpel16_mc21_mmi;
> +#endif
>          c->avg_h264_qpel_pixels_tab[0][7] = ff_avg_h264_qpel16_mc31_mmi;
>          c->avg_h264_qpel_pixels_tab[0][8] = ff_avg_h264_qpel16_mc02_mmi;
> +#if 0
>          c->avg_h264_qpel_pixels_tab[0][9] = ff_avg_h264_qpel16_mc12_mmi;
>          c->avg_h264_qpel_pixels_tab[0][10] = ff_avg_h264_qpel16_mc22_mmi;
>          c->avg_h264_qpel_pixels_tab[0][11] = ff_avg_h264_qpel16_mc32_mmi;
> +#endif
>          c->avg_h264_qpel_pixels_tab[0][12] = ff_avg_h264_qpel16_mc03_mmi;
>          c->avg_h264_qpel_pixels_tab[0][13] = ff_avg_h264_qpel16_mc13_mmi;
> +#if 0
>          c->avg_h264_qpel_pixels_tab[0][14] = ff_avg_h264_qpel16_mc23_mmi;
> +#endif
>          c->avg_h264_qpel_pixels_tab[0][15] = ff_avg_h264_qpel16_mc33_mmi;
>  
> +        //FIXME avg_h264_qpel16_hv_lowpass_mmi
>          c->avg_h264_qpel_pixels_tab[1][0] = ff_avg_h264_qpel8_mc00_mmi;
>          c->avg_h264_qpel_pixels_tab[1][1] = ff_avg_h264_qpel8_mc10_mmi;
>          c->avg_h264_qpel_pixels_tab[1][2] = ff_avg_h264_qpel8_mc20_mmi;
>          c->avg_h264_qpel_pixels_tab[1][3] = ff_avg_h264_qpel8_mc30_mmi;
>          c->avg_h264_qpel_pixels_tab[1][4] = ff_avg_h264_qpel8_mc01_mmi;
>          c->avg_h264_qpel_pixels_tab[1][5] = ff_avg_h264_qpel8_mc11_mmi;
> +#if 0
>          c->avg_h264_qpel_pixels_tab[1][6] = ff_avg_h264_qpel8_mc21_mmi;
> +#endif
>          c->avg_h264_qpel_pixels_tab[1][7] = ff_avg_h264_qpel8_mc31_mmi;
>          c->avg_h264_qpel_pixels_tab[1][8] = ff_avg_h264_qpel8_mc02_mmi;
> +#if 0
>          c->avg_h264_qpel_pixels_tab[1][9] = ff_avg_h264_qpel8_mc12_mmi;
>          c->avg_h264_qpel_pixels_tab[1][10] = ff_avg_h264_qpel8_mc22_mmi;
>          c->avg_h264_qpel_pixels_tab[1][11] = ff_avg_h264_qpel8_mc32_mmi;
> +#endif
>          c->avg_h264_qpel_pixels_tab[1][12] = ff_avg_h264_qpel8_mc03_mmi;
>          c->avg_h264_qpel_pixels_tab[1][13] = ff_avg_h264_qpel8_mc13_mmi;
> +#if 0
>          c->avg_h264_qpel_pixels_tab[1][14] = ff_avg_h264_qpel8_mc23_mmi;
> +#endif

why do these functions not work ?


[...]
-- 
Michael     GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB

The misfortune of the wise is better than the prosperity of the fool.
-- Epicurus
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 181 bytes
Desc: Digital signature
URL: <http://ffmpeg.org/pipermail/ffmpeg-devel/attachments/20160524/b6e81fa5/attachment.sig>


More information about the ffmpeg-devel mailing list