[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc non-uni hz and vt mc msa functions

2017-11-09 Thread kaustubh.raste
From: Kaustubh Raste Use mask buffer. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevcdsp_msa.c | 541 - 1 file changed, 312 insertions(+), 229 deletions(-) diff --git a/libavcodec/mips/hevcdsp_msa.c b/libavcodec/mips/hevcdsp_msa.c index b17127c.

[FFmpeg-devel] [PATCH] avcodec/mips: cleanup unused macros

2017-11-08 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_macros_msa.h | 37 - 1 file changed, 37 deletions(-) diff --git a/libavcodec/mips/hevc_macros_msa.h b/libavcodec/mips/hevc_macros_msa.h index 27c69ff..ea53812 100644 --- a/libavco

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc non-uni hv mc msa functions

2017-11-06 Thread kaustubh.raste
From: Kaustubh Raste Use mask buffer. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevcdsp_msa.c | 1478 - 1 file changed, 870 insertions(+), 608 deletions(-) diff --git a/libavcodec/mips/hevcdsp_msa.c b/libavcodec/mips/hevcdsp_msa.c index 73cc3ea.

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni weighted 4 tap vt mc msa functions

2017-11-06 Thread kaustubh.raste
From: Kaustubh Raste Use global mask buffer for appropriate mask load. Use immediate unsigned saturation for clip to max saving one vector register. Remove unused macro. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uniw_msa.c | 1052 ++-- 1 file cha

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni 4 tap hv mc msa functions

2017-11-06 Thread kaustubh.raste
From: Kaustubh Raste Use global mask buffer for appropriate mask load. Remove unused macro and table. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uni_msa.c | 1125 +++-- 1 file changed, 566 insertions(+), 559 deletions(-) diff --git a/libavcodec/m

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc bi wgt 4 tap hv mc msa functions

2017-11-05 Thread kaustubh.raste
From: Kaustubh Raste Use global mask buffer for appropriate mask load. Use immediate unsigned saturation for clip to max saving one vector register. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_biw_msa.c | 1396 +++-- 1 file changed, 872 insertions(

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc bi 4 tap hv mc msa functions

2017-11-05 Thread kaustubh.raste
From: Kaustubh Raste Use global mask buffer for appropriate mask load. Use immediate unsigned saturation for clip to max saving one vector register. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_bi_msa.c | 1140 +++--- 1 file changed, 685 insertions(

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc avg mc 10, 30, 01 and 03 msa functions

2017-11-05 Thread kaustubh.raste
From: Kaustubh Raste Align the mask buffer to 64 bytes. Load the specific destination bytes instead of MSA load and pack. Remove unused macros and functions. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 1269 1 file changed, 751 in

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni weighted 4 tap hz mc msa functions

2017-11-03 Thread kaustubh.raste
From: Kaustubh Raste Use global mask buffer for appropriate mask load. Use immediate unsigned saturation for clip to max saving one vector register. Remove unused macro. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uniw_msa.c | 892 ++-- 1 file cha

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni 4 tap hz and vt mc msa functions

2017-11-03 Thread kaustubh.raste
From: Kaustubh Raste Use global mask buffer for appropriate mask load. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uni_msa.c | 509 - 1 file changed, 274 insertions(+), 235 deletions(-) diff --git a/libavcodec/mips/hevc_mc_uni_msa.c b/libavc

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc bi wgt 4 tap hz and vt mc msa functions

2017-11-02 Thread kaustubh.raste
From: Kaustubh Raste Use global mask buffer for appropriate mask load. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_biw_msa.c | 587 - 1 file changed, 247 insertions(+), 340 deletions(-) diff --git a/libavcodec/mips/hevc_mc_biw_msa.c b/libavc

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc bi 4 tap hz and vt mc msa functions

2017-11-02 Thread kaustubh.raste
From: Kaustubh Raste Use global mask buffer for appropriate mask load. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_bi_msa.c | 428 +++--- 1 file changed, 210 insertions(+), 218 deletions(-) diff --git a/libavcodec/mips/hevc_mc_bi_msa.c b/libavcod

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc avg mc 20, 21 and 23 msa functions

2017-11-02 Thread kaustubh.raste
From: Kaustubh Raste Load the specific destination bytes instead of MSA load and pack. Remove unused macros and functions. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 1274 ++-- 1 file changed, 834 insertions(+), 440 deletions(-) diff

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc avg mc 02, 12 and 32 msa functions

2017-10-31 Thread kaustubh.raste
From: Kaustubh Raste Remove loops and unroll as block sizes are known. Load the specific destination bytes instead of MSA load and pack. Remove unused macro and functions. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 1002 +++- 1 file c

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni weighted hv mc msa functions

2017-10-31 Thread kaustubh.raste
From: Kaustubh Raste Use immediate unsigned saturation for clip to max saving one vector register. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_macros_msa.h |9 + libavcodec/mips/hevc_mc_uniw_msa.c | 1598 +--- 2 files changed, 965 insertions(+),

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni vt and hv mc msa functions

2017-10-27 Thread kaustubh.raste
From: Kaustubh Raste Remove unused macro. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uni_msa.c | 744 + 1 file changed, 499 insertions(+), 245 deletions(-) diff --git a/libavcodec/mips/hevc_mc_uni_msa.c b/libavcodec/mips/hevc_mc_uni_msa.c i

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc bi hz and hv mc msa functions

2017-10-27 Thread kaustubh.raste
From: Kaustubh Raste Align the mask buffer. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_bi_msa.c | 940 -- 1 file changed, 595 insertions(+), 345 deletions(-) diff --git a/libavcodec/mips/hevc_mc_bi_msa.c b/libavcodec/mips/hevc_mc_bi_msa.c in

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc chroma avg hv mc msa functions

2017-10-27 Thread kaustubh.raste
From: Kaustubh Raste Replace generic with block size specific function. Load the specific destination bytes instead of MSA load and pack. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264chroma_msa.c | 438 +- 1 file changed, 238 insertions(+), 200 del

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc avg mc 22, 11, 31, 13 and 33 msa functions

2017-10-27 Thread kaustubh.raste
From: Kaustubh Raste Remove loops and unroll as block sizes are known. Load the specific destination bytes instead of MSA load and pack. Remove unused macro and functions. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 781 ++-- 1 file c

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc bi weighted hv mc msa functions

2017-10-24 Thread kaustubh.raste
From: Kaustubh Raste Use immediate unsigned saturation for clip to max saving one vector register. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_biw_msa.c | 706 ++- libavutil/mips/generic_macros_msa.h | 35 ++ 2 files changed, 489 insertions(+)

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc chroma copy and avg vert mc msa functions

2017-10-24 Thread kaustubh.raste
From: Kaustubh Raste Replace generic with block size specific function. Load the specific destination bytes instead of MSA load and pack. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264chroma_msa.c | 627 +- 1 file changed, 275 insertions(+), 352 del

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc put mc 11, 31, 13 and 33 msa functions

2017-10-24 Thread kaustubh.raste
From: Kaustubh Raste Remove loops and unroll as block sizes are known. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 400 1 file changed, 240 insertions(+), 160 deletions(-) diff --git a/libavcodec/mips/h264qpel_msa.c b/libavcodec

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni weighted vert mc msa functions

2017-10-11 Thread kaustubh.raste
From: Kaustubh Raste Pack the data to half word before clipping. Use immediate unsigned saturation for clip to max saving one vector register. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uniw_msa.c | 441 ++-- 1 file changed, 222 insertions(+), 21

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni horiz mc msa functions

2017-10-11 Thread kaustubh.raste
From: Kaustubh Raste Update macros to remove adds. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uni_msa.c | 612 +++-- 1 file changed, 323 insertions(+), 289 deletions(-) diff --git a/libavcodec/mips/hevc_mc_uni_msa.c b/libavcodec/mips/hevc_mc_un

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc bi copy mc msa functions

2017-10-11 Thread kaustubh.raste
From: Kaustubh Raste Load the specific destination bytes instead of MSA load and pack. Use immediate unsigned saturation for clip to max saving one vector register. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_bi_msa.c | 652 +- 1 file changed,

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc put mc 12, 32 and 22 msa functions

2017-10-11 Thread kaustubh.raste
From: Kaustubh Raste Remove loops and unroll as block sizes are known. Removed unused functions. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 1013 +--- 1 file changed, 747 insertions(+), 266 deletions(-) diff --git a/libavcodec/mips/h

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc chroma avg horiz mc msa functions

2017-10-11 Thread kaustubh.raste
From: Kaustubh Raste Replace generic with block size specific function. Load the specific destination bytes instead of MSA load and pack. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264chroma_msa.c | 329 -- 1 file changed, 169 insertions(+), 160 del

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc uni copy mc msa functions

2017-10-09 Thread kaustubh.raste
From: Kaustubh Raste Load the specific bytes instead of MSA load. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uni_msa.c | 245 +++-- 1 file changed, 100 insertions(+), 145 deletions(-) diff --git a/libavcodec/mips/hevc_mc_uni_msa.c b/libavcodec/

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni-w horiz mc msa functions

2017-10-09 Thread kaustubh.raste
From: Kaustubh Raste Load the specific destination bytes instead of MSA load and pack. Pack the data to half word before clipping. Use immediate unsigned saturation for clip to max saving one vector register. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_macros_msa.h | 13 +- libav

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc put mc 21, 23 and 02 msa functions

2017-10-09 Thread kaustubh.raste
From: Kaustubh Raste Remove loops and unroll as block sizes are known. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 1219 ++-- 1 file changed, 802 insertions(+), 417 deletions(-) diff --git a/libavcodec/mips/h264qpel_msa.c b/libavcodec

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc chroma hv mc msa functions

2017-10-09 Thread kaustubh.raste
From: Kaustubh Raste Replace generic with block size specific function. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264chroma_msa.c | 309 -- 1 file changed, 166 insertions(+), 143 deletions(-) diff --git a/libavcodec/mips/h264chroma_msa.c b/libavco

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc bi-weighted mc msa functions

2017-10-09 Thread kaustubh.raste
From: Kaustubh Raste Replace generic with block size specific function. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264dsp_msa.c | 469 +++ libavutil/mips/generic_macros_msa.h |4 + 2 files changed, 311 insertions(+), 162 deletions(-) diff --g

[FFmpeg-devel] [PATCH] avcodec/mips: preload data in hevc sao edge 135 degree filter msa functions

2017-10-08 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_lpf_sao_msa.c | 194 1 file changed, 132 insertions(+), 62 deletions(-) diff --git a/libavcodec/mips/hevc_lpf_sao_msa.c b/libavcodec/mips/hevc_lpf_sao_msa.c index c192265..5b5537a

[FFmpeg-devel] [PATCH] avcodec/mips: Cleanup unused functions

2017-10-05 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 746 libavcodec/mips/hevc_mc_uniw_msa.c | 67 libavcodec/mips/hevcdsp_msa.c | 50 --- 3 files changed, 863 deletions(-) diff --git a/libavcodec/mips/h

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc put mc 20, 01 and 03 msa functions

2017-09-26 Thread kaustubh.raste
From: Kaustubh Raste Remove loops and unroll as block sizes are known. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 441 +++- 1 file changed, 432 insertions(+), 9 deletions(-) diff --git a/libavcodec/mips/h264qpel_msa.c b/libavcodec/m

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc chroma vert mc msa functions

2017-09-25 Thread kaustubh.raste
From: Kaustubh Raste Replace generic with block size specific function. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264chroma_msa.c | 237 ++ 1 file changed, 112 insertions(+), 125 deletions(-) diff --git a/libavcodec/mips/h264chroma_msa.c b/libavco

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc weighted mc msa functions

2017-09-25 Thread kaustubh.raste
From: Kaustubh Raste Replace generic with block size specific function. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264dsp_msa.c | 423 ++- libavutil/mips/generic_macros_msa.h | 36 +++ 2 files changed, 306 insertions(+), 153 deletions(-) diff -

[FFmpeg-devel] [PATCH] avcodec/mips: Removed generic function call in avc intra msa functions

2017-09-25 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264pred_msa.c | 215 +--- 1 file changed, 92 insertions(+), 123 deletions(-) diff --git a/libavcodec/mips/h264pred_msa.c b/libavcodec/mips/h264pred_msa.c index c297aec..b9990c1 100644 -

[FFmpeg-devel] [PATCH] avcodec/mips: preload data in hevc sao edge 45 degree filter msa functions

2017-09-25 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_lpf_sao_msa.c | 197 1 file changed, 135 insertions(+), 62 deletions(-) diff --git a/libavcodec/mips/hevc_lpf_sao_msa.c b/libavcodec/mips/hevc_lpf_sao_msa.c index 39c647e..c192265

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc chroma horiz mc msa functions

2017-09-21 Thread kaustubh.raste
From: Kaustubh Raste Replace generic with block size specific function. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264chroma_msa.c | 231 ++ 1 file changed, 133 insertions(+), 98 deletions(-) diff --git a/libavcodec/mips/h264chroma_msa.c b/libavcod

[FFmpeg-devel] [PATCH] avcodec/mips: Unrolled loops avc intra msa functions

2017-09-21 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264pred_msa.c | 318 1 file changed, 158 insertions(+), 160 deletions(-) diff --git a/libavcodec/mips/h264pred_msa.c b/libavcodec/mips/h264pred_msa.c index cddcd2e..6c7e756 100644

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc uni-w copy mc msa functions

2017-09-21 Thread kaustubh.raste
From: Kaustubh Raste Load the specific destination bytes instead of MSA load and pack. Pack the data to half word before clipping. Use immediate unsigned saturation for clip to max saving one vector register. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uniw_msa.c | 559

[FFmpeg-devel] [PATCH] avcodec/mips: Remove generic func use in hevc non-uni copy mc msa functions

2017-09-21 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevcdsp_msa.c | 168 +++-- 1 file changed, 160 insertions(+), 8 deletions(-) diff --git a/libavcodec/mips/hevcdsp_msa.c b/libavcodec/mips/hevcdsp_msa.c index f2bc748..1a854b2 100644 ---

[FFmpeg-devel] [PATCH] avcodec/mips: preload data in hevc sao edge 90 degree filter msa functions

2017-09-20 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_lpf_sao_msa.c | 181 1 file changed, 122 insertions(+), 59 deletions(-) diff --git a/libavcodec/mips/hevc_lpf_sao_msa.c b/libavcodec/mips/hevc_lpf_sao_msa.c index 3472d32..39c647e

[FFmpeg-devel] [PATCH] avcodec/mips: Reduced conditional cases in avc inter lpf msa functions

2017-09-18 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264dsp_msa.c | 274 + 1 file changed, 110 insertions(+), 164 deletions(-) diff --git a/libavcodec/mips/h264dsp_msa.c b/libavcodec/mips/h264dsp_msa.c index a17eacb..422703d 100644 --

[FFmpeg-devel] [PATCH] avcodec/mips: Unrolled loops and expanded functions in avc put mc 10 & 30 msa functions

2017-09-18 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 284 +++- 1 file changed, 278 insertions(+), 6 deletions(-) diff --git a/libavcodec/mips/h264qpel_msa.c b/libavcodec/mips/h264qpel_msa.c index 05dffea..b7f6c3d 100644 --

[FFmpeg-devel] [PATCH] avcodec/mips: preload data in hevc sao edge 0 degree filter msa functions

2017-09-18 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_lpf_sao_msa.c | 232 +--- 1 file changed, 138 insertions(+), 94 deletions(-) diff --git a/libavcodec/mips/hevc_lpf_sao_msa.c b/libavcodec/mips/hevc_lpf_sao_msa.c index 1d77432..3472d32

[FFmpeg-devel] [PATCH] avcodec/mips: Fixed rnd_val variable to 6 in hevc uni mc msa functions

2017-09-18 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_mc_uni_msa.c | 372 + 1 file changed, 133 insertions(+), 239 deletions(-) diff --git a/libavcodec/mips/hevc_mc_uni_msa.c b/libavcodec/mips/hevc_mc_uni_msa.c index 754fbdb..cf22e7f

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc sao band filter msa functions

2017-09-15 Thread kaustubh.raste
From: Kaustubh Raste Preload data in band filter 0-8 for better pipeline parallelization. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_lpf_sao_msa.c | 174 ++- libavutil/mips/generic_macros_msa.h |1 + 2 files changed, 112 insertions(+), 63 delet

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc mc copy msa functions

2017-09-14 Thread kaustubh.raste
From: Kaustubh Raste Remove loops and unroll as block sizes are known. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 81 +--- 1 file changed, 75 insertions(+), 6 deletions(-) diff --git a/libavcodec/mips/h264qpel_msa.c b/libavcodec/mi

[FFmpeg-devel] [PATCH] avcodec/mips: Improve avc lpf msa functions

2017-09-14 Thread kaustubh.raste
From: Kaustubh Raste Optimize luma intra case by reducing conditional cases. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264dsp_msa.c | 428 + 1 file changed, 138 insertions(+), 290 deletions(-) diff --git a/libavcodec/mips/h264dsp_msa.c b/libav

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc idct msa functions

2017-09-12 Thread kaustubh.raste
From: Kaustubh Raste Align the buffers. Remove reduandant constant array. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_idct_msa.c | 255 ++- 1 file changed, 171 insertions(+), 84 deletions(-) diff --git a/libavcodec/mips/hevc_idct_msa.c b/libavco

[FFmpeg-devel] [PATCH] avcodec/mips: Improve hevc lpf msa functions

2017-09-12 Thread kaustubh.raste
From: Kaustubh Raste Seperate the filter processing in all strong, all weak and strong + weak cases. Signed-off-by: Kaustubh Raste --- libavcodec/mips/hevc_lpf_sao_msa.c | 750 ++-- 1 file changed, 556 insertions(+), 194 deletions(-) diff --git a/libavcodec/mi

[FFmpeg-devel] [PATCH] avcodec/mips: Improve vp9 mc msa functions

2017-09-04 Thread kaustubh.raste
From: Kaustubh Raste Load the specific destination bytes instead of MSA load and pack. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264qpel_msa.c | 17 +- libavcodec/mips/vp9_mc_msa.c| 759 --- libavutil/mips/generic_macros_msa.h | 24 +-

[FFmpeg-devel] [PATCH] avcodec/mips: Improve vp9 idct msa functions

2017-09-04 Thread kaustubh.raste
From: Kaustubh Raste Removed memset calls. Signed-off-by: Kaustubh Raste --- libavcodec/mips/vp9_idct_msa.c | 118 1 file changed, 70 insertions(+), 48 deletions(-) diff --git a/libavcodec/mips/vp9_idct_msa.c b/libavcodec/mips/vp9_idct_msa.c index 25e

[FFmpeg-devel] [PATCH] avcodec/mips: Improve vp9 lpf msa functions

2017-09-04 Thread kaustubh.raste
From: Kaustubh Raste Updated VP9_LPF_FILTER4_4W macro to process on 8 bit data. Replaced VP9_LPF_FILTER4_8W with VP9_LPF_FILTER4_4W. Signed-off-by: Kaustubh Raste --- libavcodec/mips/vp9_lpf_msa.c | 94 ++--- 1 file changed, 14 insertions(+), 80 deletions(

[FFmpeg-devel] [PATCH] libavcodec/mips: Improve avc idct8 msa function

2017-07-30 Thread kaustubh.raste
From: Kaustubh Raste Replace memset call with msa stores. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264idct_msa.c |4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/libavcodec/mips/h264idct_msa.c b/libavcodec/mips/h264idct_msa.c index 861befe..1e1a5c8 100644 --

[FFmpeg-devel] [PATCH] libavcodec/mips: Improve avc dequant-idct luma dc msa function

2017-07-28 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264idct_msa.c | 66 +++- 1 file changed, 32 insertions(+), 34 deletions(-) diff --git a/libavcodec/mips/h264idct_msa.c b/libavcodec/mips/h264idct_msa.c index 81e09e9..861befe 100644 --

[FFmpeg-devel] [PATCH] libavcodec/mips: Optimize avc idct 4x4 for msa

2017-07-24 Thread kaustubh.raste
From: Kaustubh Raste Removed memset call and improved performance. Signed-off-by: Kaustubh Raste --- libavcodec/mips/h264idct_msa.c | 104 +++ libavutil/mips/generic_macros_msa.h | 18 ++ 2 files changed, 74 insertions(+), 48 deletions(-) diff --git

[FFmpeg-devel] [PATCH] libavutil/mips: Updated msa generic macros

2017-07-20 Thread kaustubh.raste
From: Kaustubh Raste Reduced msa load-store code. Removed inline asm of GP load-store for 64 bit. Updated variable names in GP load-store macros for naming consistency. Corrected macro descriptions. Signed-off-by: Kaustubh Raste --- libavutil/mips/generic_macros_msa.h | 629 ++---

[FFmpeg-devel] [PATCH] Add prefetch for mips

2017-07-12 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/Makefile|1 + libavcodec/mips/videodsp_init.c | 51 +++ libavcodec/videodsp.c |2 ++ libavcodec/videodsp.h |1 + 4 files changed, 55 insertions(+)

[FFmpeg-devel] [PATCH] Add prefetch for mips

2017-07-10 Thread kaustubh.raste
From: Kaustubh Raste Signed-off-by: Kaustubh Raste --- libavcodec/mips/Makefile|1 + libavcodec/mips/videodsp_mips.c | 42 +++ libavcodec/videodsp.c |2 ++ libavcodec/videodsp.h |1 + 4 files changed, 46 insertions(+)