Wed, 25 Feb 2015 16:02:10 +0530 |
Praveen Tiwari |
asm-avx2: cleanup redundant instruction
draft
|
Wed, 25 Feb 2015 15:53:31 +0530 |
Praveen Tiwari |
asm-avx2: intra_pred_ang8_32, improved 435.21c -> 323.25c sse4 asm code
draft
|
Wed, 25 Feb 2015 14:19:56 +0530 |
Praveen Tiwari |
asm-avx2: intra_pred_ang8_33, improved 265.79c -> 185.43c over sse4 asm code
draft
|
Wed, 25 Feb 2015 13:46:58 +0530 |
Praveen Tiwari |
avx2-asm: intra_pred_ang8_3, improved 340.01c -> 280.04c over sse4 asm code
draft
|
Wed, 25 Feb 2015 10:05:40 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Tue, 24 Feb 2015 17:26:37 +0530 |
Divya Manivannan |
asm-avx2: filter_vps[4x4]: improve 201c->156c
draft
|
Tue, 24 Feb 2015 17:11:03 +0530 |
Rajesh Paulraj |
asm-avx2: getResidual, fix 32-bit build error
draft
|
Tue, 24 Feb 2015 09:25:06 +0530 |
Divya Manivannan |
fix: missing constant in filter_vpp[2x4] and filter_vps[2x4]
draft
|
Tue, 24 Feb 2015 15:34:32 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Mon, 23 Feb 2015 15:28:01 +0530 |
Divya Manivannan |
asm-avx2: filter_vpp[8x4], filter_vps[8x4]: improve 213c->161c, 195c->175c
draft
|
Mon, 23 Feb 2015 14:44:28 +0530 |
Divya Manivannan |
asm-avx2: filter_vpp[2x4], filter_vps[2x4]: improve 235c->196c, 214c->174c
draft
|
Mon, 23 Feb 2015 10:22:39 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Fri, 20 Feb 2015 16:48:00 +0530 |
Sumalatha Polureddy |
asm: avx2 code for pixel_add_ps[64x64] - 152x
draft
|
Fri, 20 Feb 2015 17:55:46 +0530 |
Divya Manivannan |
asm: change in loading constant
draft
|
Fri, 20 Feb 2015 14:20:27 +0530 |
Sumalatha Polureddy |
asm: avx2 code for pixel_add_ps[32x32] - 80x
draft
|
Fri, 20 Feb 2015 13:39:51 +0530 |
Sumalatha Polureddy |
asm: avx2 code for pixel_add_ps[16x16] - 55x
draft
|
Fri, 20 Feb 2015 12:39:44 +0530 |
Rajesh Paulraj |
asm-avx2: calcResidual code for 8bbpp and 16bpp
draft
|
Fri, 20 Feb 2015 10:59:34 +0530 |
Divya Manivannan |
fix: error in filter_vps[8x8] assembly pointer
draft
|
Fri, 20 Feb 2015 10:01:23 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Thu, 19 Feb 2015 17:09:04 +0530 |
Divya Manivannan |
asm-avx2: filter_vps[32x32]: improve 4113c->2471c
draft
|
Thu, 19 Feb 2015 16:04:18 +0530 |
Divya Manivannan |
asm-avx2: filter_vps[16x16]: improve 978c->790c
draft
|
Thu, 19 Feb 2015 15:18:12 +0530 |
Divya Manivannan |
asm-avx2: filter_vps[8x8]: improve 296c->263c
draft
|
Thu, 19 Feb 2015 10:01:48 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Wed, 18 Feb 2015 17:03:02 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[12x16, 4x16], luma_vss[12x16, 4x16] for 16bpp
draft
|
Wed, 18 Feb 2015 16:05:33 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[4x8, 16x12], luma_vss[4x8, 16x12] for 16bpp
draft
|
Wed, 18 Feb 2015 15:25:58 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[8x4, 16x4, 32x24], luma_vss[8x4, 16x4, 32x24] for 16bpp
draft
|
Wed, 18 Feb 2015 15:08:06 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[16x8, 32x8], luma_vss[16x8, 32x8] for 16bpp
draft
|
Wed, 18 Feb 2015 14:54:02 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[8x16, 8x32], luma_vss[8x16, 8x32] for 16bpp
draft
|
Wed, 18 Feb 2015 14:27:37 +0530 |
Divya Manivannan |
asm-avx2: 16bpp: luma_vsp[64xN, 32x32, 32x64, 48x64, 24x32, 16x32, 16x64]
draft
|
Wed, 18 Feb 2015 14:00:36 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[16x16, 32x16, 64x16], luma_vss[16x16, 32x16, 64x16] for 16bpp
draft
|
Wed, 18 Feb 2015 13:36:17 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[4x4, 8x8], luma_vss[4x4, 8x8] for 16bpp
draft
|
Wed, 18 Feb 2015 11:32:52 +0530 |
Sumalatha Polureddy |
asm: avx2 assembly code for 8bpp avg_pixel_pp[16xN]
draft
|
Wed, 18 Feb 2015 10:31:48 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Tue, 17 Feb 2015 17:46:00 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[32x24], luma_vss[32x24]: improve 13898c->7904c, 10802c->7850c
draft
|
Tue, 17 Feb 2015 17:25:52 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[16x8, 32x8], luma_vss[16x8, 32x8]: 2507c->1535c, 4655c->2954c,
draft
|
Tue, 17 Feb 2015 16:46:20 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[16x4], luma_vss[16x4]: improve 1368c->955c, 1194c->963c
draft
|
Tue, 17 Feb 2015 16:21:03 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[16x12], luma_vss[16x12]: improve 3579c->1988c, 2968c->1992c
draft
|
Tue, 17 Feb 2015 15:45:07 +0530 |
Sumalatha Polureddy |
asm: avx2 assembly code for 8bpp avg_pixel_pp[64xN]
draft
|
Tue, 17 Feb 2015 15:34:48 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[12x16], luma_vss[12x16]: improve 3753c->2097c, 2957c->1950c
draft
|
Tue, 17 Feb 2015 15:19:01 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[64xN, 48x64, 24x32, 32x32, 32x64, 16x32, 16x64]
draft
|
Tue, 17 Feb 2015 14:35:38 +0530 |
Praveen Tiwari |
asm-avx2: cpy2Dto1D_shr[8x8, 16x16, 32x32] 16bpp asm code integration
draft
|
Tue, 17 Feb 2015 14:19:40 +0530 |
Praveen Tiwari |
asm-cpy2Dto1D_shr: nits
draft
|
Tue, 17 Feb 2015 14:15:43 +0530 |
Sumalatha Polureddy |
asm: avx2 assembly code for 8bpp avg_pixel_pp[32xN]
draft
|
Tue, 17 Feb 2015 13:59:34 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[16x16, 32x16, 64x16], luma_vss[16x16, 32x16, 64x16]
draft
|
Tue, 17 Feb 2015 12:24:04 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[8x4], luma_vss[8x4]: improve 837c->500c, 790c->476c
draft
|
Tue, 17 Feb 2015 14:11:09 +0530 |
Praveen Tiwari |
asm-avx2: cpy2Dto1D_shr_32
draft
|
Tue, 17 Feb 2015 13:47:54 +0530 |
Praveen Tiwari |
asm-avx2: cpy2Dto1D_shr_16
draft
|
Tue, 17 Feb 2015 12:19:55 +0530 |
Praveen Tiwari |
asm-avx2: cpy2Dto1D_shr_8
draft
|
Tue, 17 Feb 2015 11:59:10 +0530 |
Sumalatha Polureddy |
asm: avx assembly code for 10bpp satd[4x32] - 26x
draft
|
Tue, 17 Feb 2015 11:48:16 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[8x16, 8x32], luma_vss[8x16, 8x32]: 6808c->1310c, 4869c->2505c,
draft
|
Tue, 17 Feb 2015 10:40:58 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[8x8], luma_vss[8x8]: improve 1422c->763c, 1238c->755c
draft
|
Tue, 17 Feb 2015 10:08:56 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Mon, 16 Feb 2015 16:59:08 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[4x16], luma_vss[4x16]: improve 1499c->890c, 1282c->725c
draft
|
Mon, 16 Feb 2015 16:55:54 +0530 |
Sumalatha Polureddy |
asm: avx assembly code for 10bpp satd[12x32] - 24x
draft
|
Mon, 16 Feb 2015 16:25:54 +0530 |
Sumalatha Polureddy |
asm: avx assembly code for 10bpp satd[16x24]-21x,satd[32x48]-24x,satd[24x64]-22x,satd[8x64]-22x,satd[8x12]-24x
draft
|
Mon, 16 Feb 2015 16:08:22 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[4x8], luma_vss[4x8]: improve 835c->457c, 776c->393c
draft
|
Mon, 16 Feb 2015 12:01:02 +0530 |
Divya Manivannan |
asm-avx2: luma_vsp[4x4], luma_vss[4x4]: improve 548c->275c, 510c->240c
draft
|
Mon, 16 Feb 2015 10:09:11 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Fri, 13 Feb 2015 18:28:52 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[12x16], luma_vps[12x16]: improve 3466c->2182c, 3275c->2057c
draft
|
Fri, 13 Feb 2015 18:07:46 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[4x16], luma_vps[4x16]: improve 1510c->756c, 1295c->728c
draft
|
Fri, 13 Feb 2015 17:24:51 +0530 |
Sumalatha Polureddy |
asm-avx2: pixel_average_pp[32x32] for 8bpp
draft
|
Fri, 13 Feb 2015 16:52:55 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[4x8], luma_vps[4x8]: improve 875c->439c, 794c->413c
draft
|
Fri, 13 Feb 2015 15:48:33 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[16x12], luma_vps[16x12]: improve 3446c->2193c, 3235c->2130c
draft
|
Fri, 13 Feb 2015 15:21:51 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[8x4], luma_vps[8x4]: improve 815c->520c, 776c->504c
draft
|
Fri, 13 Feb 2015 15:05:18 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[16x4], luma_vps[16x4]: improve 1350c->1070c, 1240c->974c
draft
|
Fri, 13 Feb 2015 16:34:40 +0530 |
Sumalatha Polureddy |
asm: avx assembly code for satd[4x32] -- 23.4x
draft
|
Fri, 13 Feb 2015 16:29:37 +0530 |
Sumalatha Polureddy |
asm: avx assembly code for satd[12x32] -- 25x
draft
|
Fri, 13 Feb 2015 18:26:02 +0530 |
Praveen Tiwari |
asm-avx2: cpy2Dto1D_shl[8x8, 16x16, 32x32] 16bpp
draft
|
Fri, 13 Feb 2015 17:59:33 +0530 |
Praveen Tiwari |
asm-avx2: cpy2Dto1D_shl_32
draft
|
Fri, 13 Feb 2015 17:33:58 +0530 |
Praveen Tiwari |
asm-avx2: cpy2Dto1D_shl_16
draft
|
Fri, 13 Feb 2015 16:32:26 +0530 |
Praveen Tiwari |
avx2-asm: cpy2Dto1D_shl_8
draft
|
Fri, 13 Feb 2015 12:41:14 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[32x24], luma_vps[32x24]: improve 12928c->8439c, 11985c->8082c
draft
|
Fri, 13 Feb 2015 12:04:46 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[32x8, 16x8]: improve 4507c->3043c, 2464c->1558c
draft
|
Fri, 13 Feb 2015 11:46:48 +0530 |
Praveen Tiwari |
asm-avx2: copy_cnt[8x8, 16x16, 32x32] 16bpp
draft
|
Fri, 13 Feb 2015 11:19:20 +0530 |
Praveen Tiwari |
asm-SSE4: copy_cnt [4x4, 8x8, 16x16, 32x32] 16bpp
draft
|
Fri, 13 Feb 2015 10:25:06 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Thu, 12 Feb 2015 18:04:04 +0530 |
praveen Tiwari |
asm-avx2: blockcopy_sp, 16xN, 32xN, 64x64 16bpp
draft
|
Thu, 12 Feb 2015 17:57:52 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[8x16, 8x32]: improve 2455c->1421c, 4644c->2829c
draft
|
Thu, 12 Feb 2015 17:40:17 +0530 |
praveen Tiwari |
asm-avx2: blockcopy_ps, 16xN, 32xN, 64x64 16bpp
draft
|
Thu, 12 Feb 2015 17:27:50 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[32x16, 64x16]: improve 8693c->5612c, 17070c->10779c
draft
|
Thu, 12 Feb 2015 17:04:57 +0530 |
praveen Tiwari |
asm-avx2: blockcopy_ss, 16xN, 32xN, 64x64 16bpp
draft
|
Thu, 12 Feb 2015 16:55:40 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp and luma_vps for 16x32, 16x64, 24x32, 32x32, 32x64, 48x64,
draft
|
Thu, 12 Feb 2015 16:04:57 +0530 |
Aasaipriya Chandran |
Luma_hps[16x4 ,8x8, 16x12, 16x16, 16x32, 16x64]avx2 asm: improved 2213c->1330c, 3067c->1792c, 3661c->2201, 4644c->2730c, 7473c->4739c, 13699c->8302c
draft
|
Thu, 12 Feb 2015 15:55:42 +0530 |
Aasaipriya Chandran |
Luma_hps[8x4 ,8x8, 8x16, 8x32]avx2 asm: improved 1120c->769c, 1585c->1042c, 2387c->1609c, 3971c->2607
draft
|
Thu, 12 Feb 2015 15:53:21 +0530 |
praveen Tiwari |
asm-avx2: blockcopy_pp_24xN 16bpp
draft
|
Thu, 12 Feb 2015 15:41:24 +0530 |
Aasaipriya Chandran |
Luma_hps[4x4 ,4x8, 4x16]avx2 asm: improved 783c->448c, 1049c->592c, 1563->c 874c
draft
|
Thu, 12 Feb 2015 15:03:37 +0530 |
praveen Tiwari |
asm-avx2: blockcopy_pp_48x64 16bpp
draft
|
Thu, 12 Feb 2015 14:31:45 +0530 |
praveen Tiwari |
asm-avx2: blockcopy_pp_32xN 16bpp
draft
|
Thu, 12 Feb 2015 12:28:43 +0530 |
praveen Tiwari |
asm-avx2: blockckfill_s
draft
|
Thu, 12 Feb 2015 12:22:22 +0530 |
Rajesh Paulraj |
asm: count_nonzero[4x4](4.05x), count_nonzero[8x8](10.54x),
draft
|
Thu, 12 Feb 2015 11:57:04 +0530 |
Divya Manivannan |
asm-avx2: luma_vpp[16x16], luma_vps[16x16]: improve 4546c->2754c, 4197c->2583c
draft
|
Thu, 12 Feb 2015 11:19:40 +0530 |
Praveen Tiwari |
asm-av2: blockcopy_ps_64x64
draft
|
Thu, 12 Feb 2015 10:41:23 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Wed, 11 Feb 2015 17:33:58 +0530 |
Praveen Tiwari |
asm-avx2:blockcopy_ps[32xN]
draft
|
Wed, 11 Feb 2015 15:31:50 +0530 |
Praveen Tiwari |
asm-avx2: blockcopy_ps[16xN]
draft
|
Wed, 11 Feb 2015 17:22:02 +0800 |
Divya Manivannan |
asm-avx2: luma_vpp[8x8], luma_vps[8x8]: improve 1402c->837c, 1260c->795c
draft
|
Wed, 11 Feb 2015 14:04:31 +0530 |
Rajesh Paulraj |
fix build error in asm-primitives.cpp
draft
|
Wed, 11 Feb 2015 11:07:32 +0530 |
Divya Manivannan |
asm - avx2: luma_vpp[4x4], luma_vps[4x4]: improve 576c->275c, 539c->269c
draft
|
Mon, 09 Feb 2015 20:27:27 +0530 |
Rajesh Paulraj |
C: split count_nonzero function and added testbench code
draft
|
Tue, 10 Feb 2015 19:28:51 +0530 |
Praveen Tiwari |
avx2-asm: blockcopy_sp[16xN]
draft
|
Tue, 10 Feb 2015 18:51:20 +0530 |
Praveen Tiwari |
avx2-asm: blockcopy_sp_64x64
draft
|
Wed, 11 Feb 2015 10:06:29 +0530 |
Praveen Tiwari |
Merge with stable
draft
|
Tue, 10 Feb 2015 18:24:22 +0530 |
Praveen Tiwari |
asm-avx2: blockcopy_sp_32xN
draft
|
Tue, 10 Feb 2015 12:14:13 +0530 |
Divya Manivannan |
asm - avx2: luma_vps[4x8, 4x16]: improve 572c->389c, 955c->760c,
draft
|
Tue, 10 Feb 2015 10:25:40 +0530 |
Praveen Tiwari |
Merge with stable
draft
|
Mon, 09 Feb 2015 17:40:39 +0530 |
Divya Manivannan |
asm in avx2: luma_vps[4x8, 4x16] improve 572c->443c, 955c->861c
draft
|
Mon, 09 Feb 2015 14:22:52 +0530 |
Divya Manivannan |
asm: luma_vps[8x16, 8x32] in avx2: improve 1069c->857c, 1933c->1672c
draft
|
Mon, 09 Feb 2015 12:44:22 +0530 |
Divya Manivannan |
asm: luma_vps[8x8] in avx2: improve 1506c->404c
draft
|
Mon, 09 Feb 2015 12:26:57 +0530 |
Divya Manivannan |
asm: luma_vps[8x4] in avx2: improve 470c->242c
draft
|
Mon, 09 Feb 2015 17:17:35 +0800 |
Divya Manivannan |
asm: luma_vps[12x16] in avx2: improve 1852c->1232c
draft
|
Mon, 09 Feb 2015 12:00:10 +0530 |
Praveen Tiwari |
blockcopy_pp[48x64]: avx asm code
draft
|
Mon, 09 Feb 2015 10:25:25 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Fri, 06 Feb 2015 14:17:59 +0530 |
Divya Manivannan |
asm: luma_vps[16x16] in avx2: improve 2128c->1169c
draft
|
Fri, 06 Feb 2015 13:47:38 +0530 |
Divya Manivannan |
asm: luma_vps[16x12] in avx2: improve 1656c->910c
draft
|
Fri, 06 Feb 2015 13:26:50 +0530 |
Divya Manivannan |
asm: luma_vps[16x8] in avx2: improve 1229c->658c
draft
|
Fri, 06 Feb 2015 12:22:44 +0530 |
Divya Manivannan |
asm: luma_vps[16x4] in avx2: improve 729c->487c
draft
|
Fri, 06 Feb 2015 18:19:19 +0530 |
Praveen Tiwari |
blockcopy_pp_64xN: avx asm code
draft
|
Fri, 06 Feb 2015 11:30:12 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Fri, 06 Feb 2015 10:41:07 +0530 |
Praveen Tiwari |
Merge with public
draft
|
Thu, 05 Feb 2015 12:52:32 +0530 |
Praveen Tiwari |
Merge with public
draft
|