September 2014 Archives by author

• Messages sorted by: [ thread ] [ subject ] [ date ]
• More info on this list...

Starting: Mon Sep 1 10:26:25 CEST 2014
Ending: Tue Sep 30 17:59:13 CEST 2014
Messages: 391

• [x265] Regarding changeset 8154 "vec: remove idct8, we have SSSE3 assembly for it"   James Almer
• [x265] Regarding changeset 8154 "vec: remove idct8, we have SSSE3 assembly for it"   James Almer
• [x265] [PATCH] analysis: CU structure now holds CU-specific information,   Steve Borho
• [x265] [PATCH] Entropy: Replaced getCtxQtCbf() with table   Steve Borho
• [x265] [PATCH] analysis: CU structure now holds CU-specific information,   Steve Borho
• [x265] [PATCH] Cleaned up TComDataCU::getQuadtreeTULog2MinSizeInCU for clarity and a bit of performance   Steve Borho
• [x265] change index of m_buOffsetY[] from raster to zscan   Steve Borho
• [x265] [PATCH] dequant_normal optimization, downscaling quantCoef from int32_t* to int16_t*   Steve Borho
• [x265] [PATCH] x86asm: warn when inappropriate instruction used in function with specified cpuflags   Steve Borho
• [x265] fix cbf context   Steve Borho
• [x265] [PATCH] x86asm: warn when inappropriate instruction used in function with specified cpuflags   Steve Borho
• [x265] note: history rewrite   Steve Borho
• [x265] [PATCH] copy_cnt 4x4 AVX2 asm code, as per new interface   Steve Borho
• [x265] [PATCH] frameencoder: remove second encodeCU() pass over CTUs when SAO is disabled   Steve Borho
• [x265] [PATCH]Add iteration-skip to subpel refine   Steve Borho
• [x265] [PATCH] frameencoder: remove second encodeCU() pass over CTUs when SAO is disabled   Steve Borho
• [x265] [PATCH] asm: avx2 assembly code for dct16   Steve Borho
• [x265] [PATCH] x86inc.asm: fix vpbroadcastd bug on Mac platform   Steve Borho
• [x265] [PATCH] frameencoder: remove second encodeCU() pass over CTUs when SAO is disabled   Steve Borho
• [x265] [PATCH 1 of 4] add intra-inter data structures and param options   Steve Borho
• [x265] [PATCH 4 of 4] cli: add cli options analysis-out and analysis-in   Steve Borho
• [x265] [PATCH] dpb: select best TMVP candidate from among all of the reference frames   Steve Borho
• [x265] [PATCH] copy_cnt_8 AVX2 asm code, as per new interface   Steve Borho
• [x265] [PATCH 4 of 4] cli: add cli options analysis-out and analysis-in   Steve Borho
• [x265] [PATCH 1 of 4] add analysis data structures and param options   Steve Borho
• [x265] [PATCH 2 of 4] api: introduce x265_alloc_analysis_data and x265_free_analysis_data methods to allocate and free analysis info   Steve Borho
• [x265] [PATCH 3 of 4] store intra analysis information in buffers   Steve Borho
• [x265] [PATCH 4 of 4] cli: add cli options analysis-out and analysis-in   Steve Borho
• [x265] [PATCH 1 of 4] add analysis data structures and param options   Steve Borho
• [x265] [PATCH] search: measure RDO of intra modes within 25% of least cost [CHANGES OUTPUTS]   Steve Borho
• [x265] [PATCH 1 of 4] add analysis data structures and param options   Steve Borho
• [x265] [PATCH 4 of 4] cli: add cli options analysis-mode and analysis-file   Steve Borho
• [x265] [PATCH] search: measure RDO of intra modes within 25% of least cost [CHANGES OUTPUTS]   Steve Borho
• [x265] [PATCH] analysis: Intra picture estimation information sharing   Steve Borho
• [x265] [PATCH] denoiseDct: unit test code   Steve Borho
• [x265] [PATCH] param: preset tuning changes   Steve Borho
• [x265] [PATCH] add fanout validation module to check param compatibility   Steve Borho
• [x265] [PATCH] analysis: Intra picture estimation information sharing   Steve Borho
• [x265] [PATCH] denoiseDct: test bench code   Steve Borho
• [x265] [PATCH] analysis: add CU specific details to encodeCU()   Steve Borho
• [x265] [PATCH] api: do not reuse the analysisData buffer for more then one picture, set it NULL   Steve Borho
• [x265] inline simple functions   Steve Borho
• [x265] [PATCH] search: dump best motion statistics for P and B slices into analysisdata file   Steve Borho
• [x265] [PATCH] search: remove redundant loacal variables in encodeResAndCalcRdSkipCU   Steve Borho
• [x265] inline simple functions   Steve Borho
• [x265] [PATCH 01 of 14] motion: avoid extra iterations when no subpel motion found   Steve Borho
• [x265] [PATCH 02 of 14] bitcost: use enums for special constants rather than static const ints   Steve Borho
• [x265] [PATCH 03 of 14] nits: do not check for NULL from new operations   Steve Borho
• [x265] [PATCH 04 of 14] bitstream: add paren to avoid ambiguous precedence in X265_CHECK   Steve Borho
• [x265] [PATCH 05 of 14] entropy: fix SAO enable detection (refs #80)   Steve Borho
• [x265] [PATCH 06 of 14] encoder: use %u to sprintf unsigned ints (refs #80)   Steve Borho
• [x265] [PATCH 07 of 14] TComWeightPrediction: combine duplicate inline functions (refs #80)   Steve Borho
• [x265] [PATCH 08 of 14] predict: merge TComWeightPrediction functions into Predict   Steve Borho
• [x265] [PATCH 09 of 14] predict: don't bother keeping refidx as an array   Steve Borho
• [x265] [PATCH 10 of 14] predict: combine redundant logic paths in predInterBi()   Steve Borho
• [x265] [PATCH 11 of 14] predict: use faster unidir prediction for B frames when weighting not enabled   Steve Borho
• [x265] [PATCH 12 of 14] predict: streamline getWpScaling()   Steve Borho
• [x265] [PATCH 13 of 14] predict: remove list argument from motionCompensation(), always REF_PIC_LIST_X   Steve Borho
• [x265] [PATCH 14 of 14] predict: remove checkIdenticalMotion()   Steve Borho
• [x265] [PATCH] Changed FrameEncoder::m_tld to a pointer and set it to one of Encoder's ThreadLocalData instances   Steve Borho
• [x265] [PATCH] Changed FrameEncoder::m_tld to a pointer and set it to one of Encoder's ThreadLocalData instances   Steve Borho
• [x265] refine deblocking filter   Steve Borho
• [x265] Regarding changeset 8154 "vec: remove idct8, we have SSSE3 assembly for it"   Steve Borho
• [x265] [PATCH 1 of 5] predict: inline single call of predInterBi()   Steve Borho
• [x265] [PATCH 2 of 5] predict: inline predInterUni(), getWpScaling() and simplify motionCompensation()   Steve Borho
• [x265] [PATCH 3 of 5] predict: remove check for reallocations, comment nits   Steve Borho
• [x265] [PATCH 4 of 5] predict: combine and check allocations and return failures   Steve Borho
• [x265] [PATCH 5 of 5] predict: split weighted prediction values from WeightParam   Steve Borho
• [x265] [PATCH] encoder: rename cuCoder to analysis for better clarity   Steve Borho
• [x265] refine deblocking filter   Steve Borho
• [x265] refine deblocking filter   Steve Borho
• [x265] [PATCH] api: rename SAO options and params for clarity   Steve Borho
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   Steve Borho
• [x265] [PATCH] asm: avx2 asm code for idct32x32   Steve Borho
• [x265] [PATCH 1 of 4] analysis: hoist local function into anonymous namespace (file local)   Steve Borho
• [x265] [PATCH 2 of 4] analysis: remove unused LAMBDA_PARTITION_SELECT   Steve Borho
• [x265] [PATCH 3 of 4] analysis: coding style and comment nits   Steve Borho
• [x265] [PATCH 4 of 4] analysis: remove #define conditionals for control flow   Steve Borho
• [x265] [PATCH] search: give each Search instance an Entropy encoder (no output changes)   Steve Borho
• [x265] [PATCH] search: give each Search instance an Entropy encoder (no output changes)   Steve Borho
• [x265] [PATCH] TComDataCU: replace getTotalNumPart() with CU structure details   Steve Borho
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   Steve Borho
• [x265] [PATCH] TComDataCU: replace getTotalNumPart() with CU structure details   Steve Borho
• [x265] [PATCH] api: rename SAO options and params for clarity   Steve Borho
• [x265] [PATCH] convert c++ reference to pointer on m_scalingList   Steve Borho
• [x265] [PATCH] blockfill_s_32x32 avx2 asm code, performance improved 1354.05 cycles -> 705.81 cycles   Steve Borho
• [x265] [PATCH 0 of 2 ] TComDataCU: replace with more CU structure details   Steve Borho
• [x265] sao: remove frame-based SAO   Steve Borho
• [x265] [PATCH] rd: move lambda and analysis qp init to rdcost.h   Steve Borho
• [x265] [PATCH 2 of 3] asm: reenable IACA support, it remove by 'inappropriate instruction...' patch   BugMaster
• [x265] [PATCH 1 of 3] testbench(nquant): the Round value must be less than (2 ^ qbits)   Min Chen
• [x265] [PATCH 2 of 3] asm: optimize nquant by PSIGND, improve 13k cycles -> 11k cycles   Min Chen
• [x265] [PATCH 3 of 3] asm: avx2 version of nquant(), improve 11k cycles -> 7k cycles   Min Chen
• [x265] [PATCH] asm: replace ssse3 instruction in pixel_ssd_ss_*_sse2   Min Chen
• [x265] [PATCH 1 of 3] asm: optimize nquant by PSIGND, improve 11k cycles -> 9.8k cycles   Min Chen
• [x265] [PATCH 2 of 3] asm: reenable IACA support, it remove by 'inappropriate instruction...' patch   Min Chen
• [x265] [PATCH 3 of 3] asm: avx2 version of nquant(), improve 9.8k cycles -> 5.3k cycles   Min Chen
• [x265] [PATCH 1 of 2] asm: fix output mistake in pixel_ssd_ss_4xN   Min Chen
• [x265] [PATCH 2 of 2] asm: enable SSE2 version of pixel_ssd_ss[]   Min Chen
• [x265] [PATCH] x86inc.asm: fix vpbroadcastd bug on Mac platform   Min Chen
• [x265] [PATCH] x86inc.asm: fix vpbroadcastd bug on Mac platform   Min Chen
• [x265] [PATCH 1 of 2] asm: reduce number of movd in dequant_normal   Min Chen
• [x265] [PATCH 2 of 2] asm: AVX2 version of dequant_normal, improve 9.3k Cycles -> 4.2k Cycles   Min Chen
• [x265] [PATCH 1 of 4] testbench(quant): the Round value must be less than (2 ^ qbits)   Min Chen
• [x265] [PATCH 2 of 4] testbench(quant): the qBits value must be more than or equal to 8   Min Chen
• [x265] [PATCH 3 of 4] asm: improve quant by replace variant shift to fixed shift, 19k cycles -> 16.6k cycles   Min Chen
• [x265] [PATCH 4 of 4] asm: avx2 version of quant, improve 16.6k cycles -> 8.4k cycles   Min Chen
• [x265] [PATCH] asm: replace mova by movu to avoid AVX2 testbench crash in dct16, dct32, denoise_dct, its same speed on Haswell   Min Chen
• [x265] [PATCH] convert c++ reference to pointer on m_scalingList   Min Chen
• [x265] [PATCH] analysis: Intra picture estimation information sharing   Gopu Govindaswamy
• [x265] 1.3+94-0e0d0309e616 - GCC error at 28%   JMK
• [x265] [PATCH 4 of 4] cli: add cli options analysis-out and analysis-in   Sagar Kotecha
• [x265] [PATCH] add fanout validation module to check param compatibility   Sagar Kotecha
• [x265] [PATCH] add avx version for chroma_copy_ss 16x4, 16x8, 16x12, 16x16, 16x24, 16x32, 16x64 based on csp, approx 1.5x-2x speedup over SSE   Sagar Kotecha
• [x265] Recent Frames/second benchmarks per platform and per clip?   Raul Lopez
• [x265] [PATCH] Changes for loadCTUData   Ashok Kumar Mishra
• [x265] [PATCH 1 of 4] add analysis data structures and param options   Nicolas Morey-Chaisemartin
• [x265] change index of m_buOffsetY[] from raster to zscan   Satoshi Nakagawa
• [x265] fix cbf context   Satoshi Nakagawa
• [x265] fix cbf context   Satoshi Nakagawa
• [x265] fix getQuadtreeTULog2MinSizeInCU()   Satoshi Nakagawa
• [x265] fix CHECKED_BUILD   Satoshi Nakagawa
• [x265] fix sao   Satoshi Nakagawa
• [x265] [PATCH] x86inc.asm: fix vpbroadcastd bug on Mac platform   Satoshi Nakagawa
• [x265] sao: some cleanups   Satoshi Nakagawa
• [x265] inline simple functions   Satoshi Nakagawa
• [x265] inline simple functions   Satoshi Nakagawa
• [x265] primitives: intra_pred[4][35] => intra_pred[35][4] (avoid *35)   Satoshi Nakagawa
• [x265] simplify intra filter (with fix for da61cf406f16) (Re: primitives: intra_pred[4][35] => intra_pred[35][4] (avoid *35))   Satoshi Nakagawa
• [x265] refine deblocking filter   Satoshi Nakagawa
• [x265] refine deblocking filter   Satoshi Nakagawa
• [x265] refine deblocking filter   Satoshi Nakagawa
• [x265] sao: remove frame-based SAO   Satoshi Nakagawa
• [x265] [PATCH] Entropy: Replaced getCtxQtCbf() with table   Deepthi Nandakumar
• [x265] [PATCH] fix: hash/binary mismatch for new CU structure holds CU-specific info   Deepthi Nandakumar
• [x265] [PATCH] Resolve gcc warnings   Deepthi Nandakumar
• [x265] [PATCH 2 of 3] asm: optimize nquant by PSIGND, improve 13k cycles -> 11k cycles   Deepthi Nandakumar
• [x265] [PATCH] frameencoder: remove second encodeCU() pass over CTUs when SAO is disabled   Deepthi Nandakumar
• [x265] [PATCH] search.cpp: fixed type conversion warning   Deepthi Nandakumar
• [x265] [PATCH] copy_cnt: enable avx2 version of asm code   Deepthi Nandakumar
• [x265] [PATCH] copy_cnt: enable avx2 version of asm code   Deepthi Nandakumar
• [x265] sao: some cleanups   Deepthi Nandakumar
• [x265] [PATCH] Resolved gcc compiler error of mismatched type   Deepthi Nandakumar
• [x265] [PATCH RFC] analysis: add CU specific details to encodeCU()   Deepthi Nandakumar
• [x265] [PATCH] Search: remove redundant encode coefficients in intra for performance   Deepthi Nandakumar
• [x265] [PATCH] Search: remove redundant encode coefficients in intra for performance   Deepthi Nandakumar
• [x265] [PATCH] analysis: add CU specific details to encodeCU()   Deepthi Nandakumar
• [x265] [PATCH] analysis: add CU specific details to encodeCU()   Deepthi Nandakumar
• [x265] [PATCH] analysis: add CU specific details to encodeCU()   Deepthi Nandakumar
• [x265] [PATCH] rc: fixes for 2 pass + vbv to calculate frameSizePlanned accurately   Deepthi Nandakumar
• [x265] [PATCH] remove getNumPartInCU() and replace it with constant value   Deepthi Nandakumar
• [x265] [PATCH] remove getNumPartInCU() and replace it with macro   Deepthi Nandakumar
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   Deepthi Nandakumar
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   Deepthi Nandakumar
• [x265] primitives: intra_pred[4][35] => intra_pred[35][4] (avoid *35)   Deepthi Nandakumar
• [x265] [PATCH] asm: replace mova by movu to avoid AVX2 testbench crash in dct16, dct32, denoise_dct, its same speed on Haswell   Deepthi Nandakumar
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   Deepthi Nandakumar
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   Deepthi Nandakumar
• [x265] [PATCH 2 of 2] TComDataCU: replace getTotalNumPart() with CU structure details   Deepthi Nandakumar
• [x265] [PATCH 2 of 2] TComDataCU: replace getTotalNumPart() with CU structure details   Deepthi Nandakumar
• [x265] [PATCH] Changes for loadCTUData   Deepthi Nandakumar
• [x265] divide, encode, combine?   Michael Nordberg
• [x265] x265 --> YASM 1.3.0 update   Michal Powalko
• [x265] Recent Frames/second benchmarks per platform and per clip?   Mario Rohkrämer
• [x265] Recent Frames/second benchmarks per platform and per clip?   Mario Rohkrämer
• [x265] [PATCH] analysis: add CU specific details to encodeCU()   Santhoshini Sekar
• [x265] [PATCH] remove getNumPartInCU() and replace it with macro   Santhoshini Sekar
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   Santhoshini Sekar
• [x265] [PATCH 2 of 2] TComDataCU: replace getTotalNumPart() with CU structure details   Santhoshini Sekar
• [x265] [PATCH] Changes for loadCTUData   Santhoshini Sekar
• [x265] Fwd: [PATCH] copy_cnt_4: faster AVX2 code   Praveen Tiwari
• [x265] Fwd: Fwd: [PATCH] copy_cnt_4: faster AVX2 code   Praveen Tiwari
• [x265] [PATCH] copy_cnt: enable avx2 version of asm code   Praveen Tiwari
• [x265] [PATCH] removed copy_cnt_4 avx2 asm code: SSE version is eualy faster   Praveen Tiwari
• [x265] Fwd: [PATCH] denoiseDct: unit test code   Praveen Tiwari
• [x265] HEVC Daily Log - Murugan/Yuvaraj 9/2/22014   Murugan Vairavel
• [x265] [PATCH] x86asm: warn when inappropriate instruction used in function with specified cpuflags   Murugan Vairavel
• [x265] [PATCH] asm: avx2 asm code for idct32x32   Murugan Vairavel
• [x265] divide, encode, combine?   Tom Vaughan
• [x265] Recent Frames/second benchmarks per platform and per clip?   Tom Vaughan
• [x265] Recent Frames/second benchmarks per platform and per clip?   Tom Vaughan
• [x265] Recent Frames/second benchmarks per platform and per clip?   Tom Vaughan
• [x265] [PATCH] asm: avx2 assembly code for dct16   Yuvaraj Venkatesh
• [x265] [PATCH] asm: avx2 asm code for dct4   chen
• [x265] [PATCH] asm: avx2 asm code for dct4   chen
• [x265] [PATCH] asm: avx2 asm code for dct4   chen
• [x265] [PATCH] count_nonzero primitive optimization, downscaling quantCoef from int32_t* to int16_t*   chen
• [x265] [PATCH] cvt16to32_cnt optimization   chen
• [x265] [PATCH] added copy_shr primitive   chen
• [x265] [PATCH] added copy_shl primitive   chen
• [x265] [PATCH] fix: hash/binary mismatch for new CU structure holds CU-specific info   chen
• [x265] [PATCH 2 of 3] asm: optimize nquant by PSIGND, improve 13k cycles -> 11k cycles   chen
• [x265] [PATCH] copy_cnt 4x4, eliminated move instructions, +1x improvement   chen
• [x265] [PATCH] copy_cnt: nits   chen
• [x265] [PATCH] copy_cnt 4x4 AVX2 asm code, as per new interface   chen
• [x265] [PATCH] count_nonzero asm code, reduceded code size by combining mova and packsswb   chen
• [x265] [PATCH] asm: avx2 assembly code for dct16   chen
• [x265] [PATCH] asm: avx2 assembly code for dct16   chen
• [x265] [PATCH] copy_cnt_8 AVX2 asm code, as per new interface   chen
• [x265] [PATCH] copy_cnt_4: faster AVX2 code   chen
• [x265] [PATCH] copy_cnt_4: enable fast non zero coefficient count path   chen
• [x265] Fwd: [PATCH] copy_cnt_4: faster AVX2 code   chen
• [x265] [PATCH] asm: avx2 assembly code for dct16   chen
• [x265] [PATCH] copy_cnt_8, AVX2 asm code as per new interface, performance improved from 5.13x to 7.59x on HASWELL-I5   chen
• [x265] [PATCH] copy_cnt_16, AVX2 asm code as per new interface, performance improved from 14.22x to 23.57x on HASWELL-I5   chen
• [x265] Fwd: Fwd: [PATCH] copy_cnt_4: faster AVX2 code   chen
• [x265] [PATCH] copy_cnt_16: avx2 asm code as per new interface, improved 514.32 cycles -> 313.66 cycles   chen
• [x265] [PATCH] asm: avx2 assembly code for dct32x32   chen
• [x265] [PATCH] denoiseDct: SSE version of asm code   chen
• [x265] [PATCH] asm: avx2 assembly code for idct16x16   chen
• [x265] [PATCH] denoise_dct asm code: SSE version   chen
• [x265] [PATCH] denoise_dct: avx2 asm code   chen
• [x265] [PATCH] copy_cnt_16: avx2 asm code, improved 514.32 cycles -> 313.66 cycles   chen
• [x265] [PATCH] copy_cnt_32: avx2 asm code, improved 1521.17 cycles -> 934.46 cycles   chen
• [x265] [PATCH] blockcopy_pp: 32x8, 32x16, 32x24, 32x32, 32x48, 32x64 AVX version of asm code, approx double speedup comapre to SSE   chen
• [x265] [PATCH] asm: avx2 code for dct8x8   chen
• [x265] [PATCH] add avx version for chroma_copy_ss 16x4, 16x8, 16x12, 16x16, 16x24, 16x32, 16x64 based on csp, approx 1.5x-2x speedup over SSE   chen
• [x265] [PATCH] asm: avx2 code for dct8x8   chen
• [x265] [PATCH] add avx version for chroma_copy_ss 16x4, 16x8, 16x12, 16x16, 16x24, 16x32, 16x64 based on csp, approx 1.5x-2x speedup over SSE   chen
• [x265] [PATCH] blockcopy_ss: 64x16, 64x32, 64x48, 64x64 AVX version of asm code, approx double speedup comapre to SSE   chen
• [x265] [PATCH] asm: replace mova by movu to avoid AVX2 testbench crash in dct16, dct32, denoise_dct, its same speed on Haswell   chen
• [x265] [PATCH] blockcopy_pp_32x8: avx asm code, improved 281.20 cycles -> 165.47   chen
• [x265] [PATCH] blockcopy_pp_32x16: avx asm code, improved 477.74 cycles -> 309.99   chen
• [x265] [PATCH] blockcopy_pp_32x24: avx asm code, improved 621.84 cycles -> 371.94   chen
• [x265] [PATCH] bloccopy_pp avx asm code: 32x32, 32x48, 32x64 improved by 803.69 -> 514.90, 1126.36 -> 655.24, 1454.09 -> 835.76 cycles   chen
• [x265] [PATCH] blockcopy_pp: avx asm code indentation   chen
• [x265] [PATCH] asm: avx2 assembly code for idct8x8   chen
• [x265] [PATCH] asm: avx2 asm code for idct32x32   chen
• [x265] [PATCH] convert c++ reference to pointer on m_scalingList   chen
• [x265] [PATCH] blockfill_s_16x16 avx2 asm code, performance improved 389.21 cycles -> 204.38 cycles   chen
• [x265] [PATCH] blockfill_s_16x16 avx2 asm code: performance improved from 389.21 cycles to 204.38 cycles, over sse version of asm code   chen
• [x265] [PATCH] blockfill_s_32x32 avx2 asm code: performance improved from 1354.05 cycles to 705.81 cycles, over sse version of asm code   chen
• [x265] [PATCH] search: measure RDO of intra modes within 25% of least cost [CHANGES OUTPUTS]   dave
• [x265] [PATCH] Changed FrameEncoder::m_tld to a pointer and set it to one of Encoder's ThreadLocalData instances   dave
• [x265] [PATCH] Changed FrameEncoder::m_tld to a pointer and set it to one of Encoder's ThreadLocalData instances   dave
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   dave
• [x265] target processor detection message in CMakeLists.txt   djcj
• [x265] [PATCH] Resolve gcc warnings   dtyx265 at gmail.com
• [x265] [PATCH] Cleaned up TComDataCU::getQuadtreeTULog2MinSizeInCU for clarity and a bit of performance   dtyx265 at gmail.com
• [x265] [PATCH] Resolved gcc compiler error of mismatched type   dtyx265 at gmail.com
• [x265] [PATCH] Changed FrameEncoder::m_tld to a pointer and set it to one of Encoder's ThreadLocalData instances   dtyx265 at gmail.com
• [x265] [PATCH] Removed unnecessary call to loadCTUData   dtyx265 at gmail.com
• [x265] [PATCH] Changes for loadCTUData   dtyx265 at gmail.com
• [x265] [PATCH] rc: use m_frameDuration instead of rce->frameDuration to derive complexity for each frame in 2nd pass   aarthi at multicorewareinc.com
• [x265] [PATCH] rc: bug fix for 2 pass when bframes = 0. fixes Issue #77   aarthi at multicorewareinc.com
• [x265] [PATCH] rc: check for changes in scenecut input between multiple passes   aarthi at multicorewareinc.com
• [x265] [PATCH] rc: fixes for 2 pass + vbv to calculate frameSizePlanned accurately   aarthi at multicorewareinc.com
• [x265] [PATCH] rc: fix bugs in using boundary condition for cu while encoding each frame   aarthi at multicorewareinc.com
• [x265] [PATCH] rc: apply maxAU size restrictions while encoding each frame   aarthi at multicorewareinc.com
• [x265] [PATCH] analysis: CU structure now holds CU-specific information,   ashok at multicorewareinc.com
• [x265] [PATCH] Entropy: Replaced getCtxQtCbf() with table   ashok at multicorewareinc.com
• [x265] [PATCH] analysis: CU structure now holds CU-specific information,   ashok at multicorewareinc.com
• [x265] [PATCH] Entropy: Replaced getCtxQtCbf() with table   ashok at multicorewareinc.com
• [x265] [PATCH] TComDataCU: Reduced repeated function call to calculate depth range   ashok at multicorewareinc.com
• [x265] [PATCH] fix: hash/binary mismatch for new CU structure holds CU-specific info   ashok at multicorewareinc.com
• [x265] [PATCH] Analysis: compressIntraCU clean up   ashok at multicorewareinc.com
• [x265] [PATCH] analysis: modified compressInterCU_rd5_6() with CU-specific information   ashok at multicorewareinc.com
• [x265] [PATCH] analysis: modified compressInterCU_rd0_4() with CU-specific information   ashok at multicorewareinc.com
• [x265] [PATCH] Search: remove redundant encode coefficients in intra for performance   ashok at multicorewareinc.com
• [x265] [PATCH] Analysis: fix for binary mismatch for pass 2 in compressIntraCU()   ashok at multicorewareinc.com
• [x265] [PATCH] Analysis: fix for binary mismatch for pass 2 in compressSharedIntraCTU()   ashok at multicorewareinc.com
• [x265] [PATCH] vps: vps_timing_info is always present   deepthi at multicorewareinc.com
• [x265] [PATCH] vps: general_frame_only_constraint_flag is true in progressive videos   deepthi at multicorewareinc.com
• [x265] [PATCH] analysis: remove redundant arguments, clean up variable names   deepthi at multicorewareinc.com
• [x265] [PATCH] psy-rd: fix bug in chroma psyEnergy for intra 4x4   deepthi at multicorewareinc.com
• [x265] [PATCH] asm: avx2 asm code for dct4   dnyaneshwar at multicorewareinc.com
• [x265] [PATCH] dpb: select best TMVP candidate from among all of the reference frames   gopu at multicorewareinc.com
• [x265] [PATCH] analysis: Intra picture estimation information sharing   gopu at multicorewareinc.com
• [x265] [PATCH] analysis: Intra picture estimation information sharing   gopu at multicorewareinc.com
• [x265] [PATCH] analysis: intra picture estimation (mode and split decision)information sharing   gopu at multicorewareinc.com
• [x265] [PATCH] api: do not reuse the analysisData buffer for more then one picture, set it NULL   gopu at multicorewareinc.com
• [x265] [PATCH] search: cleanup and remove redundant variable in checkintra   gopu at multicorewareinc.com
• [x265] [PATCH] search: dump best motion statistics for P and B slices into analysisdata file   gopu at multicorewareinc.com
• [x265] [PATCH] search: remove redundant loacal variables in encodeResAndCalcRdSkipCU   gopu at multicorewareinc.com
• [x265] [PATCH] search: simplify and remove redundant variables in getBestIntraModeChroma   gopu at multicorewareinc.com
• [x265] [PATCH] asm: enable 16bpp primitives of cvt32to16 and cvt16to32 for all block sizes   murugan at multicorewareinc.com
• [x265] [PATCH] x86asm: warn when inappropriate instruction used in function with specified cpuflags   murugan at multicorewareinc.com
• [x265] [PATCH] asm: avx2 assembly code for dct32x32   murugan at multicorewareinc.com
• [x265] [PATCH] asm: fix mismatch due to dct32 avx2 assembly code   murugan at multicorewareinc.com
• [x265] [PATCH] asm: avx2 assembly code for idct16x16   murugan at multicorewareinc.com
• [x265] [PATCH] asm: avx2 asm code for idct32x32   murugan at multicorewareinc.com
• [x265] [PATCH] asm: avx2 assembly code for idct32x32   murugan at multicorewareinc.com
• [x265] [PATCH] asm: avx2 assembly code for idct4x4   murugan at multicorewareinc.com
• [x265] [PATCH] count_nonzero primitive optimization, downscaling quantCoef from int32_t* to int16_t*   praveen at multicorewareinc.com
• [x265] [PATCH] dequant_normal optimization, downscaling quantCoef from int32_t* to int16_t*   praveen at multicorewareinc.com
• [x265] [PATCH] dequant_normal asm code optimization as per new interface   praveen at multicorewareinc.com
• [x265] [PATCH] dequant_scaling optimization, downscaling quantCoef from int32_t* to int16_t*   praveen at multicorewareinc.com
• [x265] [PATCH] quant.cpp, cleaned redundant code   praveen at multicorewareinc.com
• [x265] [PATCH] nquant optimization, downscaling qCoef from int32_t* to int16_t*   praveen at multicorewareinc.com
• [x265] [PATCH] rdoQuant optimization, downscaling dstCoeff fron int32_t* to int16_t*   praveen at multicorewareinc.com
• [x265] [PATCH] signBitHidingHDQ optimization, downscaling coeff from int32_t* to int16_t*   praveen at multicorewareinc.com
• [x265] [PATCH] cvt16to32_cnt optimization   praveen at multicorewareinc.com
• [x265] [PATCH] conv16to32_count C interface modification, downscaling coeff from int32_t* to int16_t*   praveen at multicorewareinc.com
• [x265] [PATCH] conv16to32_count renamed to copy_count as per new interface   praveen at multicorewareinc.com
• [x265] [PATCH] temporarily disable avx2 version of copy_cnt primitive, need to update as per new interface   praveen at multicorewareinc.com
• [x265] [PATCH] added copy_shr primitive   praveen at multicorewareinc.com
• [x265] [PATCH] added copy_shl primitive   praveen at multicorewareinc.com
• [x265] [PATCH] optimize cvt32to16_shl by replacing copy_shl   praveen at multicorewareinc.com
• [x265] [PATCH] quant_c optimization, downscaling qCoef from int32_t* to int16_t*   praveen at multicorewareinc.com
• [x265] [PATCH] quant path cleanup   praveen at multicorewareinc.com
• [x265] [PATCH] count_nonzero asm code, reduceded code size by combining mova and packsswb   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt 4x4, eliminated move instructions, +1x improvement   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt: nits   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt 4x4 AVX2 asm code, as per new interface   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_4 asm code, corrected register uses   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt replaced align load with unaligned load to avoid code crash, we are not sure about alignment of dst buffer   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_4: enable fast non zero coefficient count path   praveen at multicorewareinc.com
• [x265] [PATCH] search.cpp: fixed type conversion warning   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_4: combine mova and paddb to reduce code size, same speedup   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_4: faster AVX2 code   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_8 AVX2 asm code, as per new interface   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_8, AVX2 asm code as per new interface, performance improved from 5.13x to 7.59x on HASWELL-I5   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_16, AVX2 asm code as per new interface, performance improved from 14.22x to 23.57x on HASWELL-I5   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_32, AVX2 asm code as per new interface, performance improved from 16.81x to 32.16x on HASWELL-I5   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt: enable avx2 version of asm code   praveen at multicorewareinc.com
• [x265] [PATCH] removed copy_cnt_4 avx2 asm code: SSE version is eualy faster   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_4 avx2 asm code: nit, same speedup by sse version   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_16: avx2 asm code as per new interface, improved 514.32 cycles -> 313.66 cycles   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_32: avx2 asm code as per new interface, improved 1521.17 cycles -> 934.46 cycles   praveen at multicorewareinc.com
• [x265] [PATCH] denoiseDct: unit test code   praveen at multicorewareinc.com
• [x265] [PATCH] denoiseDct: test bench code   praveen at multicorewareinc.com
• [x265] [PATCH] denoiseDct test code: fixed typo   praveen at multicorewareinc.com
• [x265] [PATCH] denoiseDct unit test code: fixed bound value problem   praveen at multicorewareinc.com
• [x265] [PATCH] denoiseDct asm code: nit faulty code, need a new SSE version   praveen at multicorewareinc.com
• [x265] [PATCH] denoiseDct: nit unused asm function declarations   praveen at multicorewareinc.com
• [x265] [PATCH] denoiseDct: SSE version of asm code   praveen at multicorewareinc.com
• [x265] [PATCH] denoise_dct asm code: SSE version   praveen at multicorewareinc.com
• [x265] [PATCH] denoise_dct: avx2 asm code   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_16: avx2 asm code, improved 514.32 cycles -> 313.66 cycles   praveen at multicorewareinc.com
• [x265] [PATCH] copy_cnt_32: avx2 asm code, improved 1521.17 cycles -> 934.46 cycles   praveen at multicorewareinc.com
• [x265] [PATCH] denoiseDct: align performance data while reporting speedup   praveen at multicorewareinc.com
• [x265] [PATCH] blockcopy_pp: 32x8, 32x16, 32x24, 32x32, 32x48, 32x64 AVX version of asm code, approx double speedup comapre to SSE   praveen at multicorewareinc.com
• [x265] [PATCH] testbench.cpp: temporary fix for testbench crash   praveen at multicorewareinc.com
• [x265] [PATCH] blockcopy_pp_32x8: avx asm code, improved 281.20 cycles -> 165.47   praveen at multicorewareinc.com
• [x265] [PATCH] asm-primitives.cpp: nits   praveen at multicorewareinc.com
• [x265] [PATCH] blockcopy_pp_32x16: avx asm code, improved 477.74 cycles -> 309.99   praveen at multicorewareinc.com
• [x265] [PATCH] blockcopy_pp_32x24: avx asm code, improved 621.84 cycles -> 371.94   praveen at multicorewareinc.com
• [x265] [PATCH] bloccopy_pp avx asm code: 32x32, 32x48, 32x64 improved by 803.69 -> 514.90, 1126.36 -> 655.24, 1454.09 -> 835.76 cycles   praveen at multicorewareinc.com
• [x265] [PATCH] blockcopy_pp: avx asm code indentation   praveen at multicorewareinc.com
• [x265] [PATCH] blockfill_s_16x16 avx2 asm code, performance improved 389.21 cycles -> 204.38 cycles   praveen at multicorewareinc.com
• [x265] [PATCH] blockfill_s_32x32 avx2 asm code, performance improved 1354.05 cycles -> 705.81 cycles   praveen at multicorewareinc.com
• [x265] [PATCH] blockfill_s_16x16 avx2 asm code: performance improved from 389.21 cycles to 204.38 cycles, over sse version of asm code   praveen at multicorewareinc.com
• [x265] [PATCH] blockfill_s_32x32 avx2 asm code: performance improved from 1354.05 cycles to 705.81 cycles, over sse version of asm code   praveen at multicorewareinc.com
• [x265] [PATCH 1 of 4] add intra-inter data structures and param options   sagar at multicorewareinc.com
• [x265] [PATCH 2 of 4] api: add x265_alloc_inter_intra_data and x265_free_inter_intra_data methods to allocate and free analysis info   sagar at multicorewareinc.com
• [x265] [PATCH 3 of 4] dump intra analysis information   sagar at multicorewareinc.com
• [x265] [PATCH 4 of 4] cli: add cli options analysis-out and analysis-in   sagar at multicorewareinc.com
• [x265] [PATCH] api: use generic names for analysis api   sagar at multicorewareinc.com
• [x265] [PATCH 1 of 4] add analysis data structures and param options   sagar at multicorewareinc.com
• [x265] [PATCH 2 of 4] api: introduce x265_alloc_analysis_data and x265_free_analysis_data methods to allocate and free analysis info   sagar at multicorewareinc.com
• [x265] [PATCH 3 of 4] store intra analysis information in buffers   sagar at multicorewareinc.com
• [x265] [PATCH 4 of 4] cli: add cli options analysis-out and analysis-in   sagar at multicorewareinc.com
• [x265] [PATCH 1 of 4] add analysis data structures and param options   sagar at multicorewareinc.com
• [x265] [PATCH 2 of 4] api: introduce x265_alloc_analysis_data and x265_free_analysis_data methods to allocate and free analysis buffers   sagar at multicorewareinc.com
• [x265] [PATCH 3 of 4] store analysis information in buffers   sagar at multicorewareinc.com
• [x265] [PATCH 4 of 4] cli: add cli options analysis-mode and analysis-file   sagar at multicorewareinc.com
• [x265] [PATCH] add fanout validation module to check param compatibility   sagar at multicorewareinc.com
• [x265] [PATCH] add fanout validation module to check param compatibility   sagar at multicorewareinc.com
• [x265] [PATCH] add fanout validation module to check param compatibility   sagar at multicorewareinc.com
• [x265] [PATCH] blockcopy_pp: 64x16, 64x32, 64x48, 64x64 AVX version of asm code, approx double speedup comapre to SSE   sagar at multicorewareinc.com
• [x265] [PATCH] add avx version for chroma_copy_ss 16x4, 16x8, 16x12, 16x16, 16x24, 16x32, 16x64 based on csp, approx 1.5x-2x speedup over SSE   sagar at multicorewareinc.com
• [x265] [PATCH] add avx version for chroma_copy_ss 16x4, 16x8, 16x12, 16x16, 16x24, 16x32, 16x64 based on csp, approx 1.5x-2x speedup over SSE   sagar at multicorewareinc.com
• [x265] [PATCH] blockcopy_ss: 64x16, 64x32, 64x48, 64x64 AVX version of asm code, approx double speedup comapre to SSE   sagar at multicorewareinc.com
• [x265] [PATCH RFC] analysis: add CU specific details to encodeCU()   santhoshini at multicorewareinc.com
• [x265] [PATCH] analysis: add CU specific details to encodeCU()   santhoshini at multicorewareinc.com
• [x265] [PATCH] analysis: add CU specific details to encodeCU()   santhoshini at multicorewareinc.com
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   santhoshini at multicorewareinc.com
• [x265] [PATCH] remove getNumPartInCU() and replace it with constant value   santhoshini at multicorewareinc.com
• [x265] [PATCH] remove getNumPartInCU() and replace it with macro   santhoshini at multicorewareinc.com
• [x265] [PATCH] remove getNumPartInCU() and replace it with macro   santhoshini at multicorewareinc.com
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   santhoshini at multicorewareinc.com
• [x265] [PATCH] TComDataCU: replace getTotalNumPart() with CU structure details   santhoshini at multicorewareinc.com
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   santhoshini at multicorewareinc.com
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   santhoshini at multicorewareinc.com
• [x265] [PATCH] remove getNumPartInCU() and replace it with macro   santhoshini at multicorewareinc.com
• [x265] [PATCH] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   santhoshini at multicorewareinc.com
• [x265] [PATCH] TComDataCU: replace getTotalNumPart() with CU structure details   santhoshini at multicorewareinc.com
• [x265] [PATCH 0 of 2 ] TComDataCU: replace with more CU structure details   santhoshini at multicorewareinc.com
• [x265] [PATCH 1 of 2] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   santhoshini at multicorewareinc.com
• [x265] [PATCH 2 of 2] TComDataCU: replace getTotalNumPart() with CU structure details   santhoshini at multicorewareinc.com
• [x265] [PATCH 0 of 2 ] TComDataCU: replace with more CU structure details   santhoshini at multicorewareinc.com
• [x265] [PATCH 1 of 2] TComDataCU: replace getZorderIdxInCU() with encodeIdx of CU structure   santhoshini at multicorewareinc.com
• [x265] [PATCH 2 of 2] TComDataCU: replace getTotalNumPart() with CU structure details   santhoshini at multicorewareinc.com
• [x265] [PATCH] asm: avx2 assembly code for dct16   yuvaraj at multicorewareinc.com
• [x265] [PATCH] asm: avx2 assembly code for dct16   yuvaraj at multicorewareinc.com
• [x265] [PATCH] asm: avx2 assembly code for dct16   yuvaraj at multicorewareinc.com
• [x265] [PATCH] asm: avx2 assembly code for dct16   yuvaraj at multicorewareinc.com
• [x265] [PATCH] asm: avx2 code for dct8x8   yuvaraj at multicorewareinc.com
• [x265] [PATCH] asm: avx2 code for dct8x8   yuvaraj at multicorewareinc.com
• [x265] [PATCH] asm: avx2 assembly code for idct8x8   yuvaraj at multicorewareinc.com
• [x265] [PATCH]Add iteration-skip to subpel refine   shevaxu

Last message date: Tue Sep 30 17:59:13 CEST 2014
Archived on: Thu Dec 11 23:20:13 CET 2014

• Messages sorted by: [ thread ] [ subject ] [ date ]
• More info on this list...