summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2015-06-26mips msa vp9 block error optimizationParag Salasakar
average improvement ~3x-4x Change-Id: If0fdcc34b17437a7e3e7fb4caaf1067bc175f291
2015-06-23mips msa vp9 avg optimizationParag Salasakar
average improvement ~2x-3x Change-Id: I76f7fc00c0ffdf2b4ba41bf3819f3b6044bcdeff
2015-06-23Merge "mips msa vp9 fdct 4x4 optimization"Parag Salasakar
2015-06-22Fixes for key frame coding at speed 5.Marco
Keep the same transform cutoff and partition selection for speed 5 as in speeds >=6 (non-rd speed settings). Existing setting for key frame at speed 5 allowed transform size up to 32x32 on key frames, and did not allow for 4x4 block partition size. This created more visual artifacts on first few frames. avgPSNR/overallPSNR/SSIM gains of 0.2/0.7/0.8 for rtc_derf(low-res) set, and 0/0.7/1.1 gains for rtc set. Change-Id: I8c139ec6c9bb74e14b4ffbad5f12e94f18a59c0b
2015-06-22Merge "vp9_reconintra_neon: add d45 8x8"James Zern
2015-06-22Merge "Reduce max_partition_size for low resolutions at speed 5."Marco
2015-06-22mips msa vp9 fdct 4x4 optimizationParag Salasakar
average improvement ~2x-3x Change-Id: Idf8be780b8b4228fc91f110a94e4ee1fd9af0163
2015-06-20Add assembly tests for int projections.Frank Galligan
BUG=https://code.google.com/p/webm/issues/detail?id=1022 Change-Id: I5ae4acac39fd75c56d3feff0716cb52133de3b22
2015-06-20Merge "mips msa vp9 fdct 8x8 optimization"Parag Salasakar
2015-06-19vp9_reconintra_neon: add d45 8x8James Zern
based on ssse3 implementation ~91% faster over 20M pixels Change-Id: I6d743a53352c2d6de0efe7899d7996e8b0f7fa29
2015-06-20mips msa vp9 fdct 8x8 optimizationParag Salasakar
average improvement ~4x-5x Change-Id: I37582efc2622bc20b2bf99617a76110ab24e9f6a
2015-06-20Merge "Add dynamic range comment to vp9_int_pro_row"James Zern
2015-06-19Add dynamic range comment to vp9_int_pro_rowJingning Han
Change-Id: Icaa643568159c4e2db24eef42090b002ae02a45e
2015-06-20Merge "Add dynamic range comment to vp9_int_pro_col"Jingning Han
2015-06-19Reduce max_partition_size for low resolutions at speed 5.Marco
For speed 5 real-time mode, the selection of the partition size for superblocks on the segment (aq-mode=3) uses the non-rd recursive pick partition search, and can sometimes select 64x64. For low resolutions, visually better to limit this to 32x32. Change-Id: I69657a7ed8899f8b3cf8c9c318a2509c5c72c565
2015-06-19Limit cyclic refresh revisitng blocks at the same quantizer.Alex Converse
For screen content don't refresh a block at a quantizer higher than it was last coded at. PReviosuly at realtime speeds the encoder had a tendency to recode a block from GOLDEN with a higher Q than it was last coded at. Change-Id: Iacd561806c769dcce1a81b9827ffc70090f5ba18
2015-06-19Merge "Fix a msvc compiler warning"Yaowu Xu
2015-06-19Add dynamic range comment to vp9_int_pro_colJingning Han
Change-Id: If14d9f874bd0bf2c5a455982088fd70591f5ea5a
2015-06-19Merge "Move vp8 variance files"Johann Koenig
2015-06-19Fix a msvc compiler warningYaowu Xu
Change-Id: Ida8a04370895ed14bd118324ec2577da926e4648
2015-06-19Merge "vp9_filter: make all filter tables static"James Zern
2015-06-19Merge changes I2552d810,I51952c0a,Ib82e4247,I9c8d16cbJames Zern
* changes: vp9_mcomp: make search_step_table static vp9_encodeframe: delete auto_partition_range() vp9_mcomp: don't mark setup_center_error() inline vp9_encoder: hide adjust_image_stat()
2015-06-19Merge "vp9_reconintra_neon: add d45 4x4"James Zern
2015-06-19Merge changes from topic 'vp9-intra-pred'James Zern
* changes: vp9_reconintra_neon: add d135 4x4 vp9_reconintra: correct d135 4x4 signature
2015-06-19Merge "Add dynamic resize logic for 1 pass CBR."Marco
2015-06-18Add dynamic resize logic for 1 pass CBR.Marco
Decision to scale down/up is based on buffer state and average QP over previous time window. Limit the total amount of down-scaling to be at most one scale down for now. Reset certain quantities after resize (buffer level, cyclic refresh, rate correction factor). Feature is enable via the setting rc_resize_allowed = 1. Change-Id: I9b1a53024e1e1e953fb8a1e1f75d21d160280dc7
2015-06-18Move vp8 variance filesJohann
There is a naming conflict in the chromium build system. The rest of the variance functions will move to vpx_dsp soon. Change-Id: Iff78da2aafb0d7380eda73e38d7dac72110a1e47
2015-06-18vp9_reconintra_neon: add d45 4x4James Zern
based on webp's LD4() ~59% faster over 20M pixels Change-Id: I371eaed9ce8f470451046997e130b0ba1a2f7a9c
2015-06-18vp9_reconintra_neon: add d135 4x4James Zern
based on webp's RD4() ~50% faster over 20M pixels Change-Id: Ifcb7bf7f7fc8eabf79d9e3b219ce1be67abc524a
2015-06-18vp9_reconintra: correct d135 4x4 signatureJames Zern
add missing '_c' suffix Change-Id: I928d6cf8f90db0b8ca0b1f3bbf10b3d792062cec
2015-06-18Merge "vp9_reconintra_neon: add DC 4x4 predictors"James Zern
2015-06-18vp9_reconintra_neon: add DC 4x4 predictorsJames Zern
~85-89% faster over 20M pixels Change-Id: I3812e8adfffe5255034da88dfe6546e12f4d10ee
2015-06-18Merge "vp9_reconintra_neon: add DC 32x32 predictors"James Zern
2015-06-18Merge "Add dynamic range comment to vp9_satd"Jingning Han
2015-06-18Add dynamic range comment to vp9_satdJingning Han
Change-Id: I75873846e6fdafbe7597a1bd0192115d2d1e9987
2015-06-18Merge "mips msa vp9 fdct 32x32 optimization"Parag Salasakar
2015-06-17Take out assertion for block_yrd in rtc coding flowJingning Han
The internal behavior of block_yrd differs in high bit depth settings from 8-bit one. This causes the assertion condition not true for high bit depth. Change-Id: I15dc02e7162d27cabe78c451941d769d488b1174
2015-06-17Merge "Fix integer overflow issue in rtc coding flow intra mode search"James Zern
2015-06-16Fix integer overflow issue in rtc coding flow intra mode searchJingning Han
The overflow issue affects a variable that is only used in inter mode. This commit fixes the ioc warning triggered in the intra mode. It does not affect the compression performance. Change-Id: I593d1b5650599de07f3e68176dd1442c6cb7bdbc
2015-06-17mips msa vp9 fdct 32x32 optimizationParag Salasakar
average improvement ~4x-6x Change-Id: Ibcac3ef8ed5e207cf8c121e696570e6b63d3c0f4
2015-06-17Merge "mips msa vp9 fdct 16x16 optimization"Parag Salasakar
2015-06-16Merge "Moved has_rows, has_cols in vp9_decodeframe.c"Scott LaVarnway
2015-06-16Moved has_rows, has_cols in vp9_decodeframe.cScott LaVarnway
from read_partition() to decode_partition(). Change-Id: I6bee2a0e9ff315290a690c9d773c9648dd2a200d
2015-06-16Remove duplicate calls for set_frame_size in 1 pass mode.Marco
set_frame_size() is being called twice, once before entering encode_encode_frame_to_data_rate(), and once again in that function. No need to call it twice for one-pass mode. Change-Id: I5fabaf0a90482d4f42cd89ef7ae1402c31aec600
2015-06-16Merge "Eliminated frame_type check in get_partition_probs()"Scott LaVarnway
2015-06-16Eliminated frame_type check in get_partition_probs()Scott LaVarnway
Moved the frame_type check to the tile level and stored the prob ptr in MACROBLOCKD. Change-Id: I10b5a4abd58213dc7610e3ade1a1583c01526842
2015-06-16Merge "Update use_prev_frame_mvs flag in decoder."Scott LaVarnway
2015-06-16mips msa vp9 fdct 16x16 optimizationParag Salasakar
average improvement ~4x-6x Change-Id: Id3b2243e5b3c7844c90c4231a5e75fa69911362c
2015-06-15vp9_reconintra_neon: add DC 32x32 predictorsJames Zern
~84-85% faster over 20M pixels Change-Id: Ia67a7f4a342bf7b0a9280e05c25d81a774d90469
2015-06-15Merge "vp9_ethread: create enough threads while using SVC"Yunqing Wang
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-13 15:17:59 +0000