US 12,192,486 B2
Video encoding parallelization with time-interleaving cache access
Cheng-Yen Chuang, Hsinchu (TW); Chun-Chia Chen, Hsinchu (TW); Chih-Wei Hsu, Hsinchu (TW); Tzu-Der Chuang, Hsinchu (TW); Ching-Yeh Chen, Hsinchu (TW); and Yu-Wen Huang, Hsinchu (TW)
Assigned to MediaTek Inc., (TW)
Filed by MediaTek Inc., Hsinchu (TW)
Filed on Nov. 1, 2022, as Appl. No. 17/978,530.
Claims priority of provisional application 63/290,073, filed on Dec. 16, 2021.
Prior Publication US 2023/0199199 A1, Jun. 22, 2023
Int. Cl. H04N 19/176 (2014.01); H04N 19/119 (2014.01)
CPC H04N 19/176 (2014.11) [H04N 19/119 (2014.11)] 18 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, by a plurality of processing elements (PEs) each configured to perform coding efficiency evaluation for a respective coding tool, video data comprising a coding block (CB) divided into a plurality of sub-blocks, wherein:
the plurality of PEs comprises a first number of PEs, and
the receiving of the video data by the plurality of PEs comprises each of the plurality of PEs receiving the plurality of sub-blocks of the CB in batches, each batch comprising a second number of the plurality of sub-blocks, and the second number being equal to the first number;
storing, by each of the plurality of PEs, the second number of the plurality of sub-blocks in a respective buffer accessible to the respective PE;
calculating, by each of the plurality of PEs performing the coding efficiency evaluation, a respective figure of merit (FOM) specific to the respective coding tool and the video data;
determining a coding tool specific to the video data by comparing the FOMs calculated by the plurality of PEs; and
encoding the video data using the determined coding tool.