|
For Full-Text PDF, please login, if you are a member of IEICE,
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
|
A Sub 100 mW H.264 MP@L4.1 Integer-Pel Motion Estimation Processor Core for MBAFF Encoding with Reconfigurable Ring-Connected Systolic Array and Segmentation-Free, Rectangle-Access Search-Window Buffer
Yuichiro MURACHI Junichi MIYAKOSHI Masaki HAMAMOTO Takahiro IINUMA Tomokazu ISHIHARA Fang YIN Jangchung LEE Hiroshi KAWAGUCHI Masahiko YOSHIMOTO
Publication
IEICE TRANSACTIONS on Electronics
Vol.E91-C
No.4
pp.465-478 Publication Date: 2008/04/01 Online ISSN: 1745-1353
DOI: 10.1093/ietele/e91-c.4.465 Print ISSN: 0916-8516 Type of Manuscript: Special Section PAPER (Special Section on Advanced Technologies in Digital LSIs and Memories) Category: Keyword: low power, motion estimation, H.264, systolic array, MBAFF, SRAM,
Full Text: PDF>>
Summary:
We describe a sub 100-mW H.264 MP@L4.1 integer-pel motion estimation processor core for low power video encoder. It supports macro block adaptive frame field (MBAFF) encoding and bi-directional prediction for a resolution of 1920 1080 pixels at 30 fps. The proposed processor features a novel hierarchical algorithm, reconfigurable ring-connected systolic array architecture and segmentation-free, rectangle-access search window buffer. The hierarchical algorithm consists of a fine search and a coarse search. A complementary recursive cross search is newly introduced in the coarse search. The fine search is adaptively carried out, based on an image analysis result obtained by the coarse search. The proposed systolic array architecture minimizes the amount of transferred data, and lowers computation cycles for the coarse and fine searches. In addition, we propose a novel search window buffer SRAM that has instantaneous accessibility to a rectangular area with arbitrary location. The processor core has been designed with a 90 nm CMOS design rule. Core size is 2.5 2.5 mm2. One core supports one-reference-frame and dissipates 48 mW at 1 V. Two core configuration consumes 96 mW for two-reference-frame search.
|
|