[Mp4-tech] [H.264] Performance issue on reference frames and reordering of reference frames

[WJ_Liu mtk.com.tw]

Dear experts,
The mechanism of multiple reference frames may degrade the performance of 
the cache in an embedded system. 
Also the re-ordering of the reference frames may have the same impact. 
Since a frame can contain many slices and each slice can have different 
reference list, this may seriously downgrade the overall performance.
It seems a trade-off between the encoder flexibility/capability and the 
system performance. 
Are there any information contained in the SPS/PPS/Slice header or in the 
spec that provide clues to improve the performance of the memory system?
Did the working group ever have any discussions about this?
By the way, the re-ordering mechanism can reduce the bits used to encode 
CAVLC of reference indexes, since most frequently referred frames can be 
associated with smaller indexes. Is this the main purpose for re-ordering? 
Or re-ordering can have other advantages?
Thanks in advance.
Jerry
************* Email Confidentiality Notice ********************
The information contained in this e-mail message (including any attachments) may be confidential, proprietary, privileged, or otherwise exempt from disclosure under applicable laws. It is intended to be conveyed only to the designated recipient(s).  Any use, dissemination, distribution, printing, retaining or copying of this e-mail (including its attachments) by unintended recipient(s) is strictly prohibited and may be unlawful. If you are not an intended recipient of this e-mail, or believe that you have received this e-mail in error, please notify the sender immediately (by replying to this e-mail), delete any and all copies of this e-mail (including any attachments) from your system, and do not disclose the content of this e-mail to any other person.   Thank you!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: /pipermail/mp4-tech/attachments/20060516/f96489b1/attachment-0001.html