On Wednesday 20 January 2010 15:54:34 Zeus Gómez Marmolejo wrote: > Another thing I would like to add. The performance of the FML bridge could > be slightly improved. Think about this situation: while it is doing a > REFILL (due to a previous wishbone read or write transaction) and a read > operation comes meanwhile, it has to wait till all the refill operation > has completed in order to check the cache hit and return data. But if the > read is already a hit, there's no need to wait and the data can be > returned immediately.
Yes and there is a load of similar tricks all over the system that could improve performance further. Lack of time prevents me from coding most of them; and "if it's not broken, don't fix it". For this one, another problem is that a dual-port RAM is required, and I am already planning to use the second port to implement cache coherency for the VGA output framebuffer - maintaining coherency with software is too much of a mess. Thank you for the test bench. I will review it, perform more tests on HPDMC and most probably merge it along with your patch. Sébastien _______________________________________________ http://lists.milkymist.org/listinfo.cgi/devel-milkymist.org IRC: #milkym...@freenode Webchat: www.milkymist.org/irc.html Wiki: www.milkymist.org/wiki
