Yay for the generic transfer_one_message in Linux's spi layer: @ 50 MHz cpu clock, it spends 10% of SPI I/O time recording useless stats.
-
-
Replying to @RichFelker
Simply C&P'ing it to the J-core SPI driver and removing all the accounting & crap boosted transfer speeds by 10%.
1 reply 0 retweets 1 like -
Replying to @RichFelker
@RichFelker maybe having a tunable to turn it off might be a good compromise ?1 reply 0 retweets 1 like -
Replying to @loganaden_42
@loganaden_42 Yeah, that's actually a good idea and might be acceptable upstream.1 reply 0 retweets 0 likes
@loganaden_42 For our driver though I might need to implement the per-message (vs per-xfer) API anyway when we get to adding DMA support.
10:45 PM - 23 Apr 2016
0 replies
0 retweets
0 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.