For a related example, on many processors it's possible to do a TCP
checksum + memcpy combined in the same time as just a memcpy, because
the checksum arithmetic simply consumes cycles that otherwise would be
memory stall cycles. (And someone the other day mentioned
decompression at 0.5 times memcpy speed -- that sounds plausible for
the same sort of reasons.)
paul
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu