Skip to main content
11 events
when toggle format what by license comment
Nov 22, 2019 at 14:54 comment added Petr Skocik @TobySpeight Yeah, multithreading might speed it up. Also looking scanning two bytes at a time via a 2^16 look up tables provided a pretty good speed up last time I played with it.
Mar 2, 2016 at 17:59 history edited Faheem Mitha CC BY-SA 3.0
deleted 1 character in body
Mar 2, 2016 at 17:34 comment added Barmar The read() version may benefit from read-ahead.
Mar 2, 2016 at 12:52 comment added Toby Speight There may be some benefit to reading different parts of the file in separate threads (e.g. with an OpenMP for loop) so that some progress might be made while one thread is stalled waiting for input. But on the other hand, it might hamper I/O scheduling, so all I can recommend is to try it, and measure!
Mar 2, 2016 at 5:08 history edited muru CC BY-SA 3.0
added 48 characters in body
Mar 2, 2016 at 1:12 comment added jthill mmap is going to get vastly better results on linux because it'll map to huge pages these days, and TLB misses are sloooowwwwwww.
Mar 2, 2016 at 0:27 comment added Petr Skocik I was surprised at the mmap result TBH. I used to think mmaping was faster than read/write, but then I saw some linux benchmarks that showed the opposite. Looks like it is very true in this case.
Mar 2, 2016 at 0:19 history edited Petr Skocik CC BY-SA 3.0
added 84 characters in body
Mar 2, 2016 at 0:11 history edited Petr Skocik CC BY-SA 3.0
added 880 characters in body
Mar 1, 2016 at 22:53 history edited Petr Skocik CC BY-SA 3.0
added 141 characters in body
Mar 1, 2016 at 22:46 history answered Petr Skocik CC BY-SA 3.0