[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: crc32() optimization



> 
> On Mon, 2002-11-11 at 10:26, Joakim Tjernlund wrote:
> > > Joakim.Tjernlund@xxxxxxx.se said:
> > > > Maybe, if it will help me get it into 2.4 faster. However I can not
> > > > test 2.5, so someone else needs to do that. Maybe a patch the lkm will
> > > > do it? 
> > > 
> > > I'm about to update JFFS2 in 2.5, I'll test and send it with that.
> > 
> > OK, I will try to generate a patch before the end of the day. I am at home
> > now with sick child, will go to work soon.
> 
> Im curious if its faster on a decent processor - what CPU did you do the
> benchmarking on ?

This is on a MPC860 running in 80/40 MHz configuration.

> Mostly I'm suprised it makes any difference because
> the compiler should sort out loops and the CRC is horrible to schedule
> and full of stalls anyway

ehh, how is the compiler supposed to sort out this loop?

Yes CRC is a pig, this is why I am trying to do something about it.
I think there is more to gain if you look at Algorithm 4 at  
http://www.cl.cam.ac.uk/Research/SRG/bluebook/21/crc/node6.html#SECTION00060000000000000000
since the current algorithm basically is Algorithm 3 in above link.

  Jocke 


To unsubscribe from this list: send the line "unsubscribe jffs-dev" in
the body of a message to majordomo@xxxxxxx.com