Subject: Re: But why?
To: Miguel de Icaza <firstname.lastname@example.org>
From: Jason Thorpe <email@example.com>
Date: 10/24/1996 09:19:52
On Thu, 24 Oct 1996 10:45:50 -0500
Miguel de Icaza <firstname.lastname@example.org> wrote:
> Dave actually goes and measures the speed of his code before commiting
> it to the tree. He does not go and replaces a C routine with an
> assembly routine that actually performs slower (sound familiar? the
> NetBSD checksum code had this very problem, I think Theo already
> pointed this out to you guys).
Sound familar? Uhh, not really...
The only converstaion I recall about in_cksum() was about a `faster'
i386 version. After an analysis of the test results, the conclusion
was reached that the tests were faulty, and in fact the `faster' version
was actually slower than the one in the tree... Thus, the `faster'
version was not committed to the tree.
We recently got a new in_cksum() for the sparc which is a fair bit faster
than the old one.
Jason R. Thorpe email@example.com
NASA Ames Research Center Home: 408.866.1912
NAS: M/S 258-6 Work: 415.604.0935
Moffett Field, CA 94035 Pager: 415.428.6939