Re: 2.1.6 vs. 2.0.23

Linus Torvalds (torvalds@cs.helsinki.fi)
Wed, 30 Oct 1996 02:09:51 +0200 (EET)

On 29 Oct 1996, Alexander Sanda wrote:
>
> NOTE: I'am running 2.0.23 with Robert L. Krawitz's fast-pentium-memcpy
> patch, so the results for 2.0.23 may be a little bit better than
> expected.

Interesting. The only place the fpu-copy seems to show up in is the file
re-read tests:

> *Local* Communication bandwidths in megabytes/second
> ----------------------------------------------------
> Host OS Pipe TCP File Mmap Bcopy Bcopy Mem Mem
> reread reread (libc) (hand) read write
> --------- ------------- ---- ---- ------ ------ ------ ------ ---- -----
> darkstar Linux 2.1.6 43 16.7 41.5 66.5 43 40 73 83
> darkstar. Linux 2.0.23 35 15.1 46.0 64.8 43 40 73 83

Here it definitely looks like the effects of the pentium memcpy() code: the
file re-read speed of your 2.0.23 is better than on 2.1.6, and is actually
better than the libc bcopy.

I'd have expected the same thing in the pipe throughput too, but it seems the
overhead for context switching the FPU state might impact the pipe throughput
negatively (wild hand-waving here ;)

Linus