On Wednesday 18 May 2005 00:47, David Woodhouse <dwmw2@xxxxxxxxxxxxx> wrote: > On Mon, 2005-05-16 at 14:09 -1000, Warren Togami wrote: > > > Even a 2 clock cycle delay happening hundreds of thousands or even > > > millions of times a second builds up. > > > > Isn't using system memory much longer than 2 clock cycles? > > If accessing the top of your stack is "using system memory" you're > screwed already. It ought to be in L1 cache. I presume that the top of the stack will eventually be written back to main memory. Aren't memory writes more of a performance hit than reads, especially on SMP? -- http://www.coker.com.au/selinux/ My NSA Security Enhanced Linux packages http://www.coker.com.au/bonnie++/ Bonnie++ hard drive benchmark http://www.coker.com.au/postal/ Postal SMTP/POP benchmark http://www.coker.com.au/~russell/ My home page -- fedora-devel-list mailing list fedora-devel-list@xxxxxxxxxx http://www.redhat.com/mailman/listinfo/fedora-devel-list