| To: | Jeff Garzik <jgarzik@xxxxxxxxx> |
|---|---|
| Subject: | Re: 3c59x |
| From: | Andi Kleen <ak@xxxxxxx> |
| Date: | Tue, 10 Jun 2003 19:18:16 +0200 |
| Cc: | "David S. Miller" <davem@xxxxxxxxxx>, ak@xxxxxxx, bogdan.costescu@xxxxxxxxxxxxxxxxxxxxx, hadi@xxxxxxxxxxxxxxxx, ralph+d@xxxxxxxxx, xerox@xxxxxxxxxx, sim@xxxxxxxxxxxxx, fw@xxxxxxxxxxxxx, netdev@xxxxxxxxxxx, linux-net@xxxxxxxxxxxxxxx |
| In-reply-to: | <20030610171617.GC1959@gtf.org> |
| References: | <Pine.LNX.4.44.0306101801070.26879-100000@kenzo.iwr.uni-heidelberg.de> <20030610162029.GA8168@wotan.suse.de> <20030610162342.GB1959@gtf.org> <20030610.100209.70199702.davem@redhat.com> <20030610171617.GC1959@gtf.org> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Tue, Jun 10, 2003 at 01:16:17PM -0400, Jeff Garzik wrote: > On Tue, Jun 10, 2003 at 10:02:09AM -0700, David S. Miller wrote: > > From: Jeff Garzik <jgarzik@xxxxxxxxx> > > Date: Tue, 10 Jun 2003 12:23:42 -0400 > > > > I prefer a compile-time test. > > > > This means end users don't see the benefit, so I definitely > > prefer Andi's idea. > > Making every IO a conditional branch? Ug. An IO takes hundreds or even thousands of cycles. The test and branch is completely lost in the noise. I bet you won't be able to measure a difference on any modern CPU. -Andi |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||