From owner-freebsd-hackers Mon Mar 22 9:13:20 1999 Delivered-To: freebsd-hackers@freebsd.org Received: from etinc.com (et-gw.etinc.com [207.252.1.2]) by hub.freebsd.org (Postfix) with ESMTP id DA4FA14BED for ; Mon, 22 Mar 1999 09:13:14 -0800 (PST) (envelope-from dennis@etinc.com) Received: from dbsys (dbsys.etinc.com [207.252.1.18]) by etinc.com (8.8.8/8.6.9) with SMTP id MAA20551; Mon, 22 Mar 1999 12:11:59 -0500 (EST) Message-Id: <199903221711.MAA20551@etinc.com> X-Sender: dennis@etinc.com X-Mailer: QUALCOMM Windows Eudora Pro Version 4.0 Date: Mon, 22 Mar 1999 12:07:02 -0500 To: Mike Smith From: Dennis Subject: Re: Gigabit ethernet -- what am I doing wrong? Cc: Amancio Hasty , hackers@freebsd.org In-Reply-To: <199903220200.SAA02330@dingo.cdrom.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG At 06:00 PM 3/21/99 -0800, Mike Smith wrote: >> At 12:13 PM 3/21/99 -0800, you wrote: >> > >> >Hmm.... >> >Does anyone know when the faster PCI busses (64bits or 66MHz PCI clock rate) >> >are going to be availabe ? >> >> The "availability" of 66Mhz busses is almost moot. Making ASICs work at 33mhz >> is a chore....66mhz is a waze off. > >That's close, but several of the major ASIC vendors were (or were >claiming to be) sampling devices with 66MHz PCI macrocells the last time >I looked. Any names? the vendors will be few, I think, for awhile. >> And as far a 64 bit busses.....there >> arent many >> processors that can do is, and doubling the bandwidth on a 32bit processor >> isnt >> always linear in performance. You have to get a whole new generation of >> processors before you will see any usable products. > >This has nothing whatever to do with reality, however. Most PCI >peripherals are bus masters, and most memory busses these days are at >least 64 bits wide, so 64 bit PCI has very real performance benefits. > >The processor's internal word size has little or nothing to do with the >equation. The ability to do single-cycle transfers IS affected by the internal processor's word size. If it can't do sustained single-cycle bursts then performance suffers significantly, so I disagree wholeheartedly on this. If the on-board processor doesnt have a 64bit bus it is very difficult to do single cycle transfers. Dennis To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message