This is part of The Pile, a partial archive of some open source mailing lists and newsgroups.
Subject: Re: Alphaserver1000 - can't get past ABOOT or MILO to boot Debian 2.1 From: J C Lawrence <claw@varesearch.com> Date: Thu, 16 Sep 1999 18:20:17 -0700 On Thu, 16 Sep 1999 16:05:53 -0700 simonst <simonst@WellsFargo.COM> wrote: > Any DEC Alpha Debian experts at BALUG? I must be doing something > wrong! A lesson from someone who has been there: While it is painful, bite the bullet and install the ARC console firmware instead of SRM. Things get a lot simpler and a heck of a lot easier to make work. You can (or could) get the firmware images on the DEC FTP site. === Subject: alpha install images From: "Eric H. Majzoub" <ehm@howdy.wustl.edu> Date: Thu, 6 Jan 2000 12:26:25 -0600 (CST) I have a LX164 alpha. I mirrored RH6.1 to a local hd and tried to install from it. When that failed I also tried to install via ftp. Both installations fail at the same place, when the package list is being read. Anybody else having problems with alpha installs? === Subject: Re: Best Hardware for Linux System? From: Nick Moffitt <nick@zork.net> Date: Wed, 15 Dec 1999 13:02:14 -0800 Quoting Markus Gutschke: > > Pardon me if I'm a little incredulous. FPU has been _Intel's_ > > strength, for a long time. That's what that company is so sore at > > AMD over the Athlon -- it's hitting them where they live. > > I always heard a somewhat different story, although I cannot find > the relevant numbers to verify which story is true. The basic point is that *double precision* floating point is amazingly fast on an Alpha. You can't just say "floating point" without specifying a degree of precision. Intel's FPU is still really slow when working with 64-bit floating point numbers. === Subject: Re: Best Hardware for Linux =?iso-8859-1?q?System=3F?= From: Markus Gutschke <markus@gutschke.com> Date: Wed, 15 Dec 1999 13:52:43 -800 > The basic point is that *double precision* floating point is > amazingly fast on an Alpha. You can't just say "floating point" > without specifying a degree of precision. Intel's FPU is still really > slow when working with 64-bit floating point numbers. So how does performance compare for single and for extended precision? I remember back in the days when the original Pentium came out, everybody was really excited about extended precision floating point arithmetic. What are the real-world applications? ===