Compaq: Alpha is Better Than IA-64

Compaq released a document (it's in PDF format) that states that their Alpha is better then IA-64 (Intel next generation Itanium Processor). The document compares Alpha (and future generations of Alpha) against the IA-64 (I hate this "Itanium" name - where do they get these names anyway?). Certainly worth a read. What do you think, folks?

Comments

Alpha = speed, cost

[blakestah]

The alpha processors are not changing their niche in the computer market. They are ripping fast - and Dec first and now Compaq plays to the supercomputing crowd. The XP series motherboards and 21264 chips simply rip any other motherboard/chipset out there.

However, they cost too much for anyone except a supercomputing hound. If Compaq would drop Dec's insanely idiotic OS and component licensing scheme and aid linux on alphas, they might stand a chance of making a LOT of money selling hardware. As is, people buy ten times more alphas one chip generation late and run linux instead of OSF.

Anyone interested should see the linux alpha compilers available. cc is a small improvement, and ForTran is a LARGE improvement.

http://www.unix.digital.com/linux/software.htm

But still, Itanium will come out, and an Itanium box will offer slightly less than half the floating point speed, and it will cost about 1/4th of the fast alpha box from Compaq. And the alpha motherboards will still make it tough to support third party peripherals. And Itanium will dominate the 64 bit market. And Alpha will own the supercomputing market.

Re:Alpha = speed, cost

[Jeff Mahoney]

``Insanely idiotic OS''??

Maybe you'd have a leg to stand on if Linux supported the enterprise features that Digital UNIX does.

Unfortunately, it doesn't.

Example: High performance, dynamically resizable, journalling filesystem.

Does Linux have it? No. I'm familiar with the efforts that exist to address this, I work with one of the authors of a major project for this. He'll admit that ext3/reiserfs doesn't touch ADVFS.

Example: Advanced high availability clustering solution with a shared filesystem among nodes, cluster aliasing, and context-dependant symlinks for a SINGLE disk image shared amoung up to 8 cluster nodes.

Does Linux have it? No. Be aware that Beowulf is NOT an HA solution - it's a distributed computing cluster.

Perhaps you should do some more research before blindly bashing an OS that has features that Linux has yet to dream of.

As a side note, the Alpha isn't only used for supercomputing. I'm part of a group that runs 3 clusters of AlphaServers for everything from mail, web, and database serving. Only recently did DEC/Compaq enter into the supercomputer arena with the ``SC'' series of Alphaserver.

Your typical DS/ES/GS series AlphaServer may not be meant for your average joe-blow computer enthusiast, but 14 processors does not constitute a supercomputer. The new ``SC'' series AlphaServer that DEC recently released is a 64-512 Alpha CPU model. THAT is a supercomputer.

I've been using Linux since 1995, and Digital UNIX since 1996, so I've got a pretty good feeling on the comparisons between them.

-Jeff

Moderate this down as flame bait if you like - but I have a feeling that most readers have never used Digital UNIX/Tru64, and don't have enough knowledge of it to form a good opinion.

Re:Alpha = speed, cost

[Dahan]

A couple months back, Compaq had a deal where you could get a DS10 (466MHz 21264) for $3K. Certainly not as fast as the XP-1000, but not a bad price. Looks like the price is up to $3800 now...

Previous generation PC164 motherboards were (maybe still are) selling for around $250, including a 500MHz 21164A. Just add an ATX power supply, case, 4 or 8 72 pin parity SIMMs, a hard drive and you have yourself a computer :) (I guess video and network would be nice... it's got ISA and PCI slots). I got myself one of those in May:

• PS and case: $60
• 4 32MB SIMMs: $260
• 2 gig Quantum Atlas I (fast wide): had it lying around
• Symbios 53c875 UW SCSI card: $65
• generic Trident PCI SVGA card: $15
• D-Link DFE-530TX 10/100 ethernet: $15

I've got mine running NetBSD... works great :) Recently got another 4 32MB SIMMs (they were like $45 a piece) for a total of 256MB. It's slower than the latest x86 stuff out there, but not that much slower... and don't forget, this motherboard came out in like 1996 or so.

From deep within Intel Corporation

[cje]

How do they come up with these processor names, you ask? An astute question, one that requires some of Intel and AMD's most closely-kept company secrets. A friend of mine who used to work for Intel managed to smuggle the following Perl script out, shortly before he was fired. Here it is:

#!/bin/perl

# Copyright (C) 1997 Intel Corporation
# This is a proprietary Intel perl script.

@prefix = ( "Pent", "It", "Max", "Ath", "Cort", "Trit" );
@suffix = ( "ium", "alon", "ex", "anium", "oricon", "agon",
"on", "eres", "obos", "ymede", "itan", "erion" );
@tag = ( "II", "III", "IV", "Pro", "MMX", "Deluxe" );

srand;
printf( "%s%s %s\n", $prefix[rand 6], $suffix[rand 12], $tag[rand 6] );

So if we run this script, we can see where the names come from:

sg1 237% ./pnames.pl
Cortium II
sg1 238% ./pnames.pl
Pentalon IV
sg1 239% ./pnames.pl
Penteres III
sg1 240% ./pnames.pl
Athalon Pro
sg1 241% ./pnames.pl
Pentitan II
sg1 242% ./pnames-pl
Maxymede MMX

Please show discretion when you refer this script to others. It is, after all, an Intel proprietary secret and should therefore only be shared with others on a "need-to-know" basis.