SGI NUMAflex Linux System On Display @ SC2002

jarrod.smith writes " According to SGI will unveil its Intel® Itanium® 2 NUMAflex shared-memory supercomputer architecture (which runs Linux as its OS) at Supercomputing 2002 which runs this week in Baltimore, MD. The link at SGI says the system will be on display at the show. The exhibit floor opens this evening. Unfortunately I did not go this year. Can those lucky enough to be at the meeting scope it out and post comments?"

Comments

2.5 has full support

[DarkMan]

Well, damn as nearly. Linux is only in catchup when the manufacturor will not release spec on how to use thier hardware.

When it comes to NUMA machines, Linux is up there. It may not excel at everything (yet - I'm sure that it will get there if it's not already). I'm mostly talking about the 2.5 kernel series.

From the status list

New scheduler for improved scalability (Ingo Molnar)
Support for Next Generation POSIX Threading (NGPT team)
Syscall interface for CPU task affinity (Robert Love)
Hotplug CPU support (Rusty Russell)
NUMA topology support (Matt Dobson)
Per-cpu hot & cold page lists (Andrew Morton, Martin Bligh)
NUMA aware scheduler extensions (Erich Focht, Michael Hohnbaum)

The biggest performance changes in 2.5 seem to be in the many thread and many CPU region, including NUMA.

I'd trust it. (Yes, I do do scientific supercomputing).

Re:Let's TRY to be objective...

[ChaosDiscord]

I think it's terrific that Linux is used this way but I wonder if it's because of its availability or because of its technology.

I'm involved with a number of high energy physics experiments around the world (from a "physicist needs an obscene amount of computer power but a minimal budget, I try to give it to them" standpoint). Everyone is using Linux clusters at the moment. Why? Two reasons.

The first is price. None of these projects are rolling in money. Saving a few thousand dollars while setting up a hundred node cluster is a big win. The people working on the projects are technically skilled enough that a Unix varient is not significantly harder to use than a Windows variant, so there is no increase in TCO due to support.

The second is trust. They've been repeatedly burned by proprietary software. They run into a problem and the publisher isn't inclined to help (or wants more money than they have to fix it), and they're forced to fine another solution. Linux may not be perfect, but they're free to fix their own problems. They don't view it from a "Free Software is Ethical" view, but from a pragmatic "we've been repeatedly screwed and it isn't happening again" view.