SGI's $250,000 Graphics Supercomputer from 1993 – Onyx RealityEngine² [video] • Hacker News Board

Re: SGI's $250,000 Graphics Supercomputer from 1993 – Onyx RealityEngine² [video]

#141

Post by kragen » Mon, Sep 03, 2018, 9:50 PM UTC

tachyonbeam wrote: post #138

nickpsecurity wrote: post #77

Earlier quoted context omitted.

That's a good point but underselling it. My favorite thing about them was doing a single, system image that removed bottlenecks and complexity for developer at the same time. The PC's were using slow or redundant buses to connect high-speed components. SGI removed redundancies, used fast interconnects (GB/s), made them low-latency (microseconds vs milliseconds), and NUMA-enabled them. The last part meant that sending…

I guess that's the difference between a workstation that's designed for performance and versatility before cost, and a PC, which is made to be affordable first. When the PC industry started, it was very much about repurposing whatever low-cost CPUs and off-the-shelf components were available, and finding ways of packaging this into a semi-usable machine for less than $1000. Things have changed quite a bit since, but…

Sure, the PCs that started the PC industry — things like the Apple I and the MITS Altair — were indeed "about repurposing whatever low-cost CPUs and off-the-shelf components were available, and finding ways of packaging this into a semi-usable machine for less than $1000." But, long before 1993, most CPUs and components used in PCs were being produced specifically for PCs, with uses in things like lab equipment, industrial control, and workstations a rather smaller secondary market.

Re: SGI's $250,000 Graphics Supercomputer from 1993 – Onyx RealityEngine² [video]

#142

Post by qubex » Tue, Sep 04, 2018, 2:14 PM UTC

wowtip wrote: post #137

liftbigweights wrote: post #72

We had these and a few SUN systems in our computer lab storage room. We called them the dinosaurs. It's amazing how things changed from 1993 to mid 2000s. From technology rock stars to useless junk in a little more than a decade. The "lab master" bribed us with pizza to help him clear the storage room. Quickly found out how heavy these things were and what a raw deal we got.

I heard somewhere SGI put a big chunk of iron/lead inside the case to make them heavier and add to the expensive impression when handling the machines. Not sure if that was the case, or if it is just an urban legend?

They used cast iron extensively.

Re: SGI's $250,000 Graphics Supercomputer from 1993 – Onyx RealityEngine² [video]

#143

Post by sigvirt » Tue, Sep 04, 2018, 6:58 PM UTC

harel wrote: post #32

Flashback scene begins. When I was much younger my dad (who has a print business) was tasked with printing panels for F16 jet fighter pilot cockpit to be used in a simulator of the aircraft. The simulator was developed by a private company. One Saturday he took me to their office. They had one of these and gave me a demo of it. Until then all I knew was of standard consumer computers (commodore, pc, macs etc) . In an…

Also around 1993, Onyx with RE II was used by Nameco and a company called Magic Edge to build actuated flight sim pods [1]. Coincidentally also in 1993, NASA published a guide [2] to their Vertical Motion Simulator [3]. At the time, the VMS used several SGI IRIS machines as auxiliary display processors, but custom machines for primary.

[1] http://www.system16.com/hardware.php?id=832 - Nameco Magic Edge Simulator Ha rdware at System-16, The Arcade Museum

[2] https://ntrs.nasa.gov/archive/nasa/casi.ntrs.nasa.gov/199400... - Vert ical Motion Simulator Familiarization Guide (pdf) (1993)

[3] https://www.aviationsystemsdivision.arc.nasa.gov/facilities/... - NASA Vertical Motion Simulator

One day, the din of the machinery paled and withered under a thunderous earth-shaking draconian roar - whiplashing my head out of the rack toward the windows - an F/A-18 tilted sideways at the edge of ground effect ripping a minimum radius turn back to from whence it came ... without ever leaving the airfield. Sigh. There is no simulator for That.

Re: SGI's $250,000 Graphics Supercomputer from 1993 – Onyx RealityEngine² [video]

#144

Post by sigvirt » Tue, Sep 04, 2018, 7:04 PM UTC

dis-sys wrote: post #37

I tried to search online to see whether DOOM has been ported to Onyx RE2, but couldn't find any video proof. That is really strange.

Near Y2K, as development slowed, several of the hands-on QA teams were found to be astonishingly good at Quake. Later, as labs high and low were decommissioned, a couple of sysadmins consolidated equipment and absolutely dominated the SETI at Home rankings for many months, and likely the PG&E [1] rankings as well.

[1] Pacific Gas and Electric, a California utility company

Re: SGI's $250,000 Graphics Supercomputer from 1993 – Onyx RealityEngine² [video]

#145

Post by sigvirt » Tue, Sep 04, 2018, 7:08 PM UTC

deerpig wrote: post #52

qaq wrote: post #3

Could be converted to a cool mini-fridge

SGI famously converted one of their Crimsons (which was a commercial failure) into a fridge and beer tap...

The Silicon Graphics crew did like their case mods. Adding to the list: a demo team had a deskside O2K with a top air-intake and side exhaust pipes like a dragster engine.

Re: SGI's $250,000 Graphics Supercomputer from 1993 – Onyx RealityEngine² [video]

#146

Post by brianpgordon » Wed, Sep 05, 2018, 1:44 AM UTC

AriaMinaei wrote: post #62

deerpig wrote: post #54

I have a slightly newer Infinite Reality R10000 sitting beside my desk here in Phnom Penh. A professor in Berkeley gave it to us and somehow we managed to get it to this side of the world. It uses enough power to run an apartment block and yes it is noisy. I will eventually gut it and install a six node linux cluster inside. I used these boxes in Hong Kong in the early 90's, then later in Japan in the late 90's for a…

I wonder if it's still possible to put together hardware that's a few years ahead of current high-end products. Like, can you arrange, say, ten flagship graphic cards for realtime rendering? Do we have game engines that can scale to that number?

Supposedly you could play video games on one of Nvidia's more recent data center products:

https://www.nvidia.com/en-us/data-center/hgx/

It shows up to the host computer as one really big GPU. Of course, you're going to get worse performance than just a single Titan V because it can handle any game already and there's inevitably going to be latency added by doing work over NVLink/NVSwitch. Those massive GPU products are targeted toward offline rendering or machine learning applications, not so much realtime simulation.