Everything Else

SGI Fuel getting props - "Impressed by a 10 year old computer" - Page 2

Oh, of course not. The Holy Kernel is blameless and pure. *genuflect* *genuflect* *genuflect*

It's just another fine example of everybody using one single solution everywhere ever and then being terribly shocked when someone finds a hole in it and then has the keys to the kingdom everywhere in the world.
Computers: Amiga 1200, DEC VAXStation 4000/60, DEC MicroPDP-11/73
Synthesizers: Roland JX-10/Jupiter-6/D-50/MT-32/SC-55k, Ensoniq SQ-80/Mirage, Yamaha DX7/V-50/FB-01, Korg DW-8000/03-RW/MS-20 Mini, E-mu Proteus MPS/Proteus/2, Rhodes Chroma Polaris

"'Legacy code' often differs from its suggested alternative by actually working and scaling." - Bjarne Stroustrup
Don't impugn the memory of Lunix: http://hld.c64.org/poldi/lunix/lunix.html
smit happens.

:Fuel: bigred , 900MHz R16K, 4GB RAM, V12 DCD, 6.5.30
:Indy: indy , 150MHz R4400SC, 256MB RAM, XL24, 6.5.10
:Indigo2IMP: purplehaze , 175MHz R10000, Solid IMPACT
probably posted from Image bruce , Quad 2.5GHz PowerPC 970MP, 16GB RAM, Mac OS X 10.4.11
plus IBM POWER6 p520 * Apple Network Server 500 * HP C8000 * BeBox * Solbourne S3000 * Commodore 128 * many more...
commodorejohn wrote: genuflect


ge GNU flect :D
I wish I could enter into the vegetable garden of William Gibson , on the right of a director, to decide how a film is ultimately released for public viewing, but I am not a nor Cyberpunk writer neither a dude in Hollywood , and my * flawless English * still looks like an old rusty trailer which needs a fix-up, so my personal wonderland begins with a pill ... tumbling down the rabbit hole , where the sky above the router port is the color of television, tuned to a dead channel and some gears still need a debugger there.
ClassicHasClass wrote: Don't impugn the memory of Lunix: http://hld.c64.org/poldi/lunix/lunix.html

Hah, I was wondering if someone was going to make that connection. Mea culpa, I just wanted a funny name for That One OS...
Computers: Amiga 1200, DEC VAXStation 4000/60, DEC MicroPDP-11/73
Synthesizers: Roland JX-10/Jupiter-6/D-50/MT-32/SC-55k, Ensoniq SQ-80/Mirage, Yamaha DX7/V-50/FB-01, Korg DW-8000/03-RW/MS-20 Mini, E-mu Proteus MPS/Proteus/2, Rhodes Chroma Polaris

"'Legacy code' often differs from its suggested alternative by actually working and scaling." - Bjarne Stroustrup
Oh, boy.

You may be thinking “600MHz CPU?” - but that CPU is totally badass because it is actually a MIPS CPU with a 5 stage core pipeline. Compared to a 20+ stage pipeline in Intel CPUs, it is roughly comparable to a 2.4GHz Intel CPU with just the pipeline alone.


Well, jeez. All these embedded cores with three-stage pipelines must be absolutely amazing, then. Also, the last sentence is meaningless; I guarantee that a modern Intel core, even at clock speeds well below 2.4GHz, utterly spanks a 600MHz R16k. Pipeline length is not some sort of magical proxy for clock-normalized performance. There isn't one. That's even dumber than when people try to say all cores of equal sustained-issue width have the same clock-normalized perf...

Short pipelines are great and wonderful until you have to hit a less conservative clock. We saw the limits of clock-conservative brainiac designs with IPF, too.

Add in the fact that the MIPS CPU architecture doesn’t have any baggage in it’s high-performance pipeline, and the end result is that it performs far faster than that!


You mean baggage like SPR's for multiply-divide, delay slots, and a fixed-length encoding whose merits were already debatable by 1995?

Let me just say this: this SGI fuel runs Blender much FASTER than my new Alienware laptop with it’s Intel Core i7 CPU!


Amazing, then, that an 8-processor 600MHz R16k system gets schooled by a single-processor, multiple-generations-old, intel quad core in Blender tests, by reputable members of this community - http://www.sgidepot.co.uk/perfcomp_RENDER1_blender.html . I call complete bullshit.
Oh, christ. That thread again.

The machines are 10 years old. Compare them to other machines of the same age, and there's a chance you're not talking bullshit. Claiming that a Fuel - any Fuel - can outperform even the shittiest low-budget Intel cpu for sale at the moment at whatever task, is reaaaaaaally stretching it a few lightyears beyond breaking point.

I love my SGIs. They are slow. I don't care.

Lose the psychedelic drugs, move on. :roll:
while (!asleep()) sheep++;
Alver wrote: Oh, christ. That thread again.

The machines are 10 years old. Compare them to other machines of the same age, and there's a chance you're not talking bullshit. Claiming that a Fuel - any Fuel - can outperform even the shittiest low-budget Intel cpu for sale at the moment at whatever task, is reaaaaaaally stretching it a few lightyears beyond breaking point.

I love my SGIs. They are slow. I don't care.

Lose the psychedelic drugs, move on. :roll:




"...only to have Captain John himself, come down the gang plank, a scowl on his face as he tersely replied, "She'll make point five past lightspeed.
She may not look like much, but she's got it where it counts, kid. I've
added some special modifications myself. But we're a little rushed, so
if you'll just get onboard, we'll get outta here."
:O2: O2 - (Mantadoc) - R5K - 200MHZ - 128MB RAM - 6.5.30
:Octane: Octane - (Montrealais) - R12K - 2*360MHZ - 1024MB RAM - EMXI. - 6.5.30
Alphaserver DS10 - (Vandoc) - EV6 - 466MHZ - 256MB RAM
Sun Ultra 5 - (Quedoc) - UltraSparc II - 400MHZ - 512MB RAM
ASUS K55VD - (Mapleglen)- I5 - Dual Core 2.5GHZ - 8 GB RAM
Dell L502X - (Algorail) - I7 - Quad Core 2GHZ - 6 GB RAM
Alver wrote: Claiming that a Fuel - any Fuel - can outperform even the shittiest low-budget Intel cpu for sale at the moment at whatever task, is reaaaaaaally stretching it a few lightyears beyond breaking point.

Even a teal Indigo2 will run 4Dwm faster than any Intel machine ever built :)

Let's not forget, it's the software that does the work !!

Who gives a rat's ass about the cpu ?
At the time AMD and Apple/PPC were also railing against the giga-hurts gods - apple had their "megahertz myth" ads and AMD puffed up their model numbers a bit - suddenly a 1.2 ghz chip was called an athlon 1800, etc.

Of course, this is the timeframe of the netburst architecture, even the pentium 3 outperformed it, clock-for-clock. So it is entirely possible for a high end (900mhz) fuel to outrun a 2ghz netburst p4 for some tasks.

There is a lot of writing by Darek Mihocka which is ideal for a hobbyist level (you and I are probably not going to be reading architecture white papers) in this series that explains the shortcomings of the netburst arch in terms a quasi-layperson like you and I can understand (we are not all kira :D ) http://emulators.com/docs/nx01_intro.htm

Long story short, netburst was an evolutionary dead end, intel went back to the p3, pM, core series instead.
Google: Don't Be Evil. Apple: Don't Be Greedy. Microsoft: Don't Be Stupid.
guardian452 wrote: Long story short, netburst was an evolutionary dead end ...

I keep a P-IV around just so the O350 can kick its ass* :)

*When the O350 runs, anyhow.