Slashdot Mirror
The Dual 1GHz Pentium III Myth
Sander Sassen writes: "HardwareCentral has the latest on the dual 1GHz Pentium III controversy. Here's a blurb: 'The 1 GHz Intel Pentium III seems to be the subject of much controversy, as many claims have been made about its inability to run in a dual CPU configuration. HardwareCentral has been following the discussion closely and decided to put an end to all the rumors and get a couple of GigaHertz Pentium IIIs and a dual CPU motherboard and find out what exactly is the truth of the matter.'"
Everyone knows the pentium architecture has support for multiple processors. How many people know, however, that they are limited to only TWO processors? Its the truth.
Athlons, on the other hand, can support up to 8 (well, if the motherboard guys ever figure out that configuration...) What else is good about multiple Athlons? Their bus. If you've got a 133MHz bus with 2 pentium 3s, each chip gets 67.5MHz of bus speed. Hook 8 Athlons up to a yet-to-be-built motherboard with a 400MHz bus based on the DEC EV6 architecture and you get 400MHz for EVERY CPU simultaneously.
E.
All this information is backed up on numerous sites, www.tomshardware.com, Ars Technica, etc
Even worse than the fact that there's only a 133MHz bus under there is that, thanks to the Intel bus architecure, its *SHARED* bewteen the 2 processors. The Athlon EV6 bus technology, on the other hand, will give out 400MHz to each of 8 chips (pentiums are limited to 2) simultaneously... if only the motherboard makers would get to building one...
E.
Just imagine what you could do with a (working) pair of 1GHz PentiumIIIs
Fry a steak? Heck, I don't have enough to keep my little Athlon/550 busy. It spits back kernels to me in 4+ minutes. Hardly enough time to fix a sandwich. Besides, you know the 1G P3's will start at least $1500. I've got a list of better things to have for $3k.
Any bets on whether we'll see 1G P3's or Dual-Athlon systems out first?
Nah. If he knew this he would be doing it. I've never had much patience with the "Everybody else must know better so I just won't say anything" approach, and when I have that much to say about something it's generally because I know it. Have you written software to time-and-space antialias video footage to cut down video noise? I have. The concept is proven. What failed me was 'REALbasic', the testbed: it wouldn't handle large quicktime files at all. I can see I will have to put up demos: oh well, Y-A-thing to do. John didn't get to be "JOHN CARMACK" and inspire all this rabid loyalty by not ever learning anything from people. He's about 27 million times the coder I am, that's plain. I am simply saying that he absolutely hasn't yet clued in to what 'motion blur' needs to be as a persistent effect, and this is simply because the technology is making things possible that _nobody_ did before in gaming. I suspect that if he even reads this thread again at all, he'll be curious enough to try the idea, will observe that (sure enough) there's no obvious effect, and will begin tuning in on the details to see if there is any subtle effect like I'm describing. Q3's models and graphics are more than detailed enough to take advantage of such an effect. The result should be a greater sense of fluidity and intention in the motions onscreen, and it could even enhance the ability to read motion cues and 'intention movements' off the screen, enhancing rather than distracting from gameplay.
OK, working off totally anecdotal evidence, with no numbers to back me up (at least I admit it...)
The largest speed increase I ever had was from a 486/33 to a PPro200. That huge jump aside, what I find works the best is, all other things being not-sucky (ie, not 16MB RAM, not 100mhz, etc), a switch from IDE to SCSI brings huge speed increases. My dual P3-500 box without its SCSI sucks it to my P200 for general use with SCSI (of course, now I run the SCSI on the dual P3).
That being said, lots of memory is helpful, and of course, processors do speed things up. But after, oh, about 600mhz and 256MB RAM, the bottleneck in the modern PC (remember, this whole thing is about PCs, not your incredibly powerful SGI rendering box) is the HDD.
Windows 2000: Designed for the Internet. The Internet: Designed for UNIX.
I can't quite figure out what this has to do with Divx though. Oh well.
Uhhh, you spelled sufficiently wrong in your sig? :P
Or is this a limey spelling.
Just tryin to help, I like that quote as well.
kabloie
There are plenty of applications for which faster processors are needed. High end 3-d rendering, CAD, engineering analysis, real time number crunching... there are plenty of applications for which fast processors on inexpensive systems are desirable. And yes, $1200 for a single processor can be considered relatively cheap to people that need that kind of processing power. The next step up would be either a large cluster of cheaper machines, or a large supercompuer. Both of which are very expensive, and not necessary for some of the applications listed above. The home user doesn't need it, you're right. But don't believe that just because YOU don't need it, no one else does.
-- Minds are like parachutes... they work best when open.
True, but you pay an even higher premium...
Octane with dual R12k, SSE graphics -- ~$35k
Estimated total system cost for dual 1ghz PIII ~$7000 - $10000
The octane will be faster, no doubt, but not three times as fast. The PIII system is a bargain.
And don't get me started with sun equipment... sun workstations are just PCs with different processors in 'em. UltraSparc just ain't that cool.
-- Minds are like parachutes... they work best when open.
Time flies like an arrow;
Time flies like an arrow;
Fruit flies like a bananna
Is a codec by that name, not the CC fiasco.
Time flies like an arrow;
Time flies like an arrow;
Fruit flies like a bananna
Almost every PC-related problem I see is RAM RAM RAM RAM RAM RAM RAM
No it's effing not! POV takes forever to render a frame? Ray-tracing is a lot of floating-point and not much I/O. More CPU power would speed it WAY up. Your Quake3 framerate sucks? If you have a modern 3D card, it's probably because the CPU can't feed vertices to the card fast enough. Want to watch a DVD? A faster CPU would make it smoother. (assuming you don't have hardware MPEG decode)
But if the machine had ADEQUATE RAM IT WOULDN'T HAVE TO FUCKING PAGE AT ALL!!! GET IT?
THERE ARE A LOT OF TASKS THAT REQUIRE FAST NUMBER-CRUNHING, AND THEY WOULD BE FASTER WITH A FASTER CPU, DON'T YOU FUCKING GET IT?
0 1 - just my two bits
Intel's got the x86 smp market sewn up right now, but it'll only be a matter of months until smp K7's are available. So THEY say anyways... a whole lotta potential there...
dude
your website owns, Jeff K!
(hi Lowtax!)
This sounds like a job for (Swhoooosh!)
BeOS man!
I don't care if it's 90,000 hectares. That lake was not my doing.
The pages are gone (Mon Apr 3 19:24:27 EDT 2000), when you pull them up (try 2/ instead of 1/ in the URL) they are blank. Looks like the story is missing from Slashdot now also (oops it's back on slashdot now). I wonder who got on their butt about this one (Intel maybe).
:-)
CONSPIRACY!
Neil Cherry - Linux Smart Homes For Dummies
thats why crusher.dm2 and the Q3 equivilent are most often benchmarked.
-- My Sig is a P228.
but the question remains: does Karnov benefit from fullscreen antialiasing?
-- My Sig is a P228.
Bah, people who need that kind of power don't fool themselves with toys are buying -real- workstations such as SGI/MIPS, RS/6000, SUN/sparc or Compaq/Alpha.
GHZ have no meaning.
300mhz MIPS/R12000 has better FPU performance than any existing Intel CPU at any clock speed so far.
> Examples of apps that are compute bound.
> 1) 3D, games, rendering,modling, you name it.
Usually video card bound
> 2) Any kind of realtime graphics.
What does this term mean? Did you make it up?
> 3) Photoshop type apps depending on wether you
> use filters more often or just edits to large
> files.
Cache size and speed dependent
> 4) Compiling.
Cache and I/O bound
> 5) Audio editing
> 6) Real-time video editing. (What, I have to
> wait 2 minutes to render the changes!)
Usually depend upon FPU which is largely ignored in commodity chips.
It's not that nothing is CPU bound. It's just very rarely the bottleneck.
It's just that the current Athlon has it's L2 cache off chip, which is why the access is slow. The interesting thing is that even so, the benchmarks are pretty evenly divided between the 1GHz Athlon and the 1GHz PIII. Needless to say AMSD are adding on-chip L2 to the Athlon, as well as to their "low end" Spitfire which is going to be an AWESOME CPU (even Dell appears to be giving up their "Intel only" position becuase the Spitfire will blow away Intel's Celeron so badly). With AMD having now won over ALL TEN of the top PC manufacturers, they're obviously doing something right!
Quoted from their "conclusion":
"We had not troubles operating the same setup at 1066MHz, although very unstable [...]"
If "very unstable" doesn't count as trouble, I don't know what does.
they arent that fast. I've got a 9000 class *server* and its slower than my dual 500 abit bp6. parisc stuff is sloow.
moron. even on my dual 500 with 768MB RAM the system still cant do everything i want it to. like seamless audio/video in the background, compiling on seperate windows, java stuff etc etc. more ram will only take you so far. then you need CPU horsepower.
- Did they use dual 866s overclocked or real dual 1000s?
- What exactly did they do to cool this beast? Most of the article was about modifying the slocket. No information about cooling other than it was a "powerful" solution.
Also, I've never even heard of Iwill, but they're mentioned numerous times in this article and twice right now on the hardwarecentral front page.
Anyway, if they really did use OC'd 866s, they didn't prove anything, and this article is worthless.
Hands in my pocket
I Have a Dual-500mhz machine, and i max out both cpu's all the time.
Ever considered buying more RAM? If you're maxing out a dual-500MHz machine, I would hope you've got at least 4 Gig of RAM on that baby. If you have less than 1 Gig, you're starving it, man.
I'm just mentioning this due to my observation that a lot of friends who maxed found problems like that went away when they upgraded from a measly 128Meg or 256Meg to some reasonable number like 512Meg.
Will in Seattle
My quad Pentium Pro does it in 2 1/2.
All you crazies and your new-fangled processor thingies....
You will never get 200+ fps in UT and Q3, no matter how fast the cpu is. And dual wouldn't help UT anyway, it isn't multi threaded. You would be fill rate limited, unless you found a way to get your GeForce in a resolution like 150x113 or so, which I doubt.
However, even if the EV6 bus can handle 400MHz, no Athlon runs them at the frequency. Go check out the specs on the Athlon, 200MHz bus.
It looks like they restored the site from backup...that is several days old. I write for HWC and if you look the main site is up. But even a review I did the other day is missing off the front page.
"they arent that fast. I've got a 9000 class *server* and its slower than my dual 500 abit bp6. parisc stuff is sloow."
Servers generally aren't designed with raw processing power in mind. Maximum I/O is the design goal and the processor is just one piece of the puzzle.
Case in point; where I work, we have an RS/6000 F30. It only has a lowly 166mhz POWERpc, but for database operations, it kicks the shit out of our IBM Netfinity PII400.
I have a feeling that that "slow" PARisc HP9000 would make your BP6 look silly for similar operations.
~Any apparent grammatical or typographic errors are caused by defects in your display device.
> For the most part apps are still computer bound, EXCEPT in server space. Thats why the Xeon is still chugging along at 550MHz. Examples of apps that are compute bound.
The techinical terms are CPU bound and I/O bound.
Nice summary, BTW.
Try 600-800MHZ. This was the i820 and RDRAM. They even said that the comparing systems were overclocked to 133, meaning that when run in their rated mode, they would go even slower, making the performance benifit even more pronounced.
The whole point of RDRAM was to allow deeply pipelined, concurrent memory accesses from PCI periferals, 4x AGP and 2 to 4 800+MHZ CPU's.
Each RDRAM module can independantly handle a memory access, and each RDRAM channel can independantly transfer data ( on a simple 16 bit bus ). You have tons of bandwidth, just tons of associated latency.
In a multi-CPU configuration, you're going to get memory contention and thus latency, no matter what you do, so the added latency of RDRAM is hidden in such configurations.
The problem comes about in single CPU and 2x AGP( or any minimally utilized periferal configuration ). Here the added latency seriously shines, and you potentially can get slower memory access than standard SDRAM.
In short, the memory was doing what it was designed to do.
-Michael
-Michael
Ah, that's what takes up all their time, so that they can't release any XFree86 4.0/DRI drivers, I'm sure! It's nice to figure these things out.
main(O){10<putchar(4^--O?77-(15&5128 >>4*O):10)&&main(2+O);}
Yes but thats' because they tried to pull out functionality that the chip already had.
They didn't add any functionality too the chip itself.
-T
Old truckers never die, they just get a new peterbilt
Motion blur is a hack. Anti-aliasing is too.
If (when) GPU's are capable of doing 1800x1200 at 150fps. I don't think anyone's going to care about this kind of visual trickery.
If I was at Nvidia, I would be laughing my head off at the crap hardware 3dfx puts out, but pitying for the consumers tricked into buying it.
I have a Dual P2-450 machine...unfortunately the motherboard has something wrong with it...so...its only a p2 450 machine...and i have had no problems with just a single p2 450. I don't get this need to power. There isn's nearly one program that most people use that would actually make getting a dual PIII Ghz machine worth it. i can see i high high end server but that wouldnt just have two..it would have aroung 4-8 processors. the cost would be astronomical and though its fun to drool about i dont see the point. One would be far better off buying quality componenets for a computer rather than massive amounts of processing power...unless you are in some mad dash with teh Seti@home project or something...HEY...thats a great idea!!!!!!!!!!!!!!!!!!!!!!!!!!!
i got 2 Celeron 366mHz cpu's (ppga) overclocked to 533mhz with NO EXTRA COOLING except fro the standard heatsink + fan, notithng special and it is ROCK SOLID . i ran seti@home for 4 days solid and not one hang, crash, winnt blue screen NOTHING. either you guys SUCK or u got fucked up cpu's btw, motherboard is an abit bp6 THEY ROCK!!! :)
I can buy a 1 Ghz Athlon.
When I'm singing a ballad and a pair of underwear lands on my head, I hate that. It really kills the mood.
-Tom Jones
... if AMD finally made SMP-capable Athlons.
I guess there are Alpha-based EV6 SMP boards available, aren't they?
There are lots of applications where CPU bus and memory bandwith are the bottlenecks. Why do you think some high-end servers provide 4-way interleave access to their SDRAM main memory?
and then finding the money....
MicroBerto hears three glaring letters off in the distance...
AMD
Mike Roberto (roberto@soul.apk.net) - AOL IM: MicroBerto
Berto
nah, it's not the smart people who need a fast machine for their work. it's the brain-dead managers who see the higher numbers and insist on getting that for their new server, or it's the users who don't realize that the mhz isn't the only number to look at and have too much money to burn at want to have "The Best" even if they don't need it...
yes, but that's not why Intel is in such a rush to get them out.. Intel would _much_ prefer making people pay more for their chips..
way too many people are just blinded by the one most prominate number, and know nothing about buss speed and cache and ram speed and so forth..
Good luck building a dual-1GHz PIII machine when you can't even buy ONE of the things. What's the hardware equivalent of "vaporware"?
It's rare that you're presented with a knob whose only two positions are Make History and Flee Your Glorious Destiny.
At least show a little taste when you try to piss off the MPAA!!!
Free music from Jack Merlot.
Furthermore, most dual CPU motherboards are used in workstation or server configurations, which would make meeting these temperature requirements an absolute necessity. Instability or system crashes are not an option in these configurations.
When is a system crash ever an option?Keep in mind that the 1Ghz PIII is not Intel's flagship, their PIII Zeons are, I'm sure for double price of a PIII at any clock speed they'll let you use SMP as far as the design specs allow.
Read my plan to save the Bengals
Sorry for the offtopic but that's a GREAT sig!
I can hear it now...
"...THEY'RE GEEKY, THEY'RE LINUS AND THE pain-in-Bill's-butt-PAIN." ta-da-da-DA, dunt.
Hmmmm, time for a new sig.
TangoChaz
"It's not enough to be on the right track -- you have to be moving faster than the train." -- Rod Davis, Editor of Seahorse Mag.
TangoChaz
--------------------
Wise men talk because they have something to say, fools because the
Well, the Athlon supports 8 processors. The Pentium supports 2. Its in the chip, not the motherboard where that is determined.
Not exactly. Case in point - Abit BP6, able to overcome many processor limitations that would otherwise inhibit dual processor functions, in this case celeron.
Regardless of the INTENT of the processor's manufacturer's limitations, any properly designed MB can overcome this with a good chipset and other elements of good design.
AFAIK, with the PII to Xeon socket adapters, it is possible to run more than 2 PII/PIII's in a multi-processor MD.
Can anyone confirm or refute this from athoritative testing or experience?
TangoChaz
"It's not enough to be on the right track -- you have to be moving faster than the train." -- Rod Davis, Editor of Seahorse Mag.
TangoChaz
--------------------
Wise men talk because they have something to say, fools because the
Seriously, thats some amazing speed.
What are you doing with your computer? I'm pretty sure that 350+IDE->700+IDE will make your kernel to compile faster, games running better and so on than 350+IDE->350+fast SCSI.
Of course with 700 Mhz CPU you need SCSI to boost your system even faster, though UDMA66 should work pretty well also.
_________________________
_________________________
Spelling and grammar mistakes left as an exercise for the reader.
High Mhz processors are not originally intended for the consumer market, they're aimed at the business market. I work at an engineering lab and whe we buy computers we buy the fastest box they have with al the RAM they can cram into it. It's people like US that demand 1Ghz CPU's. The people with ancient P-3 600 boxes from 6 months ago will likely all get 1Ghz boxes and the 600's will be tossed over to sales (with 512M of RAM, no less) as useless old technology.
"there is eloquence in screaming" - Patrick Jones
I run a pair of 466MHz Celerons on an Abit BP6 motherboard, totally saturating the CPUs with SETI-like stuff, full-time, over the past four months, running Redhat 6.1, and have never had a single crash, failure, or any other problem. Trust me, I keep these machines at 100% utilization.
This doesn't mean there isn't a problem, but I certainly having seen one.
>> Yes I've forgotten a few tihngs, but the market for more CPU power is clearly more important than the market for higher bandwidth
hmmm... 1000 mhz at 100 mhz bus...
CPU | DATA BUS | ACTION
1........1..........READ DATA FROM RAM
2...................PROCESS DATA (3 cycle)1/3
3...................PROCESS DATA (cont.) 2/3
4...................PROCESS DATA (cont.) 3/3 done
5--------------------ho hum waiting for data bus
6--------------------ho hum waiting for data bus
7--------------------ho hum waiting for data bus
8--------------------ho hum waiting for data bus
9--------------------ho hum waiting for data bus
10.......2..........WRITE DATA TO RAM
11..................READ DATA FROM RAM
12..................PROCESS DATA (3 cycle)
Oversimplified, not taking cache into account, but you get the point, Bus Speed Matters.
--AROS is an Open Source AmigaOS clone, and source compatible with AmigaOS! Try the x86 build at http://www.aros.org
Why make faster CPU's?? Do you like giving Micro$oft an excuse to east up _more_ of clock cycles. Fatter hardware=fatter software!!
The sooner they get the high-end chips out then the sooner the low-end chips drop in price. No-one can afford the 1Ghz chips, but the 500's are cheaper as a result.
That should have been "Nearly 40 replies"...
Information wants to be free -- but informants want to be paid.
by Anonymous Coward on Mon April 03, 15:35 PST (#35)
No, wait, there it is!
Information wants to be free -- but informants want to be paid.
____________
He who fights and runs away,
He who fights and runs away,
This would be *so* nice if it works - At the moment I run a pair of 500MHz celerons, and they pretty much fly under linux. Just imagine what you could do with a (working) pair of 1GHz PentiumIIIs... Throw in the 2.4.x kernel, and that'd be a match made in dual-heaven... :o)
ManicHawk - Just because you're manic doesn't mean the walls aren't bouncy
the higher end P3's beat the K7 at the same clock speed in most benchmarks.
Not according to the Athlon v. Pentium III tests that CNet ran:
http://www.gamecenter.com/Hard ware/Roundup/Athlonp3/
=================================
I pledge allegiance to the flag...
of the Corporate States of America...
AMD keeps beating down on Intel in the frequency race. Athlon outperforms the sorry p3 any day.
Moderate this down to (Score:-1,Troll)
Trollz rool.
I personally am tired of the i386 architecture all together. All we need is cheeper alpha systems.
"If I were to ask you a hypothetical question, what would you like it to be about?"
Interesting...I wonder if they'll send one of 'em to me? A dual GHz machine...who'da thunk it, even just a year ago? First post that actually has something to do with the topic!! HA! =) -Mynock
-Mynock
Why make faster CPU's? Well, let me see..
Photoshop 5.5, Lightwave 6.0, Lightscape, Java, MySQL, Sound Forge w/ Accoustic Mirror, Winamp, the Sims, Chessmaster.. I think you get the idea.
I will not dispute that hard drives, ram, bus speed, the phase of the moon, and other factors influence the overall system performance. I do welcome any and all updgrades and improvements in any of the myriad of factors that make my computer faster.
Faster CPU's give me faster renders, more and faster ram help there and help with compiling and other memory intensive tasks, faster and larger hard drives help when I do need to load that 4k by 4k image into photoshop or scrub through a 45 minute avi file.
The faster each and every component gets, the better the overall performance.
What I don't understand is Intel's and AMD's rush to put out a GHz. Who gives a rip! It isn't like any normal consumers can afford one of those chips anyways. They keep expanding further and further each quarter and when in reality people are still on chips from speeds around 450 to 550. If that! It doesn't make much sense, to go out and upgrade your processor every 3 months. Including at the horendous amount they ask for. Maybe Intel is just mad because someone else made a better chip. - BlackHelmetMan
"Join me on the nail side of the thumb!"
It sounds to me as you have never actually used
a machine with high bandwidth memory access and
a fast disk subsystem.
Compiling is generally not cpu bound as most
compilers preprocess a file to create about a
100000 line file that then gets compiled to a
large assembly file that then gets assembled in
to an object file. Try compiling on a machine
with a fast disk and memory bandwidth, you will
see that is where the speed comes from. not raw
cpu power.
Unable to connect to the database. Please email slashdotted already?
Ummm... PPC is obsolete now. In case you haven't noticed, Apple hasn't released a speed upgrade from the 450mhz G4 since they were released sometime around last October.
Friends don't let friends use multiple inheritance.
Two year? Get real, compared to Alpha and PPC its obsolete now!
Or not _wrong_, exactly, he's just got slightly incorrect expectations. 3dfx is NOT helping him understand these issues, because naturally they want him to produce demos that are way over-the-top, like effects sequences in The Matrix or something.
Think of it as _time_ antialiasing. You don't antialias by having some big shocking Gaussian Blur that goes out for 10 pixels: it's very local, and the effect is to make angled edges appear more clearly angled (less stair-stepped, and not fuzzed). I do have a page that gets into this w.r.t fonts: it's this page.
By the same token, if you can see visible blurring happening in action, the motion blur is _already_ too much. What 3dfx need is not to arrange for Quake to send 27 frames to make a smooth blurry contrail behind everything (no matter how nice that may look in screenshots)- what's needed is to buffer a _single_ frame and average it with the current frame at a variable blend ratio. 50/50 might even be overly strong though it would maximize the time-based antialiasing- 40/60 could be better. Screenshots might show a tiny video echo effect on the fastest moving objects, but the most significant effect at typically high frame rates would be the softening of edges only in the specific directions of movement. To demo this you'd want something like a guy dressed in black and white pinstripes- the desired effect would be that the guy wouldn't blur out, but you would have a much clearer subliminal sense of his exact movements- something it would take a gamer or multimedia geek to pick up on.
Running at sufficiently high framerates (say, over 80), the ideal density _would_ be 50/50, because as the speed is pushed, differences between frames become smaller. The end result would be strictly confined to the softening of just such edges that are moving the most, which would highlight exactly what types of motion are happening.
Serendipitously, this type of motion blur (being not a fancy cinematic 'blur' that you don't see ALL THE TIME anyhow, but time antialiasing) would be just as suited to the driver as the planned spatial antialiasing- and just as suitable for application to ALL extant games that can be played on a 3dfx card. Again, all that's needed is to buffer one frame and average it with the current frame. It's not supposed to be a lightsaber blur, and 3dfx is foolish to emphasize this concept.
Time-based antialiasing is just as effective as spatial antialiasing but people don't know what to look for, partly because nobody seems to be bothering to even try doing it properly! It'll be just the one frame buffered- or possibly two. For the purposes of 3dfx, clearly using a single extra buffer and setting a blend ratio is the way to go. For serious video, a better approach is this: think of the frames as one pixel _deep_ and treat the antialiasing as a sphere centering on each pixel. The most weight would be on the pixel being tested, the pixels that are directly left or right or up or down or earlier or later would have less of a weighting, and so on: a pixel that's one pixel up _and_ left _and_ a frame earlier would have the least weighting. I've had very good results experimenting with code that averages the frames directly before and after a frame, then doubles the size of the immediate frame and dithercopies it down to antialias it and averages it with the time shifted frames. The goal was to cut video noise, and this approach was very effective at doing so without causing lots of stupid blur. (anyone doing an open source video editing program might try this- I need to finish up my version if possible and gpl it ;) )
The long and the short of it is that 3dfx should offer this spatial antialiasing as an extra driver feature, and that Carmack shouldn't have to do anything to enable it- and the last thing you want is to dump lots of frames in for a nice pretty blur effect. As Carmack quite rightly says you can do that easily in the program anyhow and don't need special interaction with the card- the only thing he's not getting (and this is because 3dfx are pointedly not suggesting he try it) is that time based antialiasing really isn't his problem, and is an entirely undramatic effect, to be sensed rather than seen and marvelled at. And marvelling at effects might sell more 3D cards ;)
Again, the desired effects are practical rather than strictly visual in a 3D game. Racing and flying games would definitely be more exciting with such a driver feature, but in a 3D game it would be a matter of quickly sensing when a player you're chasing is turning or slowing- or whether you are dodging a flying projectile thoroughly enough. These things would be conveyed through the subtle softening of the lines perpendicular to motion- giving you more information than just the straight frames. (I really need to render up some demos of this...)
draw frame at 2X
dithercopy or otherwise antialias to a screen-size buffer
display blend of buffer and the last frame's saved buffer
copy current frame's buffer to last frame's buffer, repeat
This also uses less display RAM. However, it is inferior to this:
draw frame at 2X
make blend of buffer and the last frame's saved buffer, also at 2X
dithercopy or otherwise antialias the blend to a screen-size buffer
copy screen buffer to screen, repeat
The reason the second is so much better than the first (despite using a lot more RAM) is that subtle movements are a lot more likely to show up at the scaled-up level (this does assume that there is a buffer that gets drawn to and antialiased down, which I think is a safe assumption). Storing only the screen buffer means that for many pixels there would be no change from frame to frame- storing the larger 'aliased' buffer and averaging at that size makes it far more likely that there will be significant differences. These will be averaged, and then antialiased by either dithercopying to a smaller size, or some 3dfx approach that is effectively the same thing in practice (there are only so many ways to do this). The result would be the effect I describe, of a softening of lines perpendicular to movement, but it would take on a subtlety and delicacy quite comparable to film.
Which is of course what 3dfx really want...
The link is just as mythical as the Dual 1Ghz Pentium III.
I'm also tired of people such nonsense. The fact of the matter is that the CPU bus is not a bottleneck (it was proven in multitude of tests running 3d games on 66 and 100 MHz bus systems -- performance difference was less than 1%) and the memory bandwidth is not a bottleneck (it was proven in benchmarks comparing RDRAM to regualar PC100 SDRAM). However, for the 3d games, the CPU is the bottleneck at low resolutions. At higher resolutions (1024x768 and up), the video card becomes the bottleneck. (However, at any resolution the 3d card speed is much more important than the CPU speed). That is why a lowly Celeron equipped with GeForce DDR will kick a 1GHz machine with RDRAM and say a ATI card any time.
___
___
If you think big enough, you'll never have to do it.
JEEZ! Did you even READ the original post? Let me quote the relevant portion for you; try to engage your brain before responding.
I got news for you, in most non-server environments the proc is still the biggest bottle neck
Hmm..."non-server". Let's say it again together..."non-server." Now, let's read the relevant part of YOUR post:
The computer in question serves files...
Tell me again how your response was relevant to the original post.
Pardon me while I mock this thread.Since your feeble mind isn't going to catch the analogy, I think I'll just sit back and enjoy my self-imposed feelings of superiority.
(/FLAME)
Now, where did I put those hot dogs?
> even on my dual 500 with 768MB RAM the system still cant do everything i want it to. like seamless audio/video in the background, compiling on seperate windows, java stuff etc etc. more ram will only take you so far.
While multiple processes exacerbate your CPU load, they exacerbate your ability to feed the CPU with data more or less in proportion. Your problem may not be the amount of RAM, but you certainly have a problem with memory bandwith on any x86 ever made.
And the above analysis is before factoring in cache. Any one of the things you name is likely to put a heavy load on your cache, and when you try to do several at a time, you effectively run (several-1) of them without a cache. Or maybe all of them, if you get into a cache thrashing mode.
And it's those cache misses that make a CPU stall out for multiple cycles at a time.
--
Sheesh, evil *and* a jerk. -- Jade
I've been sysadmin in a grapics department that has several dual CPU machines. The dual processing capability doesn't give one the option to multitask when rendering. Of course, I perhaps might have been able to set it up so that it would, but for the most part, 3DSMax rendering ate both processors for lunch. Granted, they were nearly twice as fast as the nearest single processor machine in the office, but during rendering, both procs maxed at 100% utilization.
That said, the average joe MS user is far more interested in faster bandwidth. Most of that computer time is spent online (chat rooms, net games, pr0n, etc.) Joe doesn't care about 1Ghz, except perhaps as "my processor is faster than yours".
:)
So who has a budget for these things and actually wants them if not the technical incompetants? High end servers? Would rather have a fatter pipe. These processors are only useful for high end work stations. Maybe you care, but most of us don't use or need that.
Of course, I wish my processor was faster than yours...
-Ted
"just a little bit of rewiring needed. ;-) "
The rewiring is to make the motherboard support the chip. The chip supports SMP fine, no rewiring needed.
if you run the well-known BX chipset, and both cpu's are run to near saturation for longish periods of time (more than a few weeks, usually), the system WILL lock up.
I found this while stress testing my dual cpu BX boards (asus, tyan and abit). I ran 2 instances of seti@home on each cpu (yes, 4 processes on a dual system). ALL my BX systems hung eventually. even the ones with extra fans on the bx chip and heat compound under the sink.
my guess is that when the BX was released, intel felt it was "good enough" and that no one would totally saturate their CPUs. certainly NT wouldn't - and I bet linux 2.0 wouldn't either. not until linux 2.2 would both cpu's be used to this level.
so I can't believe intel anymore when they lie about their own products. dual 1ghz - gimme a break; they can't even make ONE ghz work under normal consumer conditions!
--
--
"It is now safe to switch off your computer."
Geek: I can download 5 billion pictures in 7 seconds.
Homer: But I want them now.
Discussion Never Hurt Anyone.
Libertarians
[WARNING: The contents of this post are slightly of topic, until you consider A) This is a subject regarding excessive CPU power that nonetheless consistently gets overrun and B) This site has been overrun and I can't comment on the actual contents of it.]
:-)
:-)
:-)
[WARNING 2: This is one of the more bitter posts I've made to Slashdot. You've been warned.]
And so it was so ordered, after legions upon legions of sites fell to That Which Was The Slashdot Horde:
If the content of the web page is not dependent on the identity of the user, then the content of the web page MUST not be generated specifically for that user.
Yes, that's an IETF must, damnit
This isn't a complicated concept, folks. If each user gets a very different page(think search engine), then you dynamically generate the new content live. If each user only gets a slightly different page...well, gee, dynamically generate that slight difference, but leave static everything else.
If you're dependent on the user, change the page for each user. If you're dependent on some local index of news, then change the page each time the local index of news changes. If you're dependent on an angel coming down and teaching you to code the goddamn meaning of life in Perl, *THEN CHANGE THE PAGE WHEN SOME GLOWING HALOED CREATURE WALTZES IN YOUR STUDIO*, but for *CRYING OUT LOUD* don't regenerate your page every time I try to read some godforsaken article!
It's simple stuff like this that make me feel like I have a moral obligation to be a Comp Sci major. Grrrr.
One other point...ya wanna talk overcommitment? The Linux kernel lists are going nuts about the reasonably rare situations that can arise when the OS allows processes to overcommit memory, on the probabalistic assumption that not all processes will actually use the memory they request. What to do when the memory actually commited actually becomes used? Should the OS die, so that the processes may live? What processes does the OS kill to keep itself alive? There's alot of argument about how to deal with overcommitment on the OS level, and I'll leave that fight to the experts.
But lemme tell ya, just view the Slashdot Victim of the Day to find web pages that deal with overcommitment. Since these sites aren't too likely to change their entire codebases all that soon, may I suggest that expressing Database Errors *might* not be the most graceful method of expressing degradation of resources?
In other words, faced with the choice of fewer ad impressions and less readers vs. temporarily switching to a cached copy of the page which is 99.9% accurate, might it not be nice to have built as a core element of Apache's modperl something along the lines of, "Run this script to generate this page UNLESS we're getting hammered; in that case, use mod_rewrite to change the URL to a static equivalent of our now thoroughly overloaded page"?
Ahhhh. I might actually be able to view pages about Gigahertz SMP
Yours Truly,
Dan Kaminsky
DoxPara Research
http://www.doxpara.com
P.S. Irony #1235235: It's taking me forever to finally get this comment posted
secondly, it has always been true that you need to properly spec your system based on what you plan to use it for. If it's going to be serving static webpages, you want lots of memory and a PCI architecture that can support multiple concurrent bus masters (to handle the high bandwidth). CPU speed is less important than cache size as well in this configuration.
If you're wanting to run Quake, you want a smaller amount of RAM but it needs to be low latency (say, 6ns) and have a high bandwidth (PC133). You'll want a fast processor and a faster video card. HDD is unimportant for quake, as is the bussing architecture (PCI, ISA - not the FSB).
But don't tell me there's a single metric for measuring system performance.. that's a lie, as much as saying that average access time for harddrives is "the" metric. I'd disagree, it's the track-to-track latency and aureal density that I happen to have used to spec my system. Not that it's "the" metric, but it's the two I used (as well as internal xfer rate, of course) which is directly proportional to the RPM the HDD is rated for!
To recap, the article has 6 pages on modifying the Iwill Slocket IIs (albiet with graphics).
I like the item mentioned in the conclusion better: "a new revision of the Slocket II is currently in the works that will support FCPGA SMP out of the box, making the configuration of a dual CPU system a matter of plugging the CPUs in the slockets, no soldering required."
> Granted that it is a royal pain in the butt
Yet still less trouble than actually rounding up two 1GHz processors.
--
Sheesh, evil *and* a jerk. -- Jade
DB Error: Unable to get author information!
:(
Cant read the article
-- iCEBaLM
Nearly 30 replies and nobody has made the obligatory Beowulf Cluster comment?
Information wants to be free -- but informants want to be paid.
They may or may not have been right, but in any case they certainly did not run a pair of factory 1GHz CPUs in an SMP configuration. I'll grant that the core is almost certainly the same; but even if they are correct in their contention that the stepping is the same for the two parts, it is a trivial matter for Intel to change the packaging to render the 1GHz version incapable of supporting SMP -- don't bond the SMP pin to the die, and they've done it!
The big question from my point of view is this: why would Intel say their flagship processor won't support SMP? This isn't like the case with the Celeron, where they clearly wanted people to buy the more-expensive processor instead of the cheapie... so why don't they want people to buy their most expensive product in pairs? The Celerons were too cheap, and the early FC-PGA Coppermines (the 500E and 550E) were just too overclockable; it makes sense that Intel would want to disable SMP for them, and so they played hide-the-SMP-pin. It also appears they've gone further with the CeleronII (AKA Coppermine128), and simply not bonded the SMP pin to the die -- again, a pricing issue... But why the 1GHz part? It's hard to buy Sassen's argument that it's just heat -- that applies to single-CPU systems as well as to duals.
So I don't think the controversy is over; it has just gotten more complicated, is all.
---
---
Politics is about making compromises. Religion isn't. --Michael Horton
Two 1-GHz processors on one motherboard seems like an incredible source of bus contention. How fast is the bus these CPUs are connected to? The CPUs are at 10 times the bus speed! (afaik)
Intel on the other hand has a shared front side bus, so all the CPUs can see each other's traffic and results in a substantially less complex chipset, with a lot fewer pins. Probably lower performance (depending on several factors), but certainly a cheeper solution for dual and 4-way SMP machines
- Mike
Molog
So Linus, what are we doing tonight?
So Linus, what are we going to do tonight?
The same thing we do every night Tux. Try to take over the world!
Do dual Athlons motherboard exits?, and at what cost?
I do not believe there is one out there yet, but here, near the bottom it says that tyan is making a board to be released Q4-2000 , Codename Dolphin, that is supposidly Dual-CPU capable.
I'm tired of all you people saying that faster procs are useless because of other bottlenecks. I got news for you, in most non-server environments the proc is still the biggest bottle neck. To tell the truth, I enjoyed much more the 50% boost from 200 to 300 MHz than I did the 50% boost from a 66 to a 100MHz bus. For the most part apps are still computer bound, EXCEPT in server space. Thats why the Xeon is still chugging along at 550MHz. Examples of apps that are compute bound.
1) 3D, games, rendering,modling, you name it.
2) Any kind of realtime graphics.
3) Photoshop type apps depending on wether you use filters more often or just edits to large files.
4) Compiling.
5) Audio editing
6) Real-time video editing. (What, I have to wait 2 minutes to render the changes!)
Things not compute bound
1) Serving webpages, files, etc.
2) Working with large photoshop files.
3) Some types of scientific computing where data crunching is high volume, low workload.
Yes I've forgotten a few tihngs, but the market for more CPU power is clearly more important than the market for higher bandwidth.
A deep unwavering belief is a sure sign you're missing something...