Beta

Slashdot: News for Nerds

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

cancel ×

318 comments

Dupe! (4, Insightful)

Lostie (772712) | more than 9 years ago | (#11445651)

Posted only a couple of days ago too. [slashdot.org]
Timothy do you actually read Slashdot?

Re:Dupe! (0)

Anonymous Coward | more than 9 years ago | (#11445669)

No, nor did he or any editor check the "daddypants" dupe email. If you're going to offer the address for dupe reports, then... ya know, read them. Since daddypants@slashdot.org is abandoned, perhaps everyone should just write for fun?

Re:Dupe! (1)

Arngautr (745196) | more than 9 years ago | (#11445980)

Just send it in as a story, be creative, I think they read those sometimes.

Dupe!-Was it as good for you? (5, Insightful)

Anonymous Coward | more than 9 years ago | (#11445693)

"Timothy do you actually read Slashdot?"

Here's a better question. If he will not, why should we?

Re:Dupe! (0)

Anonymous Coward | more than 9 years ago | (#11445697)

This post is from IdiotOnTheRight.

Re:Dupe! (0)

Anonymous Coward | more than 9 years ago | (#11445836)

YAD (Yet Another Dupe). I suppose that nobody is actually piloting the machine?

Maybe they should multitask less, say stop smoking weed, playing xbox, and watching wwe while they're approving article submissions?

I don't really know what goes on, but it definitely seems that whoever is in charge around here is a couple parts clueless and a couple parts incompetent. Maybe they just pass it off as that they are lazy, don't give a shit, and its not really important. Regardless, one thing is certain: slashdot continues to dissappoint.

Re:Dupe! (1)

IO ERROR (128968) | more than 9 years ago | (#11445848)

/. editors actually reading the articles? You must be new here.

Re:Dupe! (5, Insightful)

Ohreally_factor (593551) | more than 9 years ago | (#11445857)

Timothy do you actually read Slashdot?

Wouldn't that be like eating from the toilet?

Re:Dupe! (1)

Jahf (21968) | more than 9 years ago | (#11445923)

/. is now using cell technology to deliver news.

Re:Dupe! (1)

JPriest (547211) | more than 9 years ago | (#11445935)

I spotted the dupe right away also. Maybe Timothy is busy picking up the slack for the company I work for while I read slashdot...?

A Look Into The Dupe Architecture (2, Funny)

Anonymous Coward | more than 9 years ago | (#11445652)

Re:A Look Into The Dupe Architecture (1)

bossesjoe (675859) | more than 9 years ago | (#11445786)

So is this... (in all good humor)

Dupe alert (0, Redundant)

YankeeInExile (577704) | more than 9 years ago | (#11445653)

Wow -- it's dupe night here at /. Previous Article [slashdot.org]

repost (0)

Anonymous Coward | more than 9 years ago | (#11445654)

repost

x86 (4, Insightful)

mboverload (657893) | more than 9 years ago | (#11445655)

Only if it complies with x86. Seriously, x86 will be around for a century.

Re:x86 (2, Insightful)

Short Circuit (52384) | more than 9 years ago | (#11445686)

I can see x86 disappearing only if console-style computers become much more popular than they are now. If, for example, HDTV set-top boxes supported email, Word, and spreadsheets, it'd happen pretty quickly.

Treacherous Computing (2, Insightful)

tepples (727027) | more than 9 years ago | (#11445970)

If, for example, HDTV set-top boxes supported email, Word, and spreadsheets, it'd happen pretty quickly.

I'm not buying a console-style computer until it supports GCC out of the box. I want the freedom to compile my own software for a given machine and distribute it without having to go through a console maker that refuses to even talk to individual developers and smaller firms.

Re:x86 (1)

goMac2500 (741295) | more than 9 years ago | (#11445689)

Except for games the next XBox, PS3, and Nintendo Revolution are on PowerPC (The cell is PPC). If the Mac gets cell, the article claims it could be a massive turnaround, as the cell benchmarks seem to be well and beyond anything Intel could offer in the near future.

Re:x86 (0)

Anonymous Coward | more than 9 years ago | (#11445825)

What benchmarks? And why couldn't Intel produce a similar chip?

Please fanboy, I'd love to hear your rationale behind those statements you made.

Re:x86 (0)

Anonymous Coward | more than 9 years ago | (#11445907)

I agree. There is absolutely no reason why intel couldnt add a few hundred extra vector units into their next chip.

Re:x86 (-1, Troll)

Anonymous Coward | more than 9 years ago | (#11445937)

Original poster and you appear to know exactly what Intel is doing in their research department and can guarantee that they have no line of research similar to the cell. Given that the ideas behind this has been incredibly well publicized, I doubt that.

You and your faggot mac boyfriend also didn't address what benchmarks exist for a chip that doesn't even exist yet AND how those benchmarks would handle desktop applications - NOT FUCKING PS3 GAMES YOU JACKHOLE. go commit suicide.

Re:x86 (0)

Anonymous Coward | more than 9 years ago | (#11445915)

Not when free/open source software takes over, then we can just recompile everything for the best architecture at minimal cost.

(This post will be +5 insightful)

sigh (0, Troll)

Foobar of Borg (690622) | more than 9 years ago | (#11445656)

Another overly broad patent issued...

Its a dupe (3, Insightful)

mnmn (145599) | more than 9 years ago | (#11445658)

The article was interesting, but we dont have to read it twice.

Maybe slashcode should have a link repository, if someone adds a new story with a link, they get a warning another story pointing to the same link was posted 18 hours ago...

We've even seen triple-dupes.

Re:Its a dupe (1)

1tsm3 (754925) | more than 9 years ago | (#11445749)

If it's 3 it a trupe not a dupe!

Re:Its a dupe (1)

cybergrue (696844) | more than 9 years ago | (#11445770)

Thats a very good idea. Obviously, something has to be modified in the script used to add stories to the system that compares the stories to previously submitted articles. A link comparison is probably ythe best way of doing this. Of course, somethines linkes can be duplicated, especially if used a s a follow-up to a previous article.

Re:Its a dupe (1)

statusbar (314703) | more than 9 years ago | (#11445883)

Unfortunately, this story, the grandparent post, your post, and probably this one as well are all dupes!

--jeff++

Re:Its a dupe (0)

Anonymous Coward | more than 9 years ago | (#11445795)

A triple-dupe, eh?

Well, let's see now.

Second time: "dupe" from the word "dual".
Third time: should be from the prefix "tri", so that'd make it... "tripe"?

And the first time it's posted, it can be called a "scoop."

So there we go. Scoop, dupe, tripe.

I wonder what the 4th time would be... Quadpoop?

Re:Its a dupe (1)

BorgHunter (685876) | more than 9 years ago | (#11445887)

Dupe comes from the word duplicate, not dual.

Re:Its a dupe (1)

tepples (727027) | more than 9 years ago | (#11445979)

And what does the du- in duplicate come from? Remember that there is a word triplicate.

Re:Its a dupe (2, Interesting)

Peyna (14792) | more than 9 years ago | (#11446005)

The words duplicate and triplicate actually vary little from their Latin roots; duplicatus and triplicatus; "to double" and "to triple." THe word "dupe" isn't officially recognized as a synonym for duplicate, so the argument is pretty much moot.

Re:Its a dupe (2, Funny)

Ray Radlein (711289) | more than 9 years ago | (#11445831)

We've even seen triple-dupes.
"Tripes," you mean? Yeah, we've seen a lot of tripe here at Slashdot, all right.

Re:Its a dupe (1)

Rares Marian (83629) | more than 9 years ago | (#11445846)

Those are called tripe.

Re:Its a dupe (0)

Anonymous Coward | more than 9 years ago | (#11445947)

Then this story is a "bipe"?

Pearoast (0)

Anonymous Coward | more than 9 years ago | (#11445659)

Errr.... pearoast....

Looks like we need to throw all computers out (2, Insightful)

lost_n_confused (655941) | more than 9 years ago | (#11445668)

Reading the article makes it seem like all computers will disappear. I find it so hard to believe that the new cell processors will be that advanced. I can believe they are good for specialized uses but not as a general computer.

Cell Processor to be used to find /. dups (0)

Anonymous Coward | more than 9 years ago | (#11445672)

By 3Q 2006 Cells will be used to sniff out dupes on /.

The current X86 technology can't keep up.

"Cell" architecture. (0)

Anonymous Coward | more than 9 years ago | (#11445673)

"A Look Into The Cell Architecture"

Hey I know all about the cell architecture. There's DNA, and RNA, and some mitochondria, and protoplasm, and...

Thats bull (-1, Redundant)

mboverload (657893) | more than 9 years ago | (#11445676)

Much fanfare was made over the PS2 haveing a cell processor. If it was so great, why are the graphics on a PS2 so crappy? Hook a PS2 up to any high-quaily screen and you see it all fall apart.

I highly doubt any of these claims.

Re:Thats bull (0)

Anonymous Coward | more than 9 years ago | (#11445700)

the cell processor is not in the PS2, its suppose to be in the PS3. Some IBM workstation that isnt released as of yet is suppose to be the first application of the cell processor.

probably just another XBox fanboy.... (0)

Anonymous Coward | more than 9 years ago | (#11445724)

you know those guys can't READ

Re:Thats bull (1)

bsharitt (580506) | more than 9 years ago | (#11445794)

That'd be the PS3 that'll use the cell, not PS2.

No, it's not bull. (1)

Space cowboy (13680) | more than 9 years ago | (#11445812)

The PS *3* will have (an expected 4, actually) cell processors inside. The PS2 has an embedded MIPS core and a couple of (pretty cool for the time) vector processors. The Cell is a much more advanced version of the PS2 ideas.

Simon.

Re:Thats bull (0)

Anonymous Coward | more than 9 years ago | (#11445838)

Your information package for the idiot club is on its way via mail.

Dupety doo (0, Redundant)

Burdell (228580) | more than 9 years ago | (#11445677)

And maybe with this article [slashdot.org] someone can decipher if the Cell technology will eventually make a /. dupe detector that works in real-time.

Firefox Killed Linux (-1, Offtopic)

Anonymous Coward | more than 9 years ago | (#11445679)

Yep, it sure is great that I now have Firefox... now I have *no* reason to switch to Linux!

Yay open sores!!

bleh (-1, Flamebait)

Anonymous Coward | more than 9 years ago | (#11445688)

I for one welcome our new dupe overloads. And our new beowuld cluster of dupe first post posters.

Thinking about it, I'm pretty lame for saying that, I should just skip it. But no!, I'm a slashdot drone, I have to do it...

Well, at least to save face, I'll post as an AC

Finally, a... (-1, Troll)

Anonymous Coward | more than 9 years ago | (#11445690)

Finally! A better processor!
Maybe this will shut the apple zealots up.

Who at /. checks for dups? (-1, Redundant)

Ghengis (73865) | more than 9 years ago | (#11445694)

You guys have got to be kidding me. The was posted YESTERDAY!!! [slashdot.org]

Obviously working at /. doesn't require.... (0)

Anonymous Coward | more than 9 years ago | (#11445710)

an education. My Cat's hairballs could do better!

Re:Obviously working at /. doesn't require.... (0)

Anonymous Coward | more than 9 years ago | (#11445719)

But michael already works here!

Re:Who at /. checks for dups? (1)

jsight (8987) | more than 9 years ago | (#11445792)

Funny thing is, this is actually better than it used to be.

I remember when it seemed like every other day they would post the same story twice SAME day.

slashdot editors thought this article... (-1, Redundant)

bani (467531) | more than 9 years ago | (#11445715)

...was so important, you should read it twice [slashdot.org] !

who wants to bet they'll post it a third time?

Re:slashdot editors thought this article... (0)

Anonymous Coward | more than 9 years ago | (#11445789)

This whole article was duped and yet you get modded down redundant? That's some harsh sh!t...

Cut the man some slack, jack.

P.S. I won't take that bet.

Re:slashdot editors thought this article... (1)

Ohreally_factor (593551) | more than 9 years ago | (#11445900)

who wants to bet they'll post it a third time?

As I've suggested on previous occasions, it'd be better to start up a pool as to when it's posted again, and who posts it. My guess is Cmdr Taco, next Tuesday.

Odds are pretty long that Timothy would post it again, but never say never. =)

This is what happens... (1, Redundant)

Whyte (65556) | more than 9 years ago | (#11445723)

...when you don't read your own news site. :/

As someone posted above, it seems like it would be fairly trivial to at least make a "dupe check" program that tells you whether you have linked to the same URL before...

Is this a dupe? (1)

thoolie (442789) | more than 9 years ago | (#11445867)

No really? Is it? :-)

Dataflow squared (5, Interesting)

Space cowboy (13680) | more than 9 years ago | (#11445725)


The original PS2 design was for a dataflow architecture - the Cell is a continuation (and significant evolution) of the theme. Interestingly enough, if this *does* take off it may be that the best programmers of tomorrow turn out to be the PS2 low-level guys, who've already written the algorithms that are about to be important.

In the PS2, the MIPS chip was there mainly to do the simple stuff, all the heavy lifting was done on the 2 vector processors, and they were designed to have programs uploaded into them and data streamed through them using a very flexible (chainable) DMA engine. Sounds similar (if in a limited sense) to the Cell chip itself.

Simon.

They reinvented The Amiga! (4, Interesting)

Rares Marian (83629) | more than 9 years ago | (#11445778)

A measly 68k CPU with hardware that was autonomous.

A measly MIPS with hardware that is autonomous.

The only thing they need is to sync to the TV set.

Re:Dataflow squared (1)

Mskpath3 (764785) | more than 9 years ago | (#11445849)

MIPS chip, check. Snazzy vector processors, check. Flexible DMA, check. Giant mega pain in the ass to write code for - you betcha!

If the Cell is like some kind of EE on steroids, you're gonna see a lot of PS2 programmers running for the hills.

Intellectual challenge is one thing, and cool hardware is another (and the PS2 hardware is most definitely cool) but having to jump through ridiculous loops to write code for already radically overscoped and overly complex modern games is pain incarnate.

Transmeta (4, Insightful)

jfonseca (203760) | more than 9 years ago | (#11445731)

The last time I read about a revolutionary chip that would forever change the world and the company was so great they even had the Linux creator as a board member it turned out to be not much more than a loud fart in the wind. (Enter Transmeta)

This is a distributed-processing-capable chip. They're moving software into the chip, doing what software can do in a more compact and probably more efficient way. There's nothing revolutionary here and besides being a dupe story it's way overrated. The only attractive here is the fact PS3 will use it instead of embedding something open, like Mosix.

And no it won't "eventually take over the PC market."

Re:Transmeta (3, Interesting)

kai.chan (795863) | more than 9 years ago | (#11445912)

There's nothing revolutionary here

There is a _lot_ of revolutionary ideas behind the Cell processor. As shown in the write-up, the Cell takes a drastic change from the conventional arithmetic-unit/cache setup. Additionally, the way the Cell can pipeline parallelizable problems amongst the 8 processing units within itself is a revolution of chip design already. Take, for example, the video encoding/decoding example shown in the write-up, whereas an an Intel chip will require processing of each procedure in sequence, the Cell can separate each procedure, pipeline the process, and produce results in a fraction of the time it takes an Intel chip. Since much of our processing power in home electronics goes into Video, Audio and 3D Visualization (all of which are highly parallelizable), being able to separate tasks onto separate processing units dramatically increases the speed of computation.

Add to the fact that you can also pipeline processes amongst Cells within one piece of electronic, or spread the problems to multitude of other home electronics, makes the design a much different type of processor than the everyday Intel and AMD. The way to "upgrade" the Cell is also revolutionary, as buying another piece of electronics will increase the processing power of your household.

Well.. (1)

kennycoder (788223) | more than 9 years ago | (#11445737)

Not everyone checks slashdot every day and not everyone checks yesterdays news, so i can see that authors thought this artice was soo important that they posted it two times.. makes sence to me >_

Oh shut up (0)

Anonymous Coward | more than 9 years ago | (#11445744)

By that logic, Slashdot should always have the same stories, because someone may have missed it otherwise. There's a link to yesterday's stories. Click it if you're interested.

We have a winner... (0)

Anonymous Coward | more than 9 years ago | (#11445767)

You officially have the worst sarcasm filter on the planet

Re:Well.. (1)

minator (744625) | more than 9 years ago | (#11445813)

>so i can see that authors thought this artice was soo
>important that they posted it two times..

The author did not post it to Slashdot either time.
He did however wonder WTF was happening to his web stats...

Re:Well.. (1)

Wyatt Earp (1029) | more than 9 years ago | (#11445818)

The problem isn't the authors, it's the Editors. When there is a month without a dupe, I'll buy a subscription to /.

Howver that's not going to happen because Editors don't take thier job seriously. Seriously, they never have. From Sengan's great editorializing about the 1998 attack on Iraq (Comments are disabled, as I expect a lot of people will believe the US/UK side of the story...) and disabling comments to Katz to dupe after dupe.

There are always critical sections (4, Interesting)

auzy (680819) | more than 9 years ago | (#11445739)

its very rare for a system to be able to be completely parallelised.

There will always be "critical sections", data which can only be used by 1 thread at a time, which limits how much it can be split up.. Then you have programs which cant be.. I mean, you can split up a game for instance into a sound, video, and keyboard threads easily. To really utilise parallel processing takes a massive amount of code, which with current languages, seems to make it a bit implausible to get a massive increase.

It should also be remembered that the G5's and G4's already have altivec, and even though this is on a much grander scale, there will always be bottlenecks that slow it down preventing 99% of commonly used apps from getting a significantly large increase..

Re:There are always critical sections (1)

1tsm3 (754925) | more than 9 years ago | (#11445783)

Or each processor could render a particular object! Processors don't look at parallelism as you do!

Re:There are always critical sections (1)

auzy (680819) | more than 9 years ago | (#11445902)

except that when you put reflections into the equation.. then it will matter.. regardless, video cards currently perform very fast matrix operations anyway. There was nothing stopping people doing a lot of these operations on the video cards now, just many programmers were too lazy

Consider a different approach (4, Informative)

Space cowboy (13680) | more than 9 years ago | (#11445893)


All the programs that run on PC architectures expect certain things to be in place - they expect a single fast central CPU. They expect that good cache usage is important for performance. They expect to have access to gobs of RAM. Etc. Etc. The PS2 (and by extension the cell) is completely different.

Consider a different architecture. You have a job that consists of multiple things to do. Some of these can be easily parallelised, others are mainly sequential. Divide it up so the parallel ones are coded separately, maybe with some IPC to synchronise to some clock.

For a sequential part (say rendering the object list of a scene back to front to gain occlusion) the approach that worked for me on the PS2 (which is logically similar, if significantly less powerful) was to divide the job into tasks. Each task (say, one per object in the above) gets its own bit of code and knows about the data that it needs to perform its task.

The key thing is that the Harvard separation of code and data just isn't, on a PS2. You set up a DMA chain that loads the program into the processor, then streams the data through the program on the processor, lather, rinse, repeat. Make the chain self-submitting and you can effectively forget about that chunk of code now, it'll just happen.

This is still doing things sequentially (but we've agreed that this is a sequential task, right?) - the point is that it's being done highly efficiently within the architectural constraints. You have a dataflow architecture and even sequential code can hit the performance limits if you code to the architecture.

The Cell looks even more powerful, in that you can chain execution modules together, so you can load code into APU's 1,2,3,4 and stream the data through 1,2,3,4 automatically before it's considered 'done'. This was possible on the PS2, but ... awkward. It'll keep the effective instructions/clock down because you're effectively pipelining your software... Nice idea.

Simon

Re:Consider a different approach (1)

cant_get_a_good_nick (172131) | more than 9 years ago | (#11445951)

I have enough knowledge to be dangerous - would a message passing architecture microkernel be able to take advantage of this sort of architecture more than a macro-kernel would? I was thinking specifically of DragonFly BSD, and the modules that make up OS X.

Re:There are always critical sections (2, Insightful)

kai.chan (795863) | more than 9 years ago | (#11445972)

its very rare for a system to be able to be completely parallelised.

Not really. Current gaming computers are usually bogged down while trying to display a graphical-intense game. Home electronics are composed of video and audio. Much of 2D and 3D visualization and audio are "embarrassing parallel problems". Take the video encoding/decoding example from the article, you don't need to parallelize a video frame in terms of each pixel elements, instead, one opts to parallelize each video encoding process that doesn't have "critical sections". Not only can types of procedures be parallelized, a lot of for loops can also be unwound so that they, too, can be split up onto multiple processors.

Re:There are always critical sections (0)

Anonymous Coward | more than 9 years ago | (#11446009)

Danger buzzword alert!
"G5's and G4's already have altivec"

Do you even have a clue what you are talking about? "AltiVec" is the marketing buzzword for what is generically known as SIMD - single instruction, multiple data. [wikipedia.org] processing.

ALL popular desktop processors have this feature including all offerings from Intel and AMD. SIMD goes by various trade names MMX, 3DNow, SSE, KNI, VIS, MIPS-3D, and yes AltiVec.

SIMD instructions are primarily designed to aid the computation of mathematical transforms such as the Fourier transforms. They are mainly tailored to computing sums of products which is one of the most common operations involved in computing mathematical transforms. There is nothing particularly special about AltiVec. It is just another version of a common idea used in many different CPUs.

this message brought to you by the Fanboy Detox and Rehabilitation Center

Timothy, Saturday night (4, Funny)

Leto-II (1509) | more than 9 years ago | (#11445743)

Okay, who was down for Timothy on Saturday night for the /. Dupe Pool?

Re:Timothy, Saturday night (0)

Anonymous Coward | more than 9 years ago | (#11445875)

I think it might have been ... ah, yeah, this guy, "Tim O'Thy" seems to have won it.

Seriously, I think that they post dupes for fun, to see the reaction.

Re:Timothy, Saturday night (1)

Ohreally_factor (593551) | more than 9 years ago | (#11445934)

I was, but I thought he was going to dupe a different story. =)

Re:Timothy, Saturday night (1)

DarkHelmet (120004) | more than 9 years ago | (#11446013)

What, you thought he'd be out getting laid?

argh (0)

Anonymous Coward | more than 9 years ago | (#11445764)

If my job was posting news on a news site - i'm pretty damn sure i'd actually read that site.

How the mighty have fallen.

Not Again! (0, Troll)

shplorb (24647) | more than 9 years ago | (#11445766)

Besides the fact that this is a blatant dupe, anyone who takes this article seriously is as big a dickhead as the author.

It's so full of shit and blatantly wrong that I don't know where to begin.

YOu sUcK (0)

Anonymous Coward | more than 9 years ago | (#11445774)

and your mother dresses you bad

Re:Not Again! (0)

Anonymous Coward | more than 9 years ago | (#11445814)

Would be nice if you said something to prove that it's full of shit.

Re:Not Again! (0)

Anonymous Coward | more than 9 years ago | (#11445943)

he shouldnt have to its common knowledge.

Cells. (0)

Anonymous Coward | more than 9 years ago | (#11445769)

It's a cell architecture of Slashdot posts.

Auction at ebay... (1)

1tsm3 (754925) | more than 9 years ago | (#11445777)

Cell processors for sale! Slashdot calls it the best. Say that twice... May be thrice... Interested buyers check slashdot every day!

Timothy, step into my office.... (0)

Anonymous Coward | more than 9 years ago | (#11445791)

'cause you're Fuckin' FIRED!!!

Some Thoughts (5, Insightful)

logicnazi (169418) | more than 9 years ago | (#11445793)

Well, I think we all recognized that article was a little over enthusiastic but it does suggest some interesting possibilities.

First of all I want to say I think it is completly possible to make a processor with 8APUs and so forth. For starters PowerPC chips already have several seperate execution units on them, and I think they use fewer transitors than intel chips. Moreover, a huge chunk of the transitor budget goes to doing things like cache consistancy or complicated instruction prediction which is probably not used on the much simpler APUs.

Of course it seems like this is primarily of interest to game systems or signal processing applications (note that a 4 threaded 32 stream processors is just another way of saying 4 cell procesors, each has a PPC core with 8 APUs). However, I would not be so quick to dismiss this for the PC market. While it may be true that many individual applications may not easily multi-thread it seems we are approaching a point where the biggest complaint is not the maximum processing rate in one application but the ability to run multiple applications at once. On my computers I'm rarely if ever frustrated at the rate some program is running at, but slowdown in other programs when I run a processor intensive job or turn on a video. So while drawing a webpage may not be speed up by this processor drawing several webpages at the same time will be and that is the sort of thing which makes a big difference for the end user.

Also, a processor like this offers great possibilities for JIT and VM code. The main thread can dispatch instructions and threads to the APUs dynamically based on what is happening in the system. Also I find it interesting that IBM is going the same way as intel in pushing all the complexity on the compiler. It makes one wonder if itanium is really as dead as everyone thinks. Perhaps in 4 years when AMD can't squeeze anything more out of x86 intel will be ready to jump in having worked out all the bugs to their new chip.

Re:Some Thoughts (1)

Lehk228 (705449) | more than 9 years ago | (#11445995)

A 1.3 Ghz machine with 1 gig ram is enough to do everything but video editing, throw a decent 8x AGP card in and oyu can play any game out there at good quality. This Cell technology looks like a neat toy, but it will be useless for consumers, what matters now is cutting power consumption and heat loss, making things quieter and cooler will sell a lot more than making things faster.

Well, this could use some more reiteration... (1)

Rize (757409) | more than 9 years ago | (#11445810)

I'll believe it when I see it. With a crazy new architecture like this, *everything* is on paper right now. The hardware, the software, everything. The only thing that is virtually gauranteed is that the PS3 will have a few of these things in it and that it will sell in droves. Just how useful and powerful this chip will be in practice remains to be seen.

Re:Well, this could use some more reiteration... (4, Informative)

hattig (47930) | more than 9 years ago | (#11445914)

We will find out a whole lot more within the next fortnight, Cell is being described in a lot of details at ISSCC 2005 [isscc.org] in early February.

Paper Details:

  • The Design and Implementation of a First-Generation CELL Processor (10.2)
  • A Streaming Processing Unit for a CELL Processor (7.4)
  • A 4.8GHz Fully Pipelined Embedded SRAM in the Streaming Processor of a CELL Processor (26.7)
  • A Double-Precision Multiplier with Fine-Grained Clock-Gating Support for a First-Generation CELL Processor (20.3)
  • Clocking and Circuit Design for a Parallel I/O on a First-Generation CELL Processor (28.9)

pwr (1)

stel (781591) | more than 9 years ago | (#11445811)

Power consumption- the great equalizer.

DOUBLE POST! (0)

Anonymous Coward | more than 9 years ago | (#11445835)

Nice job, editor.

Merrimack streaming processor is like CELL (2, Informative)

zymano (581466) | more than 9 years ago | (#11445888)

Dally's Merrimac processor. [weblogs.com]

It's so similar that you wonder if they lifted it from him. The only difference is that Prof. Dally's chip has a big cache.

damn it (1)

TLouden (677335) | more than 9 years ago | (#11445899)

I though that I was reading slashdot before it came out. Turns out that it's just reposting the same news. Sad thing is that I actually had to go back and check to see if this really had already been posted.

Well, guess I don't have any super brain powers :(

So what really do we have here? (1)

johnnys (592333) | more than 9 years ago | (#11445908)

Ah yes. We're all going to learn a whole new way of programming: To wit:

"If there is a law in computing, Abstraction is it, it is an essential piece of today's computing technology, much of what we do would not be possible without it. Cell however, has abandoned it. The programming model for the Cell will be concrete, when you program an APU you will be programming what is in the APU itself, not some abstraction. You will be "hitting the hardware" so to speak.'

So we're all going to go back to assembler? I don't think so.

Fanboysim at it's most technical (0)

DaveCBio (659840) | more than 9 years ago | (#11445962)

This article is hype and air. Remember how the Emotion Engine was going to change the fabric of space and time? This guy was full of crap the first time this article was posted and nothing has changed. Seriously, why does /. post this crap? Someone from another board put it this way - His theory about reducing latency by transferring in larger block sizes is fascinating. So an articulated lorry should go around corners faster than an Elise because it has more wheels then? Okaaaay.

37 stories between dup (0)

DraconPern (521756) | more than 9 years ago | (#11445974)

Did you know that there are 37 stories between the two dup? I wonder if there's a story with an even smaller gap. :)

Cell architecture? (1)

deft (253558) | more than 9 years ago | (#11446006)

My bad, I thought this was going to an article about cubicles in the modern work environment.

To quote the GNAA about Timothy (-1)

LittleLebowskiUrbanA (619114) | more than 9 years ago | (#11446008)

" while Timothy responded by posting the same story six times"
Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Create a Slashdot Account

Loading...