Support NeoGAF

[Afro Thunder]

A very good article. The things are getting clear to me about all hype about Cell.
http://www.realworldtech.com/page.cfm?ArticleID=RWT021005084318&p=1
Sorry if I manage to make someone sad here.

 

[bishoptl]

 

[sprsk]

too many words, didnt read.

 

[Drexon]

Heyyy, technical references, sexxy.

 

[Afro Thunder]

too many words, didnt read.

Please, give a try, you may like it. You need ammo to talk about because we will have BIG discussions here at GAF in incoming months.

 

[Amir0x]

*sigh*

Can anyone sum it up in a paragraph?

 

[Phoenix]

Its certainly a good read. If you want to actually understand the technology itself, you probably want to read through this. Otherwise you likely won't follow the geek talk that passes through many of the threads.

 

[Phoenix]

*sigh*

Can anyone sum it up in a paragraph?

Its impressive, it doesn't suck, it has incredible potential and is more scalable than any other processor on the market. It gives up a lot of precision (double precision floating point numbers) to achieve much of its speed, but that's fine since most devs use floats. In addition it does have a unit that is capable of double precision floating point arithmatic - and it itself is very very fast. The memory system is UBER, but appears to be expensive to implement. The pipelines on the SPE are deep.... really deep and some of the predictive logic is cool. Many operations on the CPU come at trivial latencies.

The author adds this as the summary (your paragraph - you didn't even try )

The CELL processor presents an intriguing alternative in its pursuit of performance. It seems to be a forgone conclusion that the CELL processor will be an enormously successful product, and that millions of CELL processors will be sold as the processors that power the next generation Sony Playstation. However, IBM has designed some features into the CELL processor that clearly reveals its ambition in seeking new applications for the CELL processor. At ISSCC 2005, much fanfare has been generated by the rating of 256 GFlops @ 4 GHz for the CELL processor. However, it is the little mentioned double precision capability and the yet undisclosed system level coherency mechanism that appear to be the most intriguing aspects that could enable the CELL processor to find success not just inside the Playstation, but outside of it as well.

 

[Amir0x]

Its impressive, it doesn't suck, it has incredible potential and is more scalable than any other processor on the market. It gives up a lot of precision (double precision floating point numbers) to achieve much of its speed, but that's fine since most devs use floats. In addition it does have a unit that is capable of double precision floating point arithmatic - and it itself is very very fast. The memory system is UBER, but appears to be expensive to implement. The pipelines on the SPE are deep.... really deep and some of the predictive logic is cool. Many operations on the CPU come at trivial latencies.

The author adds this as the summary (your paragraph - you didn't even try )

I don't know anything about technobabble!

 

[Drek]

Can anyone sum it up in a paragraph?

I don't even need a paragraph.

Cell = ANTI-BOMBA!

 

[whytemyke]

holy shit... so basically scariest environment imagineable. Right. That's all you had to say, scariest environment imagineable.

 

[nitewulf]

In all fairness, since the SPE was presented on Monday and the CELL processor itself was presented on Tuesday, CELL project members responsible for the SPE were not present for Tuesday evening’s chat sessions. As a result, the team members responsible for the overall CELL processor and internal system interconnects were asked to recall the meaning of acronyms of internal functional units within the SPE. Hence, the task was unnecessarily complicated by the absence of key personnel that would have been able to provide the answer faster than the CELL processor can rotate a million triangles by 12 degrees about the Z axis.

After some discussion (and more wine), it was determined that the ATO unit is most likely the Atomic (memory) unit responsible for coherency observation/interaction with dataflow on the EIB. Then, after the injection of more liquid refreshments (CH3CH2OH), it was theorized that the RTB most likely stood for some sort of Register Translation Block whose precise functionality was unknown to those outside of the SPE. However, this theory would turn out to be incorrect.

:lol :lol :lol :lol

a bit of engineering humor there for you. so very very dry...and i wonder how come we get no women.
anyway, im impressed by certain aspects, and not so impressed by other aspects. programming this beast will be difficult.

 

[doncale]

A very good article. The things are getting clear to me about all hype about Cell.
http://www.realworldtech.com/page.cfm?ArticleID=RWT021005084318&p=1
Sorry if I manage to make someone sad here.

I read this entire article twice through, a few weeks ago when it was first posted. I think this article was linked to in at least one other Cell/PS3 thread. interesting read.

 

[mrklaw]

221 mm2 is the die size on 90mm

Anyone know what the PS2 GS or EE were in the first machines? I seem to remember thost being pretty hefty too

 

[Amir0x]

Man, for some reason when I entered the thread this time around I thought it said "Yes. Another Code thread" and there was going to be images of that NDS game. It's funny cause I've been in this thread before

 

[gofreak]

Anyone know what the PS2 GS or EE were in the first machines? I seem to remember thost being pretty hefty too

The EE was a little larger than that Cell chip.

Oh, and this article is old

 

[doncale]

I will be totally disappointed if Sony merely goes with a 65nm version of the Cell presented at ISSCC. even if PS3 version has a few refinements.


and don't even ask me how I would feel if Sony goes with a LESS powerful Cell chip with fewer SPEs.

 

[Koshiro]

too many words, didnt read.

The voice of today!

 

[gofreak]

I will be totally disappointed if Sony merely goes with a 65nm version of the Cell presented at ISSCC. even if PS3 version has a few refinements.


and don't even ask me how I would feel if Sony goes with a LESS powerful Cell chip with fewer SPEs.

I guess you'll be really down on the Xenon and Revolution CPUs then A little perspective?