Support NeoGAF

[midnightguy]

credit to Brimstone on B3D for this.

Brimstone wrote:
"I got the latest issue of Business 2.0 June 2005, which has a 4 page article on CELL. Here are a few intresting quotes from the article."

"Kutaragi, known for the bold stroke and the grand vision, swung for the fences from the get-go. "We want to do something that has never been done before," he told Davari and a group of IBMers at their first meeting. "let's work together to change the world." The movie The Matrix had just come out, and Kutaragi relished itspremise of a world that is actually a giant computer simulation "Think about creating a crude version of that world," he said, "where millions of people can play in a realistically rendered virtual Tokyo or New Yourk City as if they are really living there." Creating that magical realm, Kutaragi told the team, would require a chip 1,000 times as powerful as the one in the PlayStation 2. The IBMers tried not to roll their eyes. They tended to like all that Matrix stuff, but when it came to 1,000-fold chip boosts, they thought Kutaragi was out of his mind."

"Davari tapped to lead the project was Kahle...He had designed IBM's first dual core chip, the Power4, and was just coming off a project that produced the IBM chip that powers Apple's G5 computers. "I don't want to do the normal stuff," he says with a shrug. Normal obviously want what Kutaragi had in mind. Still, one of Kahle's first moves was to talk Kutaragi down from that fantasy of a 1,000-fold power increase. Kahle figured a goal of a 100- fold boost from one chip generation to the next, having rarely if ever been achieved in the history of semiconductors, was ambitious enough."


"Kutaragi was incredibly demanding and repeatedly sent Kahle back to the drawing board. At one point about a year into the project, Kutaragi made the team scrap the whole system structure and start over nearly from scratch. Another time Kutaragi decided he wanted two more cores. Why? "He just wanted to squeeze the engineering team," expains Masakazu Suzuoki, Sony's top Cell engineer, wringing his hands as if strangling a snake. "it hurt your head," Kahle recalls. Making the pain worse: The team still had to deliver the chip on the original schedule."


"To this day, few people even inside the allied companies know the details of Cell's development or the high hopes its backers hold. The Cell engineers are still not supposed to talk about much of their work to anyone outside the Austin facility. One day the air-conditioning broke down in the lab, and as the temperature soared, the engineers propped open the doors. Word got around. The company had to post guards to turn back rubbernecking colleagues eager for a glimpse of what was going on in there."




"IBM, in paticular, says it's making headway in defense, medical imaging, internet switching, and industrial inspection equipment. The company suggests that the chip could be especially useful in crunching the mammoth amounts of data the military will collect as it develops so-called network-centric operations, where heavy armor is replaced by more perfect information--such as torrents of broadband video--that must be processed on the fly."

:lol oh my god, that was a good read.


note that the Cell going into Playstation3 is only about 35 times more powerful than the Emotion Engine in Playstation2. even if Sony and IBM were to unleash the 8th SPE and unleash the full clockspeed that Cell is capable of ( 4 to 5 GHz ) that would still not come close to even the ambitious 100 fold increase that Kahle suggested Kutaragi and they aim for. it would still be roughly a 50 fold increase.

 

[vatstep]

Kutaragi = The Architect

 

[sonycowboy]

Kutaragi = The Architect

I realized the solution required a lesser mind, or a mind not bound by perfection. :lol

 

[gofreak]

Good read.

Interesting that Kutaragi's "Matrix" visions were actually imperfect (not exactly like the movie) "Think about creating a crude version of that world"

 

[Dalamar86]

The man really is crazy. Seems his crazy schemes may have payed off though.

 

[midnightguy]

The man really is crazy. Seems his crazy schemes may have payed off though.

but how so ?

 

[DarienA]

I realized the solution required a lesser mind, or a mind not bound by perfection. :lol

:lol

 

[Jeffahn]

Kutaragi: Don't mis-underestimate the power of Playstation 3!!!

...

 

[gofreak]

but how so ?

Well, on a simple level he's in charge of the dominant entertainment platform in the living room thanks to his hairbrained schemes.

On a more specific level, the higher he aims, the higher the eventual "hit" will land, even if it doesn't match his "crazy plans". If he had aimed lower, we may have got lower than what we have.

 

[Juice]

That was a good read. I was definitely in the camp of the CELL being complete bull-shit until a few months ago when I decided to remove the stick from my ass.

I am now cautiously optimistic that it will achieve gas-station blowing physics so intense that it will actually save my broken soul.

 

[TekunoRobby]

Out of his mind and into our hearts.

 

[midnightguy]

Well, on a simple level he's in charge of the dominant entertainment platform in the living room thanks to his hairbrained schemes.

On a more specific level, the higher he aims, the higher the eventual "hit" will land, even if it doesn't match his "crazy plans". If he had aimed lower, we may have got lower than what we have.

ok I see what you're saying, and I tend to agree. good explaination gofreak

 

[jenov4]

LOL, awesome read.

 

[StRaNgE]

the cell always makes me think of that damn chip in T-2 that they burn up in the end.

 

[jarrod]

note that the Cell going into Playstation3 is only about 35 times more powerful than the Emotion Engine in Playstation2. even if Sony and IBM were to unleash the 8th SPE and unleash the full clockspeed that Cell is capable of ( 4 to 5 GHz ) that would still not come close to even the ambitious 100 fold increase that Kahle suggested Kutaragi and they aim for. it would still be roughly a 50 fold increase.

So really, it's PlayStation 2.35. :lol

 

[midnightguy]

So really, it's PlayStation 2.35. :lol

:lol :lol

 

[Sagitario]

Kutaragi: Don't mis-underestimate the power of PLAYSTATION 3!!!

...

Fixed =P ...

 

[gofreak]

So really, it's PlayStation 2.35. :lol

Someone doesn't know how percentages work. 35x the power (however that figure is derived - floating point only?) = 3500% increase. So Playstation 70

note that the Cell going into Playstation3 is only about 35 times more powerful than the Emotion Engine in Playstation2. even if Sony and IBM were to unleash the 8th SPE and unleash the full clockspeed that Cell is capable of ( 4 to 5 GHz ) that would still not come close to even the ambitious 100 fold increase that Kahle suggested Kutaragi and they aim for. it would still be roughly a 50 fold increase.

35x the floating point power, right? That's one part of the equation. When you take the chip as a whole, the efficiencies gained, the improvement to architecture and soforth, 100x may not be so far from the truth in terms of all round realworld performance. 100x the power can mean anything - without their definition, comparing that to the floating point increase isn't telling the whole story.

And what do you mean by "only" 35 times the power of EE for floating point? I don't see any other consumer chips touching that floating point performance

 

[Stinkles]

What a waste. If he'd demanded a billion times more powerful, we'd have got that 1000 times.


Moore's Law is for squares.

 

[cubicle47b]

Someone doesn't know how percentages work. 35x the power (however that figure is derived - floating point only?) = 3500% increase. So Playstation 70

I'm trying to detect sarcasm and failing.

 

[jarrod]

Someone doesn't know how percentages work. 35x the power (however that figure is derived - floating point only?) = 3500% increase. So Playstation 70

I was working from the intended target (35x result when 100x was intended). Actually that's not correct either since Kutaragi wanted 1000x... Really it's PlayStation 2.035. :lol

 

[PhatSaqs]

 

[Asskicker064]

Out of his mind and into our hearts.

That is reserved only for Killdozer. Kutaragi is no match for him.

 

[gofreak]

I'm trying to detect sarcasm and failing.

I thought the winky might give it away!

I was working from the intended target (35x result when 100x was intended). Actually that's not correct either since Kutaragi wanted 1000x... Really it's PlayStation 2.035.

Not entirely fair :lol Again, 1000x what...?

 

[sonycowboy]

I was working from the intended target (35x result when 100x was intended). Actually that's not correct either since Kutaragi wanted 1000x... Really it's PlayStation 2.035. :lol

So, Ken was right. Xbox has been aiming at the PS2 the whole time

 

[midnightguy]

and the rest of it

 

[Chittagong]

So 3.6 trillion polygons / sec @ 6400 x 4800 px super high definition @ 120 FPS?

Count me in!

 

[midnightguy]

So 3.6 trillion polygons / sec @ 6400 x 4800 px super high definition @ 120 FPS?

Count me in!

haha, Next-Gen made a booboo there :lol they figured in an extra 100x increase on top of a 1000x increase :lol

 

[GaimeGuy]

Unfortunately, the media loves to exaggerate the power of new technology.

The whole Cell being 1% as powerful as a human brain is BS, too. (granted, it wasn't said by Sony)

Cell performs approximately 250 Gigaflops per second. That's 250,000,000,000 floating-point calculations.

The human brain cam perform approximately four petaflops per second. That, my friends, is 4,000,000,000,000,000 floating-point calculations. Not to mention the fact that the brain does a whole bunch of other stuff besides raw calculations, and images are processed at much higher resolutions.

 

[PS2 KID]

It's not powerful enough! They need to give us 4Ghz Cell at 65nm!!! It would be interesting to see what design they scrapped prior to Cell. To think Kutaragi wanted 2 more cores. He really is power hungry. :lol

 

[Mashing]

Well, on a simple level he's in charge of the dominant entertainment platform in the living room thanks to his hairbrained schemes.

On a more specific level, the higher he aims, the higher the eventual "hit" will land, even if it doesn't match his "crazy plans". If he had aimed lower, we may have got lower than what we have.

Until the point where he because a liability to Sony because he keeps pissing of executives of other companies. I wouldn't want to be in this shoes is that happens, corporate politics is NASTY.

 

[Guy LeDouche]

Unfortunately, the media loves to exaggerate the power of new technology.

The whole Cell being 1% as powerful as a human brain is BS, too. (granted, it wasn't said by Sony)

Cell performs approximately 250 Gigaflops per second. That's 250,000,000,000 floating-point calculations.

The human brain cam perform approximately four petaflops per second. That, my friends, is 4,000,000,000,000,000 floating-point calculations. Not to mention the fact that the brain does a whole bunch of other stuff besides raw calculations, and images are processed at much higher resolutions.

Source? Not doubting, just interested how that number was calculated. I've never heard of brain power in flops

also, lol high-res lol reminds me of the commercial where the realtor tells a couple that the house has "high-def glass windows"

 

[GaimeGuy]

Hmm.... actually, according to this site,

http://paula.univ.gda.pl/~dokgrk/bre01.html

the human brain can do 20 petaflops....

20,000,000,000,000,000 calculations per second.

Anyways, whatever the calculation power of the human brain may be, you can't compare the brain and a computer chip just by comparing the raw data calculations, because the brain is so much more than that.

You need to look at memory (according to that site I linked to, the brain can store 1000 TB of data, and compared to other figures I've heard, that is VERY low.).

Most of all, you need to look at the mind. As far as we've come along with researching the brain, humans still know very little about the mind. Emotionary responses, thoughts, feelings, and our perceptions of others are some parts of the human mind.

At the rate we're going, the ability of our computers to perform raw number crunching will surpass that of the human brain several decades, perhaps even centuries before we can even hope of approaching the brain in anything else.

 

[Guy LeDouche]

Hmm.... actually, according to this site,

http://paula.univ.gda.pl/~dokgrk/bre01.html

the human brain can do 20 petaflops....

20,000,000,000,000,000 calculations per second.

Anyways, whatever the calculation power of the human brain may be, you can't compare the brain and a computer chip just by comparing the raw data calculations, because the brain is so much more than that.

You need to look at memory (according to that site I linked to, the brain can store 1000 TB of data, and compared to other figures I've heard, that is VERY low.).

Most of all, you need to look at the mind. As far as we've come along with researching the brain, humans still know very little about the mind. Emotionary responses, thoughts, feelings, and our perceptions of others are some parts of the human mind.

At the rate we're going, the ability of our computers to perform raw number crunching will surpass that of the human brain several decades, perhaps even centuries before we can even hope of approaching the brain in anything else.

I always suspected God was a graphics whore.

 

[Hitokage]

The human brain cam perform approximately four petaflops per second. That, my friends, is 4,000,000,000,000,000 floating-point calculations. Not to mention the fact that the brain does a whole bunch of other stuff besides raw calculations, and images are processed at much higher resolutions.

The brain is not a turing machine. Most terms used in the computing world are absolutely meaningless since the human brain is so fundamentally different. Nobody can actually perform even 100 mathematical calculations per second(which is pathetically slow for a computer), but they say that stuff because that's the level a computer would need to do what the brain is good at doing.

Although it might be great if human memory were half precise as a computer store-and-retrieve.

 

[Vince]

The human brain cam perform approximately four petaflops per second. That, my friends, is 4,000,000,000,000,000 floating-point calculations. Not to mention the fact that the brain does a whole bunch of other stuff besides raw calculations, and images are processed at much higher resolutions.

I've never heard the brain's processing ability talked of in floating-point ops before, I dont know why you would even seek to do that outside of some form of comparable mapping of ability, but it's way too arbitrary an unit to use for a connectionist system in which the concept of "computation" and what composes a "memory" in biological systems on differential levels is somewhat unknown: from individual molecular interactions to mass-action at the cellular level, to holistic neural topologies. I'd stick with a bounding described solely by the number of neurons and connections with an unknown variable included to make-up for the glial, molecular interaction, differential neuronal firing rates, etc.

And the last part is somewhat wrong, the human optical system isn't that advanced and has it's downfalls that aren't obvious to you, but exist nevertheless. There are sever evolutionary constraints on the "bandwith" of incoming information that can be moved to the LGN and further onward. There is also the related problem of the inhibation due to the refactory downtime that limits the speed of information processing. A simplistic example of this is that once you saturate the sub-system, you can nolonger differentiate between datapoints -- and this is quite easy for PC games and TV as they can do it at 24fps and around 60-120fps respectively.

While I don't recommend you believe anything the man says of consciosunss, Walker's book is an easy read and had a somewhat intrguing part on the data capacity of the optical sub-system that maybe worth a read. Something that made me go Hmm.. how did I miss that after more years of studying biochemistry and neuroscience than I have fingers (EDIT: Well, almost, I'm not that old yet.. hehe) was a simple comment about how when we're driving at 60mph we are, in fact, on the order of 15' infront of where "we" percieve ourselves to be due to the neural delay.... all that education for nothing

 

[Christoff Yurievich]

http://www.ga-forum.com/showthread.php?t=50195&highlight=business+2.0

old!

 

[akascream]

I've seen the brain explained as a massively parallel architecture, explaining why we are so good at things like pattern recognition, but can't do math nearly as well as even very basic calculators. And while of course they are different (duh, one is biological), the brain is essentially just a living computer.

I've never seen those petaflops numbers before though.

 

[midnightguy]

I wanted a 4 GHz, 72-processor Cell chip, made from 8 PPEs and 64 SPEs, damnit!

even THAT would've fallen short of the original 1,000x PS2 goal :lol

 

[dorio]

Kutaragi: Don't mis-underestimate the power of Playstation 3!!!

...

:lol

 

[gofreak]

I wanted a 4 GHz, 72-processor Cell chip, made from 8 PPEs and 64 SPEs, damnit!

even THAT would've fallen short of the original 1,000x PS2 goal :lol

You seem keen to bring this up at every opportunity.

Oh drat, it's only 2x as powerful as its next best competitor (by your measure). For shame. :rolleyes

Get over it midnightguy. The chip you've got is great.

 

[Open Source]

Playstation was never about its good technology. And KK is the blind squirrel who found an acorn.

 

[TekunoRobby]

That is reserved only for Killdozer. Kutaragi is no match for him.

:lol Very true.

I was hoping someone from GAF would pick up on the quote.

 

[dorio]

:lol Wow, that sounds alot like the type of stuff he's talking about for the ps3.

In the past, workstantions and pcs had more power than home game consoles, so we could use them as development tools. But when the power of Playstation2 mateches or exceeds their power, it becomes difficult to use them for development.

How many developers ditched their workstations for ps2 development machines running Linux.

 

[GaimeGuy]

Playstation was never about its good technology. And KK is the blind squirrel who found an acorn.

The keyword is was.

Now it is.

 

[Open Source]

The keyword is was.

Now it is.

PS3 isn't available in my area yet.

 

[Legal Step]

Kutargi-san sounds cool and crazy. Nice!

 

[SoVos20]

The brain is not a turing machine. Most terms used in the computing world are absolutely meaningless since the human brain is so fundamentally different. Nobody can actually perform even 100 mathematical calculations per second(which is pathetically slow for a computer), but they say that stuff because that's the level a computer would need to do what the brain is good at doing.

Although it might be great if human memory were half precise as a computer store-and-retrieve.

Actually some savants have been shown to be able to do what would seem like impossible mathematical calculations in their heads, like say quickly comming up with different 6 digit prime numbers, some times even faster than a what we would call a fast computer today.

 

[GaimeGuy]

Actually some savants have been shown to be able to do what would seem like impossible mathematical calculations in their heads, like say quickly comming up with different 6 digit prime numbers, some times even faster than a what we would call a fast computer today.

Cool.

 

[AB 101]

Ken Kutaragi is the Japanese version of Steve Jobs.