PS3: IBM thought Kutaragi was out of his mind wanting 1,000 times PS2 CPU power

[thunderblade]

IBM thought that Ken Kutaragi was OUT OF HIS MIND wanting to make a Cell processor that had 1,000 times the performance of Playstation2's Emotion Engine processor.

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."

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.

 

[Mayhs]

so how powerful is it compared to our computer cpus?...

 

[TekSomniaK]

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

Riiiiiiiiiiiiiiiight. Anyone else think this little ditty was only added for effect?

 

[USMC2Hard4U]

Cell is an amazing architecture that is probably faster than Any x86 PC we have today, by 10 fold. However, you havve to have the software specifically coded for it, and by no means will x86 work or even perform will if emulated. So thats why it wont come to the desktop anytime soon....

I think that the PS3 is going to be the best of this generation due to its hardware. The XBox360 isnt much different, but I think PS3 has a bigger fan base overall to make it better anyway.

I am getting all 3 of the next gen stuff so I really dont care, but I like cell and think its outstanding.

 

[sergey85z]

LONG POST

Anyone but me find that Cell is way over hyped considering the Xbox cpu is a very similar design based of powerpc. The best way of comparing the PCpower Xenon and the Cell. From ARStechnica

[/QUOTE]

This system is perhaps more revolutionary than the CELL. There is alot ALOT more in the article and follow up to it.

The Xenon's triple-core design shares some DNA with the Playstation 3's Cell processor, so it's not surprising that it also embodies many of the same assumptions about the best way to wring performance out of the sorts of extremely large transistor counts that Moore's Curves have given the latest generation of integrated circuits. Like the Cell processor that will power the Playstation 3, the Xenon carries on the "RISC"-style tradition of trading programmer/compiler effort for hardware. In a nutshell, software writers who develop for Xenon must take on more of the burden of optimizing their code by making it explicitly parallel, and in return they get more execution hardware to play with.

What intrested me more is that unlike how ps3 or computers work Xbox works in a diffrent manner. Note the following from ARStechnica. Its a long article i will cut out whats important. http://arstechnica.com/articles/paedia/cpu/xbox360-1.ars/2

For 3D games, artists use a 3D rendering program to produce content for the game, e.g. character models and environmental objects like trees, terrain, buildings, etc. Each model that an artist produces is translated into a collection of polygons, which are themselves represented in the computer's memory as collections of vertices. When the computer is rendering a scene in a game in real-time, the models that are being displayed on the screen start out in main memory as stored vertex data. That vertex data is fed from main memory into the GPU (under the direction of the CPU on which the game engine runs), where it is then rendered into a 3D image and output to the monitor as a sequence of frames.

Every object that you see in the game must be painstakingly crafted by an artist—every fire hydrant, light pole, tree, hill and valley—and stored on disk as vertex data to be placed in system memory. It costs a lot of money and worker hours to populate an large, rich, 3D world with convincing-looking representations of objects, which is why in most games many common objects look exactly alike. Artists make one fire hydrant model, and use that same model on every curb; or they make a small number of tree models, and populate an entire forest with just a few trees.

(more inbetween in the full article.)

The Xbox 360's solution to this problem is to store high-level descriptions of objects in main memory, and have the CPU procedurally generate the geometry (i.e., the vertex data) of the objects on the fly. So in the case of our forest, main memory stores information about the tree, like the type, size, location of each leaf, etc., along with other relevant data like the direction of the prevailing wind. This information is passed into the Xbox 360's Xenon CPU, where the vertex data that defines the polygons out of which the tree is made are generated by one or more running threads. These threads then feed that vertex data directly into the GPU (by way of a special set of write buffers in the L2 cache, but more on that later). The GPU then takes that vertex information and renders the trees normally, just as if it had gotten that information from main memory.

The end result of all this is that the amount of data that is stored in main memory and moved into the CPU is much less than the amount of data that the CPU puts out and that the GPU ends up processing. Microsoft refers to this ratio of stored scene data to rendered vertex data as a compression ratio, the idea being that main memory stores a "compressed" version of the scene, while the GPU renders a "decompressed" version of the scene.

The technique of compressing scene data for storage in main memory and then decompressing it by means of procedural synthesis allows game developers to do more with a console's limited system memory. The console provides plenty of CPU-to-GPU bandwidth and enough computing power to procedurally render objects in real time, and the developer provides higher-level scene descriptions that allow a richer, more realistic world to be described using less storage space.