256 GFlops is most likely the theoretical maximum assuming a prototype part running at 4GHz. Realistically it's probably much closer to half of that. And then it's still just an aggregate artificial figure. Considering all the other things a Cell CPU would have to do in addition to graphics, say, running other game systems, makes exclusive graphics processing on the Cell highly unlikely.
The Cell could probably assist with transform and lighting (vertex shaders) leaving the GPU with pixel/fragment shader processing. GPUs can do this more efficiently at significantly lower clock rates.
Whoa! You sure make a lot of unqualified, even inflammatory statements there. It had to be said.
First of all, the press release doesn't say anything about final clock speeds, just prototype results. Considering this, even Intel showed a 4GHz P4 at the IDF in 2002. That was three years ago, ancient times for all intents and purposes and look where we are today...
Sure, it's likely that a 4+GHz Cell CPU will be used sometime in the future for some applications, but I was talking about a Sony console here, a consumer device.
It will be subject to design constraints, mainly in the areas of reliability, form-factor and especially cost.
It's safe to assume that at clock speeds exceeding 3GHz the Cell chip will require some form of active cooling. The chip is subject to the same power leakage issues that all CPUs have these days, probably even more so at a 234 million transistor count. For example, at a much lower transistor count IBM's 90nm PPC 970 still doesn't run at 3GHz, let alone 4GHz. Granted, a direct comparison might not be possible, but it's a good indicator.
As a matter of fact, there are no consumer level devices available today runnning at 4GHz, not even desktop CPUs (unless you do some insane cooling).
Given all that, the question becomes, how much active cooling can Sony afford to put in an everyday living room device? The console has to be small and reasonably failsafe, too. Active cooling solutions require space and are a therefore a cost factor (see Xbox). Beyond that, if the console requires a more extensive cooling solution, the more expensive and less failure tolerant it will ultimately be.
Additionally, if we assume a $300-$400 price point and traditionally low yields for higher clocked chips at the early stages of manufacturing, I think 3 to 3.5GHz is a very reasonable, almost optimistic estimate.
Finally, that a gaming console can not afford to have any autonomous thermal management which might affect clock speeds goes without saying. It would have tremendous TRC implications. If you can't figure out why or what that means, you obviously never shipped a console game.
Unless you manage to break down your systems or computational problems into eight digestible pieces and have an efficient flow of data between all the participants (especially given the tiny amounts of local RAM), you'd just have another glorified PowerPC CPU.
I don't think the final PS3 part will be clocked much higher than 3.5GHz. Otherwise it would probably involve downclocking parts of the CPU to maintain a sane thermal profile, thus making overall performance rather unpredictable.
This would especially impact games, where it's all about sustainable framerates at 100% CPU utilization.
I am upset about people getting fired in all positions when their company is making profits
EA treats each studio as a profit center. The layoffs were local to EA Los Angeles, which suggests that this particular studio didn't turn a profit, or at least missed their forecast. This might have been a move by the studio management to get their act together in order to give EA HQ less incentive to close down their entire operation. EA is not shy about shutting things down if they don't go well.
Another thing to consider is, that EA LA had the decency to lay off all 60 employees at once, thereby subjecting themselves to California's WARN provisions. This entitles everyone who was laid off to 60 days of continued salaries and benefits - on top of which they will most likely receive a severance package (as it is the case with most "without-cause" layoffs). EA could have easily weaseled out of this if they would have done smaller layoffs over a certain minimum period of time (they would have avoided bad press too!). Many companies actually do this and truly screw people over in the process.
I get the impression that the majority here likes to believe that companies such as EA are monolithic organizations, run by "the man" or small group of evil individuals who have direct involvement into whatever the company does. This is rather naive.
In most businesses (especially games), it usually it comes down to this: Individuals over commit, meaning they promise things they can't deliver (quality, profit, time). The higher these people happen to be the food chain, increasingly bigger parts of the organization will be affected by their bad judgment. In an attempt to compensate, this usually leads to all kinds of bad stuff, from crunching all the way to lay-offs. And if the individual happens to be the General Manager of a studio, the entire place might pay for it. And last time I checked, EA Los Angeles just got a new one.
Too bad Apple decided to release the iPod Shuffle after Christmas. They would have ruled holiday sales for flash-based players at that price point.
I know I would have at least picked up one or two as gifts...
I think this illustrates that there is a point when you become too large as a company to effectively produce games.
I disagree. "Lack of focus in the design vision" is a universal problem that can affect any company or team regardless of size. How about Nihilistic's StarCraft: Ghost (ship date still unknown after many years) or even Valve's Half-Life 2 (was supposed to ship over a year ago)?
If noise is an issue then Mini-ITX may be a good solution. I run a fanless 600 Mhz EPIA based system as a simple web client. With a DC power supply and a low-noise HD it's virtually inaudible.
Great. Let's stick with Valve's argument here: If the game isn't an official release, it's not appropriate to bench with it.
Oh and regarding honesty... someone should ask Valve how much money they got from ATI to show HL2 at their booth during E3 this year and not NVIDIA's, as it was orginally planned just weeks before the show. This farce has been going on for a while...
Slashdot Mirror
Regarding item 5...
256 GFlops is most likely the theoretical maximum assuming a prototype part running at 4GHz. Realistically it's probably much closer to half of that. And then it's still just an aggregate artificial figure. Considering all the other things a Cell CPU would have to do in addition to graphics, say, running other game systems, makes exclusive graphics processing on the Cell highly unlikely.
The Cell could probably assist with transform and lighting (vertex shaders) leaving the GPU with pixel/fragment shader processing. GPUs can do this more efficiently at significantly lower clock rates.
Whoa! You sure make a lot of unqualified, even inflammatory statements there. It had to be said.
First of all, the press release doesn't say anything about final clock speeds, just prototype results. Considering this, even Intel showed a 4GHz P4 at the IDF in 2002. That was three years ago, ancient times for all intents and purposes and look where we are today...
Sure, it's likely that a 4+GHz Cell CPU will be used sometime in the future for some applications, but I was talking about a Sony console here, a consumer device.
It will be subject to design constraints, mainly in the areas of reliability, form-factor and especially cost.
It's safe to assume that at clock speeds exceeding 3GHz the Cell chip will require some form of active cooling. The chip is subject to the same power leakage issues that all CPUs have these days, probably even more so at a 234 million transistor count. For example, at a much lower transistor count IBM's 90nm PPC 970 still doesn't run at 3GHz, let alone 4GHz. Granted, a direct comparison might not be possible, but it's a good indicator.
As a matter of fact, there are no consumer level devices available today runnning at 4GHz, not even desktop CPUs (unless you do some insane cooling).
Given all that, the question becomes, how much active cooling can Sony afford to put in an everyday living room device? The console has to be small and reasonably failsafe, too. Active cooling solutions require space and are a therefore a cost factor (see Xbox). Beyond that, if the console requires a more extensive cooling solution, the more expensive and less failure tolerant it will ultimately be.
Additionally, if we assume a $300-$400 price point and traditionally low yields for higher clocked chips at the early stages of manufacturing, I think 3 to 3.5GHz is a very reasonable, almost optimistic estimate.
Finally, that a gaming console can not afford to have any autonomous thermal management which might affect clock speeds goes without saying. It would have tremendous TRC implications. If you can't figure out why or what that means, you obviously never shipped a console game.
Good point.
Unless you manage to break down your systems or computational problems into eight digestible pieces and have an efficient flow of data between all the participants (especially given the tiny amounts of local RAM), you'd just have another glorified PowerPC CPU.
I don't think the final PS3 part will be clocked much higher than 3.5GHz. Otherwise it would probably involve downclocking parts of the CPU to maintain a sane thermal profile, thus making overall performance rather unpredictable. This would especially impact games, where it's all about sustainable framerates at 100% CPU utilization.
Another thing to consider is, that EA LA had the decency to lay off all 60 employees at once, thereby subjecting themselves to California's WARN provisions. This entitles everyone who was laid off to 60 days of continued salaries and benefits - on top of which they will most likely receive a severance package (as it is the case with most "without-cause" layoffs). EA could have easily weaseled out of this if they would have done smaller layoffs over a certain minimum period of time (they would have avoided bad press too!). Many companies actually do this and truly screw people over in the process.
I get the impression that the majority here likes to believe that companies such as EA are monolithic organizations, run by "the man" or small group of evil individuals who have direct involvement into whatever the company does. This is rather naive.
In most businesses (especially games), it usually it comes down to this: Individuals over commit, meaning they promise things they can't deliver (quality, profit, time). The higher these people happen to be the food chain, increasingly bigger parts of the organization will be affected by their bad judgment. In an attempt to compensate, this usually leads to all kinds of bad stuff, from crunching all the way to lay-offs. And if the individual happens to be the General Manager of a studio, the entire place might pay for it. And last time I checked, EA Los Angeles just got a new one.
Too bad Apple decided to release the iPod Shuffle after Christmas. They would have ruled holiday sales for flash-based players at that price point. I know I would have at least picked up one or two as gifts...
This has been around for a while (second link).
Off the Japanese NTT information site. No idea what it says, but it looks rather spiffy.
If noise is an issue then Mini-ITX may be a good solution. I run a fanless 600 Mhz EPIA based system as a simple web client. With a DC power supply and a low-noise HD it's virtually inaudible.
Great. Let's stick with Valve's argument here: If the game isn't an official release, it's not appropriate to bench with it.
Oh and regarding honesty... someone should ask Valve how much money they got from ATI to show HL2 at their booth during E3 this year and not NVIDIA's, as it was orginally planned just weeks before the show. This farce has been going on for a while...