Submit Hint Search The Forums LinksStatsPollsHeadlinesRSS
14,000 hints and counting!

Click here to return to the ' Power Cell (Gaming Mac; NOT console part II)' hint
The following comments are owned by whoever posted them. This site is not responsible for what they say.
Power Cell (Gaming Mac; NOT console part II)
Authored by: dcoyle on Dec 22, '06 01:51:10PM

I'll assume Magnus Dredd's specs (earlier post) are what a serious gamer would want (I'm not one). I would add to that one or more Power Cell co-processors. Google up "power cell processor board" and you'll see a plethora of PCIe boards available for your average PC. With Apple's PowerPC experience and resources, I don't think it would take a whole lot of engineering to do the same thing a whole lot better.

While originally an Intel-switch skeptic, I have to agree now that this was a smart move on Apple's part for a lot of reasons. The new Core 2 line makes incredible sense for a general purpose processor. However, for things the Cell is good at, nothing can touch it.

It's easy to imagine certain functions like DVD-encoding being off-loaded to Cell processor(s) in the same way certain things are handed off to a GPU with Quartz Extreme. Apple has already perfected Universal binaries, so it would take very little to ship applications like Final Cut that has both the Intel binaries for routine program tasks and Power Cell binaries to make audio/video things happen really, really fast. It also doesn't seem like it would take much to add all the developer functionality to X-Code since they already do Intel and PowerPC.

While TV studios and Hollywood would certainly benefit from the extra speed and functionality Cell would provide (which would benefit Apple's bottom line), gamers would probably be the biggest winners. Getting access to console games at the same time and with the same or better speed/playability, since all the developers would have to do is port Cell-on-console code to Cell-on-Mac, would probably get a whole lot of people interested in Macs.

[ Reply to This | # ]