Gizmodo 
Enter your username and password.
Tip your editors:
tips@gizmodo.com
Editorial Director:
Brian Lam | Email | Twitter
Editor:
Jason Chen
Email | AIM | Twitter
Features Editor:
Wilson Rothman
Email | Twitter
Senior Contributing Editor:
Jesus Diaz
Email | AIM | Twitter
Mark Wilson, Reviews
Email | AIM | Twitter
Contributing Editors:
Matt Buchanan
Email | AIM | Twitter
Adam Frucci
Email | Twitter
Sean Fallon
Email | Twitter
Jack Loftus
Email | Twitter
John Herrman
Email | Twitter
Dan Nosowitz
Email
Chris Mascari
Email
Danny Allen
Email | Twitter
Columnist:
Brendan I. Koerner
Interns:
Don Nguyen
Email
Chris Jacob
Email
Comment Intern:
Nick Ellenoff | Email
Comment Account Questions:
Comments@gizmodo.com
Original material is licensed under a Creative Commons License permitting non-commercial sharing with attribution.
08/27/09
looks like the name 'snow leopard' is a good fit -- rare and fast.
there's a good article on the ever-feline mac os names over here: http://onthebutton.wordpress.com/2009/08/26/apple-snow-leopard/ worth a read.
08/27/09
08/29/09
08/27/09
That is not a valid concern, you don't overload the CPUs in that way the intruction set on the CPU stops it from happening, someone is giving you a mixed version of Windows.
You also miss the common problem with GCD you can only multi-thread as well as GCD can, if Adobe bring out a new version of PS that can multi-thread better than GCD then Windows gets that functionality and mac user do without.
Much like 64 bit PS.
08/27/09
08/27/09
so you could wind up with a situation where say, four apps try to use all 16 cores in your machine, when you'd rather they split up, with say one app using eight cores, another using four, and so on.
What's wrong with the app using up all cores of the machine? Right now, there are computers that only has a single core and capable of running several apps. It's not like every app is utilizing each CPU at 100% all the time. Therefore, if you spread the apps across all cores at the same time, you get better utilization per core.
08/27/09
@ripfire: It's better to have an application use core "A" to do one of it's tasks, and use the second core for task "B" simultaneously (which isn't being done.
It's like if you have a group of people helping you move out of your house, and everyone can move stuff by themselves and load it into a their own car.
Threading is similar in the sense that those 2 tasks are running simultaneously, but instead they are both being done on the same core/processor rather than multiple ones.
This would be like having the same group of people helping you move, but you only have one car to load everything into (or have multiple cars, but can only load the next car when the first has been filled).
Currently apps can thread, and will eventually use up multiple cores/processors, but they can't specifically use separate ones simultaneously (some can use multi processors, but not so much with the cores right now), and that's what this is about. (15th edit) Like what you said about single processor machines using multiple apps: the reason there is a separate graphics card for video processing is because it's efficient to keep those apart, same essential idea if you have multiple processor/cores being able to split up apps accordingly and properly it would be "mo' better".
Very few, if any, applications need to use all of the cores on a machine (or can at this time do so efficiently), so instead of multiple apps that are just using everything at once and on top of the next, it becomes far more efficient (in many ways including power consumption and task execution) to have one app using this core, and one app using the other cores.
Your method is fine (and how it's been forever now), but this method is better. :)
08/27/09
08/27/09
It would have been nice, though, if you had mentioned some of the other initiatives such as OpenMP and Charm++ and others that are more accessible to curious developers.
08/27/09
08/27/09
08/27/09
08/27/09
08/27/09
08/27/09
08/27/09
08/27/09
08/27/09
Kudos
08/27/09
08/27/09
05/13/09