Take the 2-minute tour ×
Mathematica Stack Exchange is a question and answer site for users of Mathematica. It's 100% free, no registration required.

I'm upgrading my Mac to one of the new Mac Pro R2D2 Darth Vader models that have just been released. They come standard with twin AMD FirePro D300 cards, or twin D500 cards. I don't need that much graphics processing power, and since I understand the D500 puts out a lot more heat than the D300, and I really don't like fan noise ... I was going to go for the D300s.

However, Apple's Mac Pro blurb says:

The FirePro D500 supports fast double-precision computations, executing at one-quarter the performance of single-precision floating point rather than the 1/16 performance seen in the D300 and most consumer GPUs

And this got me wondering: If GPUs support double precision numerics, is it possible currently (or in the works??) for Mathematica to AUTOMATICALLY take advantage of the massive teraflop GPU power for numerical computations? I don't want to have to specially load CUDALink libraries or to write special code or to specially load OpenCL functions … I just want to use standard Mathematica functions.

In brief:

Can Mathematica automatically take advantage of the new Mac Pro GPU for numerical calculations? If not, I think I'll stick with the quieter, cooler D300 GPU, … and max something else out!


Addendum: Apple's new Autovectorizer in OSX Mavericks

https://developer.apple.com/library/mac/documentation/Performance/Conceptual/OpenCL_MacProgGuide/AutoVectorizer/AutoVectorizer.html#//apple_ref/doc/uid/TP40008312-CH7-SW1

Using OpenCL is easier than ever as of OS X v10.7: The autovectorizer allows you to write one kernel that runs efficiently on both a CPU and a GPU. You can invoke the autovectorizer regardless of whether you are compiling from Xcode or building the kernels at runtime.

share|improve this question
1  
Related: stackoverflow.com/q/8638905/618728 –  Mr.Wizard Dec 21 '13 at 15:42
1  
No, the current version (v9) won't do any operations faster if you have a fast GPU. You have to use OpenCLLink and use the GPU explicitly. CUDA does not work with AMD cards. –  Szabolcs Dec 21 '13 at 16:09
    
To be fair, I did notice the Image`GPUEnabledQ symbol the other day, but the current version doesn't seem to automatically take advantage of the GPU for image processing either. –  Szabolcs Dec 21 '13 at 16:09
    
Buy a nice display instead! (And keyboard and mouse too...:) As you can tell, I'm just jealous really... –  cormullion Dec 21 '13 at 16:19
    
@MrWizard Thanks for that - though that page is from 2011 ... and I believe things have been changing, as the new OS X Mavericks (the latest release of OSX) apparently features integrated OS support for OpenCL, including in XCode. Not sure if that makes any difference for Mma, or future versions of Mma?? –  wolfies Dec 21 '13 at 16:30

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.