[geeks] Game GPU clusters for supercomputering

[Joshua Boyd]

On May 23, 2008, at 12:35 AM, Patrick Giagnocavo wrote:

> Joshua Boyd wrote:
>> And of course, you can get Cell blades from IBM and Mercury.
>
> I have a client that is perfectly satisfied with nVidia GPU for  
> computing and has decided not to port to Cell.  Part of the reason  
> is cost, part of the reason is that nVidia is "good enough".  Also  
> Matlab has a plugin for the nVidia GPU, so he can quickly prototype  
> stuff.

I'm surprised they don't have a MatLab plugin for the Cell yet.

> I don't think they are very cheap.

The deskside unit is half the capacity of the rack unit, and the  
deskside unit is $5k.

>> The GPU stuff is cool looking, but there are a lot of things I  
>> like better about the Cells.  The Cells seem a bit more straight  
>> forward to program.  The Cells can take a lot more memory (first  
>> generation is 2 gigs per chip instead of 1.5 gigs, but the new  
>> model that just started shipping can take 32gigs per chip).  The  
>> Cells don't require a PC next to them.  And long term most  
>> importantly, the Cells seem to be much better in the documentation  
>> department.  With Nvidia, your choices are Cg, GLSL, or the CUDA C  
>> compiler.  The machine details aren't publicly documented.  With  
>> the Cell you have a lot of documentation and you have GCC, which  
>> means you have C, C++, Objective C, Fortran, and ADA.  I'm
>
> Just remember that being better technically doesn't necessarily  
> mean it will be a hit in the marketplace.

I know.  With the cost of IBM's blades being so expensive, and using  
the PS3 being so unprofessional, I fear that Cell might not win in  
the marketplace, and that would be terrible.

I really do like the GPU idea, but I will continue to have major  
qualms with it as long as they don't open up a lot more.