GMP on the Cell processor

[Linas Vepstas]

On Tue, Apr 17, 2007 at 10:16:07PM +0200, Michael Abshoff wrote:
> The great performance for numerical applications comes
> from the fact that you can achieve up to 200 GFlops *single* precision and
> about 1/14 of that for *double* precision 

This will get fixed in the next version. The guys who designed the first
version had thier blinders on; it never occured to them that it would 
be used for anything else but games (!) (I used to team-lead some of
those guys, wayy before cell, and yes, that's how they think, and so 
I want to whack them upside the head, just like I used to...)
Of course, Sandia national labs is thinking about building a supercomputer 
from the fixed version.

> all the SPEs in parallel. The Power Core just feeds the SPEs. The SPEs
> also supposedly provide integer operations and because each SPE has 128
> 128bit registers there is certainly potential. 

The carry bits can be sliced-n-diced every which way, so you can run
oodles of parallel 16-bit and 32-bit ops.

> provided somebody does
> start to port 

To be clear, despite my email address, I'm contemplating this only
as a gee-gooly, goof-off-on-the-side project.  Just to be clear about
this, and not mislead anyone....

> If you own a PS3 you can install Linux and have access to 6 SPEs because

Particularly remarkable is the "protein folding at home" project, which
Sony ported to the PS3. This is a massive numerical simulation, where 
the goal is to minimize the quantum mechanical energy of an arrangement
of thousands of atoms (the protien).  What's remarkable are the
statistics coming out of this:

http://fah-web.stanford.edu/cgi-bin/main.py?qtype=osstats

There are 32K PS/3s running the thing, delivering almost half a
petaflop.  Compare this to about 200K intel boxes delivering 
200 teraflops (1/5 of a petaflop). So the possibilities are there.
(Although, to first order, its really just number of cores times clock
speed.)

--linas