SETI to Upgrade Software, Telescope

Professor_Quail writes "Space.com reports that SETI@home is planning to transfer it's operations from Arecibo to another telescope in Australia, where they say lies an increased chance of finding extra-terrestrials. The Australian telescope is more powerful, with a wider view of the sky; scientists are betting that this new telescope will also help find signs of 'shriveling' black holes."

Comments

The difference with SETI@home

[Anonymous Coward]

One thing that makes me continue to run SETI@home instead of more "practical" applications like protein folding is the simple fact that SETI@home will not generate money for the originators of the project. The results of protein folding and AIDS research will ultimately result in some people getting filthy rich, and if they want that they can bloody well do the work themselves.

Optimizations

[Perdo]

Take a clue from KLAT2

"KLAT2's 80/64-bit double-precision performance is around 22.8 GFLOPS, a very respectable number. Then again, using 3DNow!, KLAT2's single-precision ScaLAPACK performance zips to over 64 GFLOPS"

Optimize clients for different architectures. MMX, 3Dnow!, SSE, SSE2, Altivec, Hyper threading, x86-64 etc.

Might be nice to jump from 50 Tflops/s to 150/s just by using processor specific instructions.

Since the client will be open source, users may try it anyway but perhaps SETI could offer some kind of contest to insure the code gets audited properly.

For programmers out there, imagine placing "Optimized code for the largest distributed computing project in the world, resulting in a threefold increase in performance" in your resume.

Being personally responsible for adding 100 Tflop/s to seti@home beats the hell out of running clients on a few idle machines.