Thread: 69 * 2^n - 1
View Single Post
Old 2013-09-26, 04:04   #14
VBCurtis
 
VBCurtis's Avatar
 
"Curtis"
Feb 2005
Riverside, CA

3·31·43 Posts
Default

CUDA-LLR is available, and in my experience stable. It only uses power-of-2 FFT sizes, and speed improves with larger exponents. The main FFT jump we care about is just over 3M for k=69, so your Teslas would be most useful in the upper 2M range, or over 5M (relative to CPU workers, that is).

Check in the hardware/GPU computing forum- I didn't see the thread when I glanced, but I've been running the program for over a year, even found a prime for k=5 with it in the 3-megabit range.
-Curtis
VBCurtis is offline   Reply With Quote