>Sadly, your acid_demeanor precludes you from such opportunities. So if you change your mind and want to take a professional approach to palidromes, you >might just establish some new friendships. Think things over a bit and let me know should you want to access more aggressive resources. YES, you can run >gentoo on those HPC resources. Off the record, have you tried a systolic algorithm and using rDMA via the DDR5 on a collection of GPUs to speed up >your search? James
GPU is appealing, the problem is ammble to a high degree of partitioning. There is some benefit to working blocks sequentially due to arithmetic redundancy. Now the main issue is that keith's approach is to use an immense lookup table to use a radix approach. Basically if your start is "abc" then here are 10 or so things you can add to get "cba" on the tail end, this saves many millions of useless tests. The bigger the lookup table the faster the algorithm... (currently around 25gb) I am using some AMD specific features, I haven't tried to port it to intel. -- IQ is a measure of how stupid you feel. Powers are not rights.
