i would like to recommend 'turing omnibus' and 'the magic machine' by a. k. dewdney. there are some available on amazon right now for $0.01 and $0.35 respectively! it is a collection of topics drawn from the old computer recreations column in scientific american. topics are laid out in pseudocode so it is not tied to any language in particular and thus remain timeless. really, no programmer's library is complete without at least one of these fine books.

depending on the nature of your research group (academic, government, military, private...) you may well be able to have cluster time free for the asking. from my experience you may have to 'apply for a grant' which is really filling out a form. the cluster i have access to has many nodes with 64 gig of ram and all nodes are stuffed with gpus as well. it never makes sense to spend money on computer equipment that you will spend a year or more learning to use. do as much development on borrowed equipment as you can and when you have working software already implemented, buy hardware as needed. good luck!

if you look at a graph of the stock price of silicon graphics (i just tried to get this at google finance, but the historical information was unavailable) you see it peaks right about the time windows 95 was released. up until then, anyone trying to do serious (be sure to screw your face into a grimace when you say that) computing turned to unix and shunned dos and win 3.1. but with the release of windows 95 people got more ambitious about what they thought could be accomplished with commodity hardware and windows. if only they realized that 15 years later they would be almost on par with *nix ;-)

i agree. i ran some memory through a week of memtest86 with no problems reported except that in the end, all my problems went away when i started swapping memory sticks and determined which one was the culprit.

save your money. if you really need time on a cluster you should apply for a grant from the ohio supercomputer center, ncsa, or investigate the offerings from your own institution. applying for a grant may sound daunting, but it really involves little more than filling out a form and asking for some cluster time. good luck!