<r>I think DrFPGA makes some excellent points. A cheap way to get some experience with fpga at roughly one tenth the price of a virtex board is <URL url="http://www.fpga4fun.com/">http://www.fpga4fun.com/</URL>. Also checkout ISE webpack, it's relatively easy to get some simple bit files together, t...

uninitialised variables are a common cause for this difference in behaviour, try valgrind or purify

pthread_t id = GetCurrentThreadID();

<t>yeh what do you need to know? valgrind{ helgrind,cachegrind,callgrind} is excellent for identifying race conditions, monitoring cache usage and calls executed, respectively. The latter has almost excruciating detail, you may want to use callgrind_annotate to summarise the profile data. There's lo...

we have an old federal home (~1860) in the US built over a cave system & subterranean creek; without a dehumidifier running there's a veritable swimming pool in the basement

I've used and would recommend reactor based patterns for this problem, eg., there's some solutions discussed here -> http://www.artima.com/articles/io_design_patterns2.html

can you set something like -fpe0 -traceback ala intel?

save yourself the hassle of manipulating bits for lack of an unsigned type (therein lies much anguish for C developers) and use bytebuffer

+1 scala; you might also check out functionaljava.org, I've hacked with this. The Sun java langspec is also a good read.

<r>what platform? Thrust (CUDA) has a merge sort, or you could check this out -> <URL url="https://wiki.cc.gatech.edu/multicore/index.php/Parallelizing_Sort_Algorithms"><LINK_TEXT text="https://wiki.cc.gatech.edu/multicore/in ... Algorithms">https://wiki.cc.gatech.edu/multicore/index.php/Parallelizi...

there's an example of a bitonic sort in gpu gems; thrust is an excellent STL-like CUDA template library with a few examples too

<t> acceleration==second derivative. After SplineUnderTension class instance foo is created with x/y data, a new point is simply foo.getInterpValue(x_new) etc. This method is robust w/ noise and large derivatives, very good for seismic data. a quick google reveals a few interesting talks on the subj...

<t>I dunno how helpful this-I'm in oil+gas- but I had to port some fortran to Java dealing with Cline's spline under tension; here's some untested C++, a quick'n'dirty port of the java. The method is particularly stable with regards to calculating the 2nd derivative, apologies in advance if I'm way ...

should be some references hereI highly recommend spike/pspike by Sameh, schenk et al for those who want something highly scalable and alternative to precon krylov type solutions (I don't know if pspike is in the public domain yet)

I have no doubt -in fact the codebase is going to amg ultimately- when we get there I think the plan is saad et als miluot