I have never tried it out by myself. In the next 3 years some GPUs will have 20 000 cores.
Looking at this http://jogamp.org/jocl/www/ benchmark it is a huge difference between GPU and CPU code. In Aparapi http://blogs.amd.com/developer/2011/09/14/i-dont-always-write-gpu-code-in-java-but-when-i-do-i-like-to-use-aparapi/ you write everything in Java. On Fri, Apr 6, 2012 at 3:28 PM, Andreas Prlic <[email protected]> wrote: > Do you have any experience with that? I don;t have first hand, but > from what I know GPU programming is very much hardware specific and > not as nicely platform independent as Java... > > Andreas > > On Thu, Apr 5, 2012 at 6:37 PM, Mic <[email protected]> wrote: > > maybe also to include OpenCL in order to able to run it on GPU. > > > > On Fri, Apr 6, 2012 at 1:49 AM, Andreas Prlic <[email protected]> wrote: > >> > >> Hi Arthur, > >> > >> > 1) The first one and the one i find most interesting can be to try to > >> > introduce the map-reduce framework to help to speed-up the pairwise > >> > alignment in the creation of the muliple sequence alignment. > >> > >> That would be a possible application. > >> > >> > 2)If the input files are big enough, it can be interesting to perform > >> > the > >> > parsing on this files while using a distributed infrastructure to > >> > speedup > >> > the process, > >> > >> I am not sure if I have encountered such large files as of yet. Do you > >> have an example? > >> > >> > 3)Another idea can be to try to have a hadoopify version of blast, in > >> > which > >> > the input file also can be splitted and then for each sequence in a > >> > chunk, > >> > the node would perform a local blast query. > >> > >> I agree, another possible application... > >> > >> What frameworks did you think about using? > >> > >> Andreas > >> _______________________________________________ > >> Biojava-l mailing list - [email protected] > >> http://lists.open-bio.org/mailman/listinfo/biojava-l > > > > > > > > -- > ----------------------------------------------------------------------- > Dr. Andreas Prlic > Senior Scientist, RCSB PDB Protein Data Bank > University of California, San Diego > (+1) 858.246.0526 > ----------------------------------------------------------------------- > _______________________________________________ Biojava-l mailing list - [email protected] http://lists.open-bio.org/mailman/listinfo/biojava-l
