On 04/30/2013 02:08 AM, Christopher LILJENSTOLPE wrote: > Supposedly, on 2013-Apr-22, at 06.19 PDT(-0700), someone claiming to be Loic > Dachary scribed: > >> Hi Christopher, >> >> Jack Lloyd is the author of fecpp ( http://www.randombit.net/code/fecpp/ ) >> and he tells me someone sent him a new SIMD approach a few weeks ago. I'm >> not sure what SIMD means yet, but I'll figure it out ;-). I tend to favor >> fecpp because it is more self contained and may be easier to embed than >> https://pypi.python.org/pypi/zfec > > I'll defer, provided that we don't incur a performance penalty (which is one > of the negatives in sharding). As far as SIMD: Single Instruction Multiple > Data. Basically, if you think of a tiled processor (like a GPU), then you > set all the tiles to do the same instruction, and stream different data to > each tile. As opposed to MIMD, where each tile runs a different instruction > on different data. You don't need parallel processing CPUs to make use of > SIMD, but you can get them going screamingly fast if you do…
Hi Christopher, Thanks for explaining :-) Although it seems disk / network I/O are the bottleneck, it's good to be able to reduce the processing footprint to a minimum. Cheers > > Christopher > >> >> Cheers >> >> -- >> Loïc Dachary, Artisan Logiciel Libre > > > -- > 李柯睿 > Check my PGP key here: http://www.asgaard.org/cdl/cdl.asc > Current vCard here: http://www.asgaard.org/cdl/cdl.vcf -- Loïc Dachary, Artisan Logiciel Libre
signature.asc
Description: OpenPGP digital signature
