Slashdot Mirror


Impressive Benchmarks: Sorting with a GPU

An anonymous reader writes "The Graphics research group at the University of North Carolina at Chapel Hill has posted some interesting benchmarks for a sorting implementation which is done entirely on a GPU. There have been efforts on doing general purpose computation on GPUs before (previous Slashdot article). However, most of them had generally utilized the fragment processing pipeline of the GPUs which is slower then the default high speed rendering pipeline. Apparently, the above implementation is done using "simple texture mapping operations" and "cache efficient memory accesses" only. There also seems to an option to download the distribution for non-commercial use, though the requirements seem pretty hefty (a very decent nVidia graphics card and the latest nVidia drivers)."

2 of 222 comments (clear)

  1. Whats new with this? by McNihil · · Score: -1, Flamebait

    Exactly... did similar things with Amiga back in 1986... TWENTY YEARS AGO!!! In 1990 I told my prof that that was the way it should be done... with a 2D blitter calculation approach... way faster than anything at that time... but I was ignored... as I will be in this post... Eff Intel and Eff MS and mark my words that we are 20 years behind in technology. Lameass Mores law! Go and eff yuourselves x86 camp.

  2. Re:I knew somebody who did math on a "blitter" by LiquidCoooled · · Score: 0, Flamebait

    Without this yobbo, you wouldn't have a job.

    --
    liqbase :: faster than paper