NVIDIA envisions GPU in 2013

Posted on Tuesday, Aug 26 2008 @ 04:33 CEST by Thomas De Maesschalck
PC Perspective published live coverage of NVISION Day 1, you can check it out over here. The keynote didn't seem that interesting as it was mainly a rehash of things we've already seen before but the session about Evolution of Computer Graphics and High Performance Computing contained some interesting snips.

The slides unveil the GPU of 2013 will embrace many features found in the CPU, five years from now GPUs are expected to have full support for C++, complete pointer support, adaptive workload partitioning, preemption and virtual pipeline.

Here are some performance figures, lots of tera figures here. NVIDIA expects a high-end GPU in 2013 will offer over 20 teraFLOPS of computing power, that's 20x as much as today.

GPU 2013:
  • Arbitrary dataflow
  • General purpose programming model
  • Special purpose hardware
  • Hardware managed threading and pipelining
  • Freely intermingle "graphics" & computation

  • About the Author

    Thomas De Maesschalck

    Thomas has been messing with computer since early childhood and firmly believes the Internet is the best thing since sliced bread. Enjoys playing with new tech, is fascinated by science, and passionate about financial markets. When not behind a computer, he can be found with running shoes on or lifting heavy weights in the weight room.

    Loading Comments