5

I want to start to write applications(C++) that will utilize the additional cores to execute portions of the code that have a need to perform lots of calculations and whose computations are independent of each other. I have the following processor : x64 Family 15 Model 104 Stepping 2 Authentic AMD ~1900 Mhz running on Windows Vista Home premium 32 bit and Opensuse 11.0 64 bit.

On the Intel platforms , I've used the following APIs Intel TBB, OpenMP. Do they work on AMD and does AMD have similar APIs.what has been your experience?

ndim
  • 35,870
  • 12
  • 47
  • 57
iceman
  • 4,211
  • 13
  • 65
  • 92

1 Answers1

6

OpenMP and TBB are both available also for AMD - it is also a compiler question. E.g. see linux TBB on AMD.
I think the latest development on this end is to use the graphic card via CUDA or similar APIs- but this depends on the nature of your calculations. If it fits, it is faster than the CPU anyway.

weismat
  • 7,195
  • 3
  • 43
  • 58
  • CUDA is very specific business indeed, since the GPU are optimized for 1 operation applied to several 'datum' at once. – Matthieu M. Oct 26 '09 at 15:37
  • My laptop has a Nvidia card (6150 Go)... how can i get started ? – iceman Oct 27 '09 at 10:19
  • Is there any link where someone has tried TBB on a AMD and discussed instrumentation results or given some performance benchmarks? Is there a AMD equivalent of the TBB library at developer.amd.com ? – iceman Oct 27 '09 at 23:12
  • (shameless plug for my own technology) - Visual Studio 2010 Beta 2 released last week, so please be sure check out the Parallel Pattern Library and Asynchronous Agents Library which run great on x64 intel & amd. – Rick Oct 28 '09 at 03:22