Difference between revisions of "CoE Cluster April 2012"

From Teknologisk videncenter
Jump to: navigation, search
m
m
Line 7: Line 7:
 
*[[/CUDA|Programmering med CUDA]]
 
*[[/CUDA|Programmering med CUDA]]
 
=Results=
 
=Results=
Having investigated CUDA C programming for Nvidia graphics cards and the CUDA architecture, we made some performance measurements using a range of numbers of blocks and threads, executing in parallel.  The test program calculated values of the [Mandelbrot Set |http://en.wikipedia.org/wiki/Mandelbrot_set] on a pixel-by-pixel basis.
+
Having investigated CUDA C programming for Nvidia graphics cards and the CUDA architecture, we made some performance measurements using a range of numbers of blocks and threads, executing in parallel.  The test program calculated values of the [http://en.wikipedia.org/wiki/Mandelbrot_set Mandelbrot Set ] on a pixel-by-pixel basis.
  
 
*[http://mars.tekkom.dk/js/cuda_benchmark.htm CUDA Benchmark] (External JavaScript)
 
*[http://mars.tekkom.dk/js/cuda_benchmark.htm CUDA Benchmark] (External JavaScript)

Revision as of 07:59, 1 May 2012

{{#img: image=Super-computer-artw.jpg | page=Linux Cluster til Center of Excelence/Beskrivelse til CoE West | width=200px | title=Linux Supercomputer projekt }}

Assignments

Results

Having investigated CUDA C programming for Nvidia graphics cards and the CUDA architecture, we made some performance measurements using a range of numbers of blocks and threads, executing in parallel. The test program calculated values of the Mandelbrot Set on a pixel-by-pixel basis.


Mpi mandelbrot.png

Mandelbrot Set drawn in 1,2 seconds, using a Master-Worker MPI pattern with 16 worker nodes and 1 master node (which collected calculated results from different parts of the image and output them to an X Window). Total image dimension 800 x 800 pixels.

Cuda mandelbrot.png

Mandelbort Set drawn in 0,12 seconds, using a single NVidia CUDA capable graphics card (GeForce GTX 460) running 32 blocks and 128 threads in each block. Total image dimension 512 x 512 pixels.

[CUDA Benchmarking Results]

Slides

Litteratur Liste

Evaluering