Friday, April 30, 2010

Laboratoire Jacques-Louis Lions - Paris VI: Gaspard2 and OpenCL Presentation

Global Synchronization??

ATI Radeon™ HD 5870 (“Cypress”) Architecture (2009) has Global Synhcronization. According to its specification:
2.72 Teraflops Single Precision,544 Gigaflops Double Precision
  • Full Hardware Implementation of DirectCompute 11 and OpenCL™ 1.0
  • IEEE754-2008 Compliance Enhancements
  • Additional Compute Features:
  • 32-bit Atomic Operations
  • Flexible 32kB Local Data Shares
  • 64kB Global Data Share
  • Global synchronization
  • Append/consume buffers
I searched for more information about it, examples in OpenCL, etc. but I didn't find. If you have any tips...write me.

Thursday, April 22, 2010

Eyeon Software Unveils Fusion 6.1 with OpenCL Supercomputing

From Khronos Group News:

Fusion 6.1 now supports the OpenCL language, which allows tools to take advantage of the GPU in modern NVIDIA and ATI graphics cards to achieve tremendous speed increases. Benchmarking improvements of up to 1000% on some of the most processor-intensive tools in Fusion (such as Defocus and Noise generators) have been reached. You can also insert OpenCL code directly into Fuse tools to create in-house GPU-accelerated tools.
http://www.eyeonline.com/Web/EyeonWeb/Press/DisplayArticle.aspx?articleid=406

Tuesday, April 13, 2010

Code Generation for OpenCL (Prezi Presentation)

I'm working hard to code our compiler to opencl source code. Meanwhile, I posted this presentation made on Prezi for the Valeo PhD Students Seminary.