I would like to apply GPU computing to my existing parallel CFD code (incompressible) which is written in C. How do I start. I heard that there are two platforms exists, CUDA and AMD FUSION which is preferred in terms of simplicity and speed
Where do I start ,What are the books, thesis available online
Thanks in advance
Do you have access to both Tesla machines and AMD Fusion machines ?
Tesla machine cost upwards of 10,000 US Dollars here in India.
What I have heard from my friends who have worked with CUDA is that you will end up rewriting almost the entire parallelization part of your solver.
So it will be a long and non-trivial process.
To start with Can I use lower end CUDA enabled graphics cards like QUARDO/GTX for scientific computing ?
|All times are GMT -4. The time now is 11:13.|