|
我摘录部分内容:
Sunday, April 20, 2008
Alpha beta
Recursion is not possible on the GPU, because the processor on the GeForce 8800 has not stack. Therefore I needed to implement recursion with a state machine and a array which simulates the stackpointer.
Sunday, April 20, 2008
Parallel move generation
One of the advantages of using GPU's multiprocessors. Instead of generation all pseudo legal moves for a given chess position in sequence, I use 64 threads to generate all legal moves parallel!
Sunday, April 20, 2008
Evaluation of a chess position
Evaluation is done with 64 threads to count the value of the pieces
Friday, May 16, 2008
Sorting
Also sorting the moves ( captures first) is now done in parallel
Friday, May 16, 2008
Tiny chess engine running
After performing some tests I have a chess engine running as one block on a multiprocessor, using alpha/beta using killer moves as well
"Hieronymus said...
Currenty about 500.000 nodes a second. But the number does not mean so much since a lot of nodes are searched for nothing."
"Anonymous said...
How did you choose to use Nvidia/CUDA rather than ATI/Brook+? Would you be opening to programming instead on an ATI GPU?
June 18, 2008 11:01 PM
Hieronymus said...
I started with a prerelease of Cuda, early 2007, there was no alternative at that time. NVIDIA was the first one to make it available. I looked at Brook but I found CUDA more flexible"
Thursday, June 19, 2008
Beated by the GPU in Chess
Okay, I am not that strong player but I got beaten by my chess chess eninge written in CUDA running on a NVIDIA GeForce 8800 GTX. |
|