GPU: Pricing and Risk – C++ AMP

So you’ve installed VS 11 and a GPU. Now what? Here are some (obvious) thoughts from a financial services viewpoint:

• Pricing – leveraging the GPU for real-time interest rates pricing would be an obvious place to start (given my previous rates blogging)
• Risk – Obviously given the current market focus on risk, market risk GPU usage is the second obvious choice (given my previous rates blogging)

GPU’s, given their current price point, and their number of 3rd party tools, open to door for performance gains that don’t require pricy custom hardware 😉

I recall from Herb’s keynote that Microsoft is pushing C++ AMP as “open”. How long before NVIDIA offer C++ AMP support?

Open: I mentioned that Microsoft intends to make the C++ AMP specification open, and encourages its implementation on other C++ compilers for any hardware or OS target. AMD announced that they will implement C++ AMP in their FSA reference compiler. NVidia also announced support.

Learning to Engineer offer a view on the benefits of C++ AMP over OpenCL and CUDA:

The ideas presented in this example itself make me excited about this platform. We only have to write whatever data-parallel code we need and the runtime can take care of the details for us. This was the promise of OpenCL, but C++ AMP does take the concept further. There is no new language subset to account for the threading and memory models of GPUs. There is no need to worry about which compute node’s memory space the data is at. It also seems from this example that there is no need to size our workload for different thread and block counts like in CUDA; the runtime will handle that too.

~ by mdavey on September 29, 2011.