Accelerator: A data-parallel DSL for programming heterogonous systems

Add to your list(s) Download to your calendar using vCal

• Satnam Singh, Microsoft Research
• Wednesday 13 January 2010, 16:30-17:30
• SS03, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Prof Simon Moore.

This presentation introduces Microsoft’s Accelerator system which is a library that provides data-parallel arrays and operations which can be implemented on GPUs, x64 SIMD multicores and FPG As. The library can be used from C++ or any .NET language e.g. C# or F#. We make the case that for certain kinds of computations this system provides a way to write a computation once and then have it instantiated on wildly different kinds of computing resources. We will also highlight differences between Accelerator and other technologies e.g. CUDA , OpenCL and Ct.

This talk is part of the Computer Laboratory Computer Architecture Group Meeting series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge talks
• Computer Laboratory Computer Architecture Group Meeting
• Department of Computer Science and Technology talks and seminars
• Interested Talks
• SS03, Computer Laboratory, William Gates Building
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31

Note that ex-directory lists are not shown.