Imperial College London > Talks@ee.imperial > CAS Talks > Approaching the Peak GPU Performance in FPGAs for Scientific Computing

Approaching the Peak GPU Performance in FPGAs for Scientific Computing

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

If you have a question about this talk, please contact Grigorios Mingas.

We consider the problem of enabling fixed-point implementations of linear algebra kernels to match the strengths of FPG As. Algorithms for solving linear equations, finding eigenvalues or finding singular values are typically nonlinear and recursive making the problem of establishing analytical bounds non-trivial. Current approached fail to provide tight bounds for this type of algorithms. We use as a case study one of the most important kernels in scientific computing, the Lanczos iteration, and we show how we can modify the problem to allow us to apply standard linear algebra analysis to prove tight analytical bounds on all variables of the process, regardless of the properties of the original matrix. It is shown that the numerical behaviour of fixed-point implementations of the modified problem does not have to be worse than a double precision floating point implementation. Using this approach it is possible to get very close to the peak GPU performance in FPG As of comparable size when solving a single problem.

This talk is part of the CAS Talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Changes to Talks@imperial | Privacy and Publicity