FiNS paper is now available!

FiNS: A Framework for Accelerating Nested Simulations on Heterogeneous Platforms

Our work on accelerating financial nested simulations with GPUs is recently published in the Europar ’15 workshop proceedings.

We managed to submit and present a representative paper of our work on accelerating nested simulations (simulations within simulations) for the HeteroPar workshop in August 2015, in Vienna. This month the conference proceedings were published thus so is our paper. The research is performed by Joris Cramwinckel where he researched a brute force approach for Solvency II requirements.

Solvency II regulations require insurers to use advanced risk management models to, among other things, compute required capital for different sources of financial risks. In these models the application of nested simulations becomes increasingly important. To keep computation times within acceptable limits high-performance computing is required. In this work we present a framework designed to significantly improve the performance of nested simulations by using heterogeneous computing. Specifically, we use modern features from CUDA — streams, Hyper-Q, and Multi-Process Service — to take full advantage of the massive parallelism of modern GPUs. We manage to reduce the execution time of such simulations from several hours to tens of minutes.


This Europar ’15 contribution is available in the Conference proceedings or can be downloaded as a chapter at Springer. The earlier working paper version can be requested by email via:

Like what you read? Give Tech Labs a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.