HPAC: Evaluating Approximate Computing Techniques on HPC OpenMP Applications

Authors: Konstantinos Parasyris, Giorgis Georgakoudis, Harshitha Menon, James Diffenderfer, Ignacio Laguna, Daniel Osei-Kuffuor, and Markus Schordan (Lawrence Livermore National Laboratory)

Abstract: As we approach the limits of Moore’s law, researchers are exploring new paradigms for high-performance computing (HPC) systems. Approximate computing gained traction by promising to deliver computing power. However, due to the stringent accuracy requirements of HPC scientific applications, the adoption of approximate computing methods in HPC requires an in-depth understanding of the application’s amenability to approximations.

We develop HPAC, a framework with compiler and runtime support for code annotation and transformation, and accuracy vs. performance trade-off analysis of OpenMP HPC applications. We perform an analysis of the effectiveness of approximate computing techniques when applied to HPC applications. The results reveal possible performance gains of approximation and its interplay with parallel execution. For instance, approximation in the LULESH proxy application provides substantial performance gains due to the reduction of memory accesses. However, approximation in the leukocyte benchmark induces load imbalance in the parallel execution and thus limiting the performance gains.




Back to Technical Papers Archive Listing