Section: New Results

Other Architecture Studies

Participants : Damien Hardy, Pierre Michaud, Ricardo Andrés Velásquez, Sylvain Collange, André Seznec, Sajith Kalathingal, Junjie Lai.

GPU, performance, simulation, vulnerability

In the framework of the ANR Cosinus PetaQCD project (ended Oct 2012), we have been modeling the demands of high performance scientific applications on hardware. GPUs have become popular and cost-effective hardware platforms. In this context, we have been addressing the gap between theoretical peak performance on GPU and the effective performance. There have been many studies on optimizing specific applications on GPU and also a lot of studies on automatic tuning tools. However, the gap between the effective performance and the maximum theoretical performance is often huge. A tighter performance upperbound of an application is needed in order to evaluate whether further optimization is worth the effort. We designed a new approach to compute the CUDA application's performance upperbound through intrinsic algorithm information coupled with low-level hardware benchmarking. Our analysis [11] , [22] allows us to understand which parameters are critical to the performance and have more insights of the performance result. As an example, we analyzed the performance upperbound of SGEMM (Single-precision General Matrix Multiply) on Fermi and Kepler GPUs. Through this study, we uncover some undocumented features on Kepler GPU architecture. Based on our analysis, our implementations of SGEMM achieve the best performance on Fermi and Kepler GPUs so far (5 % improvement on average).