69. Black-Box Kernel-Level Performance Modeling For GPUs
Authors: James D. Stevens (University of Illinois)Andreas Klöckner (University of Illinois)
Abstract: We present a mechanism to symbolically gather performance-relevant operation counts from numerically-oriented subprograms ("kernels") expressed in the Loopy programming system, and apply these counts in a simple, linear model of kernel run time. We use a series of "performance-instructive" kernels to fit the parameters of a unified model to the performance characteristics of GPU hardware from multiple hardware generations and vendors. We evaluate predictive accuracy on a broad array of computational kernels relevant to scientific computing. In terms of geometric mean, our simple, vendor- and GPU-type-independent model achieves relative accuracy comparable to that of previously published work using hardware specific models.
Two-page extended abstract: pdf