<span class="var-sub_title">GPGPU Performance Estimation with Core and Memory Frequency Scaling</span> SC18 Proceedings

The International Conference for High Performance Computing, Networking, Storage, and Analysis

GPGPU Performance Estimation with Core and Memory Frequency Scaling

Authors: Qiang Wang (Hong Kong Baptist University), Xiaowen Chu (Hong Kong Baptist University)

Abstract: Graphics processing units (GPUs) support dynamic voltage and frequency scaling to balance computational performance and energy consumption. However, simple and accurate performance estimation for a given GPU kernel under different frequency settings is still lacking for real hardware, which is important to decide the best frequency configuration for energy saving. We reveal a fine-grained analytical model to estimate the execution time of GPU kernels with both core and memory frequency scaling. Over a wide scaling range of both core and memory frequencies among 20 GPU kernels, our model achieves accurate results (4.83% error on average) with real hardware. Compared to the cycle-level simulators, our model only needs simple micro-benchmarks to extract a set of hardware parameters and kernel performance counters to produce such high accuracy.

Best Poster Finalist (BP): no

Poster: pdf
Poster summary: PDF
Reproducibility Description Appendix: PDF

Back to Poster Archive Listing