TY - GEN
T1 - GPGPU Performance Estimation with Core and Memory Frequency Scaling
AU - WANG, Qiang
AU - CHU, Xiaowen
N1 - Funding Information:
This work is supported by Shenzhen Basic Research Grant SCI-2015-SZTIC-002.
PY - 2019/2/19
Y1 - 2019/2/19
N2 - 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 2× 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 without kernel source analysis.
AB - 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 2× 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 without kernel source analysis.
KW - Dynamic Voltage and Frequency Scaling
KW - GPU Performance Modeling
KW - Graphics Processing Units
UR - http://www.scopus.com/inward/record.url?scp=85063339905&partnerID=8YFLogxK
U2 - 10.1109/PADSW.2018.8645000
DO - 10.1109/PADSW.2018.8645000
M3 - Conference proceeding
AN - SCOPUS:85063339905
T3 - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS
SP - 417
EP - 424
BT - Proceedings - 2018 IEEE 24th International Conference on Parallel and Distributed Systems, ICPADS 2018
PB - IEEE Computer Society
T2 - 24th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2018
Y2 - 11 December 2018 through 13 December 2018
ER -
