Benchmark-based Study of CPU/GPU Power-Related Features through JAX and TensorFlow
Authors:
- Roblex Nana TchakouteRTRoblex Nana Tchakoute
- Claude TadonkiCTClaude Tadonki
- Petr DokladalPDPetr Dokladal
- Youssef MesriYMYoussef Mesri
Preprint
Abstract
Power management has become a crucial focus in the modern computing landscape, considering that {\em energy} is increasingly recognized as a critical resource. This increased the importance of all topics related to {\em energy-aware computing}. This paper presents an experimental study of three prevalent power management techniques that are {\em power limitation, frequency limitation}, and {\em ACPI/P-State governor modes} (OS states related to power consumption). Through a benchmark approach with a set of six computing kernels, we investigate {\em power/performance} trade-off with various hardware units and software frameworks (mainly TensorFlow and JAX). Our experimental results show that {\em frequency limitation} is the most effective technique to improve {\em Energy-Delay Product (EDP)}, which is a convolution of energy and running time. We also observe that running at the highest frequency compared to a reduced one could lead to a reduction of factor $\frac{1}{10}$ in EDP. Another noticeable fact is that frequency management shows a consistent behavior with different CPUs, whereas opposite effects sometimes occur between TensorFlow (TF) and JAX with the same power management settings.
Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Comprehensive analysis of energy efficiency and performance of ARM and RISC-V SoCsThe Journal of Supercomputing, 2024
- The growing energy footprint of artificial intelligenceJoule, 2023
- Benchmarking the Performance and Energy Efficiency of AI Accelerators for AI Training2020
- GPU Computing with Python: Performance, Energy Efficiency and UsabilityComputation, 2020
- Scalability analysis of AVX-512 extensionsThe Journal of Supercomputing, 2019
- An analytical methodology to derive power models based on hardware and software metricsComputer Science - Research and Development, 2015
- Towards a generic power estimatorComputer Science - Research and Development, 2014