对比三款AI框架在RISC-V服务器上的耗能表现
Exploring energy consumption of AI frameworks on a 64-core RV64 Server CPU
- 测试三种框架在64核RISC-V CPU上的推理能耗
- 使用XNNPACK后端的框架更省电，低至PyTorch的60%
- 为开源芯片生态优化算法提供实证依据
在人工智能应用对大规模、高性能、数据密集型计算需求日益增长的背景下，其能源消耗问题愈发突出。解决这一挑战需要软硬件协同创新。硬件方面，基于开放、可扩展、节能指令集架构（ISA）的RISC-V正成为关键方向；软件方面，尽管新算法与框架不断涌现，但其能效特性仍不明确。本研究针对64核SOPHON SG2042 RISC-V架构，对主流机器学习应用进行全面基准测试，重点分析深度学习推理模型在PyTorch、ONNX Runtime和TensorFlow三个主流框架中的能耗表现。结果表明，采用XNNPACK后端的ONNX Runtime和TensorFlow相比使用原生OpenBLAS后端的PyTorch，能显著降低能耗。
原文摘要 · Abstract (English)
In today's era of rapid technological advancement, artificial intelligence (AI) applications require large-scale, high-performance, and data-intensive computations, leading to significant energy demands. Addressing this challenge necessitates a combined approach involving both hardware and software innovations. Hardware manufacturers are developing new, efficient, and specialized solutions, with the RISC-V architecture emerging as a prominent player due to its open, extensible, and energy-efficient instruction set architecture (ISA). Simultaneously, software developers are creating new algorithms and frameworks, yet their energy efficiency often remains unclear. In this study, we conduct a comprehensive benchmark analysis of machine learning (ML) applications on the 64-core SOPHON SG2042 RISC-V architecture. We specifically analyze the energy consumption of deep learning inference models across three leading AI frameworks: PyTorch, ONNX Runtime, and TensorFlow. Our findings show that frameworks using the XNNPACK back-end, such as ONNX Runtime and TensorFlow, consume less energy compared to PyTorch, which is compiled with the native OpenBLAS back-end.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。