Benchmarking and In-depth Performance Study of Large Language Models on Habana Gaudi Processors

Chengming Zhang, Baixi Sun, Xiaodong Yu, Zhen Xie, Weijian Zheng, Kamil A. Iskra, Pete Beckman, Dingwen Tao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Transformer models have achieved remarkable success in various machine learning tasks but suffer from high computational complexity and resource requirements. The quadratic complexity of the self-attention mechanism further exacerbates these challenges when dealing with long sequences and large datasets. Specialized AI hardware accelerators, such as the Habana GAUDI architecture, offer a promising solution to tackle these issues. GAUDI features a Matrix Multiplication Engine (MME) and a cluster of fully programmable Tensor Processing Cores (TPC). This paper explores the untapped potential of using GAUDI processors to accelerate Transformer-based models, addressing key challenges in the process. Firstly, we provide a comprehensive performance comparison between the MME and TPC components, illuminating their relative strengths and weaknesses. Secondly, we explore strategies to optimize MME and TPC utilization, offering practical insights to enhance computational efficiency. Thirdly, we evaluate the performance of Transformers on GAUDI, particularly in handling long sequences and uncovering performance bottlenecks. Lastly, we evaluate the end-to-end performance of two Transformer-based large language models (LLM) on GAUDI. The contributions of this work encompass practical insights for practitioners and researchers alike. We delve into GAUDI's capabilities for Transformers through systematic profiling, analysis, and optimization exploration. Our study bridges a research gap and offers a roadmap for optimizing Transformer-based model training on the GAUDI architecture.

Original languageEnglish
Title of host publicationProceedings of 2023 SC Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023
Pages1759-1766
Number of pages8
ISBN (Electronic)9798400707858
DOIs
StatePublished - 12 Nov 2023
Event2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023 - Denver, United States
Duration: 12 Nov 202317 Nov 2023

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2023 International Conference on High Performance Computing, Network, Storage, and Analysis, SC Workshops 2023
Country/TerritoryUnited States
CityDenver
Period12/11/2317/11/23

Fingerprint

Dive into the research topics of 'Benchmarking and In-depth Performance Study of Large Language Models on Habana Gaudi Processors'. Together they form a unique fingerprint.

Cite this