Publications
Detailed Information
NLP-Fast: A Fast, Scalable, and Flexible System to Accelerate Large-Scale Heterogeneous NLP Models
Cited 3 time in
Web of Science
Cited 6 time in Scopus
- Authors
- Issue Date
- 2021-10
- Publisher
- IEEE COMPUTER SOC
- Citation
- 30TH INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES AND COMPILATION TECHNIQUES (PACT 2021), pp.75-89
- Abstract
- Emerging natural language processing (NLP) models have become more complex and bigger to provide more sophisticated NLP services. Accordingly, there is also a strong demand for scalable and flexible computer infrastructure to support these large-scale, complex, and diverse NLP models. However, existing proposals cannot provide enough scalability and flexibility as they neither identify nor optimize a wide spectrum of performance-critical operations appearing in recent NLP models and only focus on optimizing specific operations. In this paper, we propose NLP-Fast, a novel system solution to accelerate a wide spectrum of large-scale NLP models. NLP-Fast mainly consists of two parts: (1) NLP-Perf : an in-depth performance analysis tool to identify critical operations in emerging NLP models and (2) NLP-Opt: three end-to-end optimization techniques to accelerate the identified performance-critical operations on various hardware platforms (e.g., CPU, GPU, FPGA). In this way, NLP-Fast can accelerate various types of NLP models on different hardware platforms by identifying their critical operations through NLP-Perf and applying the NLP-Opt's holistic optimizations. We evaluate NLP-Fast on CPU, GPU, and FPGA, and the overall throughputs are increased by up to 2.92x, 1.59x, and 4.47x over each platform's baseline. We release NLP-Fast to the community so that users are easily able to conduct the NLP-Fast's analysis and apply NLP-Fast's optimizations for their own NLP applications.
- ISSN
- 1089-795X
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.