DEAP: Design Space Exploration for DNN Accelerator Parallelism
Agrawal, Ekansh, Xu, Xiangyu Sam
–arXiv.org Artificial Intelligence
The boom in Large Language Models (LLMs) like GPT-4 and ChatGPT has marked a significant advancement in artificial intelligence. These models are becoming increasingly complex and powerful to train and serve. This growth in capabilities comes with a substantial increase in computational requirements, both in terms of hardware resources and energy consumption. The goal of this paper is to showcase how hardware and software co-design can come together and allow us to create customized hardware systems for specific LLM workloads. We propose a simulation workflow that allows us to combine model parallelism techniques with a multi-accelerator simulation framework for efficiency metrics. We focus on inference workloads and report power, cycle, and latency metrics upon performing a design space exploration search over multiple software and hardware configurations.
arXiv.org Artificial Intelligence
Dec-23-2023
- Country:
- North America > United States
- New York > New York County
- New York City (0.04)
- Massachusetts > Suffolk County
- Boston (0.04)
- California > Alameda County
- Berkeley (0.04)
- New York > New York County
- North America > United States
- Genre:
- Research Report (1.00)
- Workflow (0.88)
- Technology: