A Framework for Area-efficient Multi-task BERT Execution on ReRAM-based Accelerators
With the superior algorithmic performances, BERT has become the de-facto standard model for various NLP tasks. Accordingly, multiple BERT models have been adopted on a single system, which is also called multi-task BERT. Although the ReRAM-based accelerator shows the sufficient potential to execute...
Saved in:
Published in | 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD) pp. 1 - 9 |
---|---|
Main Authors | , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.11.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | With the superior algorithmic performances, BERT has become the de-facto standard model for various NLP tasks. Accordingly, multiple BERT models have been adopted on a single system, which is also called multi-task BERT. Although the ReRAM-based accelerator shows the sufficient potential to execute a single BERT model by adopting in-memory computation, processing multi-task BERT on the ReRAM-based accelerator extremely increases the overall area due to multiple fine-tuned models. In this paper, we propose a framework for area-efficient multi-task BERT execution on the ReRAM-based accelerator. Firstly, we decompose the fine-tuned model of each task by utilizing the base-model. After that, we propose a two-stage weight compressor, which shrinks the decomposed models by analyzing the properties of the ReRAM-based accelerator. We also present a profiler to generate hyper-parameters for the proposed compressor. By sharing the base-model and compressing the decomposed models, the proposed framework successfully reduces the total area of the ReRAM-based accelerator without an additional training procedure. It achieves a 0.26 x area than baseline while maintaining the algorithmic performances. |
---|---|
ISSN: | 1558-2434 |
DOI: | 10.1109/ICCAD51958.2021.9643471 |