SHARP: An adaptable, energy-efficient accelerator for recurrent neural networks
The effectiveness of Recurrent Neural Networks (RNNs) for tasks such as Automatic Speech Recognition has fostered interest in RNN inference acceleration. Due to the recurrent nature and data dependencies of RNN computations, prior work has designed customized architectures specifically tailored to t...
| Autores: | , , , , , |
|---|---|
| Formato: | artículo |
| Fecha de publicación: | 2023 |
| País: | España |
| Recursos: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/389907 |
| Acesso em linha: | https://hdl.handle.net/2117/389907 https://dx.doi.org/10.1145/3552513 |
| Access Level: | acceso abierto |
| Palavra-chave: | Neural networks (Computer science) Recurrent Neural Network (RNN) Long-Short-Term Memory (LSTM) Accelerator Scheduling Reconfigurability Low power Xarxes neuronals (Informàtica) Àrees temàtiques de la UPC::Informàtica::Arquitectura de computadors |
| Resumo: | The effectiveness of Recurrent Neural Networks (RNNs) for tasks such as Automatic Speech Recognition has fostered interest in RNN inference acceleration. Due to the recurrent nature and data dependencies of RNN computations, prior work has designed customized architectures specifically tailored to the computation pattern of RNN, getting high computation efficiency for certain chosen model sizes. However, given that the dimensionality of RNNs varies a lot for different tasks, it is crucial to generalize this efficiency to diverse configurations. In this work, we identify adaptiveness as a key feature that is missing from today’s RNN accelerators. In particular, we first show the problem of low resource utilization and low adaptiveness for the state-of-the-art RNN implementations on GPU, FPGA, and ASIC architectures. To solve these issues, we propose an intelligent tiled-based dispatching mechanism for increasing the adaptiveness of RNN computation, in order to efficiently handle the data dependencies. To do so, we propose Sharp as a hardware accelerator, which pipelines RNN computation using an effective scheduling scheme to hide most of the dependent serialization. Furthermore, Sharp employs dynamic reconfigurable architecture to adapt to the model’s characteristics. Sharp achieves 2×, 2.8×, and 82× speedups on average, considering different RNN models and resource budgets, compared to the state-of-the-art ASIC, FPGA, and GPU implementations, respectively. Furthermore, we provide significant energy reduction with respect to the previous solutions, due to the low power dissipation of Sharp (321 GFLOPS/Watt). |
|---|