Ascend: a Scalable and Unified Architecture for Ubiquitous Deep Neural Network Computing : Industry Track Paper
| Autor: | Yuxing Hu, Jing Xia, Hu Liu, Xiping Zhou, Jiajin Tu, Honghui Yuan, Heng Liao |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Memory hierarchy
business.industry Computer science 020208 electrical & electronic engineering Symmetric multiprocessor system 02 engineering and technology Data access Memory management Computer architecture Datapath Scalability 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Data center business Heterogeneous network |
| Zdroj: | HPCA |
| DOI: | 10.1109/hpca51647.2021.00071 |
| Popis: | Deep neural networks (DNNs) have been successfully applied to a great variety of applications, ranging from small IoT devices to large scale services in a data center. In order to improve the efficiency of processing these DNN models, dedicated hardware accelerators are required for all these scenarios. Theoretically, there exists an optimized acceleration architecture for each application. However, considering the cost of chip design and corresponding tool-chain development, researchers need to trade off between efficiency and generality. In this work, we demonstrate that it is practical to use a unified architecture, called Ascend, to support those applications, ranging from IoT devices to data-center services. We provide a lot of design details to explain that the success of Ascend relies on contributions from different levels. First, heterogeneous computing units are employed to support various DNN models. And the datapath is adapted according to the requirement of computing and data access. Second, when scaling the Ascend architecture from a single core to a cluster containing thousands of cores, it involves design efforts, such as memory hierarchy and system level integration. Third, a multi-tier compiler, which provides flexible choices for developers, is the last critical piece. Experimental results show that using accelerators based on the Ascend architecture can achieve comparable or even better performance in different applications. In addition, various chips based on the Ascend architecture have been successfully commercialized. More than 100 million chips have been used in real products. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|