SNS's not a synthesizer: a deep-learning-based synthesis predictor
SNS's not a synthesizer: a deep-learning-based synthesis predictor
复制标题
DOI：
10.1145/3470496.3527444
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Ceyu Xu;Chris Kjellqvist;Lisa Wu Wills
中科院分区：
文献类型：
--
作者：
Ceyu Xu;Chris Kjellqvist;Lisa Wu Wills
由于摩尔定律，在这十年中，可以安装在一个单片芯片上的晶体管的数量已经达到数十亿到数百亿。随着每一代技术的进步，每个芯片的晶体管数量以一种速度增长，这导致设计时间呈指数级增长，包括用于执行设计空间探索的合成过程。获得合成结果的如此长的延迟阻碍了有效的芯片开发过程，显著影响了上市时间。此外，这些大规模集成电路往往具有更大和更高维度的设计空间来探索，使得使用传统的合成工具来获得所有可能的设计的物理特性的成本过高。在这项工作中，我们提出了一种基于深度学习的合成预测器，称为SNS（SNS不是合成器），它预测各种设计的面积，功率和时序物理特性，比Synopsys设计预测器快两到三个数量级，同时平均提供0.4998 RRSE（相对均方根误差）。我们通过两个代表性的案例研究进一步评估SNS，一个是使用RISC-V Boom开源设计的通用乱序CPU案例研究，另一个是使用DianNao内部Chisel实现的加速器案例研究，以展示SNS的功能和有效性。
The number of transistors that can fit on one monolithic chip has reached billions to tens of billions in this decade thanks to Moore's Law. With the advancement of every technology generation, the transistor counts per chip grow at a pace that brings about exponential increase in design time, including the synthesis process used to perform design space explorations. Such a long delay in obtaining synthesis results hinders an efficient chip development process, significantly impacting time-to-market. In addition, these large-scale integrated circuits tend to have larger and higher-dimension design spaces to explore, making it prohibitively expensive to obtain physical characteristics of all possible designs using traditional synthesis tools. In this work, we propose a deep-learning-based synthesis predictor called SNS (SNS's not a Synthesizer), that predicts the area, power, and timing physical characteristics of a broad range of designs at two to three orders of magnitude faster than the Synopsys Design Compiler while providing on average a 0.4998 RRSE (root relative square error). We further evaluate SNS via two representative case studies, a general-purpose out-of-order CPU case study using RISC-V Boom open-source design and an accelerator case study using an in-house Chisel implementation of DianNao, to demonstrate the capabilities and validity of SNS.