Approximate Logic Synthesis: A Reinforcement Learning-Based Technology Mapping Approach
Approximate Logic Synthesis: A Reinforcement Learning-Based Technology Mapping Approach
复制标题
DOI：
10.1109/isqed.2019.8697679
复制
发表时间：
2019-02
期刊：
影响因子：
--
通讯作者：
G. Pasandi;Shahin Nazarian;Massoud Pedram
中科院分区：
文献类型：
--
作者：
G. Pasandi;Shahin Nazarian;Massoud Pedram
近似逻辑合成（ALS）是合成给定布尔网络并将其映射到逻辑单元库的过程，使得近似和初始（精确）布尔网表的输出之间的误差幅度/速率由预定总误差阈值从上限定。在本文中，我们提出了Q-ALS，ALS的一个新的框架，专注于技术映射阶段。Q-ALS结合了强化学习，并利用布尔差分演算来估计给定网络的每个节点可以容忍的最大错误率，使得映射网表的输出中没有一个的总错误率超过预定的最大错误率，并且最坏情况下的延迟和总面积被最小化。最大汉明距离（MHD）之间的精确和近似真值表的削减每个节点被用作误差度量。在Q-ALS中，Q-Learning代理通过足够数量的迭代进行训练，旨在为每个节点选择最适合的MHD值，并且在基于切割的技术映射方法中，选择最佳超级门（在延迟和面积方面，进一步由最适合的MHD限定）来实现每个节点。实验结果表明，与最先进的学术ALS工具相比，将主要输出的所需精度设置为95%，Q-ALS将面积和延迟方面的总成本分别降低了70%和36%，并且平均将运行时间缩短了2.21倍。
Approximate Logic Synthesis (ALS) is the process of synthesizing and mapping a given Boolean network to a library of logic cells so that the magnitude/rate of error between outputs of the approximate and initial (exact) Boolean netlists is bounded from above by a predetermined total error threshold. In this paper, we present Q-ALS, a novel framework for ALS with focus on the technology mapping phase. Q-ALS incorporates reinforcement learning and utilizes Boolean difference calculus to estimate the maximum error rate that each node of the given network can tolerate such that the total error rate at non of the outputs of the mapped netlist exceeds a predetermined maximum error rate, and the worst case delay and the total area are minimized. Maximum Hamming Distance (MHD) between exact and approximate truth tables of cuts of each node is used as the error metric. In Q-ALS, a Q-Learning agent is trained with a sufficient number of iterations aiming to select the fittest values of MHD for each node, and in a cut-based technology mapping approach, the best supergates (in terms of delay and area, bounded further by the fittest MHD) are selected towards implementing each node. Experimental results show that having set the required accuracy of 95% at the primary outputs, Q-ALS reduces the total cost in terms of area and delay by up to 70 % and 36%, respectively, and also reduces the run-time by 2.21 x on average, when compared to the best state-of-the-art academic ALS tools.