期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
基于4×4卷积核的异步卷积加速算法研究
1
作者 程海波 余旅莹 +3 位作者 李鹏飞 张海涛 何安平 杨裔 《软件工程与应用》 2018年第3期160-167,共8页
由于基于软件端卷积神经网络的卷积运算难以满足现在的卷积神经网络对运算性能与功耗的要求,为了克服困难,本文设计了一种基于4×4卷积核的异步卷积加速算法来对卷积神经网络进行加速。采用AddTree的形式来实现kernel矩阵和pic矩阵... 由于基于软件端卷积神经网络的卷积运算难以满足现在的卷积神经网络对运算性能与功耗的要求,为了克服困难,本文设计了一种基于4×4卷积核的异步卷积加速算法来对卷积神经网络进行加速。采用AddTree的形式来实现kernel矩阵和pic矩阵的乘加运算,1个Add Tree计算单元是1个4×4的卷积核与相同大小的图片矩阵的数据做乘加运算得到一个特征值,采用多个Add Tree的并行计算方式可以大幅度提升卷积计算速率。实验结果表明,该加速算法还有不受时钟频率限制的优点,可以工作在任何时钟频率下,且单个计算单元的计算速度也十分的快,计算一个特征值的时间大约在500 ns左右,相对于软件端的计算速率提升了10倍左右。 展开更多
关键词 卷积神经网络 并行 4 × 4卷积核
在线阅读 下载PDF
A High Precision and Realtime Physics-Based Hand Interaction for Virtual Instrument Experiment
2
作者 Xu Han Ning Zhou +1 位作者 Xinyan Gao anping he 《国际计算机前沿大会会议论文集》 2018年第2期46-46,共1页
关键词 Physics-based SIMULATION TendonHand-computer INTERACTION
在线阅读 下载PDF
Modular Timing Constraints for Delay-Insensitive Systems 被引量:2
3
作者 Hoon Park anping he +2 位作者 Marly Roncken Xiaoyu Song Ivan Sutherland 《Journal of Computer Science & Technology》 SCIE EI CSCD 2016年第1期77-106,共30页
This paper introduces ARCtimer, a framework for modeling, generating, verifying, and enforcing timing constraints for individual self-timed handshake components. The constraints guarantee that the component's gate-le... This paper introduces ARCtimer, a framework for modeling, generating, verifying, and enforcing timing constraints for individual self-timed handshake components. The constraints guarantee that the component's gate-level circuit implementation obeys the component's handshake protocol specification. Because the handshake protocols are delayinsensitive, self-timed systems built using ARCtimer-verified components are also delay-insensitive. By carefully considering time locally, we can ignore time globally. ARCtimer comes early in the design process as part of building a library of verified components for later system use. The library also stores static timing analysis (STA) code to validate and enforce the component's constraints in any self-timed system built using the library. The library descriptions of a handshake component's circuit, protocol, timing constraints, and STA code are robust to circuit modifications applied later in the design process by technology mapping or layout tools. In addition to presenting new work and discussing related work, this paper identifies critical choices and explains what modular timing verification entails and how it works. 展开更多
关键词 self-timed circuit delay-insensitive system model checking timing analysis design pattern
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部