• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2019 56th ACM/IEEE Design Automation Conference >ApproxLP: Approximate Multiplication with Linearization and Iterative Error Control
【24h】

ApproxLP: Approximate Multiplication with Linearization and Iterative Error Control

机译：ApproxLP：具有线性化和迭代误差控制的近似乘法

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In a data hungry world, approximate computing has emerged as one of the solutions to create higher energy efficiency and faster systems, while providing application tailored quality. In this paper, we propose ApproxLP, an Approximate Multiplier based on Linear Planes. We introduce an iterative method for approximating the product of two operands using fitted linear functions with two inputs, referred to as linear planes. The linearization of multiplication allows multiplication operations to be completely replaced with weighted addition. The proposed technique is used to find the significand of the product of two floating point numbers, decreasing the high energy cost of floating point arithmetic. Our method fully exploits the trade-off between accuracy and energy consumption by offering various degrees of approximation at different energy costs. As the level of approximation increases, the approximated product asymptotically approaches the exact product in an iterative manner. The performance of ApproxLP is evaluated over a range of multimedia and machine learning applications. A GPU enhanced by ApproxLP yields significant energy-delay product (EDP) improvement. For multimedia, neural network, and hyperdimensional computing applications, ApproxLP offers on average $2.4 imes, 2.7 imes $, and $4.3 imes $ EDP improvement respectively with sufficient computational quality for the application. ApproxLP also provides up to $4.5 imes $ EDP improvement and has $2.3 imes $ lower chip area than other state-of-the-art approximate multipliers.CCS CONCEPTS•Hardware → Integrated circuits; • Computer systems organization → Architectures;
机译：在数据匮乏的世界中，近似计算已成为创建更高能效和更快系统，同时提供应用程序定制质量的解决方案之一。在本文中，我们提出了ApproxLP，一种基于线性平面的近似乘数。我们介绍了一种迭代方法，该方法使用具有两个输入的拟合线性函数（称为线性平面）来逼近两个操作数的乘积。乘法的线性化使得乘法运算可以完全替换为加权加法。所提出的技术被用于寻找两个浮点数的乘积的有效值，从而降低了浮点算法的高能耗。我们的方法通过以不同的能源成本提供不同程度的逼近，充分利用了精度与能耗之间的权衡。随着近似水平的增加，近似乘积以迭代方式渐近逼近精确乘积。可在多种多媒体和机器学习应用程序中评估ApproxLP的性能。由ApproxLP增强的GPU可以显着提高能耗产品（EDP）。对于多媒体，神经网络和超维计算应用程序，ApproxLP分别提供平均$ 2.4倍，2.7倍和$ 4.3倍的EDP改进，并为该应用提供了足够的计算质量。与其他最新的近似乘数相比，ApproxLP还提供了高达$ 4.5倍的EDP改善，并且芯片面积减小了$ 2.3倍的CCS概念。硬件→集成电路； •计算机系统组织→体系结构；

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号