首页> 外文OA文献 >Knowledge-Based Automatic Generation of Linear Algebra Algorithms and Code
【2h】

Knowledge-Based Automatic Generation of Linear Algebra Algorithms and Code

机译:基于知识的线性代数算法自动生成算法   码

摘要

This dissertation focuses on the design and the implementation ofdomain-specific compilers for linear algebra matrix equations. The developmentof efficient libraries for such equations, which lie at the heart of mostsoftware for scientific computing, is a complex process that requires expertisein a variety of areas, including the application domain, algorithms, numericalanalysis and high-performance computing. Moreover, the process involves thecollaboration of several people for a considerable amount of time. With ourcompilers, we aim to relieve the developers from both designing algorithms andwriting code, and to generate routines that match or even surpass theperformance of those written by human experts.
机译:本文主要研究线性代数矩阵方程的领域专用编译器的设计和实现。这些方程式的有效库的开发是科学计算的大多数软件的核心,它是一个复杂的过程,需要包括应用领域,算法,数值分析和高性能计算在内的各个领域的专业知识。此外,该过程涉及大量时间的多个人的协作。通过我们的编译器,我们旨在减轻开发人员设计算法和编写代码的负担,并生成与人类专家编写的程序相匹配甚至超越其性能的例程。

著录项

  • 作者

    Fabregat-Traver, Diego;

  • 作者单位
  • 年度 2014
  • 总页数
  • 原文格式 PDF
  • 正文语种 {"code":"en","name":"English","id":9}
  • 中图分类

相似文献

  • 外文文献
  • 中文文献
  • 专利

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