coding ...

owlbarn · Nov 18, 2023 · daa471e · daa471e
1 parent bd3991e
commit daa471e
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 1 deletion.
diff --git a/project/Makefile → Makefile b/project/Makefile → Makefile
diff --git a/docs/cn/aeos.html b/docs/cn/aeos.html
@@ -1,4 +1,10 @@
-<html style="" lang="en" class="js flexbox fontface"><head><meta charset="utf-8"><meta content="width=device-width, initial-scale=1.0" name="viewport"><meta content="OCaml Scientific and Engineering Computing - Tutorial Book" name="description"><meta content="OCaml, Data Science, Data Analytics, Analytics, Functional Programming, Machine Learning, Deep Neural Network, Scientific Computing, Numerical Algorithm, Tutorial, Linear Algebra, Matrix" name="keywords"><meta content="Liang Wang" name="author"><title>Automatic Empirical Tuning - OCaml Scientific Computing Tutorials</title><link href="css/app.css" rel="stylesheet"><link href="css/prism.css" rel="stylesheet"><script src="js/min/modernizr-min.js"></script><script src="js/prism.js"></script><script src="https://use.typekit.net/gfj8wez.js"></script><script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/MathJax.js?config=TeX-MML-AM_CHTML"></script><script>try{Typekit.load();}catch(e){}</script><script async src="https://pagead2.googlesyndication.com/pagead/js/adsbygoogle.js?client=ca-pub-1868946892712371" crossorigin="anonymous"></script><script async src="https://www.googletagmanager.com/gtag/js?id=UA-123353217-1"></script><script>
+<html style="" lang="en" class="js flexbox fontface"><head><meta charset="utf-8"><meta content="width=device-width, initial-scale=1.0" name="viewport">
+<meta content="This chapter discusses the importance of parameter tuning in numerical libraries, focusing on OpenMP parameters in Owl. It explores the challenges of determining optimal thresholds for OpenMP usage in mathematical operations and introduces the Automatic Empirical Tuning (AEOS) module in Owl. The AEOS module implements a tuning phase before compiling Owl, allowing each operation to learn a suitable threshold parameter based on input size. The tuning process involves measuring execution times for different input sizes, performing linear regression to find optimal thresholds, and generating a C header file for compilation. The chapter evaluates the performance of tuned OpenMP thresholds on different platforms and operations, demonstrating significant improvements in computation performance. The AEOS module provides flexibility for future tuning methods and aims to keep the tuning process simple and effective. Overall, the chapter emphasizes the role of automatic tuning in enhancing the efficiency of numerical libraries." name="description">
+<meta content="OCaml, Data Science, Data Analytics, Analytics, Functional Programming, Machine Learning, Deep Neural Network, Scientific Computing, Numerical Algorithm, Tutorial, Linear Algebra, Matrix" name="keywords">
+<meta content="Liang Wang" name="author">
+<title>Automatic Empirical Tuning - OCaml Scientific Computing Tutorials</title><link href="css/app.css" rel="stylesheet">
+<link href="css/prism.css" rel="stylesheet">
+<script src="js/min/modernizr-min.js"></script><script src="js/prism.js"></script><script src="https://use.typekit.net/gfj8wez.js"></script><script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/MathJax.js?config=TeX-MML-AM_CHTML"></script><script>try{Typekit.load();}catch(e){}</script><script async src="https://pagead2.googlesyndication.com/pagead/js/adsbygoogle.js?client=ca-pub-1868946892712371" crossorigin="anonymous"></script><script async src="https://www.googletagmanager.com/gtag/js?id=UA-123353217-1"></script><script>
       window.dataLayer = window.dataLayer || [];
       function gtag(){dataLayer.push(arguments);}
       gtag('js', new Date());