[Coursera]High Performance Scientific Computing @UW

UW的High Performance Scientific Computing开课了（现在刚开了一个星期），不知道有没有感兴趣的小伙伴？
link：https://www.coursera.org/course/scicomp
看了第一周的lecture，感觉上这门课和coursera上大部分课一样，内容涉及很广，但是不深。
介绍了很多很实用的工具，(第一周让大家熟悉git, unix shell, ipython), 理论方面（比如并行算法）涉及的比较少，至少现在看起来是这样的。
这门课的初衷就是熟悉高性能计算的环境，并且能在单机上实现高性能计算（而不是大规模的集群）; 学到的东西很实用，自己的project可以立刻用上。
老师讲话很清楚，课程的资料也准备的很好;唯一的缺点就是没有certificate，作业要自己看sample没有auto-rater。

PS:
顺便推荐一下coursera上的Discrete Optimization，老师非常逗啊～～现在课程开了一半，作业的deadline都是最后一周，求组队。
link: https://www.coursera.org/course/optimization

下面附 course welcome page:
Welcome to High Performance Scientific Computing!

Thank you for joining the High Performance Scientific Computing course! Please take a few moments to read through the course welcome page followed by watching the course orientation and week one lecture videos. There is a lot of useful information there about the course.

For now, you should plan to allocate between five and ten hours per week on the course. There will be roughly 2.5 hours of lectures per week, as well as quizzes (graded automatically) for each lecture.

In this course you will explore how computation and simulation are increasingly important in all aspects of science and engineering. At the same time, writing efficient computer programs to take full advantage of current computers is becoming increasingly difficult. Along the way there will also be discussion of software engineering tools such as debuggers, unit testing, makefiles, and the use of version control systems. After all, your time is more valuable than computer time, and a program that runs fast is totally useless if it produces the wrong results. High performance programming is also an important aspect of high performance scientific computing, and so another main theme of the course is the use of basic tools and techniques to improve your efficiency as a computational scientist.

There is no textbook; the course is self-contained. Course notes and resources can be found linked on the navigation bar. Course lecture notes are available online, next to the lecture links. The notes should be read through thoroughly and routinely as all the course content is contained therein. You are also encouraged to interact with each other within the discussion forums in order to solve the suggested homework problems. Homework will not be collected or graded, but sample solutions will be available after the suggested completion dates.
Only freely available open source software will be used in this course, and the course notes include instructions for downloading and installing what you need. There are also instructions for two other options that allow you to avoid installing multiple software packages individually: you can either use a virtual machine VM on the free VirtualBox software, or do your computing “in the cloud” on Amazon Web Services (for which you will need to set up your own account).

Again, welcome, and I hope that you enjoy this course!

Dr. Randall J. LeVeque

Mon 31 Mar 2014 1:01 AM PDT

没有人学这门课？

wowmomsos 发表于 2014-4-18 20:19
没有人学这门课？

一直在看啊，感觉很实用，正是我需要的
不知为何这么少人关心。。。

英文授课，听起来有点费劲啊！

冰凌蓝云 发表于 2014-4-23 23:58
英文授课，听起来有点费劲啊！

有字幕。
其实我觉得这个教授讲话挺清楚的。。。

这门课地里好像没有其他人跟？
我就自己贴在这个帖子里好了。

第一周：version control和python基本语法
第二周：numpy 和 AMI(amazon的云平台)
第三周：pdb(python debugger), intro to Fortran, make files
第四周：fortran module, 内存优化， intro to 并行计算
第五周：intro to openmp, 多线程编程，private & shared variable

这门课总共十周，现在跟了一半。现在来看这是一门相当实用的课程，百科全书式地介绍了高性能计算的方方面面，给了一大推reference要自己慢慢看的。老师讲话很清楚，算是对高性能计算不错的入门。

前五周quiz的截图一并放在附件里面，就不分开五个帖子刷屏了。

时间好充裕好羡慕%>_<%

我想跟公开课可是论文+毕设，现在勉强跟一门课了

sanguine 发表于 2014-5-8 01:34
时间好充裕好羡慕%>_

时间很不充裕。。。同羡慕有时间的人
手里的项目忙到死。。

我有在跟这个课，浅显易懂。缺点是coding作业没有改分系统。有几个coding作业都要求用fortran做，实在对fortran不感冒，改用C++写的作业。

我上完课了才看见这个帖子，⊙﹏⊙b汗……
话说lecture 27的quiz有些问题啊，怎么居然跟lecture 28的一样……