Contents (hide)

1.   1.  Course content
2.   2.  Staff
1.   2.1  Professor
2.   2.2  TA
3.   3.  Course material
1.   3.1  Text
2.   3.2  Web
4.   4.  Computer systems used
5.   5.  Relation to other RPI courses
6.   6.  LMS
7.   7.  Times & places
8.   8.  Lecture summaries and announcements
9.   9.  Assessment measures, i.e., grades
11. 11.  Student feedback

1.  Course content

1.1  Catalog description

A computer engineering course. Engineering techniques for parallel processing. Providing the knowledge and hands-on experience in developing applications software for processors on inexpensive widely-available computers with massively parallel computing resources. Multithread shared memory programming with OpenMP. NVIDIA GPU multicore programming with CUDA and Thrust. Using NVIDIA gaming and graphics cards on current laptops and desktops for general purpose parallel computing using linux.

Mon and Thurs 4-5:20. 3 credits.

Instructor: W. Randolph Franklin.

Rationale:

This is the 2nd running of a new course to provide students with knowledge and hands-on experience in developing applications software for processors with massively parallel computing resources. Specifically, this course will target NVIDIA GPUs because of their low cost (useful gaming cards cost only a few hundred dollars), and ubiquity (a majority of modern desktops and laptops have NVIDIA GPUs). The techniques learned here will also be applicable to larger parallel machines -- number 2 on the top 500 list has 18,688 NVIDIA GPUs.

Effectively programming these processors will require in-depth knowledge about parallel programming principles, as well as the parallelism models, communication models, and resource limitations of these processors. The target audiences of the course are students who want to develop exciting applications for these processors, as well as those who want to develop programming tools and future implementations for these processors.

Students will learn tools such as OpenMP, CUDA, and Thrust via extensive programming work.

The target audiences are ECSE seniors and others with comparable background who wish to develop parallel software.

Prereq: ECSE-2660 CANOS or equivalent, knowledge of C++.

1.2  Why (Not) To Take This Course

Since you're spending a lot of money to take this course, you need to know some keys to success (or the alternative). Here are some indications that other courses might be a better fit.

1. You don't like programming.
2. You don't like documenting your programs.
3. You don't like math.

OTOH, here are some reasons that you might prefer to take a course from me.

1. I acknowledge that you are simultaneously taking several courses, and so try to make the workload fair. E.g., if you're taking 6 3-credit courses, then you should not be required to spend more than {$\frac{168}{6}$} hours per week per course :-).
2. I acknowledge that you're paying a lot of money for this course, and try to provide value. One such way is by digesting a lot of badly organized online material to give you the best.
3. I keep the course up-to-date and relevant.

2.  Staff

2.1  Professor

W. Randolph Franklin. BSc (Toronto), AM, PhD (Harvard)

I've been programming since the 1960s, and parallel programming since the 1980s. I graduated two PhD students in parallel computational geometry around 1990. I've been at RPI since 1978, apart from several absences, including a year at Berkeley, 3 months at Genoa (Italy), and shorter times at Laval University in Quebec City (Canada), the Commonwealth Scientific and Industrial Research Organization in Canberra (Australia), and the National University of Singapore. I also spent 2 years 7 months as Director of the Numeric, Symbolic, and Geometric Computation Program at the National Science Foundation, recommending how to spend about \$30M of your tax dollars (thanks!).

A recent funded research project (together with Cutler and Zimmie) modeled how levees fail when overtopped during a flood.

Another research project a few years ago was on representing terrain elevation, and compressing it, and siting observers and planning paths on it, was largely supported by the Defense Advanced Research Projects Agency. DARPA people are crazy. My main worry was that I wasn't crazy enough for them.

In summer 2013, I was sponsored by FAPEMIG, the science funding agency of the state of Minas Gerais in Brazil to spend a month in Brazil working with researchers at various universities.

I also like to examine terrain on foot; in summer 2008 I walked 164km, including 11km up, from Chamonix to Zermatt, in 12 days. I spent July 2009 visiting universities in Brazil, with a few days kayaking down a tributary of the Amazon, sleeping in a hammock tied to trees, and hiking for hours through the jungle. I've hiked the Grand Canyon from the South Rim to the Colorado River and back in one day. Last summer I hiked the Virgin River Narrows slot canyon top-down in Zion NP.

 Office Jonsson Engineering Center (JEC) 6026 Phone +1 (518) 276-6077 (forwards) Email m a i l AT w r f r a n k l i n DOT o r g Writing from an account showing your name, at least in the comment field, and prefixing the subject with a hashtag of #par are helpful. GPG is welcomed. Web http://wrfranklin.org/ Office hours After each lecture, usually as long as anyone wants to talk. Also by appointment. Informal meetings If you would like to lunch with me, either individually or in a group, just mention it. We can then talk about most anything legal. Preferred communication medium Email.

2.2  TA

Hanchao Liu, l i u h 9

3.  Course material

3.1  Text

There is no required text, but the following inexpensive books are recommended.

1. Sanders and Kandrot, CUDA by example. It gets excellent reviews, although it is several years old. Amazon has many options, including Kindle and renting hardcopies.
2. Kirk and Hwu, 2nd edition, Programming massively parallel processors. It concentrates on CUDA.

3.2  Web

There is a lot of free material on the web, which I'll reference. My local cache is here.

4.  Computer systems used

This course will mostly use (remotely via ssh) my NSF-funded lab computer, which has dual 8-core Xeons with 128GB of memory and K20x and K5000 Nvidia processors, and runs CUDA 7.0RC, OpenMP 4.0 and Thrust 1.8.

You may also use your personal computer that runs 64-bit linux, has a recent Nvidia GPU, and runs the above SW.

5.  Relation to other RPI courses

I try not to duplicate existing RPI courses. Parallel computing is such a large topic that there is room for many courses. You may usefully take all the parallel courses at RPI.

This unique features of this course are as follows:

1. Use of only the Nvidia GPU. (As of now) this is the most widely used and least expensive parallel platform (although Intel looks promising).
2. Emphasis on learning several programming packages, at the expense of theory. However you will learn a lot about parallel architecture.

6.  LMS

RPI LMS (formerly WebCT) will be used only for you to submit homeworks and for me to distribute grades.

Announcements and the homeworks themselves will be available on this website. You do not have to log in to see them.

7.  Times & places

Lectures are Mon & Thurs, 4-6pm, in JEC4107.

8.  Lecture summaries and announcements

will be posted here.

1. There will be no exams.
2. The grade will be based on homeworks, a term project, class presentations, and possible iclicker questions TBD.
3. Deliverables for the term project:
1. A 2-minute project proposal given to the class around the middle of the semester.
2. A 5-minute project presentation given to the class in the last week.
3. Some progress reports.
4. A write-up uploaded on the last class day. This will contain an academic paper, code and perhaps video or user manual.

9.1  Homeworks

There will be frequent homeworks. You are encouraged to do the homework in teams of 2, and submit one solution per team, on RPILMS, in any reasonable format. The other term member should submit only a note listing the team and saying who submitted the solution.

"Reasonable" means a format that I can read. A scan of neat handwriting is acceptable. I would type material with a wiki like pmwiki or blogging tool, sketch figures with xournal or draw them with inkscape, and do the math with mathjax. Your preferences are probably different.

9.2  Term project

1. For the latter part of the course, most of your homework time will be spent on a term project.
2. You are encouraged do it in teams of up to 3 people. A team of 3 people would be expected to do twice as much work as 1 person.
3. You may combine this with work for another course, provided that both courses know about this and agree. I always agree.
4. If you are a grad student, you may combine this with your research, if your prof agrees, and you tell me.
5. You may build on existing work, either your own or others'. You have to say what's new, and have the right to use the other work. E.g., using any GPLed code or any code on my website is automatically allowable (because of my Creative Commons licence).
6. You will implement, demonstrate, and document something vaguely related to parallel computing.
7. You will give a 5 minute fast forward Powerpoint talk in class. A fast forward talk is a timed Powerpoint presentation, where the slides advance automatically.
8. You may demo it to me if you wish.

Size of term project

It's impossible to specify how many lines of code makes a good term project. E.g., I take pride in writing code that is can be simultaneously shorter, more robust, and faster than some others. See my 8-line program for testing whether a point is in a polygon here.

According to Big Blues, when Bill Gates was collaborating with IBM around 1980, he once rewrote a code fragment to be shorter. However, according to the IBM metric, number of lines of code produced, he had just caused that unit to officially do negative work.

Deliverables

1. An implementation showing parallel computing.
2. An extended abstract or paper on your project, written up like a paper. You should follow the style guide for some major conference (I don't care which, but can point you to one).
3. A more detailed manual, showing how to use it.
4. A talk in class.

9.3  Correcting the Prof's errors

Occasionally I make mistakes, either in class or on the web site. The first person to correct each nontrival error will receive an extra point on his/her grade. One person may accumulate several such know-it-all points.

1. I'll post homework grading comments on LMS. Please report any errors disagreements or appeals by email within one week.
2. From time to time, I'll post your grades to LMS. Please report any missing grades within one week to the TA, with a copy to the prof.
3. It is not allowed to wait until the end of the semester, and then go back 4 months to try to find extra points. It is especially not allowed to wait until the end of the following semester, and then to ask what you may do to raise your grade.
4. I maintain standards (and the value of your diploma) by giving the grades that are earned, not the grades that are desired. Nevertheless, this course's average grade is competitive with other courses, and last year's students seemed to like the course.

9.5  Mid-semester assessment

Before the drop date, I will email you your performance to date.