High Performance Computing Systems (CMSC714)

Hours

Lectures: Tu Th 11:00 AM--12:15 PM virtually via zoom.
TA office hours: TBD virtually via zoom.

Staff

Name Email Role
Abhinav Bhatele bhatele@cs.umd.edu Instructor
Joy Kitson jkitson@umd.edu TA

Description (from catalog)

Selected topics in high performance systems, including contemporary architectures, interconnection topologies, shared memory and message-passing systems, multi-threaded kernels, latency avoidance and hiding techniques, methods for data and work partitioning, performance profiling, and debugging.

Additional description (from catalog)

The objective of this course is to study the theory and practice of high performance parallel and distributed computing. The overall goal is to expose you to tools and techniques for parallel and/or distributed environments and to study current trends and technologies.

This course will focus on current practices in high performance computing technologies, including systems, architectures, programming models, languages and software tools. The course will require students to produce questions for multiple technical papers during the semester and complete two introductory and one more extensive group research project in parallel and/or distributed programming.

Prerequisites

CMSC411 and CMSC412; or permission of instructor.

Course Topics (Subject to change)

  • Introduction (1 week)
  • Programming Models (3 weeks)
  • Parallel Architectures and Networks (2 weeks)
  • Debugging & Instrumentation (1 week)
  • Performance Tools (2 weeks)
  • Runtime systems and Parallel I/O (1 week)
  • Commercial and Scientific Applications (1 week)
Primary Text

None - Reading list will provide materials

Grading

Your grade will be determined as follows:

Number % total
Programming assignments330
Midterm exam130
Research (group) project125
Class participation-15
Programming Assignments and Group Project
  • The programming assignments, in C/C++, will use MPI and OpenMP to become familiar with parallel/distributed programming on a Linux cluster. Accounts on the university deepthought2 cluster will be forthcoming.
  • You will also do a group project, in C/C++ (or Fortran), with milestones along the way.
  • The assignments should be submitted by 11:59 PM Anywhere on Earth (AoE) on the day they are due. Late assignments will be not be accepted.
  • The instructor reserves the right to fail, regardless of overall numeric score, students who do not submit on-time a good faith attempt to complete all programming assignments and projects.
  • All submissions of assignments will be via ELMS. Posted deadlines for program submission are sharp; standard Unix time of submission is used.
Academic Integrity

The CS Department takes academic integrity seriously. Information on how the CS Department views and handle academic integrity matters can be found at Academic Integrity.

Note that academic dishonesty includes not only cheating, fabrication, and plagiarism, but also includes helping other students commit acts of academic dishonesty by allowing them to obtain copies of your work. In short, all submitted work must be your own. Cases of academic dishonesty will be pursued to the fullest extent possible as stipulated by the Office of Student Conduct.

It is very important for you to be aware of the consequences of cheating, fabrication, facilitation, and plagiarism. For more information on the Code of Academic Integrity or the Student Honor Council, please visit http://www.shc.umd.edu.

Exams/Programming Assignments

On any graded exam or programming assignments (except for group projects), you are NOT allowed to collaborate or exchange code. We compare each student's code with every other student's code to check for similarities. Every semester, we catch an embarrassingly high number of students that engage in cheating and we have to take them to the Honor Council.

Uploading code to Github

You may post your project code to private Github (or similar service) repos only. As a student, you can make a private repo for free. Just remember that your free premium subscription has an expiry date, and your code becomes public once it expires. The Honor Council can retroactively give an XF (even to students who have already graduated) if your code is then used by another student to cheat. So just be careful.

Posting graded code to a public repo will give you a free ticket to the Honor Council.

GroupMe/ Other Group Chats

We encourage students to talk about course material and help each other out in group chats. However, this does NOT include graded assignments. Talking about release tests is NOT okay.

There have been a couple instances in the past where students have posted pictures/source files of their code, or earlier sections have given away exam questions to later sections. Not only did this lower the curve for the earlier section because the later one will do better, the WHOLE group chat had to pay a visit to the Honor Council. It was an extremely ugly business. Remember that in a group of 200+, someone or the other will blow the whistle. If you happen to be an innocent person in an innocent groupchat and someone starts cheating out of the blue, leave it immediately (and better yet, say you are leaving and say you will report it).

Study Guides

Creating collaborative study guides on Google docs is OK. Encouraged, even. Just do this before the exam, and don't bring the study guide to the exam. Don't add exam questions to the study guide after the early section's midterm.

PRACTICE Exams/ Worksheets/ Lecture examples/ Ungraded Lab examples Totally cool. Highly encouraged to co-create and share (with same caveats as study guides).

Prof. Bhatele is the information owner for all Linux cluster accounts in this class, and all files in those accounts may be inspected by him at any time.

The following are examples of academic integrity violations:

  • Hardcoding of results in a project assignment. Hardcoding refers to attempting to make a program appear as if it works correctly (e.g., printing expected results for a test).
  • Using any code available on the internet/web or any other source. For example, using code from GitHub.
  • Hiring any online service to complete an assignment for you.
  • Sharing your code or your tests with any student.
  • Using online forums in order to ask for help regarding assignments.
Piazza

This term we will be using Piazza for class discussion. Rather than emailing questions to the teaching staff, I encourage you to post your questions on Piazza. The class sign up link is on ELMS.

Excused Absence and Academic Accommodations

See the section titled "Attendance, Absences, or Missed Assignments" available at Course Related Policies.

Any student who needs to be excused for an absence from a single lecture, due to a medically necessitated absence shall make a reasonable attempt to inform the instructor of his/her illness prior to the class. Upon returning to the class, present the instructor with a self-signed note attesting to the date of their illness. Each note must contain an acknowledgment by the student that the information provided is true and correct. Providing false information to University officials is prohibited under Part 9(i) of the Code of Student Conduct (V-1.00(B) University of Maryland Code of Student Conduct) and may result in disciplinary action.

Self-documentation may not be used for Major Scheduled Grading Events (midterm exams, and final project presentations) and it may only be used for two class meetings during the semester. Any student who needs to be excused for a prolonged absence (two or more consecutive class meetings), or for a Major Scheduled Grading Event, must provide written documentation of the illness from the Health Center or from an outside health care provider. This documentation must verify dates of treatment and indicate the timeframe that the student was unable to meet academic responsibilities. In addition, it must contain the name and phone number of the medical service provider to be used if verification is needed. No diagnostic information will ever be requested.

Disability Support Accommodations

See the section titled "Accessibility" available at Course Related Policies.

Miscellaneous

Copyright

All course materials are copyright UMCP, Department of Computer Science © 2021. All rights reserved. Students are permitted to use course materials for their own personal use only. Course materials may not be distributed publicly or provided to others (excepting other students in the course), in any way or format.