Home | Announcements | Schedule | Assignments | Presentations | Grades | References |
Meeting | Dates | Topic | Lecture
Material |
Complementary Material |
21/10/12 |
Begining of Spring Semester | |||
1 | 25/10/12 |
Introduction - Course Overview and requirements | Administration Lecutre |
Parallel
Computing 101
Youtube video: An Overview of High Performance Computing and Challenges for the Future Parallel Computers - Introduction , Parallelizm in Computers from: "Programming Techniques for Supercomputers 2011" by Prof. Gerhard Wellein, RRZE HPC Services Supercomputers (wikipedia) |
2 | 1/11/12 | Introduction to Parallel Processing. Basic Message Passing - MPI |
Administration Message-passing Computing |
MPI MPI Tutorials |
3 | 8/11/12 |
Preparation to
the lab. <<performance examples from hpc book>> 1) Parallel Debugger, The Allinea DDT Parallel debugger Tutorials, Webinars 2) Parallel IDE The Eclipse PTP XSEDE12 tutorial 3) Performance Tools 4) Torque - Open-Source Resource Manager |
Useful tools
and demos |
|
15/11/12 | No Class (Not final yet!!!!) | |||
4 | 22/11/12 |
Lab
#1: room 217 Getting to know Linux Hands-on practice with MPI, Embarrassingly Parallel Computation (cpi.c) Parallel Debugger (Allenea DDT) ------------------ Parallel Profiler (Jumpshot, IPM) נוכחות חובה |
Lecture Exercises in compiling and running simple MPI programs Allinea DDT training (download tar file from the course website at MTA) |
Linux tutorials |
5 | 29/11/12 |
Algorithms: 1. MPI Collective routines 2. Embarrassingly Parallel Computations 3. Partitioning and Divide and Conquer * Demos: MPI on Windows OS home assignment |
SC12 and the new Top500 list Lecture Collective routines Embarrassingly Parallel Computations Partitioning and Divide and Conquer Strategies home assignment #1 (see MTA course website) |
|
6 | .6/12/12 |
Algorithms: Synchronous Computations |
Lecture Synchronous Computations |
|
7 | 13/12/12 |
Scalapack some code examples Parallel Computing in Python Home assignment #2 |
Lecture Home assignment #2 - at the course website in MTA |
ScaLAPACK:
a portable linear algebra library for distributed memory computers - design issues and performance |
8 | 20/12/12 | Parallel
Programming
in Shared
Memory - 1. General Introduction 2. OpenMP Assigning Final Presentations |
Lecture Programming with Shared Memory I Programming with Shared MemoryII OpenMP tutorial Shared Memory (Intel) Introduction to OpenMP and Advanced OpenMP from: "Programming Techniques for Supercomputers 2011" by Prof. Gerhard Wellein, RRZE HPC Services |
OpenMP home Wikipedia OpenMP quick reference card OpenMP in Visual C/C++ "Reap the Benefits of Multithreading without All the Work" |
9 | 27/12/12 |
OpenMP
- Continued Load Balancing and Termination Detection Parallel Matlab - MatlabMPI (Engineering) | Home assignment #3 |
Lecture Impressions from SC12 Load Balancing and Termination Detection Parallel Matlab (engineering course only) |
An
Overview of OpenMP - Ruud van der Pas - Sun MicrosystemsShared Memory Programming with OpenMP |
10 | 3/1/13 |
*
OpenMP in Visual Studio (SC99 examples) * Hybrid MPI and OpenMP: 1. Slides from: "Programming Techniques for Supercomputers 2011" by Prof. Gerhard Wellein, G. Gager and J. Habich from RRZE HPC Services 2. Rutgers, ECE-451 / ECE-566 (Fall 2012), lecture 11 * Sorting Algorithms * Numerical Algorithms (part I) |
Lecture Hybrid MPI+OpenMP Reference #1 (login as a guest) Reference #2: lecture 11 Sorting Algorithms Numerical Algorithms |
|
11 | 10/1/13 |
Numerical Algorithms (part II) CilkPlus A very short introduction to HTCondor, Grid and Cloud Computing Home assignment #4 |
Lecture CilkPlus HTCondor |
|
12 | 17/1/13 |
Lab
#2:
More practice * OpenMP/CilkPlus/UPC/HTCondor * Using Allinea's DDT (room 217) |
Lecture Lab 2 slides CilkPlus tutorial HTCondor Tutorial |
|
13 | 24/1/13 |
Students Presentations נוכחות חובה *Parallel Image Processing ((chapter 12 from Wilkinson&Allen) *Parallel FFT Course closure |
Students' Presentations Lecture Preparation to the exam |
נוכחות חובה. א. לכל קבוצה מוקצות 15 דקות ב. יש לעמוד בזמן המוקצב לכל מצגת ג. יש לשלוח אל המרצה את קובץ המצגת לא יאוחר מחצות הלילה שלפני השיעור על-מנת שהן תועלנה למחשב ותהינה מוכנות בזמן השעור. שימו לב: קבוצה אשר לא תעשה כן תפסל. לא תתקבלנה מצגות בזמן השעור, לפניו או במהלך ההפסקות גם לא בשביל שיפורים ותיקונים |
Extra material FFU |
Introduction
to UPC HPSC Lecture: Unified Parallel C by David Bindel UPC tutorials from MTU *A very short introduction to GPGPU Computing Eclipse PTP IPM (see also here) |
Basic CUDA programming Barry Wilkinson University of North Carolina Charlotte. from: SIGCSE 2011 - The 42nd ACM Technical Symposium on Computer Science Education March 9-12, 2011, Dallas, Texas, USA |
||
* | 25/1/13 |
End of semester | ||
* | 6/2/13, 14:00 |
Final Exam ( I ) | ||
* | 18/3/13, 14:00 |
Final Exam ( II ) |