Readings - CMSC714: High Performance Computing

 

Note: for each class (after the intro material), 4 students will be responsible for emailing me (asussman@umd.edu) with ~4 discussion question on the reading(s) for that day by 6PM the day before the class, and be prepared to ask those questions and help explain the paper to the rest of the class.

Introduction - What and Why? 

1/28 Parallel Computing and Parallel Computers

1/30 Applications of Parallel Computing

Programming Models

2/4 Expressing Parallelism (Implicit Control)

2/6-2/11 Expressing Parallelism (Implicit Control, cont.) - A. Borhani, C. Charles, A. Coppens, S. Cui

2/13 Expressing Parallelism (Explicit Control - Message Passing and MPI)

2/18 Advanced MPI - J. Dai, T. Dao, A. Frolov, L. Hough

2/20-25 Expressing Parallelism (Hybrids and Frameworks) - N. Kadawedduwa, J. Kim, J. Liu, Z. Lu

2/27 CUDA and GPUs

No readings assigned, slides only

3/4 Profiling Programs - R. Misra, A. Namjoo, Q. Nguyen, R. Parsons

3/6 Scientific Workflows - C. Hutton, X. Qi, M. Sukanya, X. Tian

Architectures

3/11 Shared Memory - J. Umeike, R. Vishnoi, F. H.-Y. Yeh, A. Borhani

3/13 Custom Machines - C. Charles, A. Coppens, S. Cui, J. Dai

3/25 GPUs - T. Dao, A. Frolov, L. Hough, C. Hutton

3/27 High Performance Networks - N. Kadawedduwa, J. Kim, J. Liu, R. Misra

4/1 Clouds - Z. Lu, A. Namjoo, Q. Nguyen, R. Parsons

4/3 Clouds, cont. - X. Qi, M. Sukanya, X. Tian, J. Umeike

Tools

4/8 Event Ordering and Race Detection -

4/10 Data Collection and Instrumentation -

  
Web Accessibility