The following table is a tentative syllabus for this course:
| Week | Monday | Wednesday | Friday | Chapter |
|---|---|---|---|---|
| Part I: Distributed-Memory Parallelism | ||||
| 1 | Course Overview | MPI Exercise 1 | 1 | |
| 2 | Parallel Patterns | Master-Worker and Message-Passing | MPI Exercise 2 | 2 |
| 3 | Parallel Algorithm Design | Collective Communication Patterns | MPI Exercise 3 | 3 |
| 4 | Complexity | Benchmarks and Formal Models | MPI Exercise 4 | |
| 5 | MPI Process Groups | Parallel Matrix Multiplication | ||
| 6 | Advanced MPI Topics | Parallel Sorting | MPI Exercise 5 | |
| 7 | O-O MPI | C++ in MPI-2 | Final Project Selection | |
| Part II: Shared-Memory Parallelism | ||||
| 8 | Basic Patterns in Pthreads | Mutual Exclusion in Pthreads | Pthreads Exercise | 4 |
| 9 | Basic Patterns in OpenMP | Mutual Exclusion in OpenMP | OpenMP Exercise | 5 |
| Part III: Hybrids & Accelerators | ||||
| 10 | Hybrid Architectures | MPI+OpenMP | Hybrid (MPI+OpenMP) Computing | 6 |
| 11 | GPU Computing | CUDA | CUDA Computing | |
| 12 | OpenCL | OpenACC | OpenCL Computing | |
| 13 | Coprocessors | Using Intel's Xeon Phi | Using the Xeon Phi Coprocessor | |
| Part IV: Map-Reduce | ||||
| 14 | Map-Reduce | Using Map-Reduce | Using MapReduce/Hadoop | |
| 15 | Code Optimization | HPC History | The Future | |
| 16 | Research and Complete Final Projects | |||