Course Description

Prerequisites:

LINKS:

Course Organization and Presentations:

• Course Organization.
• Lecture 1, Overview.
• Lecture 2, Technology.
• Lecture 3, Programming homework environment.
• Lecture 4, Concepts.
• Lecture 5, CPU Architectures.
• Lecture 6, Memory systems.
• Lecture 7, Memory systems cont'd.
• Lecture 8, Interconnection Networks.
• Lecture 9, Interconnection Networks, cont'd.
• Lecture 10, Parallelism.
• Lecture 11, OpenMP.
• Lecture 12, Vectorization.
• Lecture 13, Vectorization cont'd.
• Lecture 14, Accelerators - GPU.
• Lecture 15, Accelerators - GPU-II.
• Lecture 16, Sorting-I.
• Lecture 17, MPI-I.
• Lecture 18, MPI-II.
• Lecture 19, Sorting-II.
• Lecture 20, Matrix-Vector multiplication.
• Lecture 21, Matrix-Matrix multiplication.

Handouts:

• Notes of Lecture 4.
• Open MPI Tutorial given at SC05.
• Notes on vector architectues.
• Notes on vectorization.
• Notes on memory systems.
• Notes on memory systems II.
• Notes on Interconnection Networks.
• Notes on Parallel Sorting.
• Notes on Parallel Sorting-II.
• Notes on Dense Matrix Multiplication.
• Notes on FFT.
• Notes on FFT-II.
• Notes on Recurrences.
• Notes on Sparse Matrices.

References: