Course Content:

This course covers the principles of parallel programming. In this lesson, there will be a review of parallel architectures, followed by an introduction to the challenges of parallel programming concepts. Initially, there will be an overview of Intel processors with the SIMD architecture (e.g., MMX, SSE, and AVX) and their instruction sets. Practical examples will then illustrate how data-level parallelism (DLP) is utilized in these architectures.

The lesson continues with an exploration of parallelism at the thread level (TLP), reviewing architectures of Intel's multicore processors. The course will also examine how Intel designs multicore processor systems from a process and system-level perspective. We will be introduced to parallel programming using POSIX and OpenMP.

Intel’s library collection, known as IPP, will be presented as tools optimized by Intel for the development of parallel programs. Additionally, the course will introduce Intel's Parallel Studio, showcasing tools provided under this title for parallel development.

Finally, there will be an introduction to GPU architectures (GPGPU) and how parallel programming is implemented using CUDA.