Parallel Computing

Most new computer architectures are parallel, requiring programmers to know the basic issues and techniques for writing this software. This course is an introduction to the basic issues of and techniques for writing parallel software.

You will be provided with an advanced foundation in various programming models and varieties of parallelism in current hardware.

Significant parallel programming assignments will be given as homework. 

Topics Include

• Fast networks, multicore, accelerators and vector instruction sets
• Implicit vs. explicit parallelism
• Shared vs. non-shared memory
• Synchronization mechanisms such as locking, atomicity, transactions and barriers
• Parallel programming models such as threads, MapReduce, Apache Spark and SIMT