Computer Architecture

Computer architecture, trends, and quantitative principles. Instruction-level parallelism, out-of-order execution, and examples. Memory hierarchy design. Multiprocessors, thread-level parallelism, and multithreading. General purpose graphics processor units (GPGPUs) and accelerators. Hardware security and side-channel attacks.

Knowledge:

• The student should have knowledge of current technology trends and their impact on computer architecture design.
• The student should have a detailed understanding of how high-level building blocks like different varieties of processors, caches, interconnects, accelerators, etc. should be assembled into a complete computer system.
• The student should have an understanding of the construction and mode of operation of modern memory systems.
• The student should have an understanding of how multiple processor cores, general-purpose graphics processing units (GPGPUs), and accelerators can be assembled into parallel computer architectures.
• The student should be familiar with hardware security measures.

Skills:

• The student should be able to evaluate architectural choices using simulation and draw sensible conclusions based on these studies.
• The student should be able to differentiate between general purpose central processing units (CPUs), general purpose graphics processing units (GPGPUs), and application specific accelerators in terms of their specific advantages and disadvantages.

General competence:

• The student should be able to leverage his/her knowledge of computer architecture at all levels of abstraction.

Lectures, exercises, mini-project, report writing, peer-evaluation.