Course content

Computer architecture fundamentals, trends, measuring performance, quantitative principles. Instruction set architectures and the role of compilers. Instruction-level parallelism, branch prediction, thread-level parallelism, VLIW and examples. Memory hierarchy design, cache, storage systems. Multiprocessors and Thread-Level Parallelism, shared memory architectures, distributed shared memory, synchronization, multithreading. Interconnection networks, topologies, clusters, case study. Vector processors.

Learning outcome

Knowledge:
- The student should have a detailed understanding of how high-level building blocks like different varieties of processors, caches, interconnects, buses, etc. should be assembled into a complete computer system.
- The student should have a detailed understanding of the construction and mode of operation of modern memory systems
- The student should have a detailed understanding of how multiple processor cores can be assembled into parallel computer architectures. This includes homogenous and heterogeneous multi-core processors and multi-processors.
- The student should know how the interplay between architecture, system software and the application affects performance in parallel computer systems
- The student should know how vector processors are constructed and their mode of operation.

Skills:
- The student should be able to evaluate architectural choices with simulators and draw sensible conclusions based on these studies.

General competence:
- The student should be able to leverage his knowledge of computer architecture in development projects at all levels of abstraction.

Learning methods and activities

Auditorium lectures and self-study. Exercise counts 20% and written exam counts 80%. Final grade (A to F) given at end of semester. If there is a re-sit examination, the examination form may change from written to oral. All lectures will be given in English. The exam will be in English. Students are free to choose Norwegian or English for written assessments.

Recommended previous knowledge

Course TDT4160 Computers and Digital Design, or equivalent.

Course materials

Computer Architecture: A Quantitative Approach, 5th edition by John L. Hennessy, David A. Patterson. Morgan Kaufmann. Eventually additional text announced at the start of the semester. All teaching materials will be in English.

Credit reductions