Seminar on Multicore Programming
- 5.3. Programming project requirements added.
- 10.2. Unlike previously stated, we have a meeting on March 12th. More topics allocated.
- 6.2. Now half of the seminar topics have been allocated. Added few references in the literature list.
- 15.1. Updated the literature page and clarified course requirements.
- 12.1. First meeting on Thursday 22nd Jan 2009 at room A232.
- Course code: T-106.5800 Seminar on Software Techniques
- Credits: 3-10 (see the requirements)
- Grading: 0-5
- Teacher: prof. Heikki Saikkoinen
- Assistant: Kenneth Oksanen, Timo Lilja
- Registration: By sending e-mail to Timo Lilja (email@example.com). Number of students is limited, we will inform you before the seminar begins whether you are accepted. Remember to include your student number!
- Time and place: Thursdays 14-16, room A232
Moore's law of doubling every 18 months is still valid in terms of transistor density, but has failed for several recent years in terms of processor speed. In fact, in recent years the greatest increase processing speed has been accomplished by integrating several CPUs on the same chip. This trend will undoubtedly continue and there already are commercial processors with tens or even hundreds of computational cores.
In this seminar we shall investigate current and near-term hardware technologies in multicore systems (e.g. Intel/AMD, Sun) as well as general purpose computing on graphics coprocessors (e.g. NVIDIA), and software technologies (e.g. OpenMP, MPI, Cilk++, CUDA) that allow the programmer to use these new resources. We also review both easily and hardly parallellizable algorithms. Passing the seminar requires frequent attending, a seminar presentation and a small programming exercise on a multicore and/or GPU.
Timo Lilja Last modified: Thu Mar 5 13:41:47 EET 2009