| Course title | |||||
| 並列処理特論 [Parallel Processing] | |||||
| Course category | courses for doctoral programs | Requirement | Credit | 2 | |
| Department | Year | ～ | Semester | 3rd | |
| Course type | 3rd | Course code | 1080443 | ||
| Instructor(s) | |||||
| 中條 拓伯 [NAKAJO Hironori] | |||||
| Facility affiliation | Faculty of Engineering | Office | afjgxte/L1151 | Email address | |
| Course description |
|
Currently, high performance computers consist of multiple computers connected via network and perform parallel processing efficiently. In this class, we discuss processor technologies especially on cache memory in a computing system. Cache technology for multi-processing is discussed, too. |
| Expected Learning |
|
Can explain parallel processing system architecture. Can judge performance of the parallel computing system quantitatively. Can apply basic knowledge on parallel processing to the students' own researches. |
| Course schedule |
|
This course uses a compact parallel processing board Parallella. https://www.parallella.org/ Also, you should read the famous text book "Computer Architecture Quantitative Approach" and make presentation of the assigned chapter. The Content of the course is as follows: #1. Basic concept of parallel processing and its purpose #2. Basic Data communication in parallel processing: shared memory and message passing #3. Basic concept of cache memory in a single processor #4. Cache organization for shared memory: Basic protocol #5. Cache organization for shared memory: Other outstanding protocols #6. Basic installation of a parallel processing board Parallella #7. Development environment of a parallel processing board Parallella #8. Practice of parallel processing using Parallella No.1: Sample program #9. Practice of parallel processing using Parallella No.2: Message passing #10. Practice of parallel processing using Parallella No.3: Evaluation of applications #11. Practice of parallel processing using Parallella No.4: Presentation of each result #12. Presentation of the assigned chapter No.1 #13. Presentation of the assigned chapter No.2 #14. Presentation of the assigned chapter No.3 #15. Presentation of the assigned chapter No.4 |
| Prerequisites |
|
Basic knowledge on system programming and network is required. In addition to 30 hours that students spend in the class, students are recommended to prepare for and revise the lectures, spending the standard amount of time as specified by the University and using the lecture handouts as well as the references specified below. |
| Required Text(s) and Materials |
| Poper Point files will be given in every lecture. |
| References |
|
John L. Hennessy and David Patterson: "Computer Architecture Quantitative Approach 6th Edition" |
| Assessment/Grading |
|
Small report in each lecture Final report on dedicated topics in advanced computing system |
| Message from instructor(s) |
| Course keywords |
| Parallel processign, processor architecture, Parallel architecture |
| Office hours |
| Remarks 1 |
| Remarks 2 |
| Related URL |
| Lecture Language |
| Language Subject |
| English |
| Last update |
| 4/8/2021 5:53:51 AM |