Course title
1M517000
Advanced Computer Architecture

usami kimiyoshi
Course content
CPU chips are the most important components in computer systems and their performance has been continuing to grow. In this lecture we study representative computer architectures that are actually used in high performance CPU chips. Furthermore, through designing hardware components (i.e. function units) and simulations, we analyze and discuss how the hardware structure influences the performance.
Purpose of class
To understand technologies in computer architecture to achieve high performance through case studies of real CPU chips
Goals and objectives
  1. To understand representative computer architectures that are actually used in high performance CPU chips
  2. To understand how the hardware structure influences the performance through a design project of hardware components
  3. To be able to actually design a hardware component used in a CPU and evaluate its performance
Language
Japanese
Class schedule

Class schedule HW assignments (Including preparation and review of the class.) Amount of Time Required
1. Guidance and overview of high-performance architecture Fundamentals of computer architecture 80minutes
2. Pipeline techniques, Hazard, Stall Review of Concept of pipelining, hazard and stall 200minutes
3. Dynamic scheduling to improve performance (1) Review of concept of dynamic scheduling 200minutes
4. Dynamic scheduling to improve performance (2) Review of issues in dynamic scheduling 200minutes
5. Superscalar technology (1) Review of concept of superscalar 200minutes
6. Superscalar technology (2) Review of basic components in superscalar architecture 200minutes
7. Case studies of superscalar technology (1) Review of superscalar in Intel Pentium processor 200minutes
8. Case studies of superscalar technology (2) Review of superscalar in Intel Pentium2 and Pentium4 processors 200minutes
9. Design project on CPU datapath components (1) Review of basic structure of adder 200minutes
10. Design project on CPU datapath components (2) Review of problems in ripple-carry adder 200minutes
11. Design project on CPU datapath components (3) Review of carry-lookahead adder 200minutes
12. Design project on CPU datapath components (4) Review of carry-select adder 200minutes
13. Multi-core and Multi-processor, Multi-threading, SIMD and MIMD Review of multi-processing technologies with multi-processors 100minutes
Review of multi-threading techniques and their pros and cons 100minutes
14. Presentation of the design and analysis results Design of high-speed adder and evaluation from performance and area 200minutes
Total. - - 2680minutes
Relationship between 'Goals and Objectives' and 'Course Outcomes'

esentation for assignments announced during class Reports and presentation on the design competition Total.
1. 20% 80% 100%
2. 0%
Total. 20% 80% -
Evaluation method and criteria
Total score of class participation and homework (20%), and presentation on the design project (80%). The criteria to pass is (1) to submit results of the design project and (2) to get at least 60% score.
Textbooks and reference materials
J. Hennessey and D. Patterson, "Computer Architecture: A quantitative approach," 5th edition, Morgan Kaufmann Publishers, 2012. 
Shen & Lipasti,"Modern Processor Design: Fundamentals of Superscalar Processors," McGraw-Hill, 2005.
Prerequisites
Basic knowledge on computer architecture is required.
Office hours and How to contact professors for questions
  • 11:00am – 12:00 on Thursdays
Relation to the environment
Non-environment-related course
Regionally-oriented
Non-regionally-oriented course
Development of social and professional independence
  • Course that cultivates an ability for utilizing knowledge
Active-learning course
About half of the classes are interactive
Last modified : Wed Oct 17 07:06:11 JST 2018