CS 2410 (Graduate) Computer Architecture
Description
This course focuses on the techniques
of quantitative analysis and evaluation of modern computing
systems. The emphasis is on the
major component subsystems of high performance computers:
pipelining, instruction level parallelism,
memory hierarchy, input/output, and network-oriented
interconnections. Students will
undertake subsystem analysis projects.
Instructor, Fall 1998
Henry Chuang
316 Alumni Hall, 624-8424, chuang@cs.pitt.edu
Office Hours: M 1-3
T 2-4
Teaching Assistant:
Longjiang Yang, 314 Alumni Hall, 624-8402, ylj@cs.pitt.edu
Office Hours:
Text Book
J. L. Hennessy and D. A. Patterson,
Computer Architecture: A Quantitative Approach, 2nd Edition,
Morgan Kaufmann Publishing Co.
Grading
Midterm exam:
25%
Final exam
: 30 %
Homeworks
: 20%
Projects (2)
: 20%
Class participation:
5%
Lecture Plan
Week 1
-
Course introduction and overview
-
Application and technology trends
-
Performance, Benchmarks, and Metrics
Week 2
-
Performance rules of thumbs
-
Amdahl's Law
-
CPI formula
Week 3
-
Instruction set architecture
-
The DLX architecture
-
Introduction to pipelining
-
Pipeline hazards and stalls
Week 4
-
Data hazards, forwarding
-
Control hazards
-
Delayed branch
Week 5
-
Dealing with exceptions and interrupts
-
Multicycle operations
-
Instruction level parallelism and advanced pipelining
-
Dynamic scheduling
-
Scoreboard
Week 6
-
Tomasulo Algorithm
-
Dynamic branch prediction
-
Superscalar, VLIW, Software pipelining
-
Speculation
Week 7
-
Midterm exam
-
Memory hierarchy, motivation, implementation
-
Cache misses
-
causes of misses & ways to reduce misses
Week 8
-
Midterm review
-
Ways to reduce miss penalty
-
Main memory organization
-
Main memory performance enhancement
Week 9
-
DRAM-specific memory organization
-
Cache data consistency and I/O
-
Cache case study: the Alpha AXP 21064
Week 10
-
I/O, Storage devices
-
Buses and interfaces
-
A little Queuing theory
Week 11
Week 12
-
Networks, architectural issues including topologies
-
Networks, implementation and performance issues
Week 13
-
Internetworking
-
Multiprocessing, multiprocessors
Week 14
-
Multiprocessor, cache coherency
-
Snoopy caches and directory schemes
-
Multiprocessors: case study
Sample Exams
Projects
(Notes have been added to clarify questions concerning (1) write stalls
at write buffer, and (2) write buffer hit)
Assignments
Slides-patterson
Some
Slides
Software
Tools
Additional
Resources