Textbook: Hwang, K., Advanced Computer Architecture:
Parallelism, Scalability, Programmability, McGraw-Hill, New York, NY,
1993.
Description: Prereq: EEL 5717, CDA 5155, or consent of the instructor. Introduction to the fundamental hardware and software topics in parallel computing including models, metrics, architectures, systems, and applications.
Time and Place: 3rd period (9:35-10:25am), MWF, Room 239, Larsen Hall.
Textbook: Hwang, K., Advanced Computer Architecture:
Parallelism, Scalability, Programmability, McGraw-Hill, New York, NY,
1993.
References: To be announced
Instructor: Dr. Alan D. George, Associate Professor of Electrical and Computer Engineering, Director of the High-performance Computing and Simulation (HCS) Research Laboratory. Office: Larsen 213, Telephone: (352)392-5225, Fax: (352)392-8671, Email: george@hcs.ufl.edu, Lab URL: http://www.hcs.ufl.edu, Office Hours: 10:30-12:00 MW or by appointment.
Prerequisites by topic: Fundamentals of computer design, performance and cost, instruction set design principles and alternatives, instruction set architecture measurements, basic processor implementation techniques, pipelining, memory-hierarchy design, input/output, and computer arithmetic.
Goals: To introduce the students to parallel computer models, metrics, architectures, systems, and applications, and for the students to gain a fundamental knowledge and understanding of the field of parallel computing.
Topics:
Engineering Applications: Parallel computer architecture, software, and system design and analysis; high-performance computing; parallel processing applications.
Project(s): Several projects will be assigned in order to explore fundamental issues in parallel computing, including one capstone project. Students will be expected to make use of UNIX workstations and the Internet for their class assignments.
Grading Policy: Midterm Examination (25%), Final Examination (25%), and Projects/Papers/Homework (50%).
Conduct Policy: All assignments are to be considered an individual effort unless otherwise specified by the instructor. Students are expected to read, understand, and follow the honor code rules as set forth by the university.
| Chp. 1 (1/6/97) | Parallel Computer Models |
| Chp. 2 (1/10/97) | Program and Network Properties |
| Chp. 3 (1/22/97) | Principles of Scalable Performance |
| Chp. 4 (2/3/97) | Processors and Memory Hierarchy |
| Chp. 5 (2/14/97) | Bus, Cache, and Shared Memory |
| Chp. 7 (3/05/97) | Multiprocessors and Multicomputers |
| Chp. 8 (3/19/97) | Multivector and SIMD Computers (excluding Sect. 8.3) |
| Chp. 9 (3/28/97) | Scalable, Multithreaded, and Dataflow Architectures |
| Chp. 10 (4/11/97) | Parallel Models, Languages, and Compilers (Sect. 1-2) |
HOMEWORK ASSIGNMENTS| Paper #1 (due 1/13/97) |
Contribution and Importance of Parallel Computing in Computing -- Past, Present, and Future (weight=1) |
| Homework #1 (due 1/22/97) | Problems 1.5, 1.8, 1.11-1.15, and 2.3-2.8 in the textbook (weight=1) |
| Homework #2 (due 2/3/97) | Problems 2.9-2.15 and 3.1-3.5 in the textbook (weight=1) |
| Project #1 (due 2/7/97) | ISA Model,
Cross-Assembler, and Simulator for a Baseline MPP Node (weight=2); examples
include: ==> the KM-1 RISC ISA ==> the BUBBA Vector ISA |
| Paper #2 (due 2/24/97) |
SIMD versus MIMD -- Past, Present, and Future (weight=1) |
| Project #2 (due 3/21/97) | Architecture,
Simulator, and Performance Analysis of a Parallel Computer (weight=4);
examples include: ==> the KM-2 Parallel Computer ==> the BUBBAstation Parallel Computer |
| Paper #3 (due 4/2/97) |
Multiprocessing versus Multicomputing (weight=1) |
| Homework #3 (due 4/9/97) | Problems 7.2, 7.5, 7.10-7.14, 8.1-8.4, 8.6-8.8 and 8.12-8.14 in the textbook (weight=1) |
| Project #3 (due 4/21/97) |
Parallel Computing with an Existing Parallel Computer System or
Testbed (weight=4); examples include: |
| Presentation (on 4/23/97) |
Student Presentations of Project #3 (weight=1) |