RIT Computer Engineering

MY HOME PAGE



  

Assignment #1, Due Thursday April 2.

Assignment #2, Due Thursday April 30.

  

For the following lecture notes you can download or view a lecture as a PDF file:

3-10-98 Computer Generations; Computing Elements; Flynn's Classification, Performance Attributes; Multiprocessors Vs. Multicomputers

3-12-98 Aymptotic Algorithm Analysis; PRAM; VLSI Complexity Model, Network Model of Multicomputers, Conditions of Parallelism

3-17-98 Parallelism: Conditions; Levels, Hardware Vs. Software; Grain Size

3-19-98 Partitioning and Scheduling; Dataflow Vs. Controlflow

3-24-98 Network Properties; Static Vs Dynamic Networks

3-26-98 Parallel Performance Metrics; Amdahl’s Law

3-31-98 Parallel Application Models: Isoefficiency, Fixed-Workload, Fixed-Time, Fixed-Memory. Scalability

4-7-98 Shared Memory Access Consistency Models

4-9-98 Multiprocessor Cache Coherence, Snoopy Bus Protocols, Goodman's Write-Once Protocol, Directory-Based Protocols

4-16-98 Process Synchronization

4-21-98 Supercomputing Case Studies, Vector Supercomputing: Cray Y-MP, NCC-NUMA MPP: Cray T3E

4-23-98 Parallel Programming: Paradigms, Issues, Models


  

Tuesday and Thursday: 5:00-6:50 PM, 17/1535


  

Dr. Muhammad Shaaban
e-mail: meseec@osfmail.isc.rit.edu
Office: 17-2507 X2373


Office Hours:
My Spring 98 schedule


  

Current: http://www.rit.edu/~meseec/eecc756-spring98/
Spring 97: http://www.rit.edu/~meseec/eecc756/


  

This course covers a number of issues involved in the design and utilization of high performance parallel computing systems. This includes: parallel computer models, the concept of scalable performance, the memory hierarchy, parallel and scalable architectures, parallel programming concepts. A number of current parallel machines will be studied.


  

Advanced Computer Architecture EECC-722.


  

Advanced Computer Architecture: Parallelism, Scalability, Programmability, Kai Hwang, McGraw-Hill 1993.
Selected papers.


  

Homework assignments: 30%
Exam: 35%
Class project: 35%


  

Attending the lecture is expected.


  

Week 1: Parallel Computer Models
Week 2: Program and Network Properties
Week 3: Principles of Scalable Performance
Week 4: Processor and Memory Hierarchy
Week 5: Bus, Cache, and Shared Memory
Week 6: Pipelining and Superscalar Techniques
Week 7: Multiprocessors and Multicomputers
Week 8: Multivector and SIMD Computers
Week 9: Software for Parallel Programming


Made with at least 30% post-consumer recycled bits