Computer Science @ UC Davis | Course Descriptions

ECS 158 PROGRAMMING ON PARALLEL ARCHITECTURES (4) III

Lecture: 3 hours

Prerequisites: Course ECS 150; ECS 154B recommended

Grading: Letter; two midterms (20% each), final exam (40%) and programming work (20%)

Catalog Description:
Techniques for software development using the shared-memory and message-passing paradigms, on parallel architectures and networks of workstations. Locks, barriers and other techniques for synchronization. Introduction to parallel algorithms.

Expanded Course Description:

Programming Paradigms
1. Shared-memory
2. Message-passing
3. Bulletin-board (tuple space)
4. Distributed shared memory (DSM)
5. Software packages: MPI, PVM, Linda, p4, Adsmith, pthreads
Overview of Parallel Architectures
1. Shared-memory and message-passing hardware
2. Interconnect structures, e.g. bus, crossbar,Omega-net, mesh
3. Cache coherency
Interprocess Synchronization
1. Review of operating systems material: Processes, timesharing, OS-based interprocess synchronization
2. Synchronization hardware, e.g. test-and-set and fetch-and-add instructions
3. Locks, barriers
Latency Problems
1. Memory/network delays
2. Latency hiding, e.g. using nonblocking messages
Collective Communication
1. Broadcast, scatter/gather, all-scatter/all-gather
Overview of Parallel Applications
1. Sorting, database
2. Graph algorithms
3. Scientific computing

Textbook:
Instructor's class notes.

Computer Usage:
Extensive programming assignments on our CSIF networked machines. The shared-memory work is done using Adsmith and the MulSim simulator, and the message-passing component using MPI.

Engineering Design Statement:
Students in the course write sophisticated, systems-level programs according to their own design. Many of the programs involve analysis of tradeoffs between efficient use of the hardware and ease of programming.

ABET Category Content:
Engineering Science: 2 units
Engineering Design: 2 units

Goals:
Student will:

learn techniques of software development using the shared-memory and message-passing paradigms on parallel architectures and networks of workstations
be introduced to parallel algorithms

Program Educational Outcomes:

The ability to work independently
The ability to work on a team
The ability to apply knowledge of basic science, mathematics, and engineering principles to solve computing and information processing problems
The ability to write correct and good programs
The ability to understand the relationship between hardware and software
The ability to understand the tradeoffs in the design of hardware systems, software systems, processes and components
The ability to construct appropriate abstractions to manage complexity and to think creatively about new problems
The ability to use experimental methods on software systems by gathering data to improve the systems
The ability to acquire the foundations to do well in graduate school
The ability to acquire the foundations to be a life-ling learner

Instructors: M. Farrens, N. Matloff , R. Pandey, K. Ma

Prepared By: N. Matloff (November 2003)

Overlap Statement:
Comparison of this course with other existing courses does not indicate any significant overlap.

5/06