M.E. Power Systems & Electric Drives:Parallel & Distributed Computing
Master
In Patiala
Description
-
Type
Master
-
Location
Patiala
Facilities
Location
Start date
Start date
Reviews
Course programme
Semester-I
Research Methodology
Computer Application to Power System Analysis
Advanced Power Electronics
Power System Dynamics & Stability
Industrial Drives & Automation
Semester II
Power Quality & FACTS Devices
Optimal Power System Operation
Intelligent Techniques & Applications
Semester III
Minor Project
Seminar
Thesis (Start)
Semester IV
Thesis (Continues)
Parallel & Distributed Computing
Introduction: What is parallel and distributed computing? Scope of parallel and distributed computing; Issues in parallel and distributed computing; Organization and contents of the course.
Models of Parallel Computing: Taxonomy of parallel structures ? Control mechanism, Address-Space Organization, Interconnection connection networks; Process Granularity; An idealized parallel computer; Dynamic Interconnection networks ? crossbar switching networks; Bus-based networks; multistage interconnection networks; Static interconnection networks ? types of static interconnection networks, evaluating static interconnection networks, embedding other networks (Linear Array, Mesh, Binary Tree) into a hypercube; Routing mechanisms for static interconnection networks ? S tree and Forward(SF) Routing; Cut - Theory (CT) Routing; Cost-Performance trade-off; Architectural Models for Parallel Algorithm design.
Basic Communication Operation: Simple message transfer between two processors; One-to-all broadcast; All-to-all broadcast; Reduction and prefix sums; One-to-all personalized communication; All-to-all personalized communication; circular shift; Faster method for some communication operation ? Routing messages in parts, All-port communication, Special hardware for Global operations.
Performance and Scalability of Parallel Systems: Performance matrics for Parallel systems ? Run time, Speed up, Efficiency and Cost; The effect of granularity and data mapping on performance; Scalability of parallel systems; Isoefficiency metric of scalability; Load imbalance and Extra computation; Minimum execution time and minimum cost-optimal execution time.
Sorting: Sorting networks; Bubble sort and its variants; Quick sort and other sorting algorithms: Enumeration sort, Bucket sort, Sample sort and Radix sort.
Search Algorithms for Discrete Optimization Problems: Sequential search algorithms; Search overhead factor; Parallel best-first search; Speedup anomalies in parallel search algorithms.
Models of Distributed Computing: Mini computer model; Workstation pool model; Client-server model; Pool of processors model; Hybrid model.
Networking and Internetworking: Network technologies; Protocols; Technology case studies; Protocol case studies.
Interprocess Communication and Remote Procedure Calling: Building blocks; Client-server communication; group communication; Case study: Interprocessor communication in UNIX; Design issues in Remote procedure calling; Implementation; Case Studies: SUN and ANSA; Asynchronous RPC.
Distributed Operating Systems: Case Studies: Mach; Chorus; UNIX emulation in Mach and Chorus; Amoeba; A comparison of Mach, Amoeba and Chorus; Clouds; Firefly RPC; The Amoeba multicast protocol.
Laboratory Work: Implementation of various parallel algorithms in parallel/distributed vnvironment.
M.E. Power Systems & Electric Drives:Parallel & Distributed Computing