Introduction MSCS 6060 – Parallel and Distributed Systems
Parallel System A parallel system consists of multiple processors that communicate with each other using shared memory 2
Distributed System A distributed system consists of multiple processors connected by a communication network 3
4 Parallel vs. Distributed System Parallel SystemsDistributed Systems MemoryTightly coupled shared memory UMA, NUMA Distributed memory Message passing, RPC, and/or used of distributed shared memory ControlGlobal clock controlNo global clock control Synchronization algorithms needed Processor interconnection Order of Tbps Bus, mesh, tree, mesh of tree, and hypercube (-related) network Order of Gbps Ethernet(bus), token ring and SCI (ring), myrinet(switching network) Main focusPerformance Scientific computing Performance(cost and scalability) Reliability/availability Information/resource sharing
5 Software and hardware service layers in distributed systems
6 Client Server Model
A Service Provided by Multiple Servers 7
Proxy Servers and Caches 8
Peer to Peer Computing 9
Mobile Agents 10
Parallel Computing Tutorial 11
12 Advantages of Distributed Computing Distributed applications airline reservation, banking system Data Sharing distributed databases Resource sharing sharing expensive processor Low cost Availability of high bandwidth networks and low cost workstations Reliability Failure of single system does not affect the whole Scalability In parallel systems, shared memory becomes a bottleneck Modularity and Heterogeneity Flexible to add a new processor
References (Parallel Computing Tutorial) Distributed Systems: Concepts and Design; 4th EdDistributed Systems: Concepts and Design; 4th Ed by G. Coulouris, J. Dollimore, T. Kindberg, Addison Wesley (ISBN ) Concurrent and Distributed Computing in JavaConcurrent and Distributed Computing in Java by Vijay K. Garg 13