14
Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Embed Size (px)

Citation preview

Page 1: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Comparing Topology based Collective Communication

Algorithms

• Vishal Sharda• Ashima Gupta

Page 2: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Work progress

• No up-to-date open source solution available for fully mapping the network to build upon

• Nomad, Cheops, Nagios, ENV, Argus etc. outdated

• Use of a third-party service to determine the topology

• Java applet to map SERC network

Page 3: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Status of current study

• Nearly all the research on this problem till now considers tightly-coupled systems.

• Thus, most of the algorithms assume point-to-point connectivity.

• So, these have to be modified to adapt to the network of heterogeneous workstations.

Page 4: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

All to all broadcast

• Also known as multinode broadcast

• Generalization of one-to-all broadcast in which all the processors simultaneously initiate a broadcast.

• Different processors may send out different message.

Page 5: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Existing Algorithms

• Direct exchange

• Circular all-to-all

• E1 algorithm

• Liquid Schedule

• Algorithms for specific topologies like start and mesh.

Page 6: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Direct Exchange

• Simplest approach

• Assumes point to point connectivity

• Each node simultaneously sends data to each other node

• Involves lot of congestion

Page 7: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Circular all-to-all

• Let p be the no. of nodes

• For each node i for step k in {1..p}, node i

sends to (i+k)mod p

receives from(i-k+P)mod p

Page 8: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

E1 algorithm

• One node receives messages from all other nodes(becomes an expert)

• Experts are formed by recursively doubling existing experts.

Page 9: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Liquid schedule algorithm

• Traffic is the set of all collective exchanges.

• A simultaneous sub traffic is part of the traffic involing non-congesting transfers.

• Identify the bottleneck links in the network.

• A liquid schedule is such that all the bottleneck links are utilized in every sub-traffic.

Page 10: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Need for Simulation

• Deciding the packet to follow a particular route needs to bypass router decisions– Needs DLL operations.

• Focus on comparing the algorithms– Incorporate simulation-based study like

standard experiments.

Page 11: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Basis of Simulation

• Execute and compare the algorithms for the network specifed at the interface.

• Some algorithms will take bandwidth of the links into account.

• Depending on the input, an algorithm may or may not show good results.

Page 12: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Implementation Approach

• Network represented as weighted undirected graph with weights inversely proportional to bandwidth.

• Simulating n processes on different nodes in a network with Java threads.

• First of all, each node will compute the shortest path to all other nodes using single source shortest path algorithm.

Page 13: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

Handling Collision

• Lot of collision involved in all-to-all broadcast.

• Several approaches possible like partitioning into subnets , choosing alternate link.

• Our approach will be to stick to the shortest link and if collision detected then wait for random time and sense again.

Page 14: Comparing Topology based Collective Communication Algorithms Vishal Sharda Ashima Gupta

ReferencesPapers :

• "ECO: Efficient Collective Operations for Communication on Heterogeneous Networks",Bruce B. Lowekamp and Adam Begueliny.

• "Network Topology Aware Scheduling of Collective Communications",Emin Gabrielyan, Roger D. Hersch.

• "On General Results for all-to-all broadcast", Ming-Syan Chen et. al

• “Efficient all-to-all broadcast in star graph interconnecion networks",Yu-Chee Tseng et.al

Websites:• freemap.qualys.com