0% found this document useful (0 votes)
8 views

Laod Balancing in Parallel Computing

This document discusses load balancing in parallel computing. It covers types of parallel computers like shared and distributed memory, interconnect methods, programming models, and load balancing approaches. Static approaches include deterministic and probabilistic, while dynamic approaches include bidding, drifting, threshold, and greedy methods. Load balancing aims to distribute work evenly across resources to maximize throughput and minimize response times.

Uploaded by

Rajnish Bishnoi
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
8 views

Laod Balancing in Parallel Computing

This document discusses load balancing in parallel computing. It covers types of parallel computers like shared and distributed memory, interconnect methods, programming models, and load balancing approaches. Static approaches include deterministic and probabilistic, while dynamic approaches include bidding, drifting, threshold, and greedy methods. Load balancing aims to distribute work evenly across resources to maximize throughput and minimize response times.

Uploaded by

Rajnish Bishnoi
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 18

LOAD BALANCING

IN
PARALLEL COMPUTING

TEAM MEMBERS:-
HEMANT SHARMA
RAJNISH BISHNOI 1
Introduction to Load Balancing
In terms computer networking the load
balancing Is a technique to
distribute workload evenly across two
or more computers, network links,
CPUs, hard drives, or other resources, in
order to get optimal resource utilization
& maximize throughput or minimize
the response time & avoid overload .
2
Types of Parallel Computers
 The parallel computers are classified as
 shared memory
 distributed memory
 Both shared and distributed memory systems have:
1. processors
2. memory
3. network

3
Interconnect Method

There is no single way to connect bunch of processors


The manner in which the nodes are connected -
Network & Topology(mesh,star).

4
Block Diagrams …

Memory

Interconnection Network

P1 P2 P3 P4 P5 Processors

A Shared Memory Parallel Computer


5
Block Diagrams …
Interconnection Network

P1 P2 P3 P4 P5

M1 M2 M3 M4 M5

A Distributed Memory Parallel Computer


6
PROCESS IN SERIAL COMPUTING

7
PROCESS IN PARALLEL COMPUTING

8
Types of parallelism

Control parallelism (Algorithmic parallelism):

Data parallelism

9
Parallel Programming Models

Different approaches are used in the development of


parallel programs

Shared Variable Model:

Message Passing Model:

10
Load Sharing and Queuing System

Keep track of available nodes in the system


Allot nodes to jobs
Maintain job queues with job priority,
reservations

11
Distributed scheduling
Distributed scheduling is composed of
two parts:

Local Scheduling

Global Scheduling

12
Network connectivity in Distributed System

P1 P2 Pk
.......

Computer N/W

Pk+1 ....... Pn-1 Pn


13
Different Approaches used in load
balancing :-

Two different form have been taken by researchers in


their attempts to achieve load balance in distributed
systems are –

 Static

 Dynamic

14
Static Load balancing :-

The Static approach further divide into two


categories -
Deterministic - A deterministic strategy assigns
tasks to processors based on a fixed criterion.
Probabilistic - A probabilistic strategy uses
probability values when the assignment is made.

15
Dynamic Load Balancing : -
well known strategies are –
 Bidding
 Drifting
 Threshold
 Greedy

16
Scope of Project

Load balancing in parallel computing has been


considered to be "the high end of computing", and has
been used to model difficult scientific and engineering
problems found in the real world .
Few of them are –

Computer Science, Mathematics

17
**THANK’S TO ALL OF YOU**

18

You might also like