parallel system interconnections and communications
Skip this Video
Download Presentation
Parallel System Interconnections and Communications

Loading in 2 Seconds...

play fullscreen
1 / 65

Parallel System Interconnections and Communications - PowerPoint PPT Presentation

  • Uploaded on

Parallel System Interconnections and Communications. Abdullah Algarni February 23,2009. Outline . Parallel Architectures - SISD - SIMD - MIMD - Shared memory systems -Distributed memory machines Physical Organization of Parallel Platforms - Ideal Parallel Computer

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
Download Presentation

PowerPoint Slideshow about 'Parallel System Interconnections and Communications' - ely

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
  • Parallel Architectures




-Shared memory systems

-Distributed memory machines

  • Physical Organization of Parallel Platforms

-Ideal Parallel Computer

  • Interconnection Networks for Parallel Computers

-Static and Dynamic Interconnection Networks


-Network interfaces

outline con
Outline (con.)
  • Network Topologies



-Multistage Networks

-Multistage Omega Network

-Completely Connected Network

-Linear Arrays



-Tree-Based Networks

-Fat Trees

-Evaluating Interconnection Networks

  • Grid Computing
classification of parallel architectures
Classification of Parallel Architectures
  • SISD: Single instruction single data

– Classical von Neumann architecture

  • SIMD: Single instruction multiple data
  • MIMD: Multiple instructions multiple data

– Most common and general parallel machine

single instruction multiple data
Single Instruction Multiple Data

• Also known as Array-processors

• A single instruction stream is broadcasted to multiple processors, each having its own data stream

– Still used in graphics cards today

multiple instructions multiple data
Multiple Instructions Multiple Data

• Each processor has its own instruction stream and input data

  • Further breakdown of MIMD usually based on the memory organization

– Shared memory systems

– Distributed memory systems

shared memory systems
Shared memory systems
  • All processes have access to the same address space

– E.g. PC with more than one processor

  • Data exchange between processes by writing/reading shared variables
  • Advantage: Shared memory systems are easy to program
  • – Current standard in scientific programming: OpenMP
shared memory systems1
Shared memory systems

• Two versions of shared memory systems available today:

  • – Symmetric multiprocessors (SMP)
  • – Non-uniform memory access (NUMA)
symmetric multi processors smps
Symmetric multi-processors (SMPs)

• All processors share the same physical main memory

• Disadvantage: Memory bandwidth per processor is limited

• Typical size: 2-32 processors

numa architectures 1 non uniform memory access
NUMA architectures (1)(Non-uniform memory access)

• More than one memory but some memory is closer to a certain processor than other memory

  • The whole memory is still addressable from all processors
numa architectures cont
NUMA architectures (cont.)

• Advantage: ItReduces the memory limitation compared to SMPs

• Disadvantage: More difficult to program efficiently

• To reduce effects of non-uniform memory access, caches are often used

• Largest example of this type:

SGI Origin with10240 processors

Columbia Supercomputer

distributed memory machines
Distributed memory machines
  • Each processor has its own address space
  • Communication between processes by explicit data exchange
  • Some protocols are used:

– Sockets

– Message passing

– Remote procedure call / remote method invocation

distributed memory machines con
Distributed memory machines(Con.)

• Performance of a distributed memory machine strongly depends on the quality of the network interconnect and the topology of the network interconnect

  • Two classes of distributed memory machines:

1) Massively parallel processing systems (MPPs)

2) Clusters

ideal parallel computer
Ideal Parallel Computer
  • A natural extension of the Random Access Machine (RAM) serial architecture is the Parallel Random Access Machine, or PRAM.
  • PRAMs consist of p processors and a global memory of unbounded size that is uniformly accessible to all processors.
  • Processors share a common clock but may execute different instructions in each cycle.
ideal parallel computer1
Ideal Parallel Computer
  • Depending on how simultaneous memory accesses are handled, PRAMs can be divided into four subclasses.
    • Exclusive-read, exclusive-write (EREW) PRAM.
    • Concurrent-read, exclusive-write (CREW) PRAM.
    • Exclusive-read, concurrent-write (ERCW) PRAM.
    • Concurrent-read, concurrent-write (CRCW) PRAM.
ideal parallel computer2
Ideal Parallel Computer
  • What does concurrent write mean, anyway?
    • Common: write only if all values are identical.
    • Arbitrary: write the data from a randomly selected processor.
    • Priority: follow a pre-determined priority order.
    • Sum: Write the sum of all data items.
physical complexity of an ideal parallel computer
Physical Complexity of an Ideal Parallel Computer
  • Processors and memories are connected via switches.
  • Since these switches must operate in O(1) time at the level of words, for a system of p processors and m words, the switch complexity is O(mp).
brain simulation
Brain simulation

Imagine how long it takes to complete Brain Simulation?

  • The human brain contains 100,000,000,000 neurons each neuron receives input from 1000 others
  • To compute a change of brain “state”, one requires 1014 calculations
  • If each could be done in 1s, it would take ~3 years to

complete one calculation.

Brain simulation

Imagine how long it takes to complete Brain Simulation?

  • The human brain contains 100,000,000,000 neurons, each neuron receives input from 1000 others
  • To compute a change of brain “state”, one requires 1014 calculations
  • If each could be done in 1s, it would take ~3 years to

complete one calculation.

  • Clearly, O(mp) for big values

of p and m, a true PRAM is not realizable.

interconnection networks for parallel computers
Interconnection Networks for Parallel Computers
  • Important metrics:

– Latency:

• minimal time to send a message from one processor to another

• Unit: ms, μs

– Bandwidth:

• amount of data which can be transferred from one processor to another in a certain time frame

• Units: Bytes/sec, KB/s, MB/s, GB/s, Bits/sec, Kb/s, Mb/s, Gb/s

static and dynamic interconnection networks
Static and DynamicInterconnection Networks

Classification of interconnection networks:

(a) a static network; and (b) a dynamic network.

  • Switches map a fixed number of inputs to outputs.
  • degree of the switch: the total number of ports on a switch is the degree of the switch.
  • The cost of a switch: grows as the square of the degree of the switch.
network interfaces
Network Interfaces
  • Processors talk to the network via a network interface.
  • The network interface may hang off the I/O bus or the memory bus.
  • In a physical sense, this distinguishes a cluster from a tightly coupled multicomputer.
  • The relative speeds of the I/O and memory buses impact the performance of the network.
network topologies
Network Topologies

- A variety of network topologies have been proposed and implemented.

- These topologies tradeoff performance for cost.

- Commercial machines often implement hybrids of multiple topologies for reasons of packaging, cost, and available components.

Single Campus Network

  • 538 nodes
  • 543 links

10 campus networks connected in ring

  • Some of the simplest and earliest parallel machines used buses.
  • All processors access a common bus for exchanging data.
  • The distance between any two nodes is O(1) in a bus. The bus also provides a convenient broadcast media.
  • However, the bandwidth of the shared bus is a major bottleneck.
  • Typical bus based machines are limited to dozens of nodes. Sun Enterprise servers and Intel Pentium based shared-bus multiprocessors are examples of such architectures.
buses first type
Buses(First type)

The execution time is lower bounded by:

TxKP seconds

P: processors

K: data items

T: time for each data access

The bounded bandwidth of a bus places limitations on the overall performance of the network as the number of nodes increases!

buses second type with chache memory
Buses(Second type, with chache memory)

If we assume that 50% of the memory accesses (0.5K) are made to local data, in this case:

The execution time is lower bounded by:

0.5x TxKP seconds

Which means that we made 50% improvement compared to the first type.


A crossbar network uses an p×m grid of switches to connect p inputs to m outputs in a non-blocking manner

  • The cost of a crossbar of p processors grows as O(p2).
  • This is generally difficult to scale for large values of p.
  • Examples of machines that employ crossbars include the Sun Ultra HPC 10000 and the Fujitsu VPP500.
multistage networks
Multistage Networks
  • Crossbars have excellent performance scalability but poor cost scalability.
  • Buses have excellent cost scalability, but poor performance scalability.
  • Multistage interconnects strike a compromise between these extremes.
multistage networks1
Multistage Networks

The schematic of a typical multistage interconnection network

multistage omega network
Multistage Omega Network
  • One of the most commonly used multistage interconnects is the Omega network.
  • This network consists of log p stages, where p is the number of inputs/outputs.

So, for 8 processors and 8 memory banks we need 3 stages

multistage omega network1
Multistage Omega Network
  • Each stage of the Omega network implements a perfect shuffle as follows:
multistage omega network2
Multistage Omega Network
  • The perfect shuffle patterns are connected using 2×2 switches.
  • The switches operate in two modes – crossover or passthrough.

Two switching configurations of the 2 × 2 switch:

(a) Pass-through; (b) Cross-over.

multistage omega network3
Multistage Omega Network
  • A complete Omega network with the perfect shuffle interconnects and switches can now be illustrated:

An omega network has p/2 × log pswitching nodes, and the cost of such a network grows as (p log p).

multistage omega network routing
Multistage Omega Network – Routing
  • Let s be the binary representation of the source and d be that of the destination.
  • The data traverses the link to the first switching node. If the most significant bits of s and d are the same, then the data is routed in pass-through mode by the switch else, it switches to crossover.
  • This process is repeated for each of the log p switching stages using the next significant bit.
multistage omega network routing1
Multistage Omega Network – Routing

Routing from s= 010 , to d=111

Routing from s= 110 , to d=101

completely connected network
Completely Connected Network
  • Each processor is connected to every other processor.
  • The number of links in the network scales as O(p2).
  • While the performance scales very well, the hardware complexity is not realizable for large values of p.
  • In this sense, these networks are

static counterparts of crossbars.


Completely Connected

star connected networks
Star Connected Networks
  • Every node is connected only to a common node at the center.
  • Distance between any pair of nodes is O(1). However, the central node becomes a bottleneck.
  • In this sense, star connected networks are static counterparts of buses.




linear arrays
Linear Arrays
  • In a linear array, each node has two neighbors, one to its left and one to its right.
  • If the nodes at either end are connected, we refer to it as a 1-D torus or a ring.

Linear arrays: (a) with no wraparound links; (b) with wraparound link.


Two- and Three Dimensional Meshes

Two and three dimensional meshes: (a) 2-D mesh with no wraparound; (b) 2-D mesh with wraparound link (2-D torus); and (c) a 3-D mesh with no wraparound.


The Construction


Properties :

  • The distance between any two nodes is at most log p.
  • Each node has log p neighbors.
tree based networks
Tree-Based Networks

Complete binary tree networks: (a) a static tree network; and (b) a dynamic tree network.

tree based networks1
Tree-Based Networks

Properties :

  • The distance between any two nodes is no more than 2logp.
  • Links higher up the tree potentially carry more traffic than those at the lower levels.
  • For this reason, a variant called a fat-tree, fattens the links as we go up the tree.
fat trees
Fat Trees

A fat tree network of 16 processing nodes.

evaluating interconnection networks
Evaluating Interconnection Networks
  • Diameter:The distance between the farthest two nodes in the network.
  • Bisection Width:The minimum number of wires you must cut to divide the network into two equal parts.
  • Cost: The number of links or switches
  • Degree: Number of links that connect to a


grid computing
Grid Computing
  • How?

By using Grid computing we can make Computational Resources sharing Across the World.

  • What is the relationship between parallel computing and grid computing?

Grid computing is a special case of parallel computing

can we tie all components tightly by software
Can we tie all components tightly by software?




High Speed Network


Problem Solving Environment

  • Menu
  • Template
  • Solver
  • Pre & Post
  • Mesh

Visual Data Server





User Access Point

Grid Resources

Talk at SASTRA

are grids a solution
Are Grids a Solution?
  • Goals of Grid Computing
  • Reduce computing costs
  • Increase computing resources
  • Reduce job turnaround time
  • Reduce Complexity to Users
  • Increase Productivity
Computational Resources





MPI, PVM,Condor...




C, Fortran

Java, Perl

Java GUI





Client - RPC like

What is needed?



what does the grid do for you
What does the Grid do for you?
  • You submit your work
  • And the Grid
    • Finds convenient places for it to be run
    • Organises efficient access to your data
      • Caching, migration, replication
    • Deals with authentication to the different sites that you will be using
    • Interfaces to local site resource allocation mechanisms, policies
    • Runs your jobs, Monitors progress, Recovers from problems, Tells you when your work is complete
typical current grid
Typical current grid
  • Virtual organisations negotiate with sites to agree access to resources
  • Grid middleware runs on each shared resource to provide
    • Data services
    • Computation services
    • Single sign-on
  • Distributed services (both people and middleware) enable the grid


E-infrastructure is the key !!!

examples of grids
Examples of Grids
  • TeraGrid (
    • USA distributed terascale facility at 4 sites for open scientific research
  • Information Power Grid (

NASAs high performance computing grid

    • GARUDA

Department of Information Technology (India Gov.).

It connect 45 institutes in 17 cities in the country at

10/100 Mbps bandwidth.

  • [1] Introduction to Parallel Computing. By AnanthGrama, Anshul Gupta, George Karypis, and Vipin Kumar.
  • [2] Parallel System Interconnections and Communications. By D. Grammatikakies, D. Frank Hsu, and MiroKraetzl
  • [3] Wikipedia, the free encyclopedia
  • [4] Introduction to Grid Computing with Globus (
  • [5] Network and Parallel Computing: Ifip International Conference Npc 2008 Shanghai China Octob. By Jian (EDT)/ Li Cao
  • [6] Network and Parallel Computing . By Jian (EDT) Cao & Minglu (EDT) Li & Min-you (EDT) Wu & Jinjun (EDT) Chen
my question
My Question
  • List three types of dynamic interconnection networksthat are used in parallel computing and evaluate each of them.
  • The answer: