Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
30 views

Distributed System Models and Enabling Technologies

This presentation discusses distributed system models and enabling technologies, focusing on scalability and computing paradigms. It covers horizontal and vertical scalability, high-performance and high-throughput computing, and various computing paradigms including RFID, GPS, and IoT. Additionally, it highlights advancements in multicore CPUs, GPU computing, and virtualization technologies for network-based systems.

Uploaded by

Kasi Lingamn
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
30 views

Distributed System Models and Enabling Technologies

This presentation discusses distributed system models and enabling technologies, focusing on scalability and computing paradigms. It covers horizontal and vertical scalability, high-performance and high-throughput computing, and various computing paradigms including RFID, GPS, and IoT. Additionally, it highlights advancements in multicore CPUs, GPU computing, and virtualization technologies for network-based systems.

Uploaded by

Kasi Lingamn
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 23

Distributed System

Models and Enabling


Technologies
This presentation explores distributed system models. We will
cover enabling technologies. The goal is to understand scalability
and paradigms.

by KASILINGAM N
Scalability
• It is the ability of a computer application or product(H/W or S/W)

to continue to function well when it is changed in size or volume


in order to meet a user needs

TYPES:
-Horizontal Scalability
-Vertical Scalability
Horizontal Scalability vs Vertical Scalability
-Add or remove resources within a single comp
-Add or remove computer resources(Node)
Example: Example:
Scaling from one to three web servers. Upgrading from one CPU to two CPUs.
Scalable Computing Over
the Internet
Age of Internet Computing
-HPC(High Performance Computing)

-HTC(High Throughput Computing)

Three Computing Paradigms


-RFID,GPS,IOT

Computing Paradigms Distinctions


-Centralized ,Parallel, Distributed, Cloud Computing
High-Performance
Computing (HPC)
1 Complex Problems
Solve large complex problems quickly.

2 Complex Calculations
Perform complex calculations at high speed.

3 System Performance
Measures system performance effectively.

4 Tightly Coupled
It is a tightly coupled system.
High-Throughput Computing
(HTC)
Maximize Performance
Maximize overall system performance.

Multiple Applications
Supports many users and applications.

Loosely Coupled
It is a loosely coupled system.

Example
Google search engine.
Evolution of HTC and HPC Systems
Computer Clusters
1 Group of Computers
Group of computers connected through network
and work as a single system.

2 Loosely or Tightly Coupled


Computers can be loosely or tightly coupled.

3 Homogeneous Computers
Collection of homogeneous computers.
Peer-to-
Peer
Networks
• Peers connect via the
Network or Internet.
• Files are shared directly.
No central server is
needed.
• Communicate each
node through message
passing.
New Computing Paradigms

RFID GPS IoT


• Reading through Satellite navigation Smart AC, smart
radio waves. to find object homes, Smart
• Saving details positions in ground. devices etc.
through
electromagnetic
fields.
Computing Paradigm Distinction

Centralized Computing 1 Parallel Computing


2

Cloud Computing
4 Distributed Computing
3
Technologies for Network Based System

1.Multicore CPU and Multithreading Technologies


1.1 Advances in CPU Processors
1.2 Multicore CPU and Many Core GPU Architecture
1.3 Multithreading Technology
2.GPU Computing To Exascale and Beyond
2.1 How GPU Works
2.2 GPU Programming Model
Technologies for Network Based System
(Continue…)

3.Memory Storage and Wide Area Networking


3.1 System Area Interconnects
4.Virtual Machines and Virtualization Middleware
5.Data Centre Virtualization for Cloud Computing
Advances in CPU Processors
Multicore CPU and Many Core GPU Architecture

-Multicore CPUs may increase from the tens of cores to hundreds more .
-Due to the memory wall problem.
-This has triggered the development of many-core GPUs with
hundreds or more thin cores.
-Both IA-32 and IA-64 instruction set architectures are built into
commercial CPUs.
-Now, x-86 processors
Multithreading Technology
GPU Computing To Exascale and Beyond
The world’s first GPU, the GeForce 256, was marketed by NVIDIA in 1999

-How GPU Works


• Early GPUs functioned as coprocessors attached to the CPU.
• Today, the NVIDIA GPU has been upgraded to 128 cores on a single chip.
Furthermore, each core on a GPU can handle eight threads of instructions.
(128*8=1024)
• This to having up to 1,024 threads executed concurrently on a single GPU.
• This is true massive parallelism, compared to only a few threads that can be
handled by a conventional CPU.
GPU Programming Model

-The use of a GPU along with a CPU for massively parallel execution in hundreds
or thousands of processing cores.
Memory Storage and Wide Area Networking
System Area Interconnects
Virtual Machines and Virtualization Middleware
Data Centre Virtualization for Cloud Computing

• Data Center Growth and Cost Breakdown


• Low-Cost Design Philosophy
• Convergence of Technology

You might also like