SERVICE INTEGRATION IN THE DATA CENTER

The SOI of the enterprise DC cannot do without important network services such as firewall capabilities
and server load balancing. The services aggregation layer is a good place to integrate firewalls and
SLBs because it is typically the demarcation between L2 and L3 in the DC, and it allows these intelligent
service devices to be shared across multiple switches in the access layer. There are two ways to
integrate firewalls and SLBs:

• The use of separate services aggregation–layer switches as external services chassis to house
firewall and SLB service modules.
• The use of standalone appliance devices.
This book covers only the services chassis approach for housing firewalls and SLBs.

Read more

3.1 SYSML PURPOSE AND KEY FEATURES

CUDA enables efficient GPGPU computing with just a few simple additions to the C language. Simplicity of expression, however, does not equate to simplicity of program execution. As when developing applications for any computer, identifying performance bottlenecks can be complicated. Following the same economy of change used to adapt C and C++, NVIDIA has extended several popular profiling tools to support GPU computing. These are tools that most Windows and UNIX developers are already proficient and comfortable using such as gprof and Visual Studio. Additional tools such as hardware-level GPU profiling and a visual profiler have been added. Those familiar with building, debugging, and profiling software under Windows and UNIX should find the transition to CUDA straightforward. All CUDA tools are freely available on the NVIDIA website including the professional edition of Parallel Nsight for Microsoft Visual Studio. In this chapter, the Microsoft and UNIX profiling tools for CUDA will be used to analyze the performance and scaling of the Nelder-Mead optimization technique when optimizing a PCA and NLPCA functor.

At the end of the chapter, the reader will have a basic understanding of:

• PCA and NPLCA analysis, including the applicability of this technique to data mining, dimension reduction, feature extraction, and other data analysis and pattern recognition problems.
• How the CUDA profiling tools can be used to identify bottlenecks and scaling issues in algorithms.
• Scalability issues and how even a simple dynamic memory allocation can have dramatic performance implications on an application.

Read more

In this video, co-author, Bruce Davie describes his bestselling book, “Computer Networks: A Systems Approach, 5th Edition”. He discusses the “Systems Approach” to teaching Computer Networking.

3.1 SYSML PURPOSE AND KEY FEATURES

SysML1 is a general-purpose graphical modeling language that supports the analysis, specification, design, verification, and validation of complex systems. These systems may include hardware, software, data, personnel, procedures, facilities, and other elements of man-made and natural systems. The language is intended to help specify and architect systems and specify their components that can then be designed using other domain-specific languages such as UML for software design and VHDL and three-dimensional geometric modeling for hardware design. SysML is intended to facilitate the application of an MBSE approach to create a cohesive and consistent model of the system that yields the benefits described in Chapter 2, Section 2.1.2.

SysML can represent the following aspects of systems, components, and other entities:

• Structural composition, interconnection, and classification
• Function-based, message-based, and state-based behavior
• Constraints on the physical and performance properties
• Allocations between behavior, structure, and constraints
• Requirements and their relationship to other requirements, design elements, and test cases

Read more

3.1 IMPLEMENTATION LEVELS OF VIRTUALIZATION

Virtualization is a computer architecture technology by which multiple virtual machines (VMs) are multiplexed in the same hardware machine. The idea of VMs can be dated back to the 1960s [53]. The purpose of a VM is to enhance resource sharing by many users and improve computer performance in terms of resource utilization and application flexibility. Hardware resources (CPU, memory, I/O devices, etc.) or software resources (operating system and software libraries) can be virtualized in various functional layers. This virtualization technology has been revitalized as the demand for distributed and cloud computing increased sharply in recent years [41].

The idea is to separate the hardware from the software to yield better system efficiency. For example, computer users gained access to much enlarged memory space when the concept of virtual memory was introduced. Similarly, virtualization techniques can be applied to enhance the use of compute engines, networks, and storage. In this chapter we will discuss VMs and their applications for building distributed systems. According to a 2009 Gartner Report, virtualization was the top strategic technology poised to change the computer industry. With sufficient storage, any computer platform can be installed in another host computer, even if they use processors with different instruction sets and run with distinct operating systems on the same hardware.

Read more