United Business Media EE Times


Search

HOMEMARKET INTELLIGENCE UNITFORUMSDESIGNNEW PRODUCTSCAREERSBLOGSCONTACTEVENTSSIGN UP!RSSMost Popular contentTrusted Sources

 


Viewpoint

Workload Management--An Enabling Technology

How do you shorten design cycles, cut time to market, and deliver better products? The answer includes workload management.

by Brad Casemore


EDA companies face increasingly complex problems: Chip and component density is growing, clock speeds are increasing, and operation voltage is decreasing. Consequently, these companies are trying to do more with less while striving to provide superior products to customers.

The combination of rapid technological advances and competitive pressure means designers are driven to bring better products to market faster than ever before. It's no surprise, then, that ASIC and IC designers eagerly adopt innovative enabling technologies to help them meet those goals.

Among these enabling technologies is workload management, which is being adopted increasingly by companies looking to shorten design cycles and beat competitors to market with next-generation products.

Workload management assumes many of the traditional operating system responsibilities at the network level, managing distributed computing resources while presenting a unified system image of what amounts to a virtual mainframe or virtual supercomputer. Batch, interactive, and parallel jobs are allocated dynamically, making full use of workstations and servers and delivering substantial improvement in overall system performance.

Although workload management is useful to any organization striving to get the most from its heterogeneous Unix and Windows NT computing resources, it has been especially popular in EDA environments.

In EDA, workload management offers a wide array of industry-specific capabilities. For example, enterprise-wide load sharing allows job queues to be automatically selected on the basis of job requirements, while dynamic allocation of software licenses ensures that job requirements are transparently matched to software and hardware resources.

Workload management also provides logical recentralizion of computing resources, enabling EDA organizations to share networked resources throughout a department or an entire company, thus eliminating workload imbalance and boosting productivity.

Another significant capability is job checkpointing and migration, which makes it possible for failed or stopped jobs to be picked up from where they left off elsewhere on the network--where the same types of computing resources are available to complete them. With APIs and script interfaces for integration with leading simulation applications, workload management can also provide transparent application support, allowing designers to work within a familiar user environment while taking full advantage of distributed computing resources.

Also, since applications can be closely coupled with a workload management batch system, users can transparently submit parallel jobs to workstation clusters. Running parallel processes lowers CPU and memory requirements and reduces the time it takes to run emulation, giving users the freedom to use all of their workstations in the design process.

What's more, the heterogeneous nature of workload management means Windows NT and Unix computing resources are seamlessly and transparently integrated. Designers need not worry about having to spend valuable time looking for the right platform on which to run their jobs.

All of those capabilities can be extended throughout enterprise-wide distributed computing environments. A growing number of EDA users have employed workload management's multiclustering feature to share resources and maximize productivity on thousands of computers in design departments thousands of miles apart.

Along with other measures, such as faster event-based simulators and better EDA methodologies, workload management plays a key role in meeting bottom-line operational requirements and delivering competitive advantage.


Brad Casemore is a senior marketing manager at Platform Computing Corp. in North York, Ont., where he currently works on issues concerning design infrastructure.

To voice an opinion on this or any Integrated System Design article, please email your message to miker@isdmag.com.


integrated system design  July 1998



[ Articles from Integrated System Design Magazine ] [ ICs and uPs ]
[ Custom ICs and Programmable Logic ] [ Vendor Guide ]
[ Design and Development Tools ] [ Home ]



For more information about isdmag.com email webmaster@isdmag.com
For advertising information email amstjohn@mfi.com
Comments on our editorial are welcome.
Copyright © 2000 Integrated System Design

  Free Subscription to EE Times
First Name Last Name
Company Name Title
Email address
  Click here for your Free Subscription to EETimes Europe
 
CAREER CENTER
Looking for a new job?
SEARCH JOBS
SPONSOR

RECENT JOB POSTINGS
CAREER NEWS
SRC Expands R&D Centers
The Semiconductor Research Corp has added a new center to its university R&D efforts.

For more great jobs, career related news, features and services, please visit EETimes' Career Center.


All White Papers »   

 
Education and
Learning


Learn Now:












Home | About | Editorial Calendar | Feedback | Subscriptions | Newsletter | Media Kit | Contact | Reprints|  RSS|   Digital|  Mobile
Network Websites
International
Network Features




All materials on this site Copyright © 2009 TechInsights, a Division of United Business Media LLC All rights reserved.
Privacy Statement | Terms of Service | About