High Performance Computing - IT Library : ZDNet Asia

White Papers

Case Studies

Vendor Webcast

Show all content

Title Date Added Company

The Global Computer 2007-01-08 01:00:33 Institute of Electrical and Electronics Engineers

The problems collaborating with others across the network are apparent to anyone who has tried doing it. That being the case, one should attempt to create an environment that doesn't have those issues. One approach is to make it appear to people and programs that there is only one computer in the world. In building such a system people will have to solve problems of scalable performance, naming, security, discovery, and manageability. If one has to succeed in hiding the boundaries between machines, the solutions one must come up with will have to be part of a coherent architecture.

Using advanced compiler technology to exploit the performance of the Cell Broadband Engine architecture 2007-03-01 11:18:31 IBM

Exploit the true potential of next generation game consoles. In this paper, IBM presents a variety of compiler techniques designed to exploit the performance potential of the SPEs and to enable the multilevel heterogeneous parallelism found in the Cell Broadband Engine architecture, enhancing programmability while continuing to provide high performance.

The paper also reviews the Cell Broadband Engine architecture and presents the results of compiler techniques, including SPE optimization, automatic code generation, single source parallelization, and partitioning.

High-Performance Server Systems and the Next Generation of Online Games 2006-03-23 05:00:08 IBM

Developing a massively multiplayer online game which utilizes physically based simulation to provide realistic behaviors requires numerical integration functions with inherently high computational costs. This simulation, performed on the individual clients of a peer-to-peer networked game or for a client/server online game, presents challenges due to many factors, including limited computing resources at the client level and network latency in the propagation of a client's state to other clients. This paper explores how a game developer who is aware of these issues might create a game for IBM's recently announced Cell Broadband Engine processor.

Emerging Computing Technologies for E&P - 2006 & Beyond 2006-03-23 04:36:22 IBM

Exploration and Production (E&P) businesses are heavily dependent on finite natural resources: oil and gas. While companies look to manage their existing capital to expand and improve traditional operations, the entire E&P ecosystem is undergoing a tectonic shift. As such, E&P companies need to operate existing assets better and increase their capital portfolio. In particular, E&P firms need robust, high performance information capabilities, platforms, and processes that support collaboration and coordination throughout the entire industry. This paper briefly discusses emerging computing technologies, research, and innovation that is required to move from today's High Performance Computing (HPC) arena to Petascale Computing.

Get More from Your Oracle Database: Best Practice Performance Management for Real Results 2006-01-01 Confio Software

DBAs are constantly challenged to increase database performance while keeping costs down. This short paper discusses Resource Mapping Methodology (RMM) which defines a systematic process for performing Wait-Event analysis to optimize database performance. It includes a brief overview of Ignite for Oracle and the business benefits that Ignite users have demonstrated.

Technologies of ETERNUS VS900 Storage Virtualization Switch 2006-06-07 01:00:26 Fujitsu

This paper gives an outline of storage virtualization and then describes a new-generation storage virtualization system that is based on Fujitsu's ETERNUS VS900 storage virtualization switch. The VS900 provides a simplified, logical view of a complicated storage system and simplifies storage management. It adopts a network-based, out-of-band virtualization model. Among other advantages, the VS900 provides high performance, reliability, and availability. It is managed by Systemwalker Resource Coordinator, which not only manages a storage system but also manages other system resources such as servers and networks to enable unified system-wide management.

Linux Clusters White Paper 2006-01-01 IBM

Clustered computing has been around for several years. Clusters have been devised, formally or informally, from many types of systems. On one extreme, the IBM eServer zSeries, when configured in a Sysplex, represents a cluster. At the other end of the power spectrum, many organizations have assembled Intel (and other) processor-based servers into clusters of various types. Initial efforts in Linux clustering have been in the High Performance Computing (HPC) area, and the current Intel Xeon, AMD Opteron, and IBM POWER high clock rate servers will continue to make this area vital. High-availability solutions for Linux clusters are now available from several Independent Software Vendors (ISVs), and span a range of capability and complexity.

Enabling Operational Business Intelligence Using Microsoft SQL Server and the AIS Platform 2006-02-10 10:49:58

Attunity Integration Suite, serves as a strategic component in any data integration infrastructure. It dramatically improves efficiencies, eliminates the needs for batch windows, deals with the growth of data volumes, delivers information in real-time, and reduces costs. AIS also provides an enterprise-scale Change Data Capture solution that complements and works seamlessly with existing ETL, EAI and EII solutions. Visit us at www.attunity.com.

CA Message Manager Archive: Intelligent-Level Retention of Messages 2006-07-04 05:42:15 CA (Computer Associates)

To handle enterprise-level message management, scalability has to be a central focus. CA Message Manager Archive (MM Archive) has been designed to process millions of messages and archive hundreds of gigabytes per day in a high availability and high performance fashion. Supporting multi-threaded processes and services in all components that can span over multiple servers, MM Archive is designed using enterprise-level best practices regarding load balancing, high resiliency and business continuity. Supporting a wide range of content sets and with flexible alternatives for capturing mail flow, MM Archive offers the most coverage and scalability as an enterprise archival solution.

Scalable Grid Service Discovery Based on UDDI 2006-04-20 06:29:36

Efficient discovery of grid services is essential for the success of grid computing. The standardization of grids based on web services has resulted in the need for scalable web service discovery mechanisms to be deployed in grids. Even though UDDI has been the de facto industry standard for web-services discovery, imposed requirements of tight-replication among registries and lack of autonomous control has severely hindered its widespread deployment and usage. With the advent of grid computing the scalability issue of UDDI will become a roadblock that will prevent its deployment in grids. This paper presents the distributed web-service discovery architecture, called DUDE (Distributed UDDI Deployment Engine). DUDE leverages DHT (Distributed Hash Tables) as a rendezvous mechanism between multiple UDDI registries.

Jump to 1 2 3 4 5 6 7 8 [9] 10

Data Management

Related TechGuides

Featured Whitepapers

10 million IT Folks can't be wrong with their server choice.

Oracle Technology Solutions for Midsize Businesses

Country Report: India

Title	Date Added	Company
The Global Computer	2007-01-08 01:00:33	Institute of Electrical and Electronics Engineers
The problems collaborating with others across the network are apparent to anyone who has tried doing it. That being the case, one should attempt to create an environment that doesn't have those issues. One approach is to make it appear to people and programs that there is only one computer in the world. In building such a system people will have to solve problems of scalable performance, naming, security, discovery, and manageability. If one has to succeed in hiding the boundaries between machines, the solutions one must come up with will have to be part of a coherent architecture.
Using advanced compiler technology to exploit the performance of the Cell Broadband Engine architecture	2007-03-01 11:18:31	IBM
Exploit the true potential of next generation game consoles. In this paper, IBM presents a variety of compiler techniques designed to exploit the performance potential of the SPEs and to enable the multilevel heterogeneous parallelism found in the Cell Broadband Engine architecture, enhancing programmability while continuing to provide high performance. The paper also reviews the Cell Broadband Engine architecture and presents the results of compiler techniques, including SPE optimization, automatic code generation, single source parallelization, and partitioning.
High-Performance Server Systems and the Next Generation of Online Games	2006-03-23 05:00:08	IBM
Developing a massively multiplayer online game which utilizes physically based simulation to provide realistic behaviors requires numerical integration functions with inherently high computational costs. This simulation, performed on the individual clients of a peer-to-peer networked game or for a client/server online game, presents challenges due to many factors, including limited computing resources at the client level and network latency in the propagation of a client's state to other clients. This paper explores how a game developer who is aware of these issues might create a game for IBM's recently announced Cell Broadband Engine processor.
Emerging Computing Technologies for E&P - 2006 & Beyond	2006-03-23 04:36:22	IBM
Exploration and Production (E&P) businesses are heavily dependent on finite natural resources: oil and gas. While companies look to manage their existing capital to expand and improve traditional operations, the entire E&P ecosystem is undergoing a tectonic shift. As such, E&P companies need to operate existing assets better and increase their capital portfolio. In particular, E&P firms need robust, high performance information capabilities, platforms, and processes that support collaboration and coordination throughout the entire industry. This paper briefly discusses emerging computing technologies, research, and innovation that is required to move from today's High Performance Computing (HPC) arena to Petascale Computing.
Get More from Your Oracle Database: Best Practice Performance Management for Real Results	2006-01-01	Confio Software
DBAs are constantly challenged to increase database performance while keeping costs down. This short paper discusses Resource Mapping Methodology (RMM) which defines a systematic process for performing Wait-Event analysis to optimize database performance. It includes a brief overview of Ignite for Oracle and the business benefits that Ignite users have demonstrated.
Technologies of ETERNUS VS900 Storage Virtualization Switch	2006-06-07 01:00:26	Fujitsu
This paper gives an outline of storage virtualization and then describes a new-generation storage virtualization system that is based on Fujitsu's ETERNUS VS900 storage virtualization switch. The VS900 provides a simplified, logical view of a complicated storage system and simplifies storage management. It adopts a network-based, out-of-band virtualization model. Among other advantages, the VS900 provides high performance, reliability, and availability. It is managed by Systemwalker Resource Coordinator, which not only manages a storage system but also manages other system resources such as servers and networks to enable unified system-wide management.
Linux Clusters White Paper	2006-01-01	IBM
Clustered computing has been around for several years. Clusters have been devised, formally or informally, from many types of systems. On one extreme, the IBM eServer zSeries, when configured in a Sysplex, represents a cluster. At the other end of the power spectrum, many organizations have assembled Intel (and other) processor-based servers into clusters of various types. Initial efforts in Linux clustering have been in the High Performance Computing (HPC) area, and the current Intel Xeon, AMD Opteron, and IBM POWER high clock rate servers will continue to make this area vital. High-availability solutions for Linux clusters are now available from several Independent Software Vendors (ISVs), and span a range of capability and complexity.
Enabling Operational Business Intelligence Using Microsoft SQL Server and the AIS Platform	2006-02-10 10:49:58
Attunity Integration Suite, serves as a strategic component in any data integration infrastructure. It dramatically improves efficiencies, eliminates the needs for batch windows, deals with the growth of data volumes, delivers information in real-time, and reduces costs. AIS also provides an enterprise-scale Change Data Capture solution that complements and works seamlessly with existing ETL, EAI and EII solutions. Visit us at www.attunity.com.
CA Message Manager Archive: Intelligent-Level Retention of Messages	2006-07-04 05:42:15	CA (Computer Associates)
To handle enterprise-level message management, scalability has to be a central focus. CA Message Manager Archive (MM Archive) has been designed to process millions of messages and archive hundreds of gigabytes per day in a high availability and high performance fashion. Supporting multi-threaded processes and services in all components that can span over multiple servers, MM Archive is designed using enterprise-level best practices regarding load balancing, high resiliency and business continuity. Supporting a wide range of content sets and with flexible alternatives for capturing mail flow, MM Archive offers the most coverage and scalability as an enterprise archival solution.
Scalable Grid Service Discovery Based on UDDI	2006-04-20 06:29:36
Efficient discovery of grid services is essential for the success of grid computing. The standardization of grids based on web services has resulted in the need for scalable web service discovery mechanisms to be deployed in grids. Even though UDDI has been the de facto industry standard for web-services discovery, imposed requirements of tight-replication among registries and lack of autonomous control has severely hindered its widespread deployment and usage. With the advent of grid computing the scalability issue of UDDI will become a roadblock that will prevent its deployment in grids. This paper presents the distributed web-service discovery architecture, called DUDE (Distributed UDDI Deployment Engine). DUDE leverages DHT (Distributed Hash Tables) as a rendezvous mechanism between multiple UDDI registries.