Product Watch: Oracle To Deliver Database For Linux. Zx10 Workstation Delivers Fast Performance. Agilent Forms SAN Division.

October 6, 2000



San Francisco, CALIF. — Oracle Corp., the largest provider of software for e-business, announced the industry’s first clustered database server on the Linux operating system, Oracle8i Parallel Server. Customers will be able to use the low-cost Linux operating system to deploy mission critical, highly available business applications or large-scale data warehouses. Targeted specifically at easing the pressure e-businesses face in today’s “always on” Internet environment, Oracle8i Parallel Server on Linux aims to eliminate costly downtime, increase revenue opportunities and ultimately ensure success for a new generation of Linux applications. Oracle also announced future support for Oracle9i Real Application Clusters, the next evolution of Oracle8i Parallel Server, on the Linux platform. To Linux, Oracle now brings its most mature and trusted high-availability technology for clustered databases. With sub-minute failover capability, Linux environments can achieve new levels of application and data availability. And powered by the new Cache Fusion Architecture, Oracle9i Real Application Clusters will help deliver huge scalability improvements to the Linux platform by providing transparent load balancing and the efficiencies of a shared cache architecture.

“The availability of enterprise class solution platforms, such as Oracle8i Parallel Server and Oracle8i running on Linux, is an important step towards allowing organizations to construct cost effective clusters based upon high volume and low cost systems,” said Dan Kusnetzky, vice president of system software, for IDC in Framingham, MA. “This type of configuration is going to be increasingly important to organizations implementing flexible, high performance, Web-based applications.” Oracle8i Parallel Server on Linux will support up to a 4-node, 8-way cluster. Three Linux vendors, SuSE, TurboLinux and VA Linux Systems, have already tested on Oracle8i Parallel Server running on Linux. Additionally several hardware vendors are working with Oracle to assemble and provide certified clusters to their customer bases. For the initial release, Oracle8i Parallel Server has been validated by Intel and certified by VA Linux Systems and NEC. Several of Oracle’s partners have beta customers or demonstrations available at Oracle OpenWorld. For instance, Intel will have a 4-node cluster demo; VA Linux is demonstrating a 4-node cluster with an EMC Symmetrix disk array. “Oracle Parallel Server on Linux creates an opportunity for LeaseExchange to truly eliminate single points of failure,” said Jay Borenstein, CTO of LeaseExchange. “We are extremely excited to have the capability of delivering this kind of stability and performance to our customers.”

With Oracle8i Parallel Server on Linux, applications running on any server in a cluster instantly have access to all data in a database. Therefore, the different servers act cooperatively to manage unpredictable workloads. In the case of a system failure, applications can continue to run on the remaining nodes with a minimum of interruption or loss of data. Used in combination with other built-in Oracle database features, Linux clusters can be up and running around-the-clock, protecting against downtime resulting from planned maintenance, hardware or software failures, or even operator error. “As Linux matures into an enterprise-class operating system, Oracle8i and Oracle8i Parallel Server provide the engine driving extremely scalable and reliable Linux-based applications and web sites,” Michael Rocha, senior vice president, Platform Technologies Division, Oracle Corporation. “The emergence of the Linux platform in business critical environments is the logical evolution of the proven open systems model. It is in the spirit of this model that Oracle announces the expansion of Oracle’s database and accompanying technologies on this platform.”


Mountain View, CALIF. — SGI announced that its new Silicon Graphics Zx10 visual workstation with Wahoo Technology, powered by an Intel Pentium III 933 MHz processor, topped competitors’ posted Pentium III 1 GHz processor performance on the industry-standard SPECgpc benchmarks (to view scores visit ). Silicon Graphics Zx10, which has a Pentium III 933 MHz processor and Wildcat 4210 3D graphics, performed up to 7% faster on the SPECgpc benchmark than the Dell Precision 420 with a Pentium III 1 GHz processor and Wildcat 4210 graphics.

Real-world application benchmark performance confirms Silicon Graphics Zx10 status as the world’s fastest Windows NT OS-based workstation. In addition, Silicon Graphics Zx10 visual workstation is available immediately with the latest Pentium III 1 GHz processor that delivers even higher performance for visual computing professionals. Featuring Wahoo Technology, an innovative approach to design integration and tuning, the Silicon Graphics Zx10 eliminates bottlenecks inherent in other architectures and delivers unprecedented systems throughput and graphics performance in an industry-standard workstation. Its industry-leading performance enables creative, scientific, and technical professionals in the digital media, MCAD, publishing and prepress, and visual simulation markets to accelerate the most demanding applications in 3D animation, high-definition digital video, real-time visual simulation, complex 3D modeling, and complex data analysis.


Palo Alto, CALIF. — Agilent Technologies Inc. announced that it has formed the Storage Networking Division to focus on the fast-growing storage area networking (SAN) market. The division will initially focus on Fibre Channel technology, where Agilent has established a strong position through its IC and board-level products. It will also focus on emerging technologies such as InfiniBand and IP SAN that promise to be important standards for the storage market. Industry veteran Julian Elliott has been named vice president and general manager of the new division after leading Agilent’s SAN efforts for the past four years. Elliott reports to Bill Sullivan, senior vice president and general manager of Agilent’s Semiconductor Products Group. Elliott has more than 15 years experience in the computer and storage market, including stints as marketing manager for Hewlett-Packard Company’s Personal Computer Group and as vice president of Marketing at BusLogic Inc. He holds a bachelor’s degree in physics from the Georgia Institute of Technology and a master’s of business administration from Stanford University.

“The formation of this division is an indication of the success Agilent has had in penetrating the storage networking market,” said Elliott. “This move sends a strong message that we intend to continue to serve this market aggressively. We believe that we have the people and the technologies in place to continue our strong growth.” Agilent is a leading supplier of Fibre Channel solutions for the rapidly expanding SAN market, providing industry-leading Tachyon Fibre Channel controllers and HBA solutions that include software and driver support for all major operating environments. Agilent also provides a complete set of components for Fibre Channel, including fiber optic transceivers, serializer/deserializer (SerDes) ICs, and port bypass circuits. Agilent has also presented early demonstrations of both the InfiniBand I/O standard, and the emerging IP SAN technology. Information about Agilent Technologies can be found on the Web at .


Tinton Falls, N.J. — ECCS, Inc., introduced the Synchronix 3000, a fault-tolerant data storage engine that delivers superior performance in speed, storage capacity, data protection and storage management, along with the advantages of full-fibre connectivity. “Our new Synchronix 3000 data storage engine is a truly superior technology,” said Gregg M. Azcuy, President and CEO of ECCS. “We’ve built such a high-level of performance into the Synchronix 3000 in speed, storage capacity, data protection and storage management, along with full-fibre connectivity, that it’s the ideal tool for organizations to meet new, expanding data storage needs in a cost-effective manner.” The Synchronix 3000 achieves real large-block transfer speeds of 190 MB per second for two channels, a speed that is significantly higher than other systems on the market, including previous ECCS systems. Storage capacity is 4.38 TB with one standard 70″ cabinet and can expand to 20.1 TB with two additional standard cabinets. And the Synchronix 3000 provides for the full use of fibre-channel capabilities among a network’s controller, host and disk drives, with operating links reaching up to 10 kilometers.

The most effective data-protection features are built into the Synchronix 3000. Enhanced RAID technology provides for RAID levels 30 and 50, as well as levels 0, 1, 3, 5, 10 and JBOD, and for unique fault-tolerant data security. The Synchronix 3000 can notify network operations of any system fault through e-mail, pager, fax and a customized program. Users don’t risk losing access to data when adding new disk drives, because the system does not have to be shut down for system changes. A redundant system provides two identical devices for monitoring environmental factors like temperature, fan operation and power-supply status. Using special software capabilities, the Synchronix 3000 provides unprecedented flexibility in meeting an organization’s specific storage requirements. It can become the central data storage for different networks, including Direct Attached Storage (DAS) and Network Attached Storage (NAS), and Storage Area Networks (SAN) with ECCS’ new SANStar data storage engine, which is the only product on the market capable of unifying an organization’s data storage resources. It provides storage capacity for any environment, because it adheres to Open Systems protocols. The Synchronix 3000 allows key components, like controllers, disk drives, power supplies and fans, to be added without making program changes, shutting down the network or losing access to data. Modular construction allows for the addition of new storage capacity. The Synchronix 3000 is delivered with ten disk drives. Additional disk drives can be added in increments as small as one drive to a maximum of 60 disk drives with each controller pair. The Synchronix 3000 enclosure is compact – 3 U or 5.25″ – for easy planning and minimal use of valuable space.


Atlanta, GA. — Sony Electronics announced that it has begun shipments of the GY-8240, a formidable addition to its family of high performance Digital Tape Format (DTF) drives, (as well as the new GW series) DTF-2 tape cassettes. The new DTF-2 drives and media offer a combination of extremely high-density tape storage (200 Gigabytes per cassette – native) with ultra high-speed data transfer rates (24 Megabytes per sec – native), while maintaining backwards compatibility with DTF-1. “Sony’s DTF product line demonstrates our continued leadership in the media rich tape storage business,” says Tom Yuhas, director of the Sony Data Systems Division. “The Sony DTF family of tape drives has been the choice for tape storage solutions by leading companies around the world, including CNN. The fact that DTF has been embraced across so many industries – including IT/data centers, medical, government, broadcasting and seismic – is a testament to the advantages of helical scan tape drives over longitudinal, linear recording.” The DTF-2 drives provide a clear migration path to even higher performance while maintaining compatibility to the current installed base of DTF-1 units. “They are an ideal choice for a variety of applications, such as mission-critical backup and restore,” added Yuhas. “Storage area networks (SAN), network attached storage (NAS), archiving of media for digital assets management, seismic processing and data acquisition are all ideal applications for DTF-2. As with DTF-1, we expect that DTF-2 will be supported by leading major integrated software vendors.”

The new GY-8240 series extends the Sony DTF family by offering high-performance data management capabilities through a combination of an extremely high transfer rate of 24 MB/sec., sustained; fast load to ready; and high-density tape storage of 200 GB per cassette, uncompressed. There are two models in the GY-8240 series. The GY-8240UWD features an Ultra Wide Differential SCSI interface with a sustained data transfer rate of 24 MB/sec and 40 MB/sec with compression. The GY-8240FC features a native Fibre Channel interface with a sustained data transfer rate of 24 MB/sec with bursts up to 100 MB/sec. The GY-8240 series represents the second generation (DTF-2) of computer tape drives using the Sony Digital Tape Format. Both units feature advanced amorphous head design and a sophisticated error correction system enabling a bit error rate of better than 1 x 10-17. The drives will also play back data written on Sony DTF-1 tape drives (GY-2120 series) at a sustained data rate of 24 MB/sec. In addition to these new drives, Sony has developed a new tape media as well. According to Tom Evans, vice president of marketing for Sony Electronics’ Media Solutions Co., the new media offers three advantages: (1) Greater tape capacity in the cassette thanks to a new material, MP++; (2) Non-contact IC memory that reads various types of information including table of contents without contacting IC, avoiding any chance of deterioration and resulting in a quicker search of the tape; and (3) Extremely low running cost. For additional information, visit .


Carlisle, MASS. — Codemesh, Inc. ( ) is now shipping the first release of JunC++ion, a patent pending technology that allows Java and C++ programs to work together in one process. With JunC++ion, Java and C++ programmers can continue to work in whatever language best solves a problem, while relying on JunC++ion to integrate the mixed language solution. JunC++ion provides businesses with a new scope of solutions to integration problems; for example, C++ clients can be part of an EJB environment, Java servlets can declare C++ native methods to web-enable C++ applications, and both Java and C++ components can use a single set of APIs, such as JDBC for database connectivity.

Alexander Krapf, president of Codemesh, has talked with interested customers throughout the US, Europe, and Asia. “As I talk with more and more customers, I realize how extensive the language integration problem has become. Integration issues add onto project requirements, skew programming solutions, and increase time-to-market. JunC++ion helps these companies get through these integration problems so that they can focus on their real business.” JunC++ion can be used throughout an organization to solve problems at several levels. C++ application developers can use JunC++ion to get access to Java classes that provide functionality they need in a C++ application. Software library providers can use JunC++ion to produce an equivalent set of APIs for both Java and C++ based on just the Java or C++ library. Organizations can use JunC++ion internally to tie together a Java/C++ mixed server environment or to accelerate a multi-component C++ to Java porting project. At all these levels, JunC++ion cuts down development time significantly because it opens up the power of Java to C++ and C++ power to Java.


Bridgewater, N.J. — StorageApps Inc. announced new SANLink Storage systems that are based on technology from LSI Logic Storage Systems, Inc. The storage systems can be configured for 180 gigabytes to more than 16 terabytes capacity – equivalent to electronically storing the contents of a floor full of academic journals to as much as the printed collection of the U.S. Library of Congress. The high-performance storage system supports Fibre Channel attachment and provides customers with high availability by allowing drives and servers to be added “on-the-fly” without downtime. “We’re offering industry-leading performance with our SANLink Storage products and responding to our customer requests for one-stop solutions for their storage infrastructure,” said Dan Petrozzo, president and chief operating officer of StorageApps.

The SANLink Storage system provides both high throughput and high transaction rates delivering 350 megabyte per second sequential read performance and 60,000 cached I/Os per second. The storage systems are available with 10,000 RPM disk drives of 18, 36 or 73 gigabytes capacity. The SANLink Storage systems are available immediately. For additional information, go to . In addition to SANLink Storage products, StorageApps develops and offers software and storage appliances that allow customers to connect any type of data storage and any server over any connection type. StorageApps provides 24/7 service to customers worldwide that range from Fortune 100 companies in financial services to dot-com businesses.


Roy, UTAH — Iomega Corporation, a global leader in data management solutions, announced shipment of its redesigned Zip 100MB Universal Serial Bus (USB) drive. In tandem with the updated design, the new Zip 100MB USB drive comes with the latest OS support for Microsoft Windows Me/95/98/NT 4.0 and 2000, as well as Mac OS 8.5.1 through 9.0.4. The new Zip 100MB USB drive is available at an estimated street price of $99.95. The Zip 100MB USB drive is hot-swappable, connecting quickly and easily to both PC and Macintosh systems without rebooting. The drive is also compatible with millions of Zip 100MB disks shipped, and users can add virtually unlimited storage capacity with additional Zip 100MB disks.

The drive’s low price and stylish design also make it a promising external storage solution for future Internet appliances and gaming consoles. “The Zip 100MB USB drive shows Iomega’s continued commitment to provide consumers with innovative, simple-to-use and cost-effective products,” said Michael Ludgate, general manager, magnetic products, Iomega Corporation. The redesigned Zip 100MB USB drive is currently available at or through major distributors and resellers.


Fountain Valley, CALIF. — StorCase Technology, Inc. announced the release of its new Ultra160 RAID Controller Module, specifically designed for the InfoStation nine-bay backplane-design RAID chassis. “With data transfer rates of more than 18,000 IOPS (I/O Operations Per Second), the InfoStation RAID Controller module provides fast-throughput and flawless performance making it perfect for data streaming, transaction processing, imaging, CAD and other demanding applications,” said Dieter Paul, President of StorCase. “Keeping our customers’ long-term growth needs and ROI in mind, StorCase designed one module to be capable of supporting up to four InfoStation chassis, 30 drives, 24 arrays, and 32 LUNs,” added Paul.

The new module option is OS-independent and supports Ultra2 or Ultra160 operation and RAID levels 0, 1, 0/1, 3, 4, 5, and 10 or JBOD. Included also is 128MB of PC133 compatible SDRAM DIMM cache memory. All InfoStation enclosures and options are 100% tested, CE, CSA, TuV and UL certified, and come with a seven-year warranty and free 24/7 technical support. For specific information regarding the RAID Controller Module, please view detailed product information on the Internet at .


San Francisco, CALIF. — Plumtree Software released the Plumtree Corporate Portal 4.0, featuring the new Massively Parallel Portal Engine. The release’s patent-pending Massively Parallel Portal Engine processes user requests for corporate information and applications from a wide variety of computers in parallel, offering customers major improvements in scalability, openness and fault-tolerance. Based on the new Plumtree Portal Network Architecture, the Plumtree Corporate Portal 4.0 empowers a network of more than 100 customers, 25 technology alliance members and 50 systems integrators to share information and services between portals and with other platforms and devices, driving deployments across organizational, geographic and business boundaries. The release also offers customers a new community user experience and enterprise-wide manageability for administrators, including LDAP support. To see Plumtree’s deployment of the new release, visit .

“Plumtree’s synchronization with our LDAP directory of nearly 100,000 users allows us to bring new users on-line without creating a duplicate set of administrative processes,” said Dan Gerbus, corporate project manager, at Procter & Gamble. “In addition, major improvements to the user interface offer users the flexibility they have been asking for. Features like multiple MyPages and communities allow Procter & Gamble to design a portal that delivers information and applications in a much more efficient manner than version 3.0.” The Plumtree Corporate Portal 4.0 is powered by the Massively Parallel Portal Engine – a patent-pending technology for assembling information and services from other systems in parallel. The portal integrates these resources as Plumtree Portal Gadgets, distributed portal components that embed key information and services from enterprise applications and Internet sites. Designed to support global deployments with hundreds of thousands of users requesting information and services from thousands of sources, the Massively Parallel Portal Engine integrates gadgets operating on separate computers, which simultaneously prepare information or services to embed in each user’s portal page.


San Jose, CALIF. — Mainsoft, the e-porting company, announced the general availability of Visual MainWin, the first application porting platform allowing developers – with no UNIX expertise – to write on Windows and port simultaneously to UNIX. Visual MainWin, which is available for a free thirty-day evaluation, can be downloaded at . Industry analyst, IDC, reported that in 1999, Windows represented 30% and UNIX represented more than 50% of the $5.8 billion in Internet server sales. In order to tap the Internet server markets, independent software vendors (ISVs) and Internet infrastructure providers must deploy on both Windows and UNIX.

Mainsoft’s customers, who include both ISVs and Internet infrastructure providers such as Microsoft, PTC, Siebel Systems, UUNET, and Wind River Systems, have tapped Mainsoft’s application porting platform to meet their increasing cross-platform challenge. Mainsoft’s software and services enable developers to focus on their core competency, rather than platform availability; decrease ulti-platform time-to-market from years to months; and reduce R&D costs for UNIX versions by up to 95%. “ESRI was looking for a way to make our Windows applications available on a UNIX platform. ESRI has one of the largest COM implementations in the world,” said Clint Brown, Director of Software Products at ESRI. “With Visual MainWin, ESRI has ported much of ArcInfo and ArcView to Solaris, greatly reducing people-hours and development resources needed for this enormous undertaking. We thank Mainsoft for helping us easily address our Sun market by enabling us to efficiently port our COM applications to Solaris.” For additional information on Mainsoft Corporation, visit the Mainsoft Web site at .


Ames, IOWA — Engineering Animation, Inc. announced the immediate availability of e-Vis 3.0, the secure, Internet-enabled visual collaboration solution for extended manufacturing enterprises. With release 3.0, e-Vis becomes the first and only Internet collaboration solution to support visual collaboration on both mechanical CAD (MCAD) and electronic CAD (ECAD) data. In addition, e-Vis 3.0 features a new online CAD translation service and interface, performance and usability improvements. e-Vis 3.0 introduces an ECAD viewer that supports visual collaboration for the design and manufacturing of electro-mechanical products by enabling users to visualize and share ECAD data over the Internet. e-Vis 3.0 also features a new online translation service that converts a variety of 3D CAD file formats into the high-performance DirectModel (.jt) format. DirectModel optimizes CAD files for faster download to the e-Vis suite of visualization, measurement and markup tools. The new translation service supports the most popular formats for the exchange of 3D CAD data, including IGES, STEP, STL and VRML.

“The improvements made in e-Vis 3.0 demonstrate EAI’s commitment to providing customers with the most comprehensive visual collaboration solution on the market,” said Adrian Sannier, EAI vice president and general manager of E-services. “The introduction of ECAD viewing and online CAD translation make e-Vis an even more powerful tool for manufacturers seeking the quality- and cost-benefits associated with enterprise-wide visual collaboration.” Engineering Animation, Inc. is the leader in Internet-enabled visual process management, collaboration, analysis and communication solutions for extended manufacturing enterprises. EAI’s solutions, which include e-Vis, Open Enterprise Visualization and Virtual Factory, help manufacturing companies drive down costs while improving business practices, efficiency, quality and time-to-market. The Company maintains its corporate headquarters and technology center in Ames, Iowa, and has offices worldwide.


San Francisco, CALIF. — Extending its technology lead in an expected $11 billion application server market, Oracle Corp., the provider of software for e-business, announced the forthcoming availability of Oracle9i Application Server, featuring patent-pending Web cache technology that dramatically increases Web site performance and scalability. E-businesses can expect impressive capacity improvements, starting with a single instance of Oracle9i Application Server on inexpensive hardware. The Oracle Store, for example, has seen more than 100-fold improvement in throughput, with a 70% decrease in back-end server load, since deploying Oracle9i Application Server. Oracle9i Application Server is the evolution of Oracle Internet Application Server 8i. Its advanced cache technology takes the pressure off of busy Web sites by storing and load balancing frequently accessed Web pages in memory, whether the pages are statically or dynamically generated. As a result, Oracle9i Application Server can service up to 7,500 HTTP requests per second on a single 2-CPU machine, whereas most dynamic Web sites require hundreds of Web servers to sustain this level of throughput.

To produce sustained quality of service during peak times, Oracle9i Application Server’s patent-pending surge protection technology provides consistent cache performance even during traffic spikes or if Web site content is changing frequently. Competing Web cache products do not offer the same level of performance guarantee, and force customers to rely on expensive and complex content delivery tools to propagate content updates to their caches. In addition, these content delivery tools cannot handle the volume of content updates demanded by today’s leading dynamic Web sites. Unlike legacy cache products that were designed to cache static content only, the Web caching technology in Oracle9i Application Server was built from the ground up to cache dynamically-created Web pages, regardless of which page generation technology is used. Dynamic Web pages, such as Java Server Pages, Microsoft Active Server Pages, and CGI (Common Gateway Interface), can be computationally intensive to generate and until Oracle9i Application Server were considered un-cacheable. Another key feature of Oracle9i Application Server will give IT departments and content distribution services the flexibility to deploy their Web caches locally and/or globally to the edges of the Internet, bringing the content closer to the customer for additional availability and even better response time. “Oracle’s new Web cache technology puts Oracle in the position of offering the ability to cache both static and dynamic Web pages within the application server,” said Steve Garone, vice president at IDC. “This, combined with the load balancing enhancements of Oracle9i Application Server, will allow customers to more effectively scale through the application server. This offers the potential of supporting ever-increasing numbers of users, and without the need for additional and expensive computing resources.”


Campbell, CALIF. — Virtio announced that Mentor Graphics XRAY Debugger is now available for Virtio platforms, which are complete virtual prototypes of IP intensive embedded system solutions. With XRAY integrated into the Virtio virtual prototyping technology, users can now run and debug production-quality software on a virtual System-on-Chip (SoC) platform before hardware is available. This process reduces the risk of costly silicon respins by identifying hardware and software interface errors early in the design cycle. A traditional bottleneck in SoC design is the time-consuming and error-prone process of evaluating multi-sourced hardware and software. With XRAY integrated into Virtio’s virtual prototyping technology, software engineers can now test code running on hardware at the very earliest stages of the design cycle. Designers can do early stage software engineering on the virtual platform, increasing the likelihood that the software will work flawlessly on the hardware platform.

“We are excited that Mentor Graphics has chosen to support Virtio’s virtual prototyping environment with the XRAY Debugger,” said Shay Ben-Chorin, Virtio president and CEO. “The announcement shows Mentor’s support for a paradigm shift in embedded systems development where systems can be prototyped, customized and evaluated risk-free over the Internet. With the XRAY Debugger, optimized platforms can be accessed on-line and debugged within a consistent environment. In addition, the integration creates an enhanced platform solution that provides our mutual partners, like MIPS Technologies, Inc. with more development options for their customers and end-users.” With the integration of the XRAY Debugger with the Virtio Explorer, designers will be able to evaluate and explore embedded system solutions and platforms on-line. Access through Virtio OnLine allows embedded system hardware and software developers to try before they buy, thereby enabling faster and better decisions in the selection of hardware IP, software IP, and software development tools.


San Francisco, CALIF. — Giganet, Inc., a leader in VI-based data center networks, announced that its award- winning cLAN products will be the first VI networking products to work with Oracle’s upcoming Oracle9i database. Early testing of Net8 with VI running over Giganet shows a significant improvement in throughput versus 100 Mbps Ethernet. This announcement reaffirms Giganet’s position as the leading VI- based network for database acceleration and scalability. When running over Giganet’s VI-based networking products, enterprises building Oracle9i environments can gain substantial performance, scalability and reliability improvements. VI reduces normal network limitations such as high system overhead and latency and accelerates application and data throughput. Net8 uses VI networks for more efficient communications between an application server and an Oracle database. Oracle9i, including support for VI-based networks, is slated for release in the first half of 2001.

“Today’s high-volume e-commerce applications can strain the network infrastructure of our customers and partners. We view VI as an important new protocol that will push the performance envelope for communications between Oracle Internet Application Server and Oracle9i,” said Howard Cohen, vice president of Distributed Systems at Oracle. Giganet has been working with Oracle, the world’s leading e-business solution provider, for a number of years on developing high performance networking for Oracle databases. This is the second Oracle database product to leverage Giganet VI networks – Oracle Parallel Server (OPS) introduced VI support in 1999. At this Oracle OpenWorld, Intel Corporation is demonstrating an Internet-based business-to-business environment with OPS database systems and application servers being connected over Giganet VI-based networks. With Giganet VI networks, the database system is freed up from the overhead of network tasks and has more CPU cycles available for applications and data processing. Additional information and benchmark performance results for Giganet cLAN and Oracle solutions can be found at .


Nashua, N.H. — Open Software Associates announced the immediate availability of NETDEPLOY GLOBAL, the world’s first suite of software management and deployment products and services based on Microsoft Windows 2000 Active Directory. NETDEPLOY GLOBAL cuts system-wide Total Cost of Ownership (TCO) by extending the software management capabilities of Windows 2000 and also by covering legacy Windows and non-Microsoft platforms. NETDEPLOY GLOBAL provides unmatched control of software assets with full-lifecy cle management throughout the global enterprise and beyond. It manages software on local networks and over the Internet for remote offices, mobile workers, and the “extended enterprise,” including business partners and customers. Combined with specific tools and services to assist companies migrating to Windows 2000, NETDEPLOY GLOBAL allows corporations to reap the benefits of Windows 2000 and Active Directory from day one, even in highly heterogeneous environments. NETDEPLOY GLOBAL, coupled with OSA’s software management consulting and service offerings, gives companies a single source for comprehensive software management solutions before, during, and after migration to Windows 2000.

NETDEPLOY GLOBAL is a sophisticated suite that directly addresses software TCO by providing a consistent software management discipline across the organization. NETDEPLOY GLOBAL bases management on software usage profiles and deployment policies scalable from the individual user to the enterprise and beyond. It covers the entire application lifecycle, including acquisition into the corporate software warehouse, pre-release testing, publishing by policy, self-healing installation, automatic updating, reporting and eventual decommissioning. NETDEPLOY GLOBAL embraces Windows 2000 by storing deployment metadata in the Active Directory and providing policy editing within Microsoft’s Group Policy. It uses native features (such as the Windows Installer) where available, and complements them with parallel services on other platforms. This gives corporations a single point of control for consistent software management across all users, regardless of the mix of operating systems. “One of the drivers of migration to Microsoft Windows 2000 is the demand for a consistent, standards-based approach to managing software,” said Fred Broussard, research analyst at International Data Corporation. “Not only does NETDEPLOY GLOBAL use Active Directory facilities, it also offers a comprehensive solution for managing different kinds of software on different kinds of systems – internal, external, server, desktop and laptop – and it’s able to do this through multiple firewalls.”


Princeton, N.J. — Dataram Corporation a leading provider of gigabyte-class memory for high-performance network servers, announces immediate availability of memory products for Compaq’s ProLiant rack-mounted DL580 and ML570 servers. Dataram is offering advanced 100MHz ECC memory for the DL580 and ML570 in 1, 2 and 4GB capacities. These memory offerings enhance the 4-way interleave architecture featured in both the DL580 and ML570, greatly increasing system bandwidth and memory performance.

Compaq’s ProLiant ML570, the follow-on to the ProLiant 5500, has a convenient 7U form factor making it a powerful server/storage solution for enterprise users. The densely optimized rackable ProLiant DL580, the follow-on to the ProLiant 6400R, is designed to meet the demands of the ASP and ISP computing environments. Both servers feature up to four Intel Pentium III Xeon processors at 700 MHz and will support up to 16GB of Dataram memory. “Compaq’s new ProLiant series has been very popular and were seeing a great demand for our memory,” stated Jeff Goldenbaum, Dataram’s Product Manager. “Adding our memory is the most economical way to increase server performance and we’re please to be able to offer upgrades for all of the ProLiant family,” continued Goldenbaum.


San Jose, CALIF. — Connex, a developer of scalable Network Attached Storage (NAS) and Storage Area Network (SAN) products, unveiled the N3100, a next-generation NAS data storage appliance that brings a wide range of storage and file serving solutions to departments and workgroups by delivering increased performance, improved scalability, higher availability and a lower total cost of ownership within conventional Windows and Unix server environments. Providing file services to heterogeneous Windows or Unix networks, the Connex N3100 offers simultaneous support for both NFS and CIFS, allowing users and devices quicker access to shared files while decreasing the demands on Unix or Windows application servers.

With a 33 percent capacity improvement over its first-generation NAS server appliance, the new Connex N3100 extends Connex’s record of best-in- class standards for performance, design modularity and data availability. The innovative Connex N3100 is the ideal file server and storage solution for areas such as pre-press, web design, medical imaging, database sharing, engineering, education and a host of environments where file capacity, access, speed, security and scalability are paramount. The Connex N3100 can be easily deployed and installed in a matter of minutes without the need to take application servers offline. Offering a robust 288 gigabytes of Ultra160 SCSI RAID-5 capability, the Connex N3100 NAS server is designed for the high-end workgroup to mid-range departmental storage applications. Optimized for modularity and high availability, the Connex N3100 allows network administrators and IT managers to break the bonds of cost of ownership, complexity and downtime required to add SCSI-attached storage to typical NT and UNIX servers.


Needham, MASS. — B&L Associates Inc., a leading provider of removable computer tape management software, today announced that the Vertices tape management system is available for Microsoft Windows 2000. The new version of Vertices, which can be hosted on any Windows 2000 Professional, Server or Advanced Server platform, controls the movement, management and retrieval of removable tapes and other types of media from any source, including legacy Windows platforms, UNIX, Linux and mainframe systems. “Windows 2000 is well on its way to becoming an enterprise workhorse taking on many mission-critical applications,” commented Michael Kramer, B&L vice president of sales and marketing. “As it moves into this role, Windows 2000 requires a mature and robust management system that controls the tapes and other media, such as CDs, once they leave the online environment. Vertices is the only product that offers complete removable tape management regardless of the operating system, regardless of the applications being run, and regardless of the size and scope of the enterprise network.”

Vertices for Windows 2000 incorporates all of the features of the Windows NT version. It tracks removable physical tapes and other media, such as magnetic tape, disk, CD-ROM, Digital Linear Tape (DLT). Vertices is designed for managing data center tapes as well as compliance programs for licensed software and for keeping track of personal computer and workstation media. For further information, contact B&L at .


San Jose, CALIF. — Promise Technology, Inc. announced release of ConnectStor network-attached storage (NAS) subsystem – a 20GB+ Ultra ATA/66 single drive unit designed for commercial applications, IT Professionals, resellers, and system integrators. ConnectStor is designed for instant plug-in storage expansion with built-in support for existing Windows 9x/ME/NT/2000, UNIX, or Linux networks. ConnectStor is one of only a few NAS units to permit the user to install and automatically configure extra drives. ConnectStor supports up to two Ultra ATA/66 drives which are then automatically recognized and configured for network storage on bootup. “We’ve positioned ConnectStor to meet the low- to middle-end of the NAS market to provide both business professionals and resellers the ability to add drives to an existing ConnectStor unit – without purchasing a separate unit – or specify their own drives,” said Sam Sirisena, Promise vice president of sales and marketing worldwide. “This strategy allows users to take full advantage of the latest storage price/performance trends of Ultra ATA drive technology versus pre-configured, dedicated closed-box NAS solutions.”

In addition, ConnectStor units embed Promise Technology’s worldwide best-selling Ultra ATA/66 ASIC now in use in millions of PCs and by major Tier 1 OEMs. “This makes ConnectStor products compatible with the widest cross-section of Ultra ATA drives available,” Sirisena added. “ConnectStor provides IT professionals with the ability to instantly expand their storage requirements for popular network operating systems in use today at lower price points than traditional SCSI-based storage,” said Sirisena. For more information, visit Promise Technology’s web site at .


Westlake Village, CALIF. — Troika Networks, a fast-growing private company driving the convergence of storage networking and clustering for improved availability and performance of e-business applications, today announced Target DMP (Dynamic Multipathing) as an optional feature, further extending the Host DMP capability currently available with the TROIKA Zentai controller. With the launch of its Zentai controller, TROIKA revolutionized storage network connectivity by introducing intelligent, dynamic multipathing within a server, or a host, as a standard feature. Target DMP extends the power of TROIKA’s Host DMP offering by taking advantage of dynamic multipathing capabilities within certain storage devices or targets, down to single logical storage units within those devices.

With the combination of Host DMP and Target DMP, TROIKA’s multipathing capabilities are available throughout the entire path – from the application to the data – reducing redundancy requirements and eliminating the need for expensive and complex products previously only available in extremely high-end devices. “With today’s e-business applications, even small enterprises need continuous data availability combined with simple and automatic manageability,” said Tracy Edmonds, vice president of software engineering. “TROIKA is bringing these features to companies where even e-mail, collaboration and departmental databases are business critical. “The addition of Target DMP to TROIKA’s DMP suite of products enables Storage Area Network (SAN) storage devices to quickly recover in the case of any link failure and increase their overall performance.” More information about TROIKA and its products is available at .


Orlando, FLA. — Citrix Systems, Inc. announced the availability of its newest members of the family of Citrix MetaFrame 1.1 for UNIX Operating Systems application server software products: Citrix MetaFrame 1.1 for the AIX Operating System, Citrix MetaFrame 1.1 for the HP-UX Operating System and Citrix MetaFrame 1.1 for the Solaris Operating Environment. These new products are being demonstrated this week at Citrix iForum 2000 in Orlando, Florida. The Citrix MetaFrame 1.1 for UNIX Operating Systems product family extends the reach of business-critical UNIX and Java applications across an enterprise, or from an Application Service Provider (ASP), to users anywhere, regardless of location, device or connection. The unique way in which MetaFrame 1.1 for UNIX can deliver UNIX applications to any Citrix Independent Computing Architecture (ICA) client, over any connection makes it an excellent alternative to using PC X Servers to deploy X.11 applications in the enterprise. This expansion of the MetaFrame product line is further evidence of Citrix’s strategy to deliver high-speed access to any application, over any device, across any connection. These new MetaFrame products are available immediately through selected members of the Citrix Solutions Network, a comprehensive channel of distributors, resellers, system integrators, and consultants worldwide. Suggested retail pricing for each product is $5,995 for a 15-concurrent user license and a one-year enrollment in Citrix’s Subscription Advantage program, which includes automatic delivery of enhancements, updates and maintenance releases.

“The software revenues in the virtual user interface (VUI) serverware market grew over 117% between 1998 and 1999,” said Dan Kusnetzky, vice president for system software research for IDC. “Citrix was the leading supplier of software in this market. IDC believes that the interest in server-centric computing, which is dependent on VUI software, will increase rapidly over the next few years. This approach allows users to access UNIX, Windows, and mainframe applications without having to be burdened with issues like system management, network management, application installation, etc.” “Citrix’s award-winning MetaFrame software technology is a natural choice for customers who want to deploy reliable UNIX server-based computing solutions,” said Gary Thomassen, director of product management for Citrix. “It provides added value to enterprise customers and ASPs by enabling access to applications and information regardless of platform. In conjunction with the Citrix NFuse application portal software, users can now have seamless access to both Windows and UNIX applications via a single Web portal interface.”


Orem, UTAH — Caldera Systems Inc. last Tuesday announced that its Linux management solution is entering open beta. This beta solution remotely manages the networked systems of any Linux distribution and is available for download from Caldera’s Web site at . Caldera’s Linux management solution is a browser- and directory-based management product for Linux systems that utilizes the inherent strengths of LDAP directories. Using this solution, network administrators can use policies and profiles to manage a half dozen or thousands of Linux systems, without having to individually manage each.

The Linux management solution will significantly benefit ASPs, ISPs, hosting companies, systems integrators and network administrators – anyone needing to manage multiple Linux servers and workstations. By consolidating management functions for labor-intensive tasks, Caldera’s management solution dramatically reduces costs, saves time and increases job efficiency. “Caldera’s Linux management solution dramatically reduces the cost, time and effort typically associated with network management,” said Paul Smith, network engineer at Metafore Corp., a beta site. “And because it supports any version of Linux, it opens the door to unifying entire Linux-networked systems for any organization.” “This management solution will be a catalyst for increased adoption of Linux by any size business – particularly the enterprise,” said Ransom Love, president and chief executive officer of Caldera Systems.


San Diego, CALIF. — JNI Corporation, the fastest growing Fibre Channel host bus adapter company in 1999, announced the general availability of two new drivers for the JNI Unix DriverSuite for servers and systems running under the Hewlett Packard HP-UX operating system and the IBM AIX operating system. The new HP-UX and AIX drivers operate with all JNI FibreStar PCI HBAs using the Emerald ASIC controller including the single ported FCE-3210 and FCE-6410, as well as the dual independent-port FCE2-6410 and FCE2-6412 adapters. The HP-UX driver supports most HP 9000 servers running under HP-UX 10.20 and 11.x, including B-Class, C-Class, J-Class, L-Class, and N-Class, and is expected to support the V-Class in late 2000. The AIX driver supports AIX 4.2 and 4.3 running on 32- and 64-bit IBM RS/6000 systems and the newly announced IBM eServer pSeries servers, from workstations to Web servers.

“Our HP-UX and AIX drivers strengthen JNI’s product offering for enterprise-level Storage Area Networks,” said Tracy Crowe, JNI vice president of marketing. “We now fully support eight different operating systems, with HP-UX and AIX joining our popular Solaris and Windows 2000 drivers. Developing enterprise level HP-UX and AIX drivers was the next logical step for our mission critical products.” As with all DriverSuite drivers, the HP-UX and AIX drivers operate under all three Fibre Channel topologies – switched fabric, arbitrated loop and point-to-point. HP-UX is also bundled with EZ Fibre configuration and management software, which simplifies installation and maintenance of the JNI HBAs.


Fort Lauderdale, FLA. — DataCore Software Corporation, an innovator in storage networking software, announced that it has further expanded its presence in the U.S., with a new customer center in the heart of Silicon Valley. The new center, dedicated to sales, customer service and training, expands DataCore Software’s ability to help customers and partners quickly gain the skills they need to maximize the benefits of DataCore Software’s SANsymphony for storage network management, regionally and nationwide. The facility will provide a full range of professional and consulting services, including training services, a state-of-art demo center, SAN assessment tools and SAN administration courses. It will also offer a technical services unit with fully trained support and training engineers on call 24 hours a day.

“The Silicon Valley is filled with companies in e-commerce, application hosting and large scale operations who are struggling with the challenges of managing the dramatic growth of data storage,” said George Teixeira, president and chief executive officer of DataCore Software. “Our new operation will provide world-class support, a critical element required to meet the demanding needs of storage customers.” Cindy Sauln, DataCore’s vice president of customer programs and services, will run the day-to-day operations of the center. Sauln joined DataCore in 1999, after having served at DEC and VERITAS Software in executive roles. “We are committed to helping our customers make the most of the SAN,” said Sauln. “The training and certification that we will offer in our Silicon Valley center are designed to ensure that our customers have the tools and techniques to speed the time from implementation to use and deliver a fast ROI.”


New York, N.Y. — HydraWEB Technologies, the original innovator of load balancing, this week announced the introduction of HydraRADIUS, the industry’s first RADIUS (Remote Authentication Dial In User Service) load balancing solution. Developed in conjunction with Lucent Technologies’ market leading NavisRadius RADIUS server products, HydraRADIUS allows dial, broadband and mobile data service providers to build access networks with improved availability and scalability. CEO and founder of HydraWEB Raj Sharma said, “HydraRADIUS is the first product in our Application Acceleration Appliance (AAA) Series. We are developing Internet traffic management systems at the application level because that’s the point at which infrastructure performance can be best managed and improved. We selected NavisRadius as our first application because of its adoption by many large service providers who can benefit from the increased performance and availability offered by the HydraRADIUS solution.”

HydraRADIUS is a complete RADIUS server and traffic management solution that helps service providers deliver networks with improved RADIUS authentication, responsiveness and accounting data integrity. HydraRADIUS reduces RADIUS packet loss and retransmissions, optimizes RADIUS server performance, improves fault tolerance, and eases routine RADIUS server maintenance tasks. “RADIUS is a mission critical component of service provider access networks. Practically every dial-up call and many broadband and mobile data connections to the Internet rely on the Lucent invented RADIUS protocol to succeed. Lucent’s NavisRadius has set the standard for flexible RADIUS policy and service management, and carrier class performance. The HydraRADIUS solution adds the system level performance benefits of intelligent traffic management and provides a powerful tool for fast growth service providers to provide maximum network availability,” said Madan Kumar, director of product management for the Lucent InterNetworking Systems Network Management division.


Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Supercomputers Take to the Solar Winds

June 5, 2020

The whims of the solar winds – charged particles flowing from the Sun’s atmosphere – can interfere with systems that are now crucial for modern life, such as satellites and GPS services – but these winds can be d Read more…

By Oliver Peckham

HPC in O&G: Deep Sea Drilling – What Happens Now   

June 4, 2020

At the beginning of March I attended the Rice Oil & Gas HPC conference in Houston. That seems a long time ago now. It’s a great event where oil and gas specialists join with compute veterans and the discussion tell Read more…

By Rosemary Francis

NCSA Wades into Post-Blue Waters Era with Delta Supercomputer

June 3, 2020

NSF has awarded the National Center for Supercomputing Applications (NCSA) $10 million for its next supercomputer - named Delta – “which will kick-start NCSA’s next generation of supercomputers post-Blue Waters,” Read more…

By John Russell

Dell Integrates Bitfusion for vHPC, GPU ‘Pools’

June 3, 2020

Dell Technologies advanced its hardware virtualization strategy to AI workloads this week with the introduction of capabilities aimed at expanding access to GPU and HPC services via its EMC, VMware and recently acquired Read more…

By George Leopold

Supercomputers Streamline Prediction of Dangerous Arrhythmia

June 2, 2020

Heart arrhythmia can prove deadly, contributing to the hundreds of thousands of deaths from cardiac arrest in the U.S. every year. Unfortunately, many of those arrhythmia are induced as side effects from various medicati Read more…

By Staff report

AWS Solution Channel

Join AWS, Univa and Intel for This Informative Session!

Event Date: June 18, 2020

More enterprises than ever are turning to HPC cloud computing. Whether you’re just getting started, or more mature in your use of cloud, this HPC Cloud webinar is an excellent opportunity to gain valuable insights and knowledge to help accelerate your HPC cloud projects. Read more…

Indiana University to Deploy Jetstream 2 Cloud with AMD, Nvidia Technology

June 2, 2020

Indiana University has been awarded a $10 million NSF grant to build ‘Jetstream 2,’ a cloud computing system that will provide 8 aggregate petaflops of computing capability in support of data analysis and AI workload Read more…

By Tiffany Trader

NCSA Wades into Post-Blue Waters Era with Delta Supercomputer

June 3, 2020

NSF has awarded the National Center for Supercomputing Applications (NCSA) $10 million for its next supercomputer - named Delta – “which will kick-start NCS Read more…

By John Russell

Indiana University to Deploy Jetstream 2 Cloud with AMD, Nvidia Technology

June 2, 2020

Indiana University has been awarded a $10 million NSF grant to build ‘Jetstream 2,’ a cloud computing system that will provide 8 aggregate petaflops of comp Read more…

By Tiffany Trader

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

By Doug Black

COVID-19 HPC Consortium Expands to Europe, Reports on Research Projects

May 28, 2020

The COVID-19 HPC Consortium, a public-private effort delivering free access to HPC processing for scientists pursuing coronavirus research – some utilizing AI Read more…

By Doug Black

$100B Plan Submitted for Massive Remake and Expansion of NSF

May 27, 2020

Legislation to reshape, expand - and rename - the National Science Foundation has been submitted in both the U.S. House and Senate. The proposal, which seems to Read more…

By John Russell

IBM Boosts Deep Learning Accuracy on Memristive Chips

May 27, 2020

IBM researchers have taken another step towards making in-memory computing based on phase change (PCM) memory devices a reality. Papers in Nature and Frontiers Read more…

By John Russell

Hats Over Hearts: Remembering Rich Brueckner

May 26, 2020

HPCwire and all of the Tabor Communications family are saddened by last week’s passing of Rich Brueckner. He was the ever-optimistic man in the Red Hat presiding over the InsideHPC media portfolio for the past decade and a constant presence at HPC’s most important events. Read more…

Nvidia Q1 Earnings Top Expectations, Datacenter Revenue Breaks $1B

May 22, 2020

Nvidia’s seemingly endless roll continued in the first quarter with the company announcing blockbuster earnings that exceeded Wall Street expectations. Nvidia Read more…

By Doug Black

Supercomputer Modeling Tests How COVID-19 Spreads in Grocery Stores

April 8, 2020

In the COVID-19 era, many people are treating simple activities like getting gas or groceries with caution as they try to heed social distancing mandates and protect their own health. Still, significant uncertainty surrounds the relative risk of different activities, and conflicting information is prevalent. A team of Finnish researchers set out to address some of these uncertainties by... Read more…

By Oliver Peckham

[email protected] Turns Its Massive Crowdsourced Computer Network Against COVID-19

March 16, 2020

For gamers, fighting against a global crisis is usually pure fantasy – but now, it’s looking more like a reality. As supercomputers around the world spin up Read more…

By Oliver Peckham

[email protected] Rallies a Legion of Computers Against the Coronavirus

March 24, 2020

Last week, we highlighted [email protected], a massive, crowdsourced computer network that has turned its resources against the coronavirus pandemic sweeping the globe – but [email protected] isn’t the only game in town. The internet is buzzing with crowdsourced computing... Read more…

By Oliver Peckham

Global Supercomputing Is Mobilizing Against COVID-19

March 12, 2020

Tech has been taking some heavy losses from the coronavirus pandemic. Global supply chains have been disrupted, virtually every major tech conference taking place over the next few months has been canceled... Read more…

By Oliver Peckham

Supercomputer Simulations Reveal the Fate of the Neanderthals

May 25, 2020

For hundreds of thousands of years, neanderthals roamed the planet, eventually (almost 50,000 years ago) giving way to homo sapiens, which quickly became the do Read more…

By Oliver Peckham

DoE Expands on Role of COVID-19 Supercomputing Consortium

March 25, 2020

After announcing the launch of the COVID-19 High Performance Computing Consortium on Sunday, the Department of Energy yesterday provided more details on its sco Read more…

By John Russell

Steve Scott Lays Out HPE-Cray Blended Product Roadmap

March 11, 2020

Last week, the day before the El Capitan processor disclosures were made at HPE's new headquarters in San Jose, Steve Scott (CTO for HPC & AI at HPE, and former Cray CTO) was on-hand at the Rice Oil & Gas HPC conference in Houston. He was there to discuss the HPE-Cray transition and blended roadmap, as well as his favorite topic, Cray's eighth-gen networking technology, Slingshot. Read more…

By Tiffany Trader

Honeywell’s Big Bet on Trapped Ion Quantum Computing

April 7, 2020

Honeywell doesn’t spring to mind when thinking of quantum computing pioneers, but a decade ago the high-tech conglomerate better known for its control systems waded deliberately into the then calmer quantum computing (QC) waters. Fast forward to March when Honeywell announced plans to introduce an ion trap-based quantum computer whose ‘performance’ would... Read more…

By John Russell

Leading Solution Providers

SC 2019 Virtual Booth Video Tour



Tech Conferences Are Being Canceled Due to Coronavirus

March 3, 2020

Several conferences scheduled to take place in the coming weeks, including Nvidia’s GPU Technology Conference (GTC) and the Strata Data + AI conference, have Read more…

By Alex Woodie

Exascale Watch: El Capitan Will Use AMD CPUs & GPUs to Reach 2 Exaflops

March 4, 2020

HPE and its collaborators reported today that El Capitan, the forthcoming exascale supercomputer to be sited at Lawrence Livermore National Laboratory and serve Read more…

By John Russell

‘Billion Molecules Against COVID-19’ Challenge to Launch with Massive Supercomputing Support

April 22, 2020

Around the world, supercomputing centers have spun up and opened their doors for COVID-19 research in what may be the most unified supercomputing effort in hist Read more…

By Oliver Peckham

Cray to Provide NOAA with Two AMD-Powered Supercomputers

February 24, 2020

The United States’ National Oceanic and Atmospheric Administration (NOAA) last week announced plans for a major refresh of its operational weather forecasting supercomputers, part of a 10-year, $505.2 million program, which will secure two HPE-Cray systems for NOAA’s National Weather Service to be fielded later this year and put into production in early 2022. Read more…

By Tiffany Trader

15 Slides on Programming Aurora and Exascale Systems

May 7, 2020

Sometime in 2021, Aurora, the first planned U.S. exascale system, is scheduled to be fired up at Argonne National Laboratory. Cray (now HPE) and Intel are the k Read more…

By John Russell

Australian Researchers Break All-Time Internet Speed Record

May 26, 2020

If you’ve been stuck at home for the last few months, you’ve probably become more attuned to the quality (or lack thereof) of your internet connection. Even Read more…

By Oliver Peckham

Summit Supercomputer is Already Making its Mark on Science

September 20, 2018

Summit, now the fastest supercomputer in the world, is quickly making its mark in science – five of the six finalists just announced for the prestigious 2018 Read more…

By John Russell

Nvidia’s Ampere A100 GPU: Up to 2.5X the HPC, 20X the AI

May 14, 2020

Nvidia's first Ampere-based graphics card, the A100 GPU, packs a whopping 54 billion transistors on 826mm2 of silicon, making it the world's largest seven-nanom Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This