Product Watch: Fortran 2.0 Ready For Public Comment. Procom Unveils New Model of NetFORCE 1500. Microtest Unveils Optical NAS Server.

July 7, 2000

SHORT TAKES

FORTRAN 2.0 READY FOR PUBLIC COMMENT

The initial version of the Fortran 2.0 Application Program Interface is ready for public comment! After over one year of effort, the OpenMP ARB is pleased to present a major enhancement to the Fortran API. Major new features in the 2.0 specification include: Array reductions; Parallelization of F90 array syntax; COPYPRIVATE for broadcast of sequential reads; Privatization of module data; Portable timing routines; Nested locks; and control of the number of threads for multi-level parallelism.

In addition to the above, several minor features have been added and many interpretations addressed and incorporated into the text. The public comment period will close on September 15, 2000. You can download the specification at http://www.openmp.org . Please send your comments via the feedback page at http://www.openmp.org . The ARB hopes to have the final version of the API available by Supercomputing 2000 in November.

PROCOM UNVEILS NEW MODEL OF NETFORCE 1500

Santa Ana, CA — Procom Technology announced the latest version of its NetFORCE 1500, an enhanced model incorporating high-performance 73 gigabyte disk drives, more than doubling the capacity to 730 gigabytes for a new capacity standard dictated by the expanding storage requirements of corporate and Internet customers. “With the escalating demand for storage – particularly among e-business customers – Procom moved quickly to roll out an enhanced-capacity NetFORCE 1500,” said Dr. Homayoun Yousefizadeh, Procom senior product manager.

“To keep pace with increasingly dynamic business environments, the IT universe as well as e-businesses operations have – of necessity – transitioned to a storage-centric view of enterprise computing,” explained Yousefizadeh. “The easiest, fastest and most cost-effective method of scaling these workgroup and Web-based storage customers is with NAS appliances such as the NetFORCE 1500. The 730 GB capacity point allows NetFORCE 1500 filers to be deployed for workgroup, departmental, Internet and now, large-scale storage applications.” NetFORCE 1500 delivers high-performance network file services at speeds outpacing similar capacity UNIX and Windows NT servers by up to 20 percent, while dramatically lowering the total cost of ownership of storage assets. Visit http://www.procom.com for more information.

ON SEMICONDUCTOR INTRODUCES VCX PORTFOLIO

Phoenix, ARIZ. — ON Semiconductor has demonstrated its commitment to the legacy standard logic families with the introduction of a VCX portfolio. With an initial offering of six16 bit VCX functions with bushold options, this expansion of the logic portfolio provides designers with a broader range of standard logic solutions to choose from when designing high performance, low voltage designs. It also offers designers the opportunity to select products with multiple voltage compatibility for 1.8 volt, 2.5 volt and 3.3 volt systems. ON Semiconductor launches its VCX portfolio with the introduction of six new products. Processed in 0.35mu CMOS technology, VCX is the fastest 3.3 volt bus interface logic family currently available. These devices are designed for very high speed, very low power operation with low voltage operation between 1.65 volts to 3.6 volts. Ideal for high speed networking and telecom applications, high performance computing systems and high speed graphics, the products in the VCX portfolio provide designers with more options in applications where traditional logic is used. In direct response to market requirements, the VCX products have typical gate propagation delays of less than 3.0ns, with output drive currents of plus or minus 24mA, over-voltage protection to 4.6 volts, are hot insertion tolerant with static current of 20muA and a current drive of 24mA. Bushold options, denoted by VCXH, on the data pins provide maximum design flexibility by eliminating the need for external conditioning pull-up or pull-down resistors. Additionally, options for series damping resistors provide performance improvements in signal quality.

ON Semiconductor’s initial VCX offering includes the NL74VCX16244 16 bit buffer / line driver, NLVCXH16244 16 bit buffer / line driver with bushold, NL74VCX16240 16 bit Inverting buffer, NL74VCXH16240 16 bit inverting buffer / line driver with bushold, NL74VCX16245 16 bit bi-directional transceiver and NL74VCXH16245 16 bit bi-directional transceiver with bushold. Plans for future products include gate and octal functions. These VCX devices are available in 48-pin TSSOP packages and are priced at a resale value of $1.40 per 2.5K unit quantities. Samples and production quantities are currently available. For more information on ON Semiconductor’s VCX devices, visit http://onsemi.com/pub/logic .

VARIAN SEMICONDUCTOR INVENTORS RECEIVE TWO PATENTS

Gloucester, MASS. — Varian Semiconductor Equipment Associates, Inc., a leading supplier of ion implantation systems, today announced that Daniel F. Downey, Ph.D. was awarded U.S. Patent Number 6,069,062 on May 30, 2000 for innovative methods for forming ultra shallow junctions in semiconductor devices. The formation of ultra shallow junctions is one of the critical problems to be overcome by integrated circuit manufacturers in order to develop faster circuits. The company also announced that U.S. Patent Number 6,075,249 was granted to Joseph Olson, Ph.D. on June 13, 2000 for improved methods and apparatus for scanning and focusing ion beams used in the manufacture of semiconductor devices. Dr. Olson’s invention allows semiconductor manufacturers to improve productivity for implanting low energy ion beams used in the formation of ultra shallow junctions. Richard A. Aurelio, Varian Semiconductor’s president and chief executive officer, commented, “A strong portfolio of intellectual property and invention is central to our technology leadership in single wafer, single platform processing. We continue to invest heavily in our research and development projects for next-generation ion implantation products. The return on this investment is a continuing flow of inventions, like those of Dr. Downey and Dr. Olson, that position us for future technology requirements that will enable our customers to produce semiconductor devices that are smaller, faster and less expensive.”

Varian Semiconductor Equipment Associates, Inc. is an industry leader in designing, manufacturing, marketing and servicing ion implantation systems, semiconductor processing equipment used in the fabrication of integrated circuits. Through the process and productivity advantages of single wafer technology, VSEA is providing chipmakers with high throughput, low cost and maximum yields. The company is based in Gloucester, Massachusetts and maintains offices around the world. Its stock is traded on the NASDAQ National Market under the symbol “VSEA.” Additional information is available on VSEA’s website http://www.vsea.com .

FUJITSU’S FLASH MEMORIES MAXIMIZE FLEXIBILITY

London, ENGLAND — Fujitsu Microelectronics Europe has announced two new 64Mbit Flash memories, which offer dual-operation for simultaneous performance of read/write/erase functions and an industry first FlexBank architecture allowing flexible allocation of data or programs to the memory banks. The memories have been developed primarily for the latest cellular telephone and mobile information terminal applications, where high-speed processing and more frequent re-writing are demanded. FlexBank architecture enables the flexible allocation of data and programs to banks according to individual system requirements. Additionally, small sector 8Kbyte x 8 blocks are available in two banks to enable customers to locate start-up programs to suit system requirements, allowing efficient use of all remaining areas as memory space. Unlike previous generations of dual operation Flash memories, where each device has four fixed data and programs banks, the new devices are able to offer unparalleled design flexibility, enabling just one memory type to be used for a multitude of applications or design upgrades, reducing stock holding and cost.

Organized as either 4MB x 16 bit or 8MB x 8 bit, the devices offer two banks of 8Mbit (banks A and D) and two banks of 24Mbit (banks B and C). Additional features include a 256byte Hi-ROM (Hidden Read Only Memory) function to prevent illegal copying and an accelerator facility, which realises faster write time. Manufactured in Fujitsu’s 0.23 micron CMOS process technology and featuring a two-layer polysilicon NOR type memory cell structure, the devices operate from a single nominal 3.0 volt power supply. The MBM29DD640E, a version which offers optional address access times of 100ns or 120ns, is designed to operate down to 2.3 volts supply voltage. The MBM29DL640E variant is available in address access times of 80ns, 90ns and 120ns. All devices provide an automatic sleep mode function which realises a stand-by current consumption of just 1uA. Consumption in read operation is 16mA in byte mode at 5MHz and in write/erase mode a current consumption of only 35mA makes for very efficient use of battery power. Erase/write operational life is 100,000 cycles minimum.

TI SOFTWARE DRIVERS REDUCE CONFIGURATION TIME

San Diego, CA — Texas Instruments introduces the industry’s first data converter software drivers that simplify the design of data converters used in conjunction with digital signal processors (DSPs). The data converter software drivers for Code Composer Studio integrated development environment (IDE), a key component of TI’s eXpressDSP Real-Time Software Technology, cut configuration time for TI data converters used with TMS320 DSPs by up to 80 percent. For DSP developers, less configuration time means lower cost and a faster time-to-market. The software drivers are easy-to-use Windows navigation tools that allow designers to select from the available data converters and insert the appropriate program code directly into the software program. These drivers are for use with TMS320C5000 and TMS320C6000 DSPs.

The first release of the data converter software drivers includes DSPcodecs and analog-to-digital converters (ADCs). The drivers are available at no additional charge on the Code Composer Studio 1.2 CD-ROM. Or get them free by downloading at http://www.ti.com/sc/dcdrivers .

AMERICAN MEGATRENDS LAUNCHES HYPERDISK 100

Atlanta, GA — American Megatrends Inc. (AMI), a leader in storage and computing innovations worldwide, today announced the addition of HyperDisk 100 to its IDE RAID product family. “With the addition of ATA/100 hard drive support to AMI’s family of PCI IDE RAID controllers, AMI can meet the demands of OEMs, VARs and System Integrators seeking low-cost RAID solutions using the latest hard drive technology,” said Sanjay Sehgal, AMI’s Director of Sales. AMI’s IDE RAID family meets the performance requirements of the desktop publishing and the graphic workstation entrepreneur and the capacity requirements of the small office/small business server.

“Quantum is pleased to have AMI support Ultra ATA/100 on its HyperDisk 100 IDE RAID controller,” said Jim McGrath, technical marketing director for Quantum’s Desktop Storage Division. “AMI’s customers will benefit from the increase in performance and headroom that Ultra ATA/100 provides for today’s and tomorrow’s applications.” Using two or more low-cost Ultra ATA/DMA drives, HyperDisk 100 provides excellent drive performance and data redundancy. In most cases, the performance gains achieved by the addition of HyperDisk 100 with an additional drive dramatically surpass those seen with an upgrade in processor and increased memory. RAID allows multiple drives to perform the work of a single drive (increased performance), provides mirroring of data to another drive (protection) and presents the combined capacity of the drives as a single larger drive to the OS. HyperDisk 100’s IDE channels, which include data striping (RAID 0) and mirroring (RAID 1), make the entire solution an important tool in today’s computing environment. These RAID levels provide users with a better application performance every time a file is saved or retrieved and offers greater economy and longevity for nearly every PC made today. There will be little to no downtime in case a drive crashes. Visit http://www.ami.com for more information.

MICROTEST UNVEILS OPTICAL NAS SERVER

Phoenix, ARIZ. — Microtest, Inc., a leading developer of network-attached storage (NAS) appliances, today introduced DiscZerver Cyclone, a new high performance optical NAS platform for OEMs and integrators. Delivering superior access speeds, DiscZerver Cyclone surpasses competitive NAS products benchmarks, by as much as three to one, while maintaining a modest sub-$1,000 starting price point. Designed for the exacting needs of optical media access and management, DiscZerver Cyclone can support up to 15 SCSI and 4 EIDE devices, including hard drives, CD-ROM, DVD-ROM and CD-R drives, allowing storage capacities in excess of one terabyte. DiscZerver Cyclone is sold in a 5-1/4 inch sled form factor, allowing for easy integration in tower enclosures.

“About 40% of the optical NAS market is served by independent integrators and solution providers building their own branded servers around engines such as DiscZerver. Microtest is building up its presence in this segment, with over thirty integrators worldwide relying on DiscZerver as the heart of their product,” indicated Jim Boren, Vice President of Sales at Microtest. He concluded, “With Cyclone, we have undertaken to significantly increase our share of the OEM and integrator optical NAS market. We have increased our network of integrators by 30% in the past quarter alone.” “CD and DVD titles contain massive amounts of information, and serving them up to a community such as an education or legal institution is a very resource-intensive job,” explained Earl Christie, VP of Marketing at PrimeArray, a Woburn, Mass.-based solutions integrator. “Microtest’s new DiscZerver Cyclone provides the long-awaited Macintosh (AFP/IP) support. By adding features like this, Microtest makes it easier for PrimeArray to maintain a competitive edge in today’s marketplace.” For more information, please visit the DiscZerver Cyclone homepage at: http://nas.microtest.com/end_user/dz_cyclone/ .

DATARAM HAS SOLUTIONS FOR COMPAQ ALPHASERVER ES40

Princeton, N.J. — Dataram Corporation, a leading provider of gigabyte-class memory for high-performance network servers, unveiled advanced 4GB memory upgrades for Compaq’s high-performance AlphaServer ES40. Dataram’s 4GB memory doubles the maximum capacity for the ES40 to 32GB providing the power to handle tough jobs with stunning speed. The ES40 system is enhanced with the latest 21264A “EV67” Alpha processor, providing as much as two-times performance improvement over previous systems. Designed to provide accelerated business advantages, Dataram’s high-performance 4GB product doubles total memory (to 32GB) in the quad-processor model for faster processing and faster data retrieval. The DRQES40/4096 consists of four 1GB modules incorporating 256Mbit SDRAM ECC technology. Dataram also offers AlphaServer ES and AlphaStation ES memory products in capacities of 512MB, 1GB and 2GB.

“Powerful and affordable, Dataram’s 4GB memory paired with the ES40 dramatically improves the performance of enterprise-wide business, and intensive Internet or database applications such as SAP, PeopleSoft, Oracle applications, SAS, or Baan; maximizing E-commerce capabilities to the next level”, expressed Bob Kanoff, Dataram’s Director of Marketing. Dataram Corporation is a leading provider of gigabyte memory for network servers, specializing in the manufacture of large-capacity memory products for Compaq, Digital, HP, IBM, Intel, SGI and Sun computers. The company serves users in diverse industries as financial services, Internet service providers, aerospace, petroleum, graphics, automotive, telecommunications, utilities and education. Dataram is registered with the International Standards Organization, having met the internationally recognized ISO 9001 quality assurance standard for design/development, production, installation and service. Dataram memory is a cost-effective alternative to purchasing memory directly from the system manufacturer and is priced up to 50% less. Products can usually be delivered within 24 hours of order placement and are backed by a lifetime warranty and an advanced replacement program. Visit http://www.dataram.com for more information.

============================================================

Subscribe to HPCwire's Weekly Update!

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

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire