The Ideal Grid Computing System: Sun Fire V20z with AMD Opteron processors

The Sun Fire V20z Computer Grid rack system is an integrated solution for Electronic Design Automation, Mechanical Computer-Aided Engineering, Petroleum, Life Sciences, and any other organization that requires excellent price/performance for its compute-intensive applications. Compelling pricing, widely scalable, and extremely reliable, the Sun Fire V20z servers are the hardware platform for the compute nodes. They deliver a powerful solution for rapid deployment, expandability, and reliability to meet your specific business needs.  

The Sun Fire V20z server includes an embedded Service Processor (SP), Flash memory, RAM, a separate Ethernet interface, and server-management tools for greater control and minimum total cost of ownership. The dedicated SP provides complete operating-system independence and maximum availability of server management.

The Sun Fire V20z Compute Grid rack system delivers the proven hardware and software solution and can enable your organization to meet and exceed its most challenging Grid Computing objectives.  

Learn more about saving time and resources when implementing Grid computing solutions with Sun Fire v20z servers>>>

Angstrom’s Titan64 Quadrablade 850 Blade Server Becomes the World’s First AMD Opteron™ processor-based 4-way Blade Server

Imagine being able to deploy the highest density 4P AMD Opteron 850 processor-based Blade server available in the market today. Imagine remote access to integrated power management and integrated serial console access in 13-pack blade enclosures that stack one on top of another like Lego(R) blocks enabling you to scale your rack as needed. Indeed, this very product, consisting of 208 processors in 52 blades and is available today from Angstrom Microsystems.

The Angstrom Microsystems Titan64 Quadrablade(tm) 850 Blade Server was developed by the acknowledged leader in high-performance computing (HPC) providing AMD64 expertise and knowledge of HPC software in the bio-informatics, scientific computing, financial modeling, graphics rendering, and oil and gas industries. Angstrom enhances clustering technology for these markets with remote management software and LinuxBIOS expertise. Its clients include Industrial Light & Magic, ConocoPhilips, NIH, Instinet and Akamai.

A Titan64 QuadraBlade 850 rack is comprised of four stacked nests, each nest housing 13 QuadraBlade 850s for a total of 4 x 13 blade, or 52 blades. Each blade is a four-processor cache coherent, shared memory (SMP) system with the option of 3 SCSI, IDE, SATA HDDs and high-speed interconnects such as Myrinet(tm) or Infiniband. Unlike other 4-way AMD Opteron processor solutions, Angstrom is one of few vendors to provide
AMD Opteron 850 processor-based servers in an ultra-dense blade format.

Learn more about the scalability, reliability, and the best memory density delivered by the Titan64 QuadraBlade>>>

Expand The Memory Of Your 32-Bit Application Using Microsoft’s 4GT

The 4GB memory limit of 32-bit computing, for many applications, results in a performance penalty since effective data processing requires sufficient addressable memory. 64-bit processing, using AMD64 technology, enables applications to gain access to a much larger memory space and also provides additional performance gains due to the larger number of CPU registers.

Now Available for Download: The AMD Core Math Library

The AMD Core Math Library (ACML) is a highly optimized library that contains numeric functions for mathematical, engineering, scientific and financial applications. Co-developed by AMD and the Numerical Algorithms Group (NAG), Version 2.0 of ACML was released in April 2004 and provides an expanded feature set, optimization of existing features, and improved performance.

ACML 2.0 comprises a full implementation of Level 1, 2, and 3 BLAS with key routines optimized for high performance on AMD Opteron processors. Taking advantage of the highly tuned BLAS kernels, a key set of Linear Algebra Package (LAPACK) routines have been further optimized to achieve greater performance than standard LAPACK implementations. ACML 2.0 also offers a comprehensive suite of FFTs in single-, double-, single-complex and double-complex data types. Leveraging the PGI compiler, ACML 2.0 for Linux development also provides support for OpenMP and Non-OpenMP.

Developers using ACML 2.0 can achieve greater code accuracy and speed of delivery while maximizing performance and functionality of x86-based applications running on 32-bit Windows and 32- and 64-bit Linux operating systems.

Download the AMD Core Math Library today>>>

Some Tips On Developing Applications for IBM’s DB2 Running on AMD64 Processors

IBM’s DB2 Universal Database 8.1 is one of the industry’s top relational databases, and it’s also one of the most powerful enterprise applications available for servers running the AMD Opteron processor with Direct Connect Architecture.

Alan Zeichick provides an introduction to developing 32-bit and 64-bit stored procedures and user-defined functions for 64-bit DB2 on AMD64>>>