Following AMD's recent success of its 6-core Opteron processor in the TOP500 supercomputer list, Intel has sensed a market for "HPC-optimized" processors, which the company expects will be out in the first half of 2010. These could be either variants of the Nehalem-EX multi-socket capable processors, or that by design, Nehalem-EX suits HPC (high-performance computing) applications better.

These 6-core processors will carry clock speeds higher than 8-core Xeon processors around that time. The processors will be able to work in systems with up to 256 processors (logical CPUs). In addition to these Intel also announced that it will be releasing a beta version of its Ct technology by the end of this year. Ct makes parallel programming in the C and C++ programming languages easier, by automatically optimizing code to exploit multi-core and many-core systems.

Unveiled at the footnote of the GPU Technology Conference 2009, by none other than NVIDIA CEO Jen-Hsun Huang, NVIDIA's Fermi architecture looks promising, at least in the field of GPGPU, which was extensively discussed upon in his address. The first reference board based on NVIDIA's newest 'GT300' GPU is a Tesla HPC processor card, which quickly became the face of the Fermi architecture. Singapore HardwareZone, and PCPop caught some of the first closeup pictures of the Tesla accelerator, and the GPU's BGA itself. Decked in a dash of chrome, the Tesla HPC processor card isn't particularly long, instead a great deal of compacting by its designers is evident. It draws power from one 8-pin, and 6-pin PCI-E power connectors, which aren't located next to each other. The cooler's blower also draws air from openings in the PCB, and a backplate further cools the GPU (and possibly other components located) from behind. From the looks of it, the GPU package itself isn't larger than that of the GT200 or its predecessor, the G80. Looks like NVIDIA is ready with a working prototype against all odds, after all, doesn't it? Not quite. On close inspection of the PCB, it doesn't look like a working sample. Components that are expected to have pins protruding soldered on the other side, don't have them, and the PCB seems to be abruptly ending. Perhaps it's only a dummy made to display at GTC, and give an indication of how the card ends up looking like. In other words, it doesn't look like NVIDIA has a working prototype/sample of the card they intended to have displayed the other day.

NVIDIA Corp. today introduced its next generation CUDA GPU architecture, codenamed "Fermi". An entirely new ground-up design, the "Fermi" architecture is the foundation for the world's first computational graphics processing units (GPUs), delivering breakthroughs in both graphics and GPU computing.

"NVIDIA and the Fermi team have taken a giant step towards making GPUs attractive for a broader class of programs," said Dave Patterson, director Parallel Computing Research Laboratory, U.C. Berkeley and co-author of Computer Architecture: A Quantitative Approach. "I believe history will record Fermi as a significant milestone."

NVIDIA today announced work with Microsoft to promote NVIDIA Tesla graphics processing units (GPUs) for high performance parallel computing using the Windows HPC Server 2008 operating system.

"The coupling of GPUs and CPUs illustrates the enormous power and opportunity of multicore co-processing," said Dan Reed, corporate vice president of Extreme Computing at Microsoft. "NVIDIA's work with Microsoft and the Windows HPC Server platform, is helping enable scientists and researchers in many fields achieve supercomputer performance on diverse applications."

NVIDIA Research developed several GPU-enabled applications on the Windows HPC Server 2008 platform, such as a ray tracing application that can be used for advanced photo-realistic modeling of automobiles. Related to this, NVIDIA worked with Microsoft Research to install a large Tesla GPU computing cluster and is studying applications that are optimized for the GPU.

Pliant Technology, developer of Enterprise Flash Drives (EFDs), a new class of high-performance, high-reliability storage drives, today announced the availability of its first family of products. Pliant's Lightning EFDs integrate an advanced software architecture and a proprietary ASIC controller design to dramatically improve performance and reliability of storage and IT systems, while significantly reducing cost, space requirements and energy consumption.

Pliant's Lightning EFDs enable enterprise data centers, financial services organizations, high-performance computing (HPC) environments, and digital media applications to 'do more for less,' by providing IT managers and system architects with breakthrough levels of performance, reliability and efficiency. Lightning EFDs deliver the industry's highest sustained performance with the most predictable performance profile across a wide range of read/write workloads, and have been specifically designed for demanding, mission-critical 24x7 applications.

NVIDIA today announced that HP's most powerful and expandable workstation-the HP Z800 Workstation-is now configurable with up to two NVIDIA Tesla graphics processing units (GPUs), another key indicator of the demand being seen for GPUs in the high performance computing (HPC) space.

Enterprises that rely on HP workstations to accelerate their work in fields ranging from scientific research and industrial design, to 3D animation and seismic exploration, can now reap the benefits of NVIDIA Tesla GPUs and tackle demanding computational workloads right at the desktop.

Some of the first AMD socket G34 motherboards were caught on camera, at the ongoing Computex event, by Inpai. The new socket succeeds the G3MX, which was discontinued in its development process itself. It facilitates upcoming six-core, and twelve-core "Magny-Corus" processors by AMD, which will use HyperTransport 3.0 system interface (for the first time on the enterprise AMD platform), and support the quad-channel (per socket) memory interface. One of the first processors in line for this socket is the based on the "Istanbul" six-core silicon.

The Inventec G34 HPC motherboard (left, below) will be targeted at the server and HPC markets. The two sockets are wired to twelve DDR3 DIMM slots per socket, each array supporting a 256-bit wide (quad-channel) memory interface. The Quanta G34 looks to be more workstation oriented, featuring several PCI-Express slots, and eight DIMM slots per socket. Like Socket F, the new socket physically will be a land-grid array, with pins on the socket, and contact points on the processor package. Its pin-count is known to be 1974.

ELSA Japan, a leading computer graphics solution provider and Lucidlogix (Kfar Netter, Israel, CEO - Moshe Steiner) announce an agreement to deploy Lucid's HYDRA based chip in ELSA Japan High Performance products.

The companies have teamed up to transform high performance computing in the Japanese marketplace. For the first time, a product based on Lucid's HYDRA technology will be used in a new line of ELSA Japan high performance systems for the HPC, broadcast and medical markets.

AMD today announced that its Quad-Core AMD Opteron processors are powering "Jaguar," the first ever wholly x86-based supercomputer to achieve the petaflop performance milestone. AMD Opteron processors now help drive seven of the Top 10 supercomputer systems in the world.

The AMD Opteron processor-based and IBM PowerXCell processor-based "Roadrunner" system at Los Alamos National Labs again captures the number 1 spot on the bi-annual TOP500 Supercomputer Sites list, while the "Jaguar" supercomputer at Oak Ridge National Laboratory comes in at number 2 and is the highest performing entirely x86-based system ever on the survey. "Jaguar" is based on Cray XT4 and XT5 systems and runs on over 45,000 Quad-Core AMD Opteron processors, enabling a balanced system with unrivaled x86 performance.