Michael Feldman, the editor of HPCWire writes, “These are interesting times for the microprocessor industry. At the same time the multicore revolution is happening, we’re also seeing the rise of data parallel architectures. Yes, vector computing is back, but this time, it’s not just for nerds.”
Full Story

[Read more →]

Justin Rattner of Intel writest, “Voltage and power reductions in our products come from a broad engagement between process, design and architecture. For our latest 45nm products, the careful design of the SRAM cell and our invention of high-k metal gate transistors were key contributors to reducing minimum voltages.” Previously, he wrote about the Climate [...]

[Read more →]

As many as half of all embedded designs have an FPGA next to a microcontroller. The FPGA can be used to implement anything from glue logic, to custom IP, to accelerators for computationally intensive algorithms. By taking on some of the processing tasks, FPGAs help to improve system performance, thereby freeing up the MCU from [...]

[Read more →]

Tom Halfhill, Senior Analyst at InStat, writes for the Microprocessor Report, a newsletter dedicated to discussing new developments in microprocessors and microprocessor-based systems. Steve Leibson writes for EDN to show some of Tom’s editorial because he’s conveniently put an excerpt of it in InStat’s free email newsletter called Processor Watch:
Full Story

[Read more →]

At last month’s International Supercomputing Conference in Dresden, NASA presented the results of an internal study exploring the suitability of the Cell BE architecture towards accelerating key aspects of climate modeling. Centered on the computationally intensive solar radiation component of the Goddard Earth Observing System Model v5 (GEOS-5), the study required that roughly 2,000 lines [...]

[Read more →]

NVIDIA Corporation, the worldwide leader in visual computing technologies, and the University of Utah today announced that the university has been recognized as a CUDA Center of Excellence, a milestone that marks the beginning of a significant partnership between the two organizations.
Full Story

[Read more →]

Warren East, chief executive officer of ARM Holdings plc (Cambridge, England), has declined to name the company that has taken a multi-year architecture license for ARM’s current and future technologies. But East gave enough clues while speaking to financial analysts on Wednesday (July 30) to show clearly that Apple is a contender.
Full Story

[Read more →]

The processor market is diverging between two paths, the general and the predictable. Where does HPC hitch it’s wagon?
Full Story

[Read more →]

Microsoft researchers are developing a new operating system that’s designed from the ground up to support Internet-based computing and multicore architectures and which could one day replace the company’s storied Windows franchise.
Full Story

[Read more →]

Toshiba Electronics Europe has begun offering the Cortex-A9MP and the Cortex-R4F processor cores from ARM Holdings plc (Cambridge, England) for use with the company’s ASICs in process technologies down to 40-nm. Toshiba’s European LSI Design and Engineering Centre (Dusseldorf, Germany) can provide support to European customers that choose the ARM cores.
Full Story

[Read more →]

Parallelization is a core strategic-planning consideration for all software makers, and the amount of performance benefit available from parallelizing a given application (or part of an application) is a key aspect of setting performance goals for the parallelization process. Matt Gillespie provides an overview of Amdahl’s Law and Gustafson’s Trend, placing them in the context [...]

[Read more →]

The current generations of multi-core processors have successfully improved upon their single-core predecessors, in terms of performance, power consumption, and thermal properties. Hardware parallelism (in the form of the number of cores per processor) has taken the place of clock speed as the specification of first interest when describing a processor. Asymmetric multi-core computing is [...]

[Read more →]

Plurality Ltd. has raised $8 million from Libot, a group of private investors. The company’s Hypercore multicore processor is a scalable, easily programmable, general-purpose processor. Plurality plans to reach market in early 2009, initially with a 64-core processor and then with a 256-core processor. For the sake of comparison, Intel Corporation and Advanced Micro Devices [...]

[Read more →]

The Embedded Microprocessor Benchmark Consortium (EEMBC) today announced the publication of new certified benchmark scores for the ARM processor-based Freescale i.MX31 multimedia applications processor. Tested with the ARM(R) RealView(R) RVCT 3.1 build 559 compiler, the new results supersede a previous set of certified scores using a GCC version 3.43 compiler and limited -O2 optimizations.

Full Story

[Read more →]

Michael Pearce of Intel summarizes a set of interesting topics from his Gamefest conference visit. An excerpt from his blog post:
“ * Memory Models: Foundation Knowledge for Concurrent Code - walking through the memory model that defines the contract between the programmer and the execution environment - and how the execution environment [...]

[Read more →]

Patrick Madden, a professor of computer science at Binghamton University, posts a blog entry to make a point about Amdahl’s law and how some tasks cannot be finished faster by thinking parallel. Here is an excerpt:
“Like it or not, there are some things that can’t be made faster with parallel machines (as far as I, [...]

[Read more →]

Toshiba Electronics Europe (TEE) is now offering the ARM Cortex-A9MP and the ARM Cortex-R4F processor cores for use with the company’s full range of ASIC technologies - including processes down to 40nm With local support from Toshiba’s European LSI Design and Engineering Centre (ELDEC), European customers can choose the ARM cores to improve performance, reduce [...]

[Read more →]

A typical application has a set of control-oriented operations, such as compare, branching, and looping. Certain applications, such as a data sort operation, are control heavy. Even in a more data-intensive application, such as video processing (discussed in Part 1 and Part 2), control operations can consume a significant part of the application’s execution time. [...]

[Read more →]

Here are some predictions about what might happen by the end of this year in Supercomputing world. The article predicts that the world’s first (mostly) non-classified Petaflop supercomputing monster should be unveiled (not with Cell processors or with GPUs, but with CPUs), and discusses MPI’s problems to effectively address the global shared memory opportunities, even [...]

[Read more →]

The two architectures behind the VIA Nano and Intel Atom processors are significantly different from a very technical overview.  One is based on efficiency of performance (Nano) while the other is based on simplicity of performance (Atom). Here is a performance and power comparison. The conclusion: Coming from a very small CPU design team here [...]

[Read more →]