by Jared Bell, AnandTech
Investigating Sandy Bridge Memory ScalingFull Story

[Read more →]

by Richard Gerber and Andrew Binstock
ABSTRACT: Parallel programming makes use of threads to enable two or more operations to proceed in parallel. The entire concept of parallel programming centers on the design, development, and deployment of threads within an application and the coordination between threads and their respective operations. This article examines how to break [...]

[Read more →]

Simply saying, a scheduler is a software utility responsible for assigning jobs and tasks to resources according to pre-determined policies and availability of resource. A job can be comprised of one or more tasks along with relevant information on the required resources (number of nodes, GPUs, network bandwidth, application license etc.). Jobs are submitted to [...]

[Read more →]

by Ravi Mandalia
Open source software developer Mozilla is working towards bringing multi-core processor support for its Firefox web browser.
The company, which recently dished out Firefox 5, said in a blog post that it will bring multi-process content support on Firefox.

[Read more →]

Objective Interface Systems Inc. (OIS) has stated that its ORBexpress supports QNX Software Systems Ltd’s QNX Neutrino real-time operating system (RTOS) 6.5 that offers symmetric multiprocessing on ARM, Power, x86 and on processors with up to 32 cores, providing massive scalability for compute-intensive applications.

[Read more →]

by Gaston Hillar
Embree provides a collection of high-performance ray tracing kernels that target modern Intel multicore microprocessors. In addition, Embree includes an example photo-realistic rendering engine. If you want to learn how ray tracing kernels are used in practice and how to optimize multithreaded code with Advanced Vector Extensions (AVX), you will find valuable examples [...]

[Read more →]

Microsoft Research and the Systems Groups at ETH Zurich have released the latest version of their research operating system, Barrelfish, under an MIT licence and placed it in a Mercurial repository for public access. BarrelFish is an experimental operating system which has been designed to run on systems with heterogeneous CPUs, such as a computer [...]

[Read more →]

from Legit Reviews
DonanimHaber has a bunch of benchmark results posted up for an AMD FX-8130P Bulldozer processor that they have for testing. The FX-8130P was paired with Gigabyte 990FXA-UD5 motherboard, NVIDIA GeForce GTX 580 graphics card and 4GB of Kingston HyperX DDR3-1866MHz. Some of the benchmarks run aren’t multi-core intensive and the results of Super [...]

[Read more →]

by Ben Smith, HPC Opinion
Logic is the beginning of wisdom. Not always we use logic to determine our actions, but the more we try, the better decisions we will take. Today CPUs and GPUs are separate entities. CPU is the place where applications are being executed on, and the GPU is a compute offloaded device, [...]

[Read more →]

Last week the OpenMP Architecture Review Board has voted on the final release of the OpenMP 3.1 API Specification. After a successful vote, the Architecture Review Board has released the OpenMP 3.1 API Specification. It is available on the OpenMP webpage for download as a PDF. OpenMP 3.1 is a minor release that does [...]

[Read more →]

Professors Marc Snir, William Gropp, and Peter Kogge wrote a white paper identifying the research needs to achieve exascale performance that is necessary for progress in science. Here is an excerpt.
“As petascale systems begin to be deployed in national labs and academia, the race has started for the next level of performance: exascale systems. DOE [...]

[Read more →]

By Heather Clancy
IBM actually was behind six of the top 10 computers on the latest edition of Green500 list; a prototype of its next-generation Blue Gene/Q supercomputer wound up on top. It holds more than half of the top 100 positions on the list.

[Read more →]

By Gaston Hillar
Microsoft places strong emphasis on GPU programming with forthcoming C++ AMP
The next version of Microsoft Visual C++ will introduce C++ Accelerated Massive Parallelism, also known as “C++ AMP.” Herb Sutter announced C++ AMP and unveiled Microsoft’s plans to provide heterogeneous platform support in Visual C++. The first targets are GPU (Graphics Processing Unit) [...]

[Read more →]

by Ben “HPC” Smith, HPC-Opinion
The first time GPUDirect was mentioned was in the NVIDIA press release announcing the GPUDirect project as collaboration with Mellanox Technologies - “NVIDIA Tesla GPUs To Communicate Faster Over Mellanox InfiniBand Networks”, http://www.nvidia.com/object/io_1258539409179.html. Since then you can find more press releases and numerous papers describing what it is, and the performance [...]

[Read more →]

Intelligence In Software: Tech Trends
Changing the Ways Data Centers Are Built
By Tim Kridel for Intelligence In Software

Enterprise IT departments have spent the past several years flocking to the cloud largely for the flexibility it provides, both in terms of technology and economics.
In the case of public clouds, where a third party owns and operates the [...]

[Read more →]

Intelligence In Software: Tech Trends
Which Comes First: Parallel Languages or Patterns?
By Clay Breshears for Intelligence In Software

On the shuttle to the UPCRC (Universal Parallel Computation Research Center) Annual Summit meeting on the Microsoft campus in Redmond, Wash., I was listening in on a discussion about parallel programming patterns. Being a parallel programmer, I was interested [...]

[Read more →]

Intelligence In Software: S/W Dev Tools & Tips
By Herman Mehling for Intelligence In Software

The cloud and cloud-based solutions are here to stay. Recent IDC research shows that worldwide revenue from public IT cloud services exceeded $16 billion in 2009 and is forecasted to reach $55.5 billion in 2014. Clearly, the pace of growth is [...]

[Read more →]

By Stefan Wörthmüller
A crash course tutorial
Today, all programs must parallelize tasks if they are to enjoy the power available through multicore processors. Until recently, though, parallel programming was the domain of server programmers and their scientific counterparts. Now, programmers from other domains are faced with the problem of migrating existing applications from serial to multithreaded [...]

[Read more →]