Featured

Vectorization Gets Explicit with Intel’s Updated Parallel Tool

Intel Parallel Studio XE 2015′s explicit vectorization feature allows programmers to define SIMD and other loops that should split and run in parallel on separate compute nodes. Intel has released a new version of its HPC application development suite with support for more hardware and development languages and a simple …

Read Full Post Posted in Verify

Next-Gen Code Worthy of World’s Most Powerful Supercomputers

Project aims to maximize power of world’s largest supercomputers by breaking big apps into tiny pieces. Modern supercomputer designs take parallel computing to such an extreme that even applications designed specifically for massive computers with thousands of computing nodes aren’t able to recognize all the myriad computing resources available and …

Read Full Post Posted in Design

Speculative Locks Are Powerful When Used with Caution

Speculative locks work closely with Transactional Synchronization Extensions (TSX), allowing for multiple threads to obtain a lock simultaneously. The technology is difficult to use and requires careful considerations on when to use it. Jeff Cogswell gives you the details. Back in April, I talked about Intel’s Transactional Synchronization Extensions (TSX) …

Read Full Post Posted in Build

Most Recent Posts Blog Archive

Latest Supercomputer Center to Get Big Boost From Intel

The San Diego Supercomputer Center (SDSC) at UC San Diego has joined the Intel Parallel Computing Center (IPCC) program, a move that will allow the research unit to optimize its molecular and neuroscience research applications for parallel computing. Intel’s IPCC program provides funding and resources to universities, institutions and labs …

Read Full Post Posted in Design

Parallel Coders Face Off Again at Supercomputing Conference

Intel is set to kick off its second Intel Parallel Universe Computing Challenge, a game show charity event in which eight teams will compete for a $26,000 prize for the charity of their choice. The competition, to be held at the SC14 conference in New Orleans in November, will include …

Read Full Post Posted in Design

Congress Passes Bill to Support Next-Gen Supercomputing

In an effort to keep the nation competitive, the U.S. House of Representatives has passed a bill that would require the Department of Energy to develop a plan for next-generation exascale computing. The American Supercomputing Leadership Act of 2014 (H.R. 2495) had bipartisan support and was passed by a voice …

Read Full Post Posted in Design

How TBB Goes Atomic

Threading Building Blocks includes several atomic functions. But how does it make these atomics work? Jeff Cogswell looks under the hood of TBB to find what assembly code it uses.   Threading Building Blocks  contains several atomic operations that allow you to run lockless parallel applications. In order to accomplish …

Read Full Post Posted in Verify

Parallelizing Tachyon Ray Tracer

Parallel Studio includes a sample program called Tachyon, which is an open-source ray tracer. Intel has included versions of the code that add parallelization, greatly speeding it up. Jeff Cogswell shows you how to try it out. When you install Parallel Studio XE, you get several sample applications that live …

Read Full Post Posted in Verify

Flood-Forecasting Supercomputer Could Save Lives

Scientists at the National Center for Atmospheric Research (NCAR) are using a supercomputer in hopes of better predicting severe storms and floods in Colorado and to provide enough warning time for residents to evacuate and for authorities to deploy emergency management resources. Their goal is to prevent a repeat of …

Read Full Post Posted in Design

How Numerical Integration Adds Up for Parallel Coding

In the second part of a look at the intersection between scientific applications and parallel programming, Jeff Cogswell explores numerical integration as a prime example of how scientific applications can use parallelization in their mathematical functions. Last time, I talked about how software such as SeisSol, a seismology simulator, uses …

Read Full Post Posted in Verify

Supercomputer-Designed Racecar Sets Speed Record

Ohio State University engineering students have set a new speed record with an electric racecar they designed using a supercomputer. The racecar, driven by a professional driver for the university’s Venturi Buckeye Bullet team, averaged 212.615 miles per hour during two runs at Bonneville Salt Flats near Wendover, Utah in …

Read Full Post Posted in Design

Applying Scientific Apps to Parallel Programming

To come up with a highly parallel scientific app for modeling seismic activity, developers turned to an important mathematical technique for solving differential equations. Jeff Cogswell discusses how similar functions work well with parallel programming. We recently ran a news story on Go Parallel about a high-performance application called SeisSol. …

Read Full Post Posted in Verify

Cisco Retools UCS for Hyperscale Datacenter, Cloud

Disaggregating server CPU, memory, storage and networking pieces into high-speed cloud fabric may deliver super-dense, scalable, Xeon-power servers for hyperscale datacenters. Cisco Systems has launched a new version of its Unified Computing System (UCS) that puts metal behind a server-design concept similar to one rolled out by Intel earlier this …

Read Full Post Posted in Design