Featured

Apache Spark Lets You Take Parallel Programming Across a Cluster

Parallel programming in a cluster of nodes shares many of the same concepts as parallel programming across cores and vectors. Apache Spark is a clustered, in-memory processing engine that lets you scale your software across thousands of nodes. Jeff Cogswell introduces it. When working in parallel programming, we often live …

Read Full Post Posted in Build

Multithreaded Code Made Easy with Worksharing Constructs

OpenMP includes four constructs that together make up what are called worksharing constructs. Three of these are available in C++ and all four are available in Fortran. Jeff Cogswell shows you how you can use them to easily write multithreaded code. OpenMP includes many different constructs for dividing up your …

Read Full Post Posted in Build

IPCC Advances HPCs and Parallel Computing

One year since its launch, the Intel Parallel Computing Centers (IPCC) program has made great strides in helping the high-performance computing (HPC) community modernize its scientific applications for multi-core and many-core environments, according to a recent story in Scientific Computing. The IPCC program offers a variety of support for software …

Read Full Post Posted in Design

Most Recent Posts Blog Archive

Scale Performance from Multicore to Many-Core

Implementing a parallel algorithm can get frustrating at times. Developers can thread an application, but see little performance gain. Or they can hit a scalability ceiling where performance gains level off as more cores are added. A newly updated tool, the Advisor XE 2015, can help solve those issues by …

Read Full Post Posted in Build

Boost Your App Performance with Optimization Reports

Intel’s latest compilers produce new, user-friendly optimization reports that provide developers the information they need to increase the performance of their applications. Previous compilers scattered information across different reports, resulting in messages that were cryptic, confusing or not logically ordered. The single report stream was also hard to navigate, hard …

Read Full Post Posted in Build

Allocate Memory Effectively in TBB

Threading Building Blocks (TBB) includes drop-in replacement functions for the C-type memory allocation functions, as well as replacements for the C++-type allocators. Jeff Cogswell introduces them. When you’re using Threading Building Blocks and writing an app that makes use of the basic memory allocation functions, there’s a feature whereby you …

Read Full Post Posted in Build

Cray Enters New Territory with Chapel Parallel Language

Supercomputer manufacturer Cray is developing a general-purpose, parallel programming language called Chapel that supports Intel architecture. Jeff Cogswell gives you a quick tour. When people think of Cray, they usually think of supercomputers. But something else is coming out of the company: A language for parallel programming that is portable …

Read Full Post Posted in Build

Catching Gravitational Waves to Answer Big Bang Questions

Scientists have long believed that galactic events, such as supernova explosions or black hole mergers, leave a trace called gravitational waves, which are ripples in the fabric of space-time much like how a boat produces waves in the water. Now scientists are beginning to take advantage of supercomputers — specifically, …

Read Full Post Posted in Design

World’s Fastest Astronomical Supercomputer Reaches Petascale Speeds

The world’s fastest supercomputer for astronomical research just got a lot faster. The National Astronomical Observatory of Japan’s Center for Computational Astrophysics (CfCA) has doubled the power of its Aterui supercomputer, from 502 teraflops to 1.058 petaflops per second, according to a recent press release. In order to meet increased …

Read Full Post Posted in Design

Apache Spark Lets You Take Parallel Programming Across a Cluster

Parallel programming in a cluster of nodes shares many of the same concepts as parallel programming across cores and vectors. Apache Spark is a clustered, in-memory processing engine that lets you scale your software across thousands of nodes. Jeff Cogswell introduces it. When working in parallel programming, we often live …

Read Full Post Posted in Build

Multithreaded Code Made Easy with Worksharing Constructs

OpenMP includes four constructs that together make up what are called worksharing constructs. Three of these are available in C++ and all four are available in Fortran. Jeff Cogswell shows you how you can use them to easily write multithreaded code. OpenMP includes many different constructs for dividing up your …

Read Full Post Posted in Build