Most Recent Build Posts RSS



Efficiently Tune Your OpenMP Code to Bust Bottlenecks

Sometimes OpenMP applications don’t run as fast or as efficiently as planned. A newly updated tool by Intel, called the VTune Amplifier XE 2015, can help developers find and fix performance bottlenecks and efficiency problems. The VTune Amplifier XE 2015, part of Intel Parallel Studio XE 2015 Professional Edition, shows …

Read Full Post Posted in Build | Tagged , | Leave a comment

Smooth Out Speed Bumps in C++, Fortran with VTune

You’ve written your high-performance program, but it’s running slower than a three-legged donkey in the Kentucky Derby. Clearly, you need to identify where the problems are, which parts can benefit from being rewritten, etc. Intel’s VTune Amplifier XE is an application for both Windows and Linux that can help you …

Read Full Post Posted in Build | Tagged , , | Leave a comment

Speed Up Image Processing with OpenMP

Image processing can be significantly optimized with the help of OpenMP. Rick Leinecker shows you how, walks you through the OpenMP techniques employed that make the processing faster, and analyzes an iterative OpenMP construct. Since OpenMP applies concurrent processor operations, synchronization is essential to avoid race conditions. In the demonstration …

Read Full Post Posted in Build | Tagged , | Leave a comment

How to Make C++ Run Faster with Vectorization and Parallelization

If you want your C++ program to run significantly faster, turn to vectorization and parallelization. David Bolton walks you through these two high-performance techniques and shows you the steps toward speeding up your code.

Read Full Post Posted in Build | Tagged , , | Leave a comment

High-Performance Fortran: What You Need to Know

High-Performance Fortran (HPF) is an extension to Fortran 90 and later additions in Fortran 95 that you can use to speed up your programs. It was an early parallel technology, developed between 1991 and 1996 and although it is not used so much now, it’s had a lasting effect and …

Read Full Post Posted in Build | Tagged | Leave a comment

How to Avoid Typical OpenMP Traps

In this article I’ve put together a few common OpenMP questions and their answers. If you are new to OpenMP or have a baffling error, I recommend that you read 32 OpenMP Traps For C++ Developers. It’s a great way to classify the most typical traps and help you avoid …

Read Full Post Posted in Build | Tagged | Leave a comment

Performance, Power and Price: Get the Most Out of Xeon Phi

What is the relationship between price-performance and performance vs. power consumption? This Colfax International white paper written by Andrey Vladimirov takes a deep dive into parallel scalability, power and cost factors both with and without Xeon Phi coprocessors. The results are mapped for clusters vs. single devices, with a performance …

Read Full Post Posted in Build | Tagged | Leave a comment

Calculating Pi with Monte Carlo and MKL

The Math Kernel library provides a great way for calculating huge arrays of random numbers. Creating a Monte Carlo simulation is then easy once you have these random numbers. Jeff Cogswell shows how you can use both MKL and a Monte Carlo algorithm to estimate pi, thus learning the mechanics …

Read Full Post Posted in Build | Leave a comment

Tackling Concurrent Kernel Offloading in Xeon Phi

The Xeon Phi coprocessor includes 61 cores, allowing for great scalability in programs. But some programs don’t scale well, requiring different approaches to maximizing performance. In this blog, Jeff Cogswell explores a chapter from the book “High Performance Parallelism Pearls,” which covers this topic in detail. Here at Go Parallel, …

Read Full Post Posted in Build | Leave a comment

Tapping into Random Number Generators in MKL

The Math Kernel Library (MKL) includes a whole set of random number generators that are parallel-friendly and thread-safe. These generators can quickly fill entire arrays with random numbers, even when the arrays contain millions of elements, all with a single function call. Jeff Cogswell puts them to use and looks …

Read Full Post Posted in Build | Leave a comment