Welcome to The Parallel
In this issue, learn which Intel® software development tools are best for your task.
FEATURE: Which Tool Do I Use? A Roadmap to Increasing Your Application’s Performance
To fully utilize today’s and tomorrow’s hardware, you must modernize your software. This modernization is best when it includes using software development tools and libraries that help in threading and vectorizing your application. By using the correct tool at each phase of your performance tuning, you can greatly increase performance at lower cost.
FEATURE: Modernizing Code for Tomorrow’s HPC Problem-Solving
The author shares tips on code modernization, or increasing parallel programming, that have proven valuable for dedicated HPC software developers, domain specialists, and data scientists alike.
ALSO IN THIS ISSUE
Full Speed Ahead: Get a Helping Hand from the Vectorization Advisor
With Vectorization Advisor recommendations, the Hartree Centre was able to get an 18 percent speedup in their DL_MESO code, which uses mesoscale simulations for computer-aided formulation of shampoos, detergent powders, agrochemicals, and petroleum additives.
Optimizing Image Processing
As China’s largest online direct sales company, JD.com handles several billion product images every day. By using Intel® software development tools, JD.com sped up its image processing 17x—handling 300,000 images in 162 seconds.
Boosting Speech Recognition Performance: Qihoo360 Euler* Optimization with Intel® Math Kernel Library and Intel® C++ Compiler
The Euler* platform, a distributed off-line computing platform that supports machine learning-related computation models for real businesses, is critical for Qihoo360 Technology Co., Ltd., a Chinese Internet security company. The company collaborated with Intel to optimize its applications on Intel® architecture, speeding up performance 5x.
How Fortran Developers Can Boost Productivity with Submodules
This article dives into submodules, a major contribution of Fortran 2008 now supported in Intel® Fortran Compiler 16.0 and a reason why many Fortran developers feel they can significantly increase their productivity.