This article provides an overview of the methods available in Intel® Parallel Composer, along with a comparison of their key benefits.
Get a high-level overview of the automatic parallelization and vectorization methods used by the Intel® C++ and Fortran Compilers.
This article contains a training materials (in PDF format) on Intel® MKL Sparse Solvers which includes details of PARDISO/DSS, Iterative Solvers features and performance.
Sparse BLAS routines can be useful to implement iterative methods for solving large sparse systems of equations or eigenvalue problems
Introduction and functionalities of Intel MKL
Webinar slides - Dr. Tim Mattson, Principal Engineer at Intel's Microprocessor Technology Labs, will lead a webinar focused on actual code and the parallel programming APIs available to software developers. Tim will begin with an overview of the high level issues that apply to the task of creating a parallel program and then move on to consider the most commonly used parallel algorithms. He will then discuss the major parallel programming APIs (OpenMP*, MPI, and Windows* threads) showing how they are used with different algorithms and different platforms. After attending this webinar, developers should be conversant with major concurrent APIs and algorithms and be well positioned to start incorporating these techniques in their applications.
Webinar slides - New innovations bring new challenges. For many C/C++ developers, introducing parallelism means spending hours tuning an application for multicore performance. Learn techniques with a new performance tuning profiler found in Intel® Parallel Studio and quickly identify performance issues. Using application source code, Intel parallelism expert Gary Carleton demonstrates how developers can quickly solve the three most common performance issues: (1) bottlenecks, (2) locks and waits, and (3) amount and locations of threads. Windows* developers now have a tool that brings new levels of transparency for quickly and accurately tuning threaded applications for optimal performance. Recommended companion technical webinar: The Good, the Bad, and the Ugly: Improve Parallel Application Quality and Performance.
Webinar slides - Error checking, data races, and deadlock are notorious yet critical issues to track down in threaded apps. Learn new techniques using Intel® Parallel Studio developer tools and save hours of debugging time, while improving application reliability. Intel® Parallel Inspector offers unique threading analysis techniques, drilling down to source code lines where problems can occur, and enabling developers to locate and isolate common threading problems. Learn how to use Parallel Inspector to find memory leaks and common memory overruns. Tap into debugging extension plug-ins and use error checking capabilities found in Parallel Studio to improve application reliability and performance. Recommended companion technical webinars: Find Errors in Windows C++ Applications, and Static Analysis and Intel® C++ Compilers.
Webinar slides - Use the Intel® Threading Building Blocks (Intel® TBB) template library to introduce parallelism into applications. The use of Lambda expressions available in Intel® Parallel Composer are discussed, along with data parallel and task parallel models of parallel programming. Specific focus is placed on representing common parallel programming patterns, such as pipelines and concurrent queues, using Intel TBB templates. The newest enhancements to the Intel TBB library are also explored, including task-to-thread affinity and task cancellation support.
Webinar slides - There is a better way to develop code for images than writing it from scratch. Now, using new Intel® Parallel Studio products, developers can efficiently transform image processing for improved productivity and performance. Integrated with Microsoft Visual Studio* for C/C++, Intel® Parallel Composer, Intel® Parallel Amplifier, and Intel® Parallel Inspector enable developers to implement and optimize images with parallelism. Parallel development techniques, such as harmonization or Sobel filters in Intel® Integrated Performance Primitives (IPP), and OpenMP* at the primitive function level, will be used to demonstrate how to enhance image processing for multicore. Starting at a high level with a non-threaded application, Parallel Amplifier will locate hotspots within the application. As threads are added at a higher level with OpenMP, Parallel Inspector quickly finds and fixes threading errors. Implementing parallelism using Parallel Studio provides forward-scaling, saving developers from rewriting code with each new processor innovation.