Zone des développeurs Intel® :
Performance

Points forts

Juste publié ! Intel® Xeon Phi™ Coprocessor High Performance Programming 
Apprenez les fondements de la programmation pour cette nouvelle architecture et les nouveaux produits. Nouveau !
Intel® System Studio
Intel® System Studio est une suite exhaustive d’outils intégrés de développement de logiciels qui peut accélérer la mise sur le marché, renforcer la fiabilité des systèmes et améliorer l’efficacité énergétique et les performances. Nouveau !
Au cas où vous l’avez manqué – Rediffusion du webinaire en direct de deux jours
Introduction au développement d’applications hautes performances pour processeurs Intel® Xeon® et coprocesseurs Intel® Xeon Phi™.
Structured Parallel Programming
Les auteurs Michael McCool, Arch D. Robison et James Reinders utilisent une approche basée sur des modèles structurés qui devrait rendre le sujet accessible à tous les développeurs de logiciels.

Optimisez les performances de vos applications grâce à la programmation parallèle et avec l'aide des ressources novatrices d'Intel.

Ressources de développement


Outils de développement

 

Intel® Parallel Studio

Intel® Parallel Studio, qui apporte aux développeurs Microsoft Visual Studio* C/C++ un traitement parallèle de bout en bout simplifié, fournit des outils avancés permettant d’optimiser les applications clientes pour un traitement multicœur et à nombreux cœurs.

Produits Intel® de développement logiciel ›

Explorez tous les outils qui vous aideront à optimiser vos applications pour l’architecture Intel. Certains outils sont disponibles pour une période d’évaluation gratuite de 45 jours.

Base de connaissances sur les outils

Trouvez des guides et des informations d'assistance sur les outils Intel.

Improving Performance with MPI-3 Non-Blocking Collectives
Par James Tullos (Intel)Publié le 08/01/20140
The new MPI-3 non-blocking collectives offer potential improvements to application performance.  These gains can be significant for the right application.  But for some applications, you could end up lowering your performance by adding non-blocking collectives.  I'm going to discuss what the non-...
What's new? - Intel® Inspector XE 2015
Par Holly Wilper (Intel)Publié le 07/24/20140
What's new in Intel® Inspector XE 2015 New uninitialized memory error detection algorithm that uses deeper analysis method to substantially reduce the number of false positives. Independent control of uninitialized memory analysis, which is off by default Improved on-demand leak detection and ...
Intel® Inspector XE 2015 Release Notes
Par Holly Wilper (Intel)Publié le 07/24/20140
This page provides the current Release Notes for the Intel® Inspector XE 2015 for Linux* and Windows* products.     Intel® Inspector XE 2015for Windows* Intel® Inspector XE 2015for Linux*  What's New! English English English ...
Black-Scholes-Merton Formula on Intel® Xeon Phi™ Coprocessor
Par shuo-li (Intel)Publié le 07/22/20141
Download Available under theIntel Sample Source Code License Agreement license Introduction Financial derivative pricing is a cornerstone of quantitative Finance. The most common form of financial derivatives is common stock options, which are contracts between two parties regarding buying or s...
S’abonner à Articles de la Zone des développeurs Intel
Aucun contenu trouvé
S’abonner à Blogs de la Zone des développeurs Intel®
Help! Unity and Parallel Studio
Par Don Fantom J.1
  Hello, I'm a fresh. I 'm working on a project, in which I use the Unity to develop a game. We mainly use the C# script. I want to know if I can use the parallel studio 2013 to detect the effort, hotsopt and usage of my project? And how to detect? If it can't do that, is there any authority alternative ? Your help would be greatly appreciated!!! Thanks Very Much.
Haswell TSX using RTM (beginner student)
Par tshan k.3
Hello, I am just getting introduced into haswell's TSX infrastructure using RTM. I have downloaded the rtm.h header files from online and i tried producing a simple counter. Unfortunately every time i compile and run the program, the _xbegin function does not execute the transaction inside.  I would be greatly appreciated for your help. thanks #include <stdio.h> #include <stdlib.h> #include "rtm.h" void main(){     int N=5;     int i;     int status;     int counter = 0;     status = _xbegin(); if (status == _XBEGIN_STARTED) {     for (i=0; i<N ; i++)  {         counter++;         printf("counter value: %d\n", counter);     }     _xend(); }      else          printf("did not work\n"); }
Using thread_local on C++ throws error
Par Rihab A.5
I have been trying to convert a C++ MPI code into OpenMP. There are large number of static member variables (mostly dynamic lists of class objects), and i am trying to use 'thread_local' to make sure there are no conflicts. But the file does not compile and threw error: "error: expected a ";"". I was using ICC 14.  When i tried to use ICC 15 beta version, the particular file where i used thread_local compiled, but the compilation of the whole application failed at some other point: "undefined reference to '__cxa_thread_atexit'". Would greatly appreciate help in solving this issue.  
Poor threading performance on Intel Xeon E5-2680 v2
Par Pascal10
Hello I am running a visualization program (visualizing a large dataset) where I can either use MPI or pthreads. When I run it on my desktop which has an Intel i7-2600K (4 cores, 8 threads), I get better performance using pThreads (I'm using a lot of threads, e.g 32) compared to using MPI which is normal (I guess). But when I run the same code on one node (which is part of a cluster) which has Intels Xeon E5-2680 v2 (10 cores, 20 threads), the performance I get using pthreads is worse than MPI; about 70s while using MPI compared to 180s using pthreads. Even worse, the performance on the Intel Xeon E5-2680 v2 is lower than on that of the Intel i7-2600K, it's around 100s on the 2600k but 180 on the  E5-2680 (same number of threads on both). I check using the top command and all the cores are active when I run the program.   So my question is why is that happening? Is there some other way I should be compiling the code on the E5-2680? Is there some variables I should set like KMP_AFFIN...
HTM/STM and Scheduling
Par Simone A.1
Hi, I have a question about Hardware and Software Transactional Memory. Given the types of versioning (eager and lazy) and conflict detection (optimistic and pessimistic) and let's say that 2 or more threads are performing a transaction that write/read the same memory location. The scheduling of the threads could affect the ability of detect a conflict? Which combination of versioning and conflict detection would be better to always catch the conflicts? Hope my question is clear. Thanks. Best Regards, Simone
Locking CPU cache lines for a thread ( L1)
Par Younis A.14
Hi I'm working on securing access to L1 cache by locking it line by line. Is there any way to do it? For example, two threads accessing the L1 and L1 lines are locked for a certain time to each thread accessed them. Regards, Younis
Responsive OpenMP Theads in Hybrid Parallel Environment
Par Don K.1
I have a Fortran code that runs both MPI and OpenMP.  I have done some profiling of the code on an 8 core windows laptop varying the number of mpi  tasks vs. openmp threads and have some understanding of where some performance bottlenecks for each parallel method might surface.  The problem I am having is when I port over to a Linux cluster with several 8-core nodes.  Specifically, my openmp thread parallelism performance is very poor.  Running 8 mpi tasks per node is significantly faster than 8 openmp threads per node (1 mpi task), but even 2 omp threads + 4 mpi tasks runs was running very slowly, more so than I could solely attribute to a thread starvation issue.  I saw a few related posts in this area and am hoping for further insight and recommendations in to this issue.  What I have tried so far ... 1.  setenv OMP_WAIT_POLICY active      ## seems to make sense 2.  setenv KMP_BLOCKTIME 1          ## this is counter to what I have read but when I set this to a large number (2500...
Optimizing cilk with ternary conditional
Par Fabio G.3
What is the best way to optimize the cycle cilk_for(i=0;i<n;i++){ x[i]=x[i]<0?0:x[i]; }or somethings like that? Thanks, Fabio
S’abonner à Forums

Points forts