Filters

Forum topic

Different environment variable on different compute node

I have two computers, the value of environment variable on different computer is not the same. For example, TMP is set to "C:\tmp" on compute 1, and TMP is set to "D:\Temp_Dir" on computer 2.

Authored by Yongjun L. Last updated on 03/29/2017 - 13:41
Forum topic

mpiicc architecture incompatibility on Xeon Phi x200 KNL

Hello,

i receive the following errors while trying to compile High Performance Linpack for Intel Xeon Phi x200 (KNL), do you have any suggestion?

---------------

Authored by Simone Tinti Last updated on 03/29/2017 - 04:04
Forum topic

Which logical core does MPI background threads are pinned?

I program in C++ which parallelizes using both MPI and OpenMP (1 MPI process per machine, Multiple threads are exploited by each MPI process)

Authored by seongyun k. Last updated on 03/27/2017 - 06:39
Forum topic

What could be a cause of the MPI program to run slower on multinode cluster?

Hello everyone,

Authored by Arthur V. Ratz Last updated on 03/27/2017 - 05:30
Forum topic

Nested MPI process failed with GetParentPort error

Hello,

we are trying to execute a tricky code with intel mpi 5.0.2.044.

We have a main program executed via

Authored by CALUGARU D. Last updated on 03/24/2017 - 04:10
Article

Using Intel® Omni-Path Architecture

This document shows how to install the Intel® Omni-Path Host Fabric Interface (Intel® OP HFI) card and the Intel® Omni-Path Architecture (Intel® OPA) software on the host.

Authored by Nguyen, Loc Q Last updated on 03/23/2017 - 11:19
Article

英特尔® 数学核心函数库(英特尔® MKL)新添免费选择,依靠自己,免版税

以下指南提供了免费获取 最新版英特尔® 数学核心函数库(英特尔® MKL)的各种方法,无需访问英特尔® 卓越支持(通过在英特尔数学核心函数库论坛上发帖获取支持)。您可以随时在世界各地购买全套工具(英特尔® Parallel Studio XE ),获取在线服务中心的优先支持并访问前代库。
Authored by admin Last updated on 03/21/2017 - 19:03
Forum topic

Heterogeneous Offload for Marching Cubes and Mesh Export

Greetings,

We seek advice and collaborators as the project is GPLv3 and on GITHUB.

There exists a parallel Open MP segment within the Marching Cubes class header of Mandelbulber.

Authored by Pancoast, Robert Last updated on 03/21/2017 - 11:15
Forum topic

Efficiently use vector registers

I am considering to vectorize an application on Xeon Phi. The calculation part of the program looks like this (only a part of the code):

Authored by zhen jia Last updated on 03/21/2017 - 10:13
Forum topic

How to understand offload report time?

Hi All,

When I set OFFLOAD_REPORT = 1, offload program will output the offload time of MIC.

example:

[Host-TIME] 26.24

[MIC-TIME] 24.13

Authored by yu, frank Last updated on 03/21/2017 - 00:24
For more complete information about compiler optimizations, see our Optimization Notice.