Cluster Computing

mpi failed using Intel sample code

Hi,

I have installed intel parallel studio xe cluster edition 2016  on HPC environment.

All compilers are working fine.

when I tried to execute the following commands:

#mpirun hostname 

#mpirun  --machinfile hosts  hostname

It executed successfully returning all nodes' hostname

And I compiled the following sample <Intel_DIR>/compilers_and_libraries/linux/samples/en/mpi/test.c

using the following:

#mpiicc test.c

and execute the following command:  

#mpirun a.out

#mpirun --machinfile hosts a.out

A Bus error

Hi all,

I'm running a pretty heavy MPI application (the WRF model) on Linux and get a BUS error (please see below the output for the type of the error) --- any idea how to isolate the cause (specific line of bad coding), or system/compiler/MPI related issue ?

Have you guys had an experience of catching these bugs with one of Intel's new tools ?

Thanks in advance for your perspective and experience,

Jack.

###

rsl.error.0010:[n13:mpi_rank_10][error_sighandler] Caught error: Bus error (signal 7)

Problem of offloading 2-D Array

#include<stdio.h>
#include<stdlib.h>
#include<string.h>

int main()
{
    int* p1[10];
    int* p2[10];
    int start[10];
    int len[10];
    for(int i=0;i<10;i++)
    {
        p1[i]=new int[(i+1)*1000];
        p2[i]=new int[(i+1)*1000];
        len[i]=(i+1)*1000;
        start[i]=0;
    }
    /*
        #pragma offload target(mic)\
        nocopy(p1[0:10]:\
        extent(start[0:10]:len[0:10]) alloc_if(1) free_if(0))\
        nocopy(p2[0:10]:\
        extent(start[0:10]:len[0:10]) alloc_if(1) free_if(0))
        {
            ;
        }

execute vTune error in symmetric mode

I want to use VTune to analyze a program on phi and CPU in symmetric mode .But when I run the following command and get error information.

   wj@mcc21:~/mic_test$ mpirun -host mcc21 -n 1 ./cpu : -host mic0 -n 1 amplxe-cl  -c advanced-hotspots /home/wj/graph/mic
/home/wj/bin/amplxe-cl: /home/wj/bin/amplxe-cl: cannot execute binary file
   I have already scp amplexe-cl to phi.What's wrong? By the way,How to use VTune to detect TLB miss and Cache miss in symmetric mode.Could you please give the specific command?

amplxe: Error: Cannot find product on the target system at mic0

Hi,
    I want to use vtune on phi in native mode.But when I run the command,I get following information.
    
wj@mcc21:~/mic_test$ amplxe-cl -r ./ -target-system=mic-native:0 -collect advanced-hotspots /home/wj/a
amplxe: Using target: mic-native:0
amplxe: Error: Cannot find product on the target system at mic0:/amplxe/vtune_amplifier_xe_2016.2.0.444464/
VTune Amplifier was not properly installed on the Xeon Phi card. To make installation please run under the following commands under root or sudo:

Knights Landing Development Platforms Available - Get a Head Start on Optimizing Code

Get a head start with Developer Access Program (DAP) - an early access program for developers worldwide to purchase an Intel® Xeon Phi™ Processor based system aka Ninja Developer Platform. Pre-order and start modernizing your code today! http://dap.xeonphi.com/

 

use Intel(R) Xeon(R) CPU E5-2680 v3 as coproceesor in windows remotely

Intel(R) Xeon(R) CPU E5-2680 v3 with red hat 4.8

I want use this system as coprocessor in windows (visual studio 2012) (is is possible ?). This system is located in other place in same network. I can access it through putty. I installed MPSS 3.6.1 and Intel composer XE 2013 sp1. When i run  micctrl --addssh <username> <public-key> this command , it gives error :

 Error manipulating coprocessors: Intel(R) Xeon Phi(TM) coprocessor driver is not  loaded or you have insufficient access.

 

 

 

The Next Leap in Performance for Many of Today’s Most Critical Applications

On March 31, 2016, Intel Corporation announced the release of the next-generation Intel® Xeon® processor E5-2600 v4 product family. These new processors are designed to help organizations respond more quickly and intelligently as the business world continues to speed up. In almost every industry, critical applications have to process larger volumes of data at higher speeds to enable faster research and innovation and to support real time, analytics-driven business models.  

2 nodes on Windows 7 x64 assistance

Installed Parallel Studio XE 2016 Update 2 Cluster edition on Windows 7 Pro x64 (installed on two systems) and attempting to run the MPI test program.

Each system can run the test program on itself, but I cannot run on other system from either system.

hydra_service.exe can be -remove and -install correctly.

I can see and copy files from each system to the other system (to shared folder), test program installed in shared folder.

Subscribe to Cluster Computing