线程

Linker Problems with Nonstandard GCC Installation

In our CentOS 6.6 system we have a nonstandard gcc installation - let's say it's /opt/gcc49 - and the "standard" gcc installation as well, both with their own includes and libstdc++.

 

There's an option in icpc command, -cxxlib, which can be used to define the directory for C++ standard library. Using -cxxlib=/opt/gcc49 option helps with header files, but not with libstdc++ - even with this option it still takes /usr/lib/libstdc++.a instead of /opt/gcc49/lib/libstdc++.a

 

Is cilk slower on Linux than on Windows?

Currently, I am getting decent results with Intel 15 Cilk on Windows. However, the results is not nearly as good on Linux. My feeling is the overhead of a spawn is bigger on Linux. Any suggestions/comments?

I had expected the opposite results i.e. better results on Linux. 

I am using fairly new hardware and have tried to disable hyperthreading. Disabling hypertreading improves the result a bit but not much.

 

Modified Cholesky factorisation

Hello,

I'm using MKL to calculate Cholesky factorisation of a covariance matrix. MKL (?POTRF function) is of course much faster than my own naiive implementation (input: 6500x6500 matrix), however there is a problem. Our client requires a *modified* version of the algorithm (below - custom minimum conditions) and therefore MKL gives different results. After I remove the custom minimum conditions (<0.001) from my implementation, both algorithms give *perfectly* equal results. 

Is it possible to force MKL to respect these custom conditions somehow? Thanks for any help.

Create a LIB File from Intel IPP

Hello,

I'm using Visual Studio 2013 and the Intel IPP 8.2.

I have some Auxiliary Functions I build upon Intel IPP for image manipulation in C++ style by overloading some operators and defining function which are composition of many Intel IPP functions.

Now, I want to build a library of that functions I created and I want this library to be "Self Defined".
Namely, on my future projects I want to link to that library (And only that) and be able to use my functions (Which relies on Intel IPP).
Basically, it is something like the question here:

MICs and VLANs

We have a VLAN that needs to be accessed via VLAN Tagging.  This is enabled
on the compute hosts as eth2.3.  I've configured eth2 as a bridge (br1) and
included the mic cards (mic0, mic1) in this bridge.  Creating br1.3 works
to route on the vlan, but the MIC hosts don't seem to support this.

Are there any packages we may be missing for VLAN support?

Two bridges

Hi guys,

We have faced with a requirement to setup two network bridges and include both MICs into the both networks (on each host of the cluster). Is it possible to implement such configuration with the latest MPSS?

Best regards,

OpenMP not using all processors

I am trying to use MKL libraries and OpenMP in a MSVS C++ application on Windows7. The application shows affinity for all 24 processors (2 nodes, 6 processors, HyperThreaded). omp_get_num_procs() also shows 24 processors.  When I run the program only 1 node and 6 processors are accessed. This is confirmed  when I use "KMP_AFFINITY=verbose,none". It ouputs "OMP: Info #179: KMP_AFFINITY: 1 packages x 6 cores/pkg x 1 threads/core (6 total cores)".  I get no compiler or linker complaints.

订阅 线程