Intel® Many Integrated Core Architecture (Intel MIC Architecture)

offload inside parallel region: problem with private allocatable


I'm trying to offload some computation inside a parallel OMP region. I have problems with a PRIVATE allocatable array. I paste here simple code that shows the problem. The first time the offloaded code works as it should. The second time, the ALLOCATABLE variable p4 is not updated on the MIC.

The output is:

Offload pointer in struct


I'm new to MIC programming, so this is probably a silly question, but I've searched and could not find a solution.

I have a struct with a pointer in it and I want to offload that pointer (the array) to MIC. AFAIK, I can't offload the whole struct, because it's not bitwise copyable. But I was hoping I could offload just the pointer, as a normal array. Below is a minimal example, which segfaults. What am I doing wrong?

As a side question, what are my options if I need to copy the whole struct?

MODULEFILE creation the easy way

If you use Environment Modules  (from Sourceforge, SGI, Cray, etc) to setup and control your shell environment variables, we've created a new article on how to quickly and correctly create a modulefile.  The technique is fast and produces a correct modulefile for any Intel Developer Products tool.

The article is here:


Why does scif_register() return 0?

Hi, All.

My team is trying to transfer bulk data between host and mic using SCIF RMA. All our demo code works fine. When we add the SCIF RMA to the real project, it connects successfully but it gets return 0 from scif_register() and scif_vwriteto() failed error.We have checked so many times. The code we are inserting is exactly the same with the demo code which works fine. 

Did anyone encounter such problem when using scoff rma? Or would you please offer some advice?

Thanks a lot:)



Poor perfomance of FFT on the mic


I would like to share my short experience with Xeon Phi and hope that the performance can be improved.

My program solves a problem similar to the heat equation. Each iteration contains 3 Fourier transforsm and 2 simple  matrix operation (N operations). I wrote a omp program using fftw library. In order to run using mkl library I compiled the wrappers which are provided with the compiler with libmic option.

How do I easily upgrade the RPMs installed on the Phi

Hi all,

I just saw the hotfixes released for mpss 3.[345].  Currently I've got a few RPMs from the mpss-<VERSION>-k1om.tar package installed on my Phi's and I am wondering what the best upgrade path for those is. I'm using

$  cat /etc/mpss/conf.d/rpm.conf
Overlay rpm /var/mpss/rpm on

and install the RPMs in /var/mpss/rpm using trial and error - that is, I have to figure out the RPM dependencies by looking at whether they install on the Phi.

Airflow in Xeon Phi 3120A

Hello everyone,

we have 4 actively cooled Xeon Phi 3120A installed in a machine with additional cooling. However, we keep having overheating problems. We have not found any information regarding the airflow in the Phi cards - is it supposed to blow air out of the back of the case or suck air in?

On top of that, we have 4 very closely stacked cards - there is only very little space between the individual cards. Has anyone run such a setup and has not experienced heating problems or even solved them?


Thanks for any help!

Subscribe to Intel® Many Integrated Core Architecture (Intel MIC Architecture)