Intel® Many Integrated Core Architecture (Intel MIC Architecture)

Rebuild modules for newer kernels fails

Hi, the systems hosting the MICs have been updated and hence the mpss must be updated.


Linux compute-19-17.local 3.19.1-1.el6.elrepo.x86_64 #1 SMP


gcc version 4.4.7 20120313 (Red Hat 4.4.7-11) (GCC)

Trying to rebuild the modules fails (it works fine with 2.6 type kernels) :

rpmbuild --rebuild mpss-modules-3.5-1.src.rpm

<cut ....>

Gateway not set for mic0 when br0 is dhcp

So I cannot seem to get the default route set for my mic cards except by manually doing so after logging on to them.

I have a system with 2 MIC cards in it.
The cards are bridged with eth0 on the host into br0
br0 is set to get its IP via dhcp
The mic cards have static IPs


/usr/sbin/micctrl --addbridge=br0 --type=external --ip=dhcp --netbits=16 --mtu=9000
/usr/sbin/micctrl --network=static --bridge=br0 --ip= --gw= mic0

Need Phi Optimization Expert to work on new project for Road Material Simulation


We require a Intel Phi processor optimization expert to help with optimization FORTRAN code for road material stress simulation. The models have been coded and are working, just need a guru to help move the load off to Phi cards.

Currently it takes 20 days to run a simulation point on a regular Intel i7 2.8 Ghz Quad core notebook processor, we need to get that down to under 40 minutes.

problem in setting threads at MIC

hi all,

This a program, I had written in fortran.

!dir$ offload begin target(mic)
call omp_set_num_threads(240)
!dir$ end offload

!dir$ offload begin target(mic)
!$omp parallel
print *,The number of threads are',omp_get_num_threads()
!$omp end parallel
!dir$ end offload

However in the final output I still get 

The number of threads are 1

why? How do I set more threads?


auto vectorized and auto parallelized only interested loop.

Hi all,

It turn out one of the loop I was interested in offloading to MIC as per optimization report suggested it was both auto vectorized and auto parallelized.

What I would want is only auto parallelize only this loop.

The -vec-report vectorised all loops and paralelized them.

This is important to for me as I would want to check percentage reduction in time taken on my application just by reducing the time taken in this loop.

How do I do this? Is there a way to do this?

offload error (trying my first program)

I am just trying to get our XeonPhi to work properly. It worked for offload computing a couple of months ago when I tried it, but now I get the following error:

offload error: cannot find offload entry __offload_entry_Conceptual_Transformation_cpp_40f_7e694fe6ef39bee36b1d18aad1ea599dicc43479367WrTpxg
offload error: process on the device 0 unexpectedly exited with code 1

icc version 14.0.2 (gcc version 4.7.2 compatibility)

MPSS 3.5

Code is just a simple example to try out offloading. Any help appreciated.

analyzing .optrpt file


With the intention to ensure/check if a given loop is parallel or not, I generated an .optrpt file.

I used the following flags for the same:   -parallel -opt-report-phase=par -opt-report:5

However I have three doubts persisting that the auto-parallelization flags failed to answer.

1) I had a two level nested loop like this
do k=1,km-1
                   do kk=1,2
<code is here>

Intel® Many Integrated Core Architecture (Intel MIC Architecture) abonnieren