Cluster Computing

Intel MPI and I_MPI_EXTRA_FILESYSTEM: How to tell it's on?


I hope the Intel MPI experts here can help me out. Intel MPI was recently installed on our cluster, a cluster that uses a GPFS filesystem. Looking at the release notes I saw that "I_MPI_EXTRA_FILESYSTEM_LIST gpfs" was now available. Great! I thought I'd try to see if I can see an effect or not.

Intel Phi compiling cl file occurs Stack dump: Segmentation fault (core dumped) Y86 DAG->DAG and Function Pass Manager


when i compile the cl file on Intel Many Integrated Core and linux system,i gets the below errors

Stack dump:
0.      Running pass 'Function Pass Manager' on module 'Program'.
1.      Running pass 'Y86 DAG->DAG Instruction Selection' on function '@test_kernel'
Segmentation fault (core dumped)

who can get me some suggestions? Thank you!

here is my code of OpenCL kernel

Online SAP HR training in Hyderabad USA,UK,Canada,Australia,India,Dubai, @ +91 800 8000 311





• What is SAP?

• ASAP Methodology

• About versions and Architecture

• SAP landscape

• HR in SAP

• Why SAP HR as ERP Solution for a company




• Enterprise Structure

• Personnel Structure

• Organizational Structure




• Overview of Organizational Objects and Structures

Problem in offload to Intel MIC with Intel 15 Compiler


I recently updated my Intel compiler from Intel 14 to Intel 15 (Trail version).

I ran a cluster job on 8 nodes.

The program had an offload section to print "hi this is offload section"(The printing per node happens multiple times).

It seems like some nodes have printed the offload while others have thrown an error.

Here is the output/error I got.

What does __kmp_hierarchical_barrier_release imply in vTune?


I profiled my program running on Xeon Phi in native mode via vTune and realized that a lot of time goes to __kmp_hierarchical_barrier_release. What does this normally imply? I know it must be some OpenMP issue, but have no idea how to solve it.

BTW, the same piece of code, whening running on Xeon, vTune tells that some significant portion of time (much less than the __kmp_hierarchical_barrier_release in Phi though) goes to __kmp_launch_threads.

Thanks in advance!

Cannot use jemalloc with IntelMPI


I've tried to bench several memory allocators on Linux (64-bit) such as ptmalloc2, tcmalloc and jemalloc with an application linked against IntelMPI (

Launching any application linked with jemalloc will cause the execution to abort with a signal 11. But the same application, when not linked with IntelMPI will work without any issue.

Is IntelMPI doing its own malloc/free ?
How can this issue be overcome ?



Starting out, with 2 to 12 Phi's

So I bought 2 of the 31S1P's (not yet in use) and am contemplating getting another 10 for a fluid dynamics simulation. I'm trying to figure out how to proceed. I apologize if some of these are stupid questions. I think they're reasonable though as my setup is a bit unique: luckily I have a few 3d printers, in case I need to print brackets or ducts, and a 3600 CFM fan with 15" diameter. Some questions:

problems in offload in fortran modules

Hi all,

I have been trying to run what is called CESM(climate earth system model) and added an offload to one of its Fortran modules.

!dir$ offload begin target (mic)
    print *,'hi this is the offload section'
!dir$ end offload

I performed a successful build. The ar I replaced with the xiar and managed a successful build of the modules.

However while running the final executable i get the following error.

Subscribe to Cluster Computing