Intel(R) Xeon Phi(tm) Coprocessor -- Cluster training - call for demand!

[BelindaLiviero]

Intel is evaluating to offer a 4 hour web-based basic tutorial covering the fundamental principles of how to integrate an Intel Xeon Phi coprocessor into a Linux based cluster.

During the course each attendant would have remote access to a Linux server and be able to do each step as shown in the outline below.  The course will be given free of charge. Requirements are an Internet connection, a web browser, and Putty.   We are settling on the sharing technology we will be using, and will publish that at a later date.

If you are interested in such an offer please reply to this forum thread -- you have the ability to reply privately, if you don't want to be identified.

If we have enough interest, we'll pull it together!

Topics:

• Finding information on Intel Xeon Phi coprocessor on the web
• Download the driver software
• Unpacking the driver software package, explanation of components
• Discussion on prerequisites of the compute server (for instance what software needs to be installed, reserved IP addresses, user names, network file systems)
• Basic concepts (host, host OS, host kernel, coprocessor, Intel(R) MPSS stack, layout of files, boot image of the uOS, ramfs of the uOS)
• Recompiling HOST kernel packages; diagnose output  and understand errors (necessary to work with nonstandard kernels)
• Install a minimal set of MPSS rpm packages using rpm
• Create a default MPSS configuration (using “micctrl --initdefaults “)
• Startup (aka boot) the coprocessor
• Connect via minicom to the coprocessor (this allows one to connect to the Intel Xeon Phi coprocessor WITHOUT figuring out network problems)
• modify uOS filesystem by overlaying an /etc/passwd file; reboot the coprocessor
• Create a bridgded network on the host
• Configure the coprocessor for bridged networking by modifying micX.conf  directly
• Reboot card and connect via ssh
• Set up a ssh key-pair; diagnose ssh gotchas
• Mount a NFS file system on the coprocessor
• Configure a user known in the cluster by modifying the /etc/passwd file of the coprocessor
• Group up with neighbor – run MPI benchmark natively over Ethernet
• Recompile the MPSS OFED package to support a nonstandard kernel on the HOST
• Install MPSS-OFED rpms
• Start OFED on the coprocessor
• Group up with neighbor – run MPI benchmark natively over InfiniBand
• Create a minimal startup script wrapping everything up; this startup script can be used by a batch scheduling system to restart a coprocessor on behalf of a user before running a job.
• Where to find more resources or ask questions

In future (advanced) courses we might want to talk about topics like:

• Change micX.conf configuration to adopt to diskless clients
• The tools (micinfo, micrasd, ….)
• Logging – syslog, sar (how to enable logging, typical output and problems to look out for)
• cron: maintenance  log rotation,  detect issues like missing daemons, problems
• Adding more programs/libraries/files to the coprocessors (including pros and cons)
• Troubleshooting startups/shutdowns
• Upgrading the MPSS stack on an established installation
• Diagnose system and coprocessor health
• Customizing installation scripts

[Vadim_Karpusenko]

This sounds very interesting. Please, count me in.

Vadim Karpusenko <vadim@colfax-intl.com>

[Gethin_W_]

Yes, thanks.  I'm interested.

[yectli_h_]

I'm also interested. thanks

[Vishal1]

I'm very interested.

[Vitaly_V__K_]

I'm interested.

[Ole_Saastad]

Yes, please. I'm interested.

[Girish_Nair]

Oh boy. That would be a dream come true. Very excited. A big YES.

[drMikeT]

I would be interested ...

Michael

[Tod_M_Intel]

Very interested, thanks!

Tod

[Giorgis_G_]

Count me in. Very interested.

Giorgis

[Carlos_Alexandre_T_]

I am extremely interested! Thanks!

[BelindaLiviero]

Thank you for registering your interest -- we are still planning on this - the timing of the sessions is likely to start in ~May.

One question I must ask is somewhat logistical:   the best 'webinar' tool that we have used at Intel in the past is one that supports access from Microsoft* Windows, iOS, or Android clients but not Linux  (more here: http://support.citrixonline.com/webinar/all_files/G2W010003 )

Will this be a big problem for you folks?   Do all of you have one of the supported types of systems from which you can connect?

[VIKRANT_G_]

I am interested in this

[Georg_G_]

I'm very interested attending this course.

Georg

[ekiefner]

Yes, I am very interested too to join this Web training about INtel MIC and Linux Cluster.

Erhard

[BelindaLiviero]

All,

You are receiving this message if you’ve indicated to us in the past that you’d be interested in training on cluster administration with large installations of Intel® Xeon Phi™ Coprocessors.  

Starting this May, Intel will lead 4-hour webinars, with some hands-on exercises, on Basic Cluster administration with  Intel Xeon Phi Coprocessors.

There is an 18 person limit on webinar attendance because it is hands-on.   Attendees who register will receive notification within a few days to confirm registration.

Where and When:   Three webinar sessions are available now, and more will be scheduled throughout the summer depending on demand.   

Monday, May 12, 2014 5:00 PM - 9:00 PM PDT       Register at:  https://www1.gotomeeting.com/register/909192649  (very limited seating)

Wednesday, May 14 5:00 PM – 9:00 PM PDT          Register at: https://www1.gotomeeting.com/register/822739432

Wednesday, May 21 8:00 AM – 12:00 PM PDT       Register at: https://www1.gotomeeting.com/register/899481456

Agenda: In this course led by an instructor the attendants will learn how to integrate Xeon Phi coprocessors into a cluster. The session will include:

• Discussion on prerequisites of the compute server (for instance what software needs to be installed, reserved IP addresses, user names, network file systems)
• Unpacking the driver software package, explanation of components
• Basic concepts (host, host OS, host kernel, coprocessor, MPSS stack, layout of MPSS files, boot image of the uOS, ramfs of the uOS)
• Recompiling HOST kernel packages; diagnose output  and understand errors (necessary to work with nonstandard kernels)
• Install a minimal set of MPSS rpm packages using rpm
• Create a default MPSS configuration (using “micctrl --initdefaults “)
• Startup (aka boot) the coprocessor
• Connect via minicom to the coprocessor (this allows one to connect to the Xeon Phi WITHOUT figuring out network problems)
• modify uOS filesystem by overlaying an /etc/passwd file
• Create a bridgded network on the host
• Configure the coprocessor for bridged networking by modifying micX.conf  directly
• Reboot card and connect via ssh
• Set up a ssh key-pair; diagnose ssh gotchas
• Mount a NFS file system on the coprocessor
• Configure a user known in the cluster by modifying the /etc/passwd file of the coprocessor
• Group up with neighbor – run MPI benchmark natively over Ethernet
• Recompile the MPSS OFED package to support a nonstandard kernel on the HOST
• Install MPSS-OFED rpms
• Start OFED on the coprocessor
• Group up with neighbor – run MPI benchmark natively over InfiniBand
• Create a minimal startup script wrapping everything up; this startup script can be used by a batch scheduling system to restart a coprocessor on behalf of a user before running a job.
• Where to find more resources or ask questions

Each attendant will connect via ssh to a cluster, and be able to run all necessary commands alongside the presentation.

[BelindaLiviero]

space is still available on the May 14 webinar -- otherwise most other dates are full!

Please let us know if more sessions are needed

[ashish_s_]

I joined this forum some days back. I want to attend Intel Phi cluster trainings again. Can you share presentation of those webinars or provide information on any scheduled training on the same in future?

Thanks,

Ashish K Singh

[Alfonso_P_]

I' am interested for the slides/presentation too.

[TaylorIoTKidd]

We have plans for more training but no definite dates.

I'll forward your requests on.

Regards
---
Taylor