Colfax’s remote access program allows you to evaluate and optimize own code, and to test computational applications optimized for Intel® architecture, on systems based on Intel® Xeon Phi™ product family x200 (formerly Knights Landing).
Request Access Now
Please fill out and submit the form below to request access to the Colfax Cluster. You will get additional instructions via the email address that you provide.
How It Works
This program works by providing for 14 days remote access to a computing cluster hosted at Colfax. The program is free and open to everyone. However, to prevent abuse, the program sponsor (Intel) and organizer (Colfax) reserve the right to screen and deny any access request.
- You submit a request for access
by filling out a simple form above.
- Request gets approved
usually within a few hours. You will receive an email message with an approval notification and connection instructions.
- We send you connection instructions
You will be able to use SSH to access the Colfax Cluster from a PC, Mac or a Linux machine. Access is granted for 14 consecutive days.
- Bring your own code
We provide essential tools: Intel® compilers and performance libraries. You are welcome to compile and run your own applications, test performance, validate programming approaches and perform any other development work that you require.
- Move to the next step
If you would like to own a developer platform based on an Intel® Xeon Phi™ processor, visit dap.xeonphi.com.
If you would like to learn more before jumping into action, attend an upcoming free 1-hour webinar about the remote access program on May 2, 2017.
When you get access, you will log in to a Linux-based head node of a batch farm. There you can stage your code and data, compile, and submit calculations to a queue. Once the queued job completes, your results will be in your home folder.
- Jobs are scheduled on Intel® Xeon Phi™ processors 7250 (formerly Knights Landing)
- Each processor has 64 cores with 4-way hyper-threading.
- Each processor has access to 96 GiB of on-platform RAM (DDR4) and 16 GiB of high-bandwidth memory (MCDRAM).
- You can request nodes in flat or cache mode of MCDRAM.
- Only one job will run on any processor at a time.
- Intel® Omni-Path Architecture interconnects are available for distributed-memory jobs.
- You will get 50 GB of file storage quota.
- Your home directory is not visible to other users.
- Once your access period expires, your home directory on the cluster will be deleted.
Precompiled Optimized Software
Miscellaneous software optimized for Intel® architecture, including Intel® Xeon Phi™ processors, is available on the cluster:
- Intel® Parallel Studio XE Cluster Edition and the tools and libraries included with it:
- Intel® C, C++ and Fortran compilers
- Intel® MPI library
- Intel® OpenMP library
- Intel® Threading Building Blocks (TBB) library
- Intel® Math Kernel Library (MKL)
- Intel® Data Analytics Acceleration Library (DAAL)
- Intel® Python 2.7 and 3.5
- Intel® Caffe
- Educational exercises for performance optimization from the HOW Series training available from GitHub
“Intel, Xeon, and Intel Xeon Phi are trademarks of Intel Corporation or its subsidiaries in the U.S. and/or other countries.”