The Evaluation Platform hardware consists of a dedicated 4-node cluster with a Mellanox 4x FDR Infiniband interconnect (54.54 Gigabits/second data bandwidth) where each node has 64 GiB of 4-channel 2133 MHz DDR4 SDRAM (68 Gigabytes/second) memory; two Intel Xeon E5-2670 v3 (Haswell) CPUs, each with 12 cores (24 cores per node) and a clock speed of 2.30 GHz (peak floating point performance per node is 883.2 GFlops/sec); and 480 GB Intel® SSD 530 Series disk drives with SATA 3.0 6 Gbit/sec interfaces (sequential read (up to)540 MB/s, sequential write (up to)490 MB/s).
One of the nodes manages the evaluations run on the other "compute" nodes. Expanding the number of "compute" nodes is under consideration.
Results from each submission are gzipped and placed in a tar file on dtn2.pnl.gov, an externally-facing gateway for transferring large amounts of data efficiently. It is connected to the Internet via multiple 10 gigabit per second links to the Pacific Northwest Gigapop and the Seattle Internet Exchange. It is not uncommon to see transfer rates over 1 gbps to various sites around the world.
The Evaluation Platform software uses the CentOS Linux release 7.4.1708 (Core) operating system (kernel-3.10.0-514.21.1.el7.x86_64). A list of software in /usr/bin is available for download. Additional software that may be available includes MATPOWER using MATLAB. In addition to MATLAB, the following programs and toolboxes from MathWorks may be available: Simulink; Control System Toolbox; Global Optimization Toolbox; Optimization Toolbox; Parallel Computing Toolbox; Signal Processing Toolbox; Simscape; and Simscape Power Systems. The GAMS modeling language, with a full set of solvers, is available. Other solver libraries that may be available include IBM® ILOG CPLEX, GUROBI, and FICO® Xpress. Check Available Solvers for a complete list and the version currently in use and Languages for a complete list of ways to invoke your code.
Requests for additional software will be considered. Please include requests on your registration form or send them to the GO Operations Team with subject line "Request for Additional Software".
Requests for access to nodes consisting of 2.1 GHz dual socket 8-core Broadwell (E5-2620 v4) with 64 GB 2133 MHz DDR4 memory, 56 Gb/s FDR interconnect, and dual NVIDIA P100 12GB PCI-e based GPUs will be considered. Send them to the GO Operations Team with subject line "GPU request". The P100 data sheet has performance specifications. Since this would break the uniform evaluation model the Competition is striving for there is no assurance that such requests would be granted for other than demonstration purposes.
Currently each submission has exclusive access to only one of the compute nodes but the GO Operations Team is developing a containerized MPI capability with the ability to access multiple nodes and is looking for Entrants interested in "early access." If this is of interest, send a request to the GO Operations Team with subject line "MPI". Please tell us what flavor of MPI you would like to use and how many nodes and tasks per node (assume 24 cores per node) you are likely to use.
If you have any questions or concerns regarding the evaluation platform, please contact the GO Operations Team with subject line "Evaluation Platform".