NAMD 2.11 on STMV (2fs timestep, 12A cutoff + PME every 3 steps) on TACC Stampede
NAMD 2.11 disables asynchronous offload on MIC due to memory/performance leaks in the Intel runtime.
Plot data, job, config, and output files: directory or 153k tar.gz
NAMD 2.10 on STMV (2fs timestep, 12A cutoff + PME every 3 steps) on TACC Stampede
NAMD 2.10 on 20STMV and 210STMV (2fs timestep, 12A cutoff + PME every 3 steps)
James C. Phillips, Yanhua Sun, Nikhil Jain, Eric J. Bohm, and Laximant V. Kale.
Mapping to Irregular Torus Topologies and Other Techniques for Petascale Biomolecular Simulation.
In Proceedings of the 2014 International Conference for High Performance Computing, Networking, Storage, and Analysis (SC14), 2014.
abstract, conference, journal
NAMD 2.8 on ApoA1
92,224 atoms, 12A cutoff + PME every 4 steps, periodic
Time is in seconds per step, averaged over a number of steps, after load balancing. NAMD prints this data, labeled Benchmark time, twice near the beginning of a run. Due to its measurement-based load balancing system, NAMD performance may improve dramatically after the first couple of hundred timesteps.