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)

Figure from: 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
Download this benchmark: directory, 2.5K .tar.gz,




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.

Download this benchmark: config, directory, 2.8M archive, raw benchmark data

Previous versions: 2.6, 2.5, 2.4, 2.3, 2.2