MOLECULAR DYNAMICS PERFORMANCE GUIDE - Digital Research Alliance of CANADA

ADVANCED SEARCH

APPLIED FILTERS: NAMD3 _____ _____ _____ _____ _____ _____ _____ _____

  • EXPLORING THE DATABASE

    Default view
    When this page is viewed no filters are initially applied. All benchmarks are selected and sorted by simulation speed. The chart on the right displays only top 30 benchmarks for clarity.
  • Selecting benchmarks
    A subset of benchmarks can be selected using a custom chain of filters. Selected database entries can be downloaded as CSV files for further analysis or viewed in the Benchmark Details table at the bottom of the page.
  • Detailed views
    A detailed view of each database entry can be accessed from Benchmark ID and Software ID search forms. Detailed views include submission commands and simulation input files. View example: PMEMD @Narval (benchmark ID=46).
  • Parallel efficiency
    Efficiency is computed as PS/(SS * N) where PS is speed of the parallel program, SS is speed of the serial program, and N is the number of CPUs or GPUs.
  • Viewing parallel speedup and efficiency
    To view the graph of the dependence of parallel speedup and efficiency on the number of CPU/GPU equivalents select only one software and one cluster. View example: GROMACS @Narval .

  • Viewing QM/MM benchmarks
    To view QM/MM benchmarks select simulation system 4cg1 .

Performance Chart For Selected Benchmarks

*Data updated Sept. 7, 2025

Cost Of GPU-accelerated Simulations

*Data updated Sept. 7, 2025

  • OPTIMIZING GPU USAGE

    Parallel scaling to multiple GPUs
    Parallel scaling to multiple GPUs strongly depends on the compibation of software, hardware and simulation parameters. Often simulations do not run faster on multiple GPUs (PMEMD @Cedar example). Simulations on nodes with direct interconnect between GPUs (NVLink) are more likely to benefit from multiple GPUs, but efficiency decreases and cost goes up with the number of GPUs (NAMD3 @Cedar example ).
  • Benchmarking GPU accelerated MD Engines
    For benchmarking we use the optimal number of cores per GPU (the number needed for the fastest simulation time but not exceeding the maximum number of CPU cores per GPU in a GPU equivalent).

BENCHMARK RESULTS

CPUY: CPU years per 1 microsecond long simulation. GPUY: GPU years per 1 microsecond long simulation. | T: tasks | C: cores | N: nodes. Speed is in ns/day. Integration step = 1 fs. Measured with dataset 6n40 (239,131 atoms).

*More information is available by clicking ID in the table above
ID Software Module Toolch Arch Data Speed CPU CPUeff CPUY GPUY T C N GPU NVLink Site
38 NAMD3.cuda binary_pack/3.0a9 - - 6n4o 1.79e+01 Xeon Gold 6248 62.9 0.0 0.307 1 2 1 2RTX6000 No Siku
279 NAMD3.cuda namd-multicore/3.0.1 gfbfc avx512 9naw 1.60e+01 EPYC 9654 79.3 0.0 0.342 1 2 1 2H100-SXM5 Yes Rorqual
36 NAMD3.cuda binary_pack/3.0a9 - - 6n4o 1.42e+01 Xeon Gold 6248 100.0 0.0 0.193 1 1 1 1RTX6000 No Siku
78 NAMD3.cuda binary_pack/3.0a9 - - 6n4o 1.39e+01 Xeon Gold 6248 7.9 0.0 1.575 1 8 1 8V100-SXM2 Yes Graham
76 NAMD3.cuda binary_pack/3.0a9 - - 6n4o 1.25e+01 Xeon Gold 6248 28.4 0.0 0.438 1 2 1 2V100-SXM2 Yes Graham
278 NAMD3.cuda namd-multicore/3.0.1 gfbfc avx512 9naw 1.01e+01 EPYC 9654 100.0 0.0 0.271 1 1 1 1H100-SXM5 Yes Rorqual
55 NAMD3.cuda binary_pack/3.0a9 - - 6n4o 9.93e+00 Xeon E5-2650 56.5 0.0 0.552 1 2 1 2P100-PCIE No Cedar
30 NAMD3.cuda binary_pack/3.0a9 - - 6n4o 9.58e+00 Xeon Gold 6238 77.1 0.0 0.572 1 2 1 2T4 Yes Graham
37 NAMD3.cuda binary_pack/3.0a9 - - 6n4o 9.56e+00 Xeon Gold 6248 16.8 0.0 1.146 1 4 1 4RTX6000 No Siku
32 NAMD3.cuda binary_pack/3.0a9 - - 6n4o 9.17e+00 Xeon E5-2683 100.0 0.0 0.299 1 1 1 1P100-PCIE No Graham
Date Updated: Sept. 7, 2025, 11:35 p.m.