NVIDIA HPC Application Performance

For Deep Learning performance, please go here.

Modern HPC data centers are key to solving some of the world’s most important scientific and engineering challenges. The NVIDIA Data Center GPUs fundamentally change the economics of the data center, delivering breakthrough performance with dramatically fewer servers, less power consumption, and reduced networking overhead, resulting in total cost savings of 5X-10X.

The number of CPU-only servers replaced by a single GPU-accelerated server is called the node replacement factor (NRF). To arrive at NRF, we measure application performance with up to 8 CPU-only servers. Then we use linear scaling to scale beyond 8 servers to calculate the NRF. The NRF will vary by application.

Engineering

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual Intel SPR 8480C@2GHz with 4x NVIDIA H100 SXM 80GB | FUN3D Benchmark: dpw_wbt0_crs-3.6Mn_5, CUDA Version: 11.8

Geoscience

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual SPR 8480C@2GHz with 4x NVIDIA H100 SXM 80GB | ICON Benchmark: QUBICC 160 km resolution, CUDA Version: 11.8 | RTM Benchmark: Isotropic Radius 4, CUDA Version: 11.8 | SPECFEM3D Benchmark: four_material_simple_model, CUDA Version: 11.8

Molecular Dynamics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual SPR 8480C@2GHz with 4x NVIDIA H100 SXM 80GB | AMBER Benchmark: DC-Cellulose_NPT, CUDA Version: 11.8 | GROMACS Benchmark: STMV, CUDA Version: 11.8 | LAMMPS Benchmark: SNAP, CUDA Version: 11.8 | NAMD Benchmark: apoa1_nve_cuda, CUDA Version: 11.8

Physics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual SPR 8480C@2GHz with 4x NVIDIA H100 SXM 80GB | Chroma Benchmark: szscl21_24_128, CUDA Version: 11.3.1 | GTC Benchmark: moi#proc.in, CUDA Version: 11.8 | MILC Benchmark: Apex Medium, CUDA Version: 11.8

Detailed H100 application performance data is located below in alphabetical order.

AMBER

Molecular Dynamics

Suite of programs to simulate molecular dynamics on biomolecule

VERSION

22.0-AT_22.3

ACCELERATED FEATURES

  • PMEMD Explicit Solvent and GB Implicit Solvent

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

http://ambermd.org/GPUSupport.php

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
AMBER [PME-Cellulose_NPT_4fs]ns/dayDC-Cellulose_NPTyes4.133186331,264
AMBER [PME-Cellulose_NPT_4fs]NRFDC-Cellulose_NPTyes1x77x153x306x
AMBER [PME-Cellulose_NVE_4fs]ns/dayDC-Cellulose_NVEyes4.123136491,260
AMBER [PME-Cellulose_NVE_4fs]NRFDC-Cellulose_NVEyes1x76x157x306x
AMBER [PME-FactorIX_NPT_4fs]ns/dayDC-FactorIX_NPTyes20.711,3262,6805,330
AMBER [PME-FactorIX_NPT_4fs]NRFDC-FactorIX_NPTyes1x64x129x257x
AMBER [PME-FactorIX_NVE_4fs]ns/dayDC-FactorIX_NVEyes20.951,3562,7215,416
AMBER [PME-FactorIX_NVE_4fs]NRFDC-FactorIX_NVEyes1x65x130x259x
AMBER [PME-JAC_NPT_4fs]ns/dayDC-JAC_NPTyes84.614,5409,19717,967
AMBER [PME-JAC_NPT_4fs]NRFDC-JAC_NPTyes1x54x109x212x
AMBER [PME-JAC_NVE_4fs]ns/dayDC-JAC_NVEyes85.164,5909,30120,152
AMBER [PME-JAC_NVE_4fs]NRFDC-JAC_NVEyes1x54x109x237x
AMBER [PME-STMV_NPT_4fs]ns/dayDC-STMV_NPTyes1.3885170340
AMBER [PME-STMV_NPT_4fs]NRFDC-STMV_NPTyes1x62x123x246x
AMBER [FEP-GTI_Complex 1fs]ns/dayFEP-GTI_Complexyes9.89194388776
AMBER [FEP-GTI_Complex 1fs]NRFFEP-GTI_Complexyes1x20x39x78x

FUN3D

Engineering

Suite of tools actively developed at NASA for Aeronautics and Space Technology by modeling fluid flow

VERSION

13.7 (update 1)

ACCELERATED FEATURES

  • Full range of Mach number regimes for the Reynolds-averaged Navier Stokes (RANS) formulation

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://fun3d.larc.nasa.gov

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
FUN3DLoop Time (Sec)dpw_wbt0_crs-3.6Mn_5no495301710
FUN3DNRFdpw_wbt0_crs-3.6Mn_5yes1x21x37x59x

GROMACS

Molecular Dynamics

Simulation of biochemical molecules with complicated bond interactions

VERSION

2022.3

ACCELERATED FEATURES

  • Implicit (5x), Explicit (2x) Solvent

SCALABILITY

Multi-GPU, Single Node

MORE INFORMATION

http://www.gromacs.org

https://ngc.nvidia.com/catalog/containers/hpc:gromacs

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
GROMACS [ADH Dodec]ns/dayADH Dodecyes67626723896
GROMACS [ADH Dodec]NRFADH Dodecyes1x12x14x18x
GROMACS [Cellulose]ns/dayCelluloseyes19189246350
GROMACS [Cellulose]NRFCelluloseyes1x14x19x27x
GROMACS [STMV]ns/daySTMVyes44268115
GROMACS [STMV]NRFSTMVyes1x10x17x28x

GTC

Physics

GTC is used for Gyrokinetic Particle Simulation of Turbulent Transport in Burning Plasmas

VERSION

V 4.5 Updated

ACCELERATED FEATURES

  • Push, shift, and collision

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
GTCMpush/Secmoi#proc.inyes357581,3702,441
GTCNRFmoi#proc.inyes1x22x40x71x

ICON

Weather and Climate

A global unified atmosphere model for numerical weather prediction and climate modeling research

VERSION

2.6.5_RC

ACCELERATED FEATURES

  • Full model of dynamics and physics

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://code.mpimet.mpg.de/projects/iconpublic

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
ICON [SLAM 191 - 160KM - no radiation]Integrate_nh (sec)SLAM 191 levels 160 km resolution without radiationno2,431204149113
ICON [SLAM 191 - 160KM - no radiation]NRFSLAM 191 levels 160 km resolution without radiationyes1x12x16x22x
ICON [QUBICC 160 km resolution]Integrate_nh (sec)SLAM 191 levels 160 km resolution with radiationno2,213188133101
ICON [QUBICC 160 km resolution]NRFSLAM 191 levels 160 km resolution with radiationyes1x12x17x22x

LAMMPS

Molecular Dynamics

Classical molecular dynamics package

VERSION

stable_23Jun2022_update1

ACCELERATED FEATURES

  • Lennard-Jones, Gay-Berne, Tersoff, many more potentials

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://lammps.sandia.gov/index.html

https://ngc.nvidia.com/catalog/containers/hpc:lammps

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
LAMMPS [LJ 2.5]ATOM-Time Steps/sLJ 2.5yes1.11E+081.07E+091.93E+093.35E+09
LAMMPS [LJ 2.5]NRFLJ 2.5yes1x10x18x31x
LAMMPS [EAM]ATOM-Time Steps/sEAMyes5.33E+075.13E+089.12E+081.60E+09
LAMMPS [EAM]NRFEAMyes1x10x18x31x
LAMMPS [ReaxFF/C]ATOM-Time Steps/sReaxFF/Cyes4.45E+051.02E+071.84E+073.04E+07
LAMMPS [ReaxFF/C]NRFReaxFF/Cyes1x31x57x94x
LAMMPS [SNAP]ATOM-Time Steps/sSNAPyes1.08E+053.87E+067.69E+061.52E+07
LAMMPS [SNAP]NRFSNAPyes1x37x74x147x
LAMMPS [Tersoff]ATOM-Time Steps/sTersoffyes2.77E+079.16E+081.64E+092.95E+09
LAMMPS [Tersoff]NRFTersoffyes1x34x60x108x

MILC

Physics

Lattice Quantum Chromodynamics (LQCD) codes simulate how elemental particles are formed and bound by the “strong force” to create larger particles like protons and neutrons

VERSION

feature/gauge-action-quda_16a2d47119

ACCELERATED FEATURES

  • Staggered fermions, Krylov solvers, Gauge-link fattening

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://ngc.nvidia.com/catalog/containers/hpc:milc

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
MILCTotal Time (Sec)Apex Mediumno71,5951,172634355
MILCNRFApex Mediumyes1x67x124x222x

NAMD

Molecular Dynamics

Designed for high-performance simulation of large molecular systems

VERSION

GPU, AMD CPU V 3.0a13 ; Intel CPU V 2.15a AVX512

ACCELERATED FEATURES

  • Full electrostatics with PME and most simulation features

SCALABILITY

Up to 100M atom capable, multi-GPU, single node

MORE INFORMATION

http://www.ks.uiuc.edu/Research/namd/

https://ngc.nvidia.com/catalog/containers/hpc:namd

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
NAMD [apoa1_npt_cuda]Ave ns/dayapoa1_npt_cudayes19.152845491,048
NAMD [apoa1_npt_cuda]NRFapoa1_npt_cudayes1x15x29x55x
NAMD [apoa1_nptsr_cuda]Ave ns/dayapoa1_nptsr_cudayes19.592915701,124
NAMD [apoa1_nptsr_cuda]NRFapoa1_nptsr_cudayes1x15x29x57x
NAMD [apoa1_nve_cuda]Ave ns/dayapoa1_nve_cudayes20.753636981,386
NAMD [apoa1_nve_cuda]NRFapoa1_nve_cudayes1x17x34x67x
NAMD [stmv_npt_cuda]Ave ns/daystmv_npt_cudayes1.87234589
NAMD [stmv_npt_cuda]NRFstmv_npt_cudayes1x12x24x48x
NAMD [stmv_nptsr_cuda]Ave ns/daystmv_nptsr_cudayes1.81234692
NAMD [stmv_nptsr_cuda]NRFstmv_nptsr_cudayes1x13x26x51x
NAMD [stmv_nve_cuda]Ave ns/daystmv_nve_cudayes1.942754108
NAMD [stmv_nve_cuda]NRFstmv_nve_cudayes1x14x28x56x

RTM

Geoscience

Reverse time migration (RTM) modeling is a critical component in the seismic processing workflow of oil and gas exploration

VERSION

nvidia_2021_05

ACCELERATED FEATURES

  • Batch algorithm

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://www.tsunamidevelopment.com/assets/rtm.pdf

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
RTM [Isotropic Radius 4]Mcells/sIsotropic Radius 4yes11,318124,975249,251498,066
RTM [Isotropic Radius 4]NRFIsotropic Radius 4yes1x11x22x44x
RTM [TTI Radius 8 1-pass]Mcells/sTTI Radius 8 1-passyes3,77322,10944,13588,094
RTM [TTI Radius 8 1-pass]NRFTTI Radius 8 1-passyes1x6x12x23x
RTM [TTI RX 2Pass mgpu]Mcells/sTTI RX 2Pass mgpuyes3,77321,70443,08885,784
RTM [TTI RX 2Pass mgpu]NRFTTI RX 2Pass mgpuyes1x6x11x23x

SPECFEM3D

Geoscience

Simulates Seismic wave propagation

VERSION

devel_fef2ace9

ACCELERATED FEATURES

  • OpenCL and CUDA hardware accelerators, based on an automatic source-to-source transformation library

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://geodynamics.org/cig/software/specfem3d/

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x H100 SXM2x H100 SXM4x H100 SXM
SPECFEM3DTotal Time (Sec)four_material_simple_modelno1,268462414
SPECFEM3DNRFfour_material_simple_modelyes1x32x59x105x

Engineering

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7763@2.45GHz with 4x NVIDIA L40 | FUN3D Benchmark: dpw_wbt0_crs-3.6Mn_5, CUDA Version: 11.8

Molecular Dynamics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7763@2.45GHz with 4x NVIDIA L40 | AMBER Benchmark: DC-STMV_NPT, CUDA Version: 11.8 | GROMACS Benchmark: STMV, CUDA Version: 11.8 | LAMMPS Benchmark: SNAP, CUDA Version: 11.8 | NAMD Benchmark: apoa1_nve_cuda, CUDA Version: 11.8

Detailed L40 application performance data is located below in alphabetical order.

AMBER

Molecular Dynamics

Suite of programs to simulate molecular dynamics on biomolecule

VERSION

22.0-AT_22.3

ACCELERATED FEATURES

  • PMEMD Explicit Solvent and GB Implicit Solvent

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

http://ambermd.org/GPUSupport.php

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x L402x L404x L408x L40
AMBER [PME-FactorIX_NPT_4fs]ns/dayDC-FactorIX_NPTyes20.717791,5753,1476,303
AMBER [PME-FactorIX_NPT_4fs]NRFDC-FactorIX_NPTyes1x38x76x152x304x
AMBER [PME-FactorIX_NVE_4fs]ns/dayDC-FactorIX_NVEyes20.957971,6133,1826,428
AMBER [PME-FactorIX_NVE_4fs]NRFDC-FactorIX_NVEyes1x38x77x152x307x
AMBER [PME-JAC_NPT_4fs]ns/dayDC-JAC_NPTyes84.613,2706,56112,90126,316
AMBER [PME-JAC_NPT_4fs]NRFDC-JAC_NPTyes1x39x78x152x311x
AMBER [PME-JAC_NVE_4fs]ns/dayDC-JAC_NVEyes85.163,2976,65613,25026,477
AMBER [PME-JAC_NVE_4fs]NRFDC-JAC_NVEyes1x39x78x156x311x
AMBER [PME-STMV_NPT_4fs]ns/dayDC-STMV_NPTyes1.3862124248497
AMBER [PME-STMV_NPT_4fs]NRFDC-STMV_NPTyes1x45x90x180x360x

FUN3D

Engineering

Suite of tools actively developed at NASA for Aeronautics and Space Technology by modeling fluid flow

VERSION

13.7 (update 1)

ACCELERATED FEATURES

  • Full range of Mach number regimes for the Reynolds-averaged Navier Stokes (RANS) formulation

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://fun3d.larc.nasa.gov

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x L402x L404x L408x L40
FUN3DLoop Time (Sec)dpw_wbt0_crs-3.6Mn_5no495119613219
FUN3DNRFdpw_wbt0_crs-3.6Mn_5yes1x5x10x19x32x

GROMACS

Molecular Dynamics

Simulation of biochemical molecules with complicated bond interactions

VERSION

2022.3

ACCELERATED FEATURES

  • Implicit (5x), Explicit (2x) Solvent

SCALABILITY

Multi-GPU, Single Node

MORE INFORMATION

http://www.gromacs.org

https://ngc.nvidia.com/catalog/containers/hpc:gromacs

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x L402x L404x L40
GROMACS [ADH Dodec]ns/dayADH Dodecyes67566--
GROMACS [ADH Dodec]NRFADH Dodecyes1x11x--
GROMACS [Cellulose]ns/dayCelluloseyes19161-212
GROMACS [Cellulose]NRFCelluloseyes1x12x-16x
GROMACS [STMV]ns/daySTMVyes4335581
GROMACS [STMV]NRFSTMVyes1x8x13x20x

LAMMPS

Molecular Dynamics

Classical molecular dynamics package

VERSION

stable_23Jun2022_update1

ACCELERATED FEATURES

  • Lennard-Jones, Gay-Berne, Tersoff, many more potentials

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://lammps.sandia.gov/index.html

https://ngc.nvidia.com/catalog/containers/hpc:lammps

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x L402x L404x L408x L40
LAMMPS [ReaxFF/C]ATOM-Time Steps/sReaxFF/Cyes4.45E+051.51E+062.89E+065.35E+068.11E+06
LAMMPS [ReaxFF/C]NRFReaxFF/Cyes1x4x9x16x25x
LAMMPS [SNAP]ATOM-Time Steps/sSNAPyes1.08E+055.82E+051.16E+062.32E+064.58E+06
LAMMPS [SNAP]NRFSNAPyes1x6x11x22x44x
LAMMPS [Tersoff]ATOM-Time Steps/sTersoffyes2.77E+071.23E+082.40E+084.63E+087.01E+08
LAMMPS [Tersoff]NRFTersoffyes1x4x9x17x26x

NAMD

Molecular Dynamics

Designed for high-performance simulation of large molecular systems

VERSION

GPU, AMD CPU V 3.0a13 ; Intel CPU V 2.15a AVX512

ACCELERATED FEATURES

  • Full electrostatics with PME and most simulation features

SCALABILITY

Up to 100M atom capable, multi-GPU, single node

MORE INFORMATION

http://www.ks.uiuc.edu/Research/namd/

https://ngc.nvidia.com/catalog/containers/hpc:namd

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x L402x L404x L408x L40
NAMD [apoa1_npt_cuda]Ave ns/dayapoa1_npt_cudayes19.151883867611,542
NAMD [apoa1_npt_cuda]NRFapoa1_npt_cudayes1x10x20x40x81x
NAMD [apoa1_nptsr_cuda]Ave ns/dayapoa1_nptsr_cudayes19.591913887671,571
NAMD [apoa1_nptsr_cuda]NRFapoa1_nptsr_cudayes1x10x20x39x80x
NAMD [apoa1_nve_cuda]Ave ns/dayapoa1_nve_cudayes20.752404819701,917
NAMD [apoa1_nve_cuda]NRFapoa1_nve_cudayes1x12x23x47x92x
NAMD [stmv_npt_cuda]Ave ns/daystmv_npt_cudayes1.87153059120
NAMD [stmv_npt_cuda]NRFstmv_npt_cudayes1x8x16x32x64x
NAMD [stmv_nptsr_cuda]Ave ns/daystmv_nptsr_cudayes1.81153162123
NAMD [stmv_nptsr_cuda]NRFstmv_nptsr_cudayes1x8x17x34x68x
NAMD [stmv_nve_cuda]Ave ns/daystmv_nve_cudayes1.94183570142
NAMD [stmv_nve_cuda]NRFstmv_nve_cudayes1x9x18x36x73x

Molecular Dynamics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7763@2.45GHz with 4x NVIDIA L4 | AMBER Benchmark: DC-JAC_NPT, CUDA Version: 11.8 | GROMACS Benchmark: STMV, CUDA Version: 11.8 | NAMD Benchmark: apoa1_nve_cuda, CUDA Version: 11.8

Detailed L4 application performance data is located below in alphabetical order.

AMBER

Molecular Dynamics

Suite of programs to simulate molecular dynamics on biomolecule

VERSION

22.0-AT_22.3

ACCELERATED FEATURES

  • PMEMD Explicit Solvent and GB Implicit Solvent

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

http://ambermd.org/GPUSupport.php

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x L42x L44x L48x L4
AMBER [PME-JAC_NPT_4fs]ns/dayDC-JAC_NPTyes84.611,1462,3234,7319,554
AMBER [PME-JAC_NPT_4fs]NRFDC-JAC_NPTyes1x14x27x56x113x
AMBER [PME-JAC_NVE_4fs]ns/dayDC-JAC_NVEyes85.161,1622,3664,8119,666
AMBER [PME-JAC_NVE_4fs]NRFDC-JAC_NVEyes1x14x28x56x113x

GROMACS

Molecular Dynamics

Simulation of biochemical molecules with complicated bond interactions

VERSION

2022.3

ACCELERATED FEATURES

  • Implicit (5x), Explicit (2x) Solvent

SCALABILITY

Multi-GPU, Single Node

MORE INFORMATION

http://www.gromacs.org

https://ngc.nvidia.com/catalog/containers/hpc:gromacs

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x L42x L44x L48x L4
GROMACS [ADH Dodec]ns/dayADH Dodecyes67209346464-
GROMACS [ADH Dodec]NRFADH Dodecyes1x4x7x9x-
GROMACS [Cellulose]ns/dayCelluloseyes195794133162
GROMACS [Cellulose]NRFCelluloseyes1x3x6x10x12x
GROMACS [STMV]ns/daySTMVyes412224363
GROMACS [STMV]NRFSTMVyes1x3x5x10x15x

NAMD

Molecular Dynamics

Designed for high-performance simulation of large molecular systems

VERSION

GPU, AMD CPU V 3.0a13 ; Intel CPU V 2.15a AVX512

ACCELERATED FEATURES

  • Full electrostatics with PME and most simulation features

SCALABILITY

Up to 100M atom capable, multi-GPU, single node

MORE INFORMATION

http://www.ks.uiuc.edu/Research/namd/

https://ngc.nvidia.com/catalog/containers/hpc:namd

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x L42x L44x L48x L4
NAMD [apoa1_npt_cuda]Ave ns/dayapoa1_npt_cudayes19.1563128260520
NAMD [apoa1_npt_cuda]NRFapoa1_npt_cudayes1x3x7x14x27x
NAMD [apoa1_nptsr_cuda]Ave ns/dayapoa1_nptsr_cudayes19.59-131266535
NAMD [apoa1_nptsr_cuda]NRFapoa1_nptsr_cudayes1x-7x14x27x
NAMD [apoa1_nve_cuda]Ave ns/dayapoa1_nve_cudayes20.7586172347701
NAMD [apoa1_nve_cuda]NRFapoa1_nve_cudayes1x4x8x17x34x
NAMD [stmv_npt_cuda]Ave ns/daystmv_npt_cudayes1.87591837
NAMD [stmv_npt_cuda]NRFstmv_npt_cudayes1x2x5x10x20x
NAMD [stmv_nptsr_cuda]Ave ns/daystmv_nptsr_cudayes1.815-1939
NAMD [stmv_nptsr_cuda]NRFstmv_nptsr_cudayes1x3x-11x22x
NAMD [stmv_nve_cuda]Ave ns/daystmv_nve_cudayes1.946122447
NAMD [stmv_nve_cuda]NRFstmv_nve_cudayes1x3x6x12x24x

Engineering

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A100 SXM 80GB | FUN3D Benchmark: dpw_wbt0_crs-3.6Mn_5, CUDA Version: 11.8

Geoscience

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A100 SXM 80GB | ICON Benchmark: QUBICC 160 km resolution, CUDA Version: 11.8 | RTM Benchmark: Isotropic Radius 4, CUDA Version: 11.8 | SPECFEM3D Benchmark: four_material_simple_model, CUDA Version: 11.8

Molecular Dynamics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A100 SXM 80GB | AMBER Benchmark: DC-Cellulose_NVE, CUDA Version: 11.8 | GROMACS Benchmark: STMV, CUDA Version: 11.8 | LAMMPS Benchmark: SNAP, CUDA Version: 11.8 | NAMD Benchmark: apoa1_nve_cuda, CUDA Version: 11.8 | Relion Benchmark: Plasmodium Ribosome (2D), CUDA Version: 11.4.2

Physics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A100 SXM 80GB | Chroma Benchmark: szscl21_24_128, CUDA Version: 11.3.1 | MILC Benchmark: Apex Medium, CUDA Version: 11.8

Quantum Mechanics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A100 SXM 80GB | Quantum Espresso Benchmark: AUSURF112-jR, CUDA Version: 11.8

Detailed A100 application performance data is located below in alphabetical order.

AMBER

Molecular Dynamics

Suite of programs to simulate molecular dynamics on biomolecule

VERSION

22.0-AT_22.3

ACCELERATED FEATURES

  • PMEMD Explicit Solvent and GB Implicit Solvent

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

http://ambermd.org/GPUSupport.php

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
AMBER [PME-Cellulose_NPT_4fs]ns/dayDC-Cellulose_NPTyes4.131823647261,4561723346741,375
AMBER [PME-Cellulose_NPT_4fs]NRFDC-Cellulose_NPTyes1x44x88x176x353x42x81x163x333x
AMBER [PME-Cellulose_NVE_4fs]ns/dayDC-Cellulose_NVEyes4.121853717391,4831763406861,366
AMBER [PME-Cellulose_NVE_4fs]NRFDC-Cellulose_NVEyes1x45x90x179x360x43x83x167x331x
AMBER [PME-FactorIX_NPT_4fs]ns/dayDC-FactorIX_NPTyes20.717961,5943,1756,3837691,5253,0546,139
AMBER [PME-FactorIX_NPT_4fs]NRFDC-FactorIX_NPTyes1x38x77x153x308x37x74x147x296x
AMBER [PME-FactorIX_NVE_4fs]ns/dayDC-FactorIX_NVEyes20.958131,6313,2576,5327811,5143,1326,303
AMBER [PME-FactorIX_NVE_4fs]NRFDC-FactorIX_NVEyes1x39x78x155x312x37x72x149x301x
AMBER [PME-JAC_NPT_4fs]ns/dayDC-JAC_NPTyes84.612,8835,76111,51223,4332,8195,47611,12123,249
AMBER [PME-JAC_NPT_4fs]NRFDC-JAC_NPTyes1x34x68x136x277x33x65x131x275x
AMBER [PME-JAC_NVE_4fs]ns/dayDC-JAC_NVEyes85.162,9535,89411,69323,9352,9005,78711,39623,903
AMBER [PME-JAC_NVE_4fs]NRFDC-JAC_NVEyes1x35x69x137x281x34x68x134x281x
AMBER [PME-STMV_NPT_4fs]ns/dayDC-STMV_NPTyes1.385410721442953107214427
AMBER [PME-STMV_NPT_4fs]NRFDC-STMV_NPTyes1x39x78x155x311x39x77x155x310x
AMBER [FEP-GTI_Complex 1fs]ns/dayFEP-GTI_Complexyes9.891332665331,0661342685361,073
AMBER [FEP-GTI_Complex 1fs]NRFFEP-GTI_Complexyes1x13x27x54x108x14x27x54x108x

Chroma

Physics

Lattice Quantum Chromodynamics (LQCD)

VERSION

V 2021.08

ACCELERATED FEATURES

  • Wilson-clover fermions, Krylov solvers, Domain-decomposition

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://jeffersonlab.github.io/chroma/

https://ngc.nvidia.com/catalog/containers/hpc:chroma

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
ChromaTotal Time (Sec)szscl21_24_128no1,11536201174425139
ChromaNRFszscl21_24_128yes1x32x55x99x163x26x46x84x129x

FUN3D

Engineering

Suite of tools actively developed at NASA for Aeronautics and Space Technology by modeling fluid flow

VERSION

13.7 (update 1)

ACCELERATED FEATURES

  • Full range of Mach number regimes for the Reynolds-averaged Navier Stokes (RANS) formulation

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://fun3d.larc.nasa.gov

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
FUN3DLoop Time (Sec)dpw_wbt0_crs-3.6Mn_5no4955228161154291613
FUN3DNRFdpw_wbt0_crs-3.6Mn_5yes1x12x22x39x55x11x21x39x49x

GROMACS

Molecular Dynamics

Simulation of biochemical molecules with complicated bond interactions

VERSION

2022.3

ACCELERATED FEATURES

  • Implicit (5x), Explicit (2x) Solvent

SCALABILITY

Multi-GPU, Single Node

MORE INFORMATION

http://www.gromacs.org

https://ngc.nvidia.com/catalog/containers/hpc:gromacs

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
GROMACS [ADH Dodec]ns/dayADH Dodecyes67372506677-389-518-
GROMACS [ADH Dodec]NRFADH Dodecyes1x7x10x13x-8x-10x-
GROMACS [Cellulose]ns/dayCelluloseyes19108174254290108122183-
GROMACS [Cellulose]NRFCelluloseyes1x8x13x19x22x8x9x14x-
GROMACS [STMV]ns/daySTMVyes424448012824396592
GROMACS [STMV]NRFSTMVyes1x5x11x20x31x5x9x16x22x

GTC

Physics

GTC is used for Gyrokinetic Particle Simulation of Turbulent Transport in Burning Plasmas

VERSION

V 4.5 Updated

ACCELERATED FEATURES

  • Push, shift, and collision

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
GTCMpush/Secmoi#proc.inyes354728983,6224789091,7552,706
GTCNRFmoi#proc.inyes1x14x26x105x14x26x51x79x

ICON

Weather and Climate

A global unified atmosphere model for numerical weather prediction and climate modeling research

VERSION

2.6.5_RC

ACCELERATED FEATURES

  • Full model of dynamics and physics

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://code.mpimet.mpg.de/projects/iconpublic

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB
ICON [SLAM 191 - 160KM - no radiation]Integrate_nh (sec)SLAM 191 levels 160 km resolution without radiationno2,431317218158134318224165
ICON [SLAM 191 - 160KM - no radiation]NRFSLAM 191 levels 160 km resolution without radiationyes1x8x11x15x18x8x11x15x
ICON [QUBICC 160 km resolution]Integrate_nh (sec)SLAM 191 levels 160 km resolution with radiationno2,213293197144120291192140
ICON [QUBICC 160 km resolution]NRFSLAM 191 levels 160 km resolution with radiationyes1x8x11x15x18x8x12x16x

LAMMPS

Molecular Dynamics

Classical molecular dynamics package

VERSION

stable_23Jun2022_update1

ACCELERATED FEATURES

  • Lennard-Jones, Gay-Berne, Tersoff, many more potentials

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://lammps.sandia.gov/index.html

https://ngc.nvidia.com/catalog/containers/hpc:lammps

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
LAMMPS [LJ 2.5]ATOM-Time Steps/sLJ 2.5yes1.11E+086.00E+081.12E+092.01E+093.66E+096.00E+081.07E+091.81E+09-
LAMMPS [LJ 2.5]NRFLJ 2.5yes1x6x10x19x34x6x10x17x-
LAMMPS [EAM]ATOM-Time Steps/sEAMyes5.33E+072.93E+085.35E+089.23E+081.58E+092.88E+085.04E+088.48E+08-
LAMMPS [EAM]NRFEAMyes1x6x10x18x31x5x10x17x-
LAMMPS [ReaxFF/C]ATOM-Time Steps/sReaxFF/Cyes4.45E+055.24E+069.68E+061.70E+072.69E+075.28E+069.53E+061.62E+071.97E+07
LAMMPS [ReaxFF/C]NRFReaxFF/Cyes1x16x30x52x83x16x29x50x61x
LAMMPS [SNAP]ATOM-Time Steps/sSNAPyes1.08E+052.21E+064.39E+068.73E+061.67E+072.11E+064.09E+068.12E+061.58E+07
LAMMPS [SNAP]NRFSNAPyes1x21x42x85x162x20x40x79x153x
LAMMPS [Tersoff]ATOM-Time Steps/sTersoffyes2.77E+075.28E+089.81E+081.75E+092.99E+095.09E+088.74E+081.40E+09-
LAMMPS [Tersoff]NRFTersoffyes1x19x36x64x110x19x32x51x-

MILC

Physics

Lattice Quantum Chromodynamics (LQCD) codes simulate how elemental particles are formed and bound by the “strong force” to create larger particles like protons and neutrons

VERSION

feature/gauge-action-quda_16a2d47119

ACCELERATED FEATURES

  • Staggered fermions, Krylov solvers, Gauge-link fattening

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://ngc.nvidia.com/catalog/containers/hpc:milc

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB
MILCTotal Time (Sec)Apex Mediumno71,5952,0291,1846293612,0881,111614
MILCNRFApex Mediumyes1x39x67x125x218x38x71x128x

NAMD

Molecular Dynamics

Designed for high-performance simulation of large molecular systems

VERSION

GPU, AMD CPU V 3.0a13 ; Intel CPU V 2.15a AVX512

ACCELERATED FEATURES

  • Full electrostatics with PME and most simulation features

SCALABILITY

Up to 100M atom capable, multi-GPU, single node

MORE INFORMATION

http://www.ks.uiuc.edu/Research/namd/

https://ngc.nvidia.com/catalog/containers/hpc:namd

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
NAMD [apoa1_npt_cuda]Ave ns/dayapoa1_npt_cudayes19.151753476891,3681723416931,372
NAMD [apoa1_npt_cuda]NRFapoa1_npt_cudayes1x9x18x36x71x9x18x36x72x
NAMD [apoa1_nptsr_cuda]Ave ns/dayapoa1_nptsr_cudayes19.591783577141,3891783547111,399
NAMD [apoa1_nptsr_cuda]NRFapoa1_nptsr_cudayes1x9x18x36x71x9x18x36x71x
NAMD [apoa1_nve_cuda]Ave ns/dayapoa1_nve_cudayes20.752154368701,7312144248511,714
NAMD [apoa1_nve_cuda]NRFapoa1_nve_cudayes1x10x21x42x83x10x20x41x83x
NAMD [stmv_npt_cuda]Ave ns/daystmv_npt_cudayes1.8714274365132753104
NAMD [stmv_npt_cuda]NRFstmv_npt_cudayes1x7x14x23x35x7x14x29x56x
NAMD [stmv_nptsr_cuda]Ave ns/daystmv_nptsr_cudayes1.8114285666142655110
NAMD [stmv_nptsr_cuda]NRFstmv_nptsr_cudayes1x8x15x31x36x8x15x31x61x
NAMD [stmv_nve_cuda]Ave ns/daystmv_nve_cudayes1.94163250128163161127
NAMD [stmv_nve_cuda]NRFstmv_nve_cudayes1x8x17x26x66x8x16x31x65x

Quantum Espresso

Material Science (Quantum Chemistry)

An Open-source suite of computer codes for electronic structure calculations and materials modeling at the nanoscale

VERSION

V7.0 CPU; V7.1 GPU

ACCELERATED FEATURES

  • linear algebra (matrix multiply)
  • explicit computational kernels
  • 3D FFTs

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://www.quantum-espresso.org

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
Quantum EspresssoTotal CPU Time (Sec)AUSURF112-jRno718111714736114704939
Quantum EspresssoNRFAUSURF112-jRyes1x7x11x17x22x7x11x16x20x

RELION

Microscopy

Stand-alone computer program that employs an empirical Bayesianapproach to refinement of (multiple) 3D reconstructions or 2D class averages in electron cryo-microscopy (cryo-EM)

VERSION

3.1.3

ACCELERATED FEATURES

  • Reduced memory requirements; high-resolution cryo-EM structure determination in a matter of day on a single workstation

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

https://www2.mrc-lmb.cam.ac.uk/relion/index.php/Download_%26_install

https://ngc.nvidia.com/catalog/containers/hpc:relion

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB
Relion [Plasmodium Ribosome]Total Wall Clock (Sec)MB numbers Plasmodium Ribosime on Relion-3.0no12,7422,7361,6271,4392,6011,5231,383
Relion [Plasmodium Ribosome]NRFMB numbers Plasmodium Ribosime on Relion-3.0yes1x5x8x9x5x8x9x

RTM

Geoscience

Reverse time migration (RTM) modeling is a critical component in the seismic processing workflow of oil and gas exploration

VERSION

nvidia_2021_05

ACCELERATED FEATURES

  • Batch algorithm

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://www.tsunamidevelopment.com/assets/rtm.pdf

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
RTM [Isotropic Radius 4]Mcells/sIsotropic Radius 4yes11,31889,561178,511356,907713,88389,536178,551339,823713,096
RTM [Isotropic Radius 4]NRFIsotropic Radius 4yes1x8x16x32x63x8x16x30x63x
RTM [TTI Radius 8 1-pass]Mcells/sTTI Radius 8 1-passyes3,77312,90325,76451,122102,18712,90125,79651,402102,510
RTM [TTI Radius 8 1-pass]NRFTTI Radius 8 1-passyes1x3x7x14x27x3x7x14x27x
RTM [TTI RX 2Pass mgpu]Mcells/sTTI RX 2Pass mgpuyes3,77313,95727,66454,933108,60713,74327,26553,741107,880
RTM [TTI RX 2Pass mgpu]NRFTTI RX 2Pass mgpuyes1x4x7x15x29x4x7x14x29x

SPECFEM3D

Geoscience

Simulates Seismic wave propagation

VERSION

devel_fef2ace9

ACCELERATED FEATURES

  • OpenCL and CUDA hardware accelerators, based on an automatic source-to-source transformation library

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://geodynamics.org/cig/software/specfem3d/

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A100 SXM4 80GB2x A100 SXM4 80GB4x A100 SXM4 80GB8x A100 SXM4 80GB1x A100 PCIe 80GB2x A100 PCIe 80GB4x A100 PCIe 80GB8x A100 PCIe 80GB
SPECFEM3DTotal Time (Sec)four_material_simple_modelno1,2687740211378412215
SPECFEM3DNRFfour_material_simple_modelyes1x19x36x68x116x19x35x67x100x

Engineering

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A30 | FUN3D Benchmark: dpw_wbt0_crs-3.6Mn_5, CUDA Version: 11.8

Geoscience

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A30 | ICON Benchmark: QUBICC 160km resolution, CUDA Version: 11.8 | RTM Benchmark: Isotropic Radius 4, CUDA Version: 11.8 | SPECFEM3D Benchmark: four_material_simple_model, CUDA Version: 11.8

Molecular Dynamics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A30 | AMBER Benchmark: DC-Cellulose_NVE, CUDA Version: 11.8 | GROMACS Benchmark: STMV, CUDA Version: 11.8 | LAMMPS Benchmark: SNAP, CUDA Version: 11.8 | NAMD Benchmark: apoa1_nve_cuda, CUDA Version: 11.8 | Relion Benchmark: Plasmodium Ribosome (2D), CUDA Version: 11.4.2

Physics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A30 | Chroma Benchmark: szscl21_24_128, CUDA Version: 11.3.1 | GTC Benchmark: moi#proc.in, CUDA Version: 11.8 | MILC Benchmark: Apex Medium, CUDA Version: 11.8

Quantum Mechanics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A30 | Quantum Espresso Benchmark: AUSURF112-jR, CUDA Version: 11.8

Detailed A30 application performance data is located below in alphabetical order.

AMBER

Molecular Dynamics

Suite of programs to simulate molecular dynamics on biomolecule

VERSION

22.0-AT_22.3

ACCELERATED FEATURES

  • PMEMD Explicit Solvent and GB Implicit Solvent

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

http://ambermd.org/GPUSupport.php

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
AMBER [PME-Cellulose_NPT_4fs]ns/dayDC-Cellulose_NPTyes4.1389177355714
AMBER [PME-Cellulose_NPT_4fs]NRFDC-Cellulose_NPTyes1x22x43x86x173x
AMBER [PME-Cellulose_NVE_4fs]ns/dayDC-Cellulose_NVEyes4.1291181362727
AMBER [PME-Cellulose_NVE_4fs]NRFDC-Cellulose_NVEyes1x22x44x88x176x
AMBER [PME-FactorIX_NPT_4fs]ns/dayDC-FactorIX_NPTyes20.714068111,6163,241
AMBER [PME-FactorIX_NPT_4fs]NRFDC-FactorIX_NPTyes1x20x39x78x156x
AMBER [PME-FactorIX_NVE_4fs]ns/dayDC-FactorIX_NVEyes20.954188261,6513,311
AMBER [PME-FactorIX_NVE_4fs]NRFDC-FactorIX_NVEyes1x20x39x79x158x
AMBER [PME-JAC_NPT_4fs]ns/dayDC-JAC_NPTyes84.611,5032,9895,97311,932
AMBER [PME-JAC_NPT_4fs]NRFDC-JAC_NPTyes1x18x35x71x141x
AMBER [PME-JAC_NVE_4fs]ns/dayDC-JAC_NVEyes85.161,5313,0456,07712,277
AMBER [PME-JAC_NVE_4fs]NRFDC-JAC_NVEyes1x18x36x71x144x
AMBER [PME-STMV_NPT_4fs]ns/dayDC-STMV_NPTyes1.382958116233
AMBER [PME-STMV_NPT_4fs]NRFDC-STMV_NPTyes1x21x42x84x169x
AMBER [FEP-GTI_Complex 1fs]ns/dayFEP-GTI_Complexyes9.8999198395790
AMBER [FEP-GTI_Complex 1fs]NRFFEP-GTI_Complexyes1x10x20x40x80x

Chroma

Physics

Lattice Quantum Chromodynamics (LQCD)

VERSION

V 2021.08

ACCELERATED FEATURES

  • Wilson-clover fermions, Krylov solvers, Domain-decomposition

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://jeffersonlab.github.io/chroma/

https://ngc.nvidia.com/catalog/containers/hpc:chroma

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)2x A304x A308x A30
ChromaTotal Time (Sec)szscl21_24_128no1,115351811
ChromaNRFszscl21_24_128yes1x33x62x103x

FUN3D

Engineering

Suite of tools actively developed at NASA for Aeronautics and Space Technology by modeling fluid flow

VERSION

13.7 (update 1)

ACCELERATED FEATURES

  • Full range of Mach number regimes for the Reynolds-averaged Navier Stokes (RANS) formulation

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://fun3d.larc.nasa.gov

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
FUN3DLoop Time (Sec)dpw_wbt0_crs-3.6Mn_5no495111552918
FUN3DNRFdpw_wbt0_crs-3.6Mn_5yes1x5x11x21x34x

GROMACS

Molecular Dynamics

Simulation of biochemical molecules with complicated bond interactions

VERSION

2022.3

ACCELERATED FEATURES

  • Implicit (5x), Explicit (2x) Solvent

SCALABILITY

Multi-GPU, Single Node

MORE INFORMATION

http://www.gromacs.org

https://ngc.nvidia.com/catalog/containers/hpc:gromacs

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
GROMACS [ADH Dodec]ns/dayADH Dodecyes67201287378-
GROMACS [ADH Dodec]NRFADH Dodecyes1x3x6x7x-
GROMACS [Cellulose]ns/dayCelluloseyes196091119147
GROMACS [Cellulose]NRFCelluloseyes1x3x5x9x11x
GROMACS [STMV]ns/daySTMVyes412224159
GROMACS [STMV]NRFSTMVyes1x3x5x10x14x

GTC

Physics

GTC is used for Gyrokinetic Particle Simulation of Turbulent Transport in Burning Plasmas

VERSION

V 4.5 Updated

ACCELERATED FEATURES

  • Push, shift, and collision

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
GTCMpush/Secmoi#proc.inyes352855311,0491,774
GTCNRFmoi#proc.inyes1x8x15x31x52x

ICON

Weather and Climate

A global unified atmosphere model for numerical weather prediction and climate modeling research

VERSION

2.6.5_RC

ACCELERATED FEATURES

  • Full model of dynamics and physics

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://code.mpimet.mpg.de/projects/iconpublic

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
ICON [SLAM 191 - 160KM - no radiation]Integrate_nh (sec)SLAM 191 levels 160 km resolution without radiationno2,431571354233206
ICON [SLAM 191 - 160KM - no radiation]NRFSLAM 191 levels 160 km resolution without radiationyes1x4x7x10x12x
ICON [QUBICC 160 km resolution]Integrate_nh (sec)SLAM 191 levels 160 km resolution with radiationno2,213502302193164
ICON [QUBICC 160 km resolution]NRFSLAM 191 levels 160 km resolution with radiationyes1x4x7x11x13x

LAMMPS

Molecular Dynamics

Classical molecular dynamics package

VERSION

stable_23Jun2022_update1

ACCELERATED FEATURES

  • Lennard-Jones, Gay-Berne, Tersoff, many more potentials

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://lammps.sandia.gov/index.html

https://ngc.nvidia.com/catalog/containers/hpc:lammps

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
LAMMPS [LJ 2.5]ATOM-Time Steps/sLJ 2.5yes1.11E+083.09E+085.94E+081.10E+091.46E+09
LAMMPS [LJ 2.5]NRFLJ 2.5yes1x3x5x10x14x
LAMMPS [EAM]ATOM-Time Steps/sEAMyes5.33E+071.37E+082.58E+084.70E+087.30E+08
LAMMPS [EAM]NRFEAMyes1x3x5x9x14x
LAMMPS [ReaxFF/C]ATOM-Time Steps/sReaxFF/Cyes4.45E+052.88E+065.52E+069.98E+061.41E+07
LAMMPS [ReaxFF/C]NRFReaxFF/Cyes1x9x17x31x44x
LAMMPS [SNAP]ATOM-Time Steps/sSNAPyes1.08E+051.11E+062.19E+064.37E+068.54E+06
LAMMPS [SNAP]NRFSNAPyes1x11x21x42x83x
LAMMPS [Tersoff]ATOM-Time Steps/sTersoffyes2.77E+072.51E+084.37E+087.96E+081.03E+09
LAMMPS [Tersoff]NRFTersoffyes1x9x16x29x38x

MILC

Physics

Lattice Quantum Chromodynamics (LQCD) codes simulate how elemental particles are formed and bound by the “strong force” to create larger particles like protons and neutrons

VERSION

feature/gauge-action-quda_16a2d47119

ACCELERATED FEATURES

  • Staggered fermions, Krylov solvers, Gauge-link fattening

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://ngc.nvidia.com/catalog/containers/hpc:milc

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
MILCTotal Time (Sec)Apex Mediumno71,5954,7102,0251,087697
MILCNRFApex Mediumyes1x17x39x72x113x

NAMD

Molecular Dynamics

Designed for high-performance simulation of large molecular systems

VERSION

GPU, AMD CPU V 3.0a13 ; Intel CPU V 2.15a AVX512

ACCELERATED FEATURES

  • Full electrostatics with PME and most simulation features

SCALABILITY

Up to 100M atom capable, multi-GPU, single node

MORE INFORMATION

http://www.ks.uiuc.edu/Research/namd/

https://ngc.nvidia.com/catalog/containers/hpc:namd

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
NAMD [apoa1_npt_cuda]Ave ns/dayapoa1_npt_cudayes19.1591181362726
NAMD [apoa1_npt_cuda]NRFapoa1_npt_cudayes1x5x9x19x38x
NAMD [apoa1_nptsr_cuda]Ave ns/dayapoa1_nptsr_cudayes19.5994187371745
NAMD [apoa1_nptsr_cuda]NRFapoa1_nptsr_cudayes1x5x10x19x38x
NAMD [apoa1_nve_cuda]Ave ns/dayapoa1_nve_cudayes20.75111221441882
NAMD [apoa1_nve_cuda]NRFapoa1_nve_cudayes1x5x11x21x42x
NAMD [stmv_npt_cuda]Ave ns/daystmv_npt_cudayes1.877142958
NAMD [stmv_npt_cuda]NRFstmv_npt_cudayes1x4x8x15x31x
NAMD [stmv_nptsr_cuda]Ave ns/daystmv_nptsr_cudayes1.817153059
NAMD [stmv_nptsr_cuda]NRFstmv_nptsr_cudayes1x4x8x16x33x
NAMD [stmv_nve_cuda]Ave ns/daystmv_nve_cudayes1.948163265
NAMD [stmv_nve_cuda]NRFstmv_nve_cudayes1x4x8x17x34x

RELION

Microscopy

Stand-alone computer program that employs an empirical Bayesianapproach to refinement of (multiple) 3D reconstructions or 2D class averages in electron cryo-microscopy (cryo-EM)

VERSION

3.1.3

ACCELERATED FEATURES

  • Reduced memory requirements; high-resolution cryo-EM structure determination in a matter of day on a single workstation

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

https://www2.mrc-lmb.cam.ac.uk/relion/index.php/Download_%26_install

https://ngc.nvidia.com/catalog/containers/hpc:relion

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
Relion [Plasmodium Ribosome]Total Wall Clock (Sec)MB numbers Plasmodium Ribosime on Relion-3.0no12,7423,4171,8611,4231,297
Relion [Plasmodium Ribosome]NRFMB numbers Plasmodium Ribosime on Relion-3.0yes1x4x7x9x10x

RTM

Geoscience

Reverse time migration (RTM) modeling is a critical component in the seismic processing workflow of oil and gas exploration

VERSION

nvidia_2021_05

ACCELERATED FEATURES

  • Batch algorithm

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://www.tsunamidevelopment.com/assets/rtm.pdf

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
RTM [Isotropic Radius 4]Mcells/sIsotropic Radius 4yes11,31844,05187,806175,438350,760
RTM [Isotropic Radius 4]NRFIsotropic Radius 4yes1x4x8x16x31x
RTM [TTI Radius 8 1-pass]Mcells/sTTI Radius 8 1-passyes3,7736,75713,36126,71053,281
RTM [TTI Radius 8 1-pass]NRFTTI Radius 8 1-passyes1x2x4x7x14x
RTM [TTI RX 2Pass mgpu]Mcells/sTTI RX 2Pass mgpuyes3,7737,02613,89927,64255,140
RTM [TTI RX 2Pass mgpu]NRFTTI RX 2Pass mgpuyes1x2x4x7x15x

SPECFEM3D

Geoscience

Simulates Seismic wave propagation

VERSION

devel_fef2ace9

ACCELERATED FEATURES

  • OpenCL and CUDA hardware accelerators, based on an automatic source-to-source transformation library

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://geodynamics.org/cig/software/specfem3d/

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A302x A304x A308x A30
SPECFEM3DTotal Time (Sec)four_material_simple_modelno1,268156804123
SPECFEM3DNRFfour_material_simple_modelyes1x9x18x35x64x

Engineering

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A40 | FUN3D Benchmark: dpw_wbt0_crs-3.6Mn_5, CUDA Version: 11.8

Geoscience

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A40 | ICON Benchmark: QUBICC 160 km resolution, CUDA Version: 11.8 | SPECFEM3D Benchmark: four_material_simple_model, CUDA Version: 11.8

Molecular Dynamics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A40 | AMBER Benchmark: DC-Cellulose_NVE, CUDA Version: 11.8 | GROMACS Benchmark: STMV, CUDA Version: 11.8 | LAMMPS Benchmark: SNAP, CUDA Version: 11.8 | NAMD Benchmark: apoa1_nve_cuda, CUDA Version: 11.8 | Relion Benchmark: Plasmodium Ribosome (2D), CUDA Version: 11.4.2

Physics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual EPYC 7742@2.25GHz with 4x NVIDIA A40 | Chroma Benchmark: szscl21_24_128, CUDA Version: 11.3.1 | GTC Benchmark: moi#proc.in, CUDA Version: 11.8 | MILC Benchmark: Apex Medium, CUDA Version: 11.8

Detailed A40 application performance data is located below in alphabetical order.

AMBER

Molecular Dynamics

Suite of programs to simulate molecular dynamics on biomolecule

VERSION

22.0-AT_22.3

ACCELERATED FEATURES

  • PMEMD Explicit Solvent and GB Implicit Solvent

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

http://ambermd.org/GPUSupport.php

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
AMBER [PME-Cellulose_NPT_4fs]ns/dayDC-Cellulose_NPTyes4.1397195390781
AMBER [PME-Cellulose_NPT_4fs]NRFDC-Cellulose_NPTyes1x23x47x94x189x
AMBER [PME-Cellulose_NVE_4fs]ns/dayDC-Cellulose_NVEyes4.1298198396794
AMBER [PME-Cellulose_NVE_4fs]NRFDC-Cellulose_NVEyes1x24x48x96x193x
AMBER [PME-FactorIX_NPT_4fs]ns/dayDC-FactorIX_NPTyes20.714869841,9653,954
AMBER [PME-FactorIX_NPT_4fs]NRFDC-FactorIX_NPTyes1x23x48x95x191x
AMBER [PME-FactorIX_NVE_4fs]ns/dayDC-FactorIX_NVEyes20.954971,0062,0154,022
AMBER [PME-FactorIX_NVE_4fs]NRFDC-FactorIX_NVEyes1x24x48x96x192x
AMBER [PME-JAC_NPT_4fs]ns/dayDC-JAC_NPTyes84.611,9223,8897,78015,568
AMBER [PME-JAC_NPT_4fs]NRFDC-JAC_NPTyes1x23x46x92x184x
AMBER [PME-JAC_NVE_4fs]ns/dayDC-JAC_NVEyes85.161,9483,9467,90616,037
AMBER [PME-JAC_NVE_4fs]NRFDC-JAC_NVEyes1x23x46x93x188x
AMBER [PME-STMV_NPT_4fs]ns/dayDC-STMV_NPTyes1.383263127254
AMBER [PME-STMV_NPT_4fs]NRFDC-STMV_NPTyes1x23x46x92x184x
AMBER [FEP-GTI_Complex 1fs]ns/dayFEP-GTI_Complexyes9.89116232463926
AMBER [FEP-GTI_Complex 1fs]NRFFEP-GTI_Complexyes1x12x23x47x94x

Chroma

Physics

Lattice Quantum Chromodynamics (LQCD)

VERSION

V 2021.08

ACCELERATED FEATURES

  • Wilson-clover fermions, Krylov solvers, Domain-decomposition

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://jeffersonlab.github.io/chroma/

https://ngc.nvidia.com/catalog/containers/hpc:chroma

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
ChromaTotal Time (Sec)szscl21_24_128no1,11578412213
ChromaNRFszscl21_24_128yes1x15x28x52x89x

FUN3D

Engineering

Suite of tools actively developed at NASA for Aeronautics and Space Technology by modeling fluid flow

VERSION

13.7 (update 1)

ACCELERATED FEATURES

  • Full range of Mach number regimes for the Reynolds-averaged Navier Stokes (RANS) formulation

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://fun3d.larc.nasa.gov

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
FUN3DLoop Time (Sec)dpw_wbt0_crs-3.6Mn_5no4952311175932
FUN3DNRFdpw_wbt0_crs-3.6Mn_5yes1x2x5x10x19x

GROMACS

Molecular Dynamics

Simulation of biochemical molecules with complicated bond interactions

VERSION

2022.3

ACCELERATED FEATURES

  • Implicit (5x), Explicit (2x) Solvent

SCALABILITY

Multi-GPU, Single Node

MORE INFORMATION

http://www.gromacs.org

https://ngc.nvidia.com/catalog/containers/hpc:gromacs

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
GROMACS [ADH Dodec]ns/dayADH Dodecyes67340379505-
GROMACS [ADH Dodec]NRFADH Dodecyes1x7x8x10x-
GROMACS [Cellulose]ns/dayCelluloseyes1977110160177
GROMACS [Cellulose]NRFCelluloseyes1x5x8x12x13x
GROMACS [STMV]ns/daySTMVyes420386175
GROMACS [STMV]NRFSTMVyes1x5x9x15x18x

GTC

Physics

GTC is used for Gyrokinetic Particle Simulation of Turbulent Transport in Burning Plasmas

VERSION

V 4.5 Updated

ACCELERATED FEATURES

  • Push, shift, and collision

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
GTCMpush/Secmoi#proc.inyes353055631,1121,854
GTCNRFmoi#proc.inyes1x9x16x32x54x

ICON

Weather and Climate

A global unified atmosphere model for numerical weather prediction and climate modeling research

VERSION

2.6.5_RC

ACCELERATED FEATURES

  • Full model of dynamics and physics

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://code.mpimet.mpg.de/projects/iconpublic

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
ICON [SLAM 191 - 160KM - no radiation]Integrate_nh (sec)SLAM 191 levels 160 km resolution without radiationno2,431741420262223
ICON [SLAM 191 - 160KM - no radiation]NRFSLAM 191 levels 160 km resolution without radiationyes1x3x6x9x11x
ICON [QUBICC 160 km resolution]Integrate_nh (sec)SLAM 191 levels 160 km resolution with radiationno2,213747415253192
ICON [QUBICC 160 km resolution]NRFSLAM 191 levels 160 km resolution with radiationyes1x3x5x9x12x

LAMMPS

Molecular Dynamics

Classical molecular dynamics package

VERSION

stable_23Jun2022_update1

ACCELERATED FEATURES

  • Lennard-Jones, Gay-Berne, Tersoff, many more potentials

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://lammps.sandia.gov/index.html

https://ngc.nvidia.com/catalog/containers/hpc:lammps

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
LAMMPS [ReaxFF/C]ATOM-Time Steps/sReaxFF/Cyes4.45E+056.85E+051.32E+062.50E+064.28E+06
LAMMPS [ReaxFF/C]NRFReaxFF/Cyes1x2x3x7x13x
LAMMPS [SNAP]ATOM-Time Steps/sSNAPyes1.08E+052.43E+054.87E+059.74E+051.93E+06
LAMMPS [SNAP]NRFSNAPyes1x2x5x9x19x
LAMMPS [Tersoff]ATOM-Time Steps/sTersoffyes2.77E+075.23E+071.03E+082.02E+083.51E+08
LAMMPS [Tersoff]NRFTersoffyes1x2x4x7x13x

MILC

Physics

Lattice Quantum Chromodynamics (LQCD) codes simulate how elemental particles are formed and bound by the “strong force” to create larger particles like protons and neutrons

VERSION

feature/gauge-action-quda_16a2d47119

ACCELERATED FEATURES

  • Staggered fermions, Krylov solvers, Gauge-link fattening

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://ngc.nvidia.com/catalog/containers/hpc:milc

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
MILCTotal Time (Sec)Apex Mediumno71,5956,0053,0941,7621,074
MILCNRFApex Mediumyes1x13x25x45x73x

NAMD

Molecular Dynamics

Designed for high-performance simulation of large molecular systems

VERSION

GPU, AMD CPU V 3.0a13 ; Intel CPU V 2.15a AVX512

ACCELERATED FEATURES

  • Full electrostatics with PME and most simulation features

SCALABILITY

Up to 100M atom capable, multi-GPU, single node

MORE INFORMATION

http://www.ks.uiuc.edu/Research/namd/

https://ngc.nvidia.com/catalog/containers/hpc:namd

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
NAMD [apoa1_npt_cuda]Ave ns/dayapoa1_npt_cudayes19.15103208416835
NAMD [apoa1_npt_cuda]NRFapoa1_npt_cudayes1x5x11x22x44x
NAMD [apoa1_nptsr_cuda]Ave ns/dayapoa1_nptsr_cudayes19.59109220440882
NAMD [apoa1_nptsr_cuda]NRFapoa1_nptsr_cudayes1x6x11x22x45x
NAMD [apoa1_nve_cuda]Ave ns/dayapoa1_nve_cudayes20.751442925851,172
NAMD [apoa1_nve_cuda]NRFapoa1_nve_cudayes1x7x14x28x56x
NAMD [stmv_npt_cuda]Ave ns/daystmv_npt_cudayes1.878153061
NAMD [stmv_npt_cuda]NRFstmv_npt_cudayes1x4x8x16x32x
NAMD [stmv_nptsr_cuda]Ave ns/daystmv_nptsr_cudayes1.818163264
NAMD [stmv_nptsr_cuda]NRFstmv_nptsr_cudayes1x4x9x18x35x
NAMD [stmv_nve_cuda]Ave ns/daystmv_nve_cudayes1.9410203979
NAMD [stmv_nve_cuda]NRFstmv_nve_cudayes1x5x10x20x41x

RELION

Microscopy

Stand-alone computer program that employs an empirical Bayesianapproach to refinement of (multiple) 3D reconstructions or 2D class averages in electron cryo-microscopy (cryo-EM)

VERSION

3.1.3

ACCELERATED FEATURES

  • Reduced memory requirements; high-resolution cryo-EM structure determination in a matter of day on a single workstation

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

https://www2.mrc-lmb.cam.ac.uk/relion/index.php/Download_%26_install

https://ngc.nvidia.com/catalog/containers/hpc:relion

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
Relion [Plasmodium Ribosome]Total Wall Clock (Sec)MB numbers Plasmodium Ribosime on Relion-3.0no12,7423,2071,7161,3441,323
Relion [Plasmodium Ribosome]NRFMB numbers Plasmodium Ribosime on Relion-3.0yes1x4x7x9x10x

SPECFEM3D

Geoscience

Simulates Seismic wave propagation

VERSION

devel_fef2ace9

ACCELERATED FEATURES

  • OpenCL and CUDA hardware accelerators, based on an automatic source-to-source transformation library

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://geodynamics.org/cig/software/specfem3d/

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x A402x A404x A408x A40
SPECFEM3DTotal Time (Sec)four_material_simple_modelno1,2682031035329
SPECFEM3DNRFfour_material_simple_modelyes1x6x14x27x50x

Engineering

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual Xeon Gold 6240@2.60GHz with 4x NVIDIA V100 SXM2 | FUN3D Benchmark: dpw_wbt0_crs-3.6Mn_5, CUDA Version: 11.8

Geoscience

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual Xeon Gold 6240@2.60GHz 4x NVIDIA V100 SXM2 | ICON Benchmark: QUBICC 160 km resolution, CUDA Version: 11.8 | RTM Benchmark: Isotropic Radius 4, CUDA Version: 11.8 | SPENFEM3D Benchmark: four_material_simple_model, CUDA Version: 11.8

Microscopy and Molecular Dynamics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual Xeon Gold 6240@2.60GHz with 4x NVIDIA V100 SXM2 | AMBER Benchmark: DC-Cellulose_NVE, CUDA Version: 11.8 | GROMACS Benchmark: STMV, CUDA Version: 11.8 | LAMMPS Benchmark: SNAP, CUDA Version: 11.8 | NAMD Benchmark: apoa1_nve_cuda, CUDA Version: 11.8

Physics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual Xeon Gold 6240@2.60GHz with 4x NVIDIA V100 SXM2 | Chroma Benchmark: szscl21_24_128, CUDA Version: 11.3.1 | GTC Benchmark: moi#proc.in, CUDA Version: 11.8 | MILC Benchmark: Apex Medium, CUDA Version: 11.8

Quantum Mechanics

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual Xeon Gold 6240@2.60GHz with 4x NVIDIA V100 SXM2 | Quantum Espresso Benchmark: AUSURF112-jR, CUDA Version: 11.8

Detailed V100 application performance data is located below in alphabetical order.

AMBER

Molecular Dynamics

Suite of programs to simulate molecular dynamics on biomolecule

VERSION

22.0-AT_22.3

ACCELERATED FEATURES

  • PMEMD Explicit Solvent and GB Implicit Solvent

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

http://ambermd.org/GPUSupport.php

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
AMBER [PME-Cellulose_NPT_4fs]ns/dayDC-Cellulose_NPTyes4.1310020240680597199400808
AMBER [PME-Cellulose_NPT_4fs]NRFDC-Cellulose_NPTyes1x24x49x98x195x24x48x97x196x
AMBER [PME-Cellulose_NVE_4fs]ns/dayDC-Cellulose_NVEyes4.1210120541281899202406815
AMBER [PME-Cellulose_NVE_4fs]NRFDC-Cellulose_NVEyes1x25x50x100x198x24x49x98x198x
AMBER [PME-FactorIX_NPT_4fs]ns/dayDC-FactorIX_NPTyes20.714839531,9153,7874709361,8733,784
AMBER [PME-FactorIX_NPT_4fs]NRFDC-FactorIX_NPTyes1x23x46x92x183x23x45x90x183x
AMBER [PME-FactorIX_NVE_4fs]ns/dayDC-FactorIX_NVEyes20.954969781,9643,8924759591,9263,869
AMBER [PME-FactorIX_NVE_4fs]NRFDC-FactorIX_NVEyes1x24x47x94x186x23x46x92x185x
AMBER [PME-JAC_NPT_4fs]ns/dayDC-JAC_NPTyes84.611,8703,2936,61313,0311,7893,2936,59813,149
AMBER [PME-JAC_NPT_4fs]NRFDC-JAC_NPTyes1x22x39x78x154x21x39x78x155x
AMBER [PME-JAC_NVE_4fs]ns/dayDC-JAC_NVEyes85.161,9073,3896,79513,3711,8223,3876,77913,533
AMBER [PME-JAC_NVE_4fs]NRFDC-JAC_NVEyes1x22x40x80x157x21x40x80x159x
AMBER [PME-STMV_NPT_4fs]ns/dayDC-STMV_NPTyes1.3831621252492857113226
AMBER [PME-STMV_NPT_4fs]NRFDC-STMV_NPTyes1x23x45x90x180x20x41x82x164x
AMBER [FEP-GTI_Complex 1fs]ns/dayFEP-GTI_Complexyes9.89120240480960122245489979
AMBER [FEP-GTI_Complex 1fs]NRFFEP-GTI_Complexyes1x12x24x49x97x12x25x49x99x

Chroma

Physics

Lattice Quantum Chromodynamics (LQCD)

VERSION

V 2021.08

ACCELERATED FEATURES

  • Wilson-clover fermions, Krylov solvers, Domain-decomposition

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://jeffersonlab.github.io/chroma/

https://ngc.nvidia.com/catalog/containers/hpc:chroma

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
ChromaTotal Time (Sec)szscl21_24_128no1,115165311710142281513
ChromaNRFszscl21_24_128yes1x7x37x68x111x8x41x77x85x

FUN3D

Engineering

Suite of tools actively developed at NASA for Aeronautics and Space Technology by modeling fluid flow

VERSION

13.7 (update 1)

ACCELERATED FEATURES

  • Full range of Mach number regimes for the Reynolds-averaged Navier Stokes (RANS) formulation

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://fun3d.larc.nasa.gov

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
FUN3DLoop Time (Sec)dpw_wbt0_crs-3.6Mn_5no4959950261588452314
FUN3DNRFdpw_wbt0_crs-3.6Mn_5yes1x5x12x24x41x6x14x26x44x

GROMACS

Molecular Dynamics

Simulation of biochemical molecules with complicated bond interactions

VERSION

2022.3

ACCELERATED FEATURES

  • Implicit (5x), Explicit (2x) Solvent

SCALABILITY

Multi-GPU, Single Node

MORE INFORMATION

http://www.gromacs.org

https://ngc.nvidia.com/catalog/containers/hpc:gromacs

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB1x RTX60002x RTX60004x RTX60001x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB
GROMACS [ADH Dodec]ns/dayADH Dodecyes67266311472251296-270288330
GROMACS [ADH Dodec]NRFADH Dodecyes1x5x6x9x5x6x-5x6x7x
GROMACS [Cellulose]ns/dayCelluloseyes19711031566083-7398-
GROMACS [Cellulose]NRFCelluloseyes1x4x6x12x3x5x-4x6x-
GROMACS [STMV]ns/daySTMVyes4163053132532162938
GROMACS [STMV]NRFSTMVyes1x3x7x13x3x6x7x3x7x9x

GTC

Physics

GTC is used for Gyrokinetic Particle Simulation of Turbulent Transport in Burning Plasmas

VERSION

V 4.5 Updated

ACCELERATED FEATURES

  • Push, shift, and collision

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
GTCMpush/Secmoi#proc.inyes352715101,0111,7962985521,0811,945
GTCNRFmoi#proc.inyes1x8x15x29x52x9x16x31x57x

ICON

Weather and Climate

A global unified atmosphere model for numerical weather prediction and climate modeling research

VERSION

2.6.5_RC

ACCELERATED FEATURES

  • Full model of dynamics and physics

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://code.mpimet.mpg.de/projects/iconpublic

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB
ICON [SLAM 191 - 160KM - no radiation]Integrate_nh (sec)SLAM 191 levels 160 km resolution without radiationno2,431591353223167819578248
ICON [SLAM 191 - 160KM - no radiation]NRFSLAM 191 levels 160 km resolution without radiationyes1x4x7x11x15x3x4x10x
ICON [QUBICC 160 km resolution]Integrate_nh (sec)SLAM 191 levels 160 km resolution with radiationno2,213514304192143697438215
ICON [QUBICC 160 km resolution]NRFSLAM 191 levels 160 km resolution with radiationyes1x4x7x12x16x3x5x10x

LAMMPS

Molecular Dynamics

Classical molecular dynamics package

VERSION

stable_23Jun2022_update1

ACCELERATED FEATURES

  • Lennard-Jones, Gay-Berne, Tersoff, many more potentials

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://lammps.sandia.gov/index.html

https://ngc.nvidia.com/catalog/containers/hpc:lammps

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
LAMMPS [LJ 2.5]ATOM-Time Steps/sLJ 2.5yes1.11E+083.41E+086.34E+081.24E+092.24E+093.45E+086.23E+081.15E+091.87E+09
LAMMPS [LJ 2.5]NRFLJ 2.5yes1x3x6x11x21x3x6x11x17x
LAMMPS [EAM]ATOM-Time Steps/sEAMyes5.33E+071.23E+082.67E+085.39E+089.74E+081.25E+082.66E+085.15E+088.23E+08
LAMMPS [EAM]NRFEAMyes1x2x5x11x19x2x5x10x16x
LAMMPS [ReaxFF/C]ATOM-Time Steps/sReaxFF/Cyes4.45E+053.23E+066.09E+061.14E+071.94E+073.44E+066.42E+061.19E+071.91E+07
LAMMPS [ReaxFF/C]NRFReaxFF/Cyes1x10x19x35x60x11x20x37x59x
LAMMPS [SNAP]ATOM-Time Steps/sSNAPyes1.08E+051.42E+062.86E+065.69E+061.14E+071.40E+062.80E+065.58E+061.12E+07
LAMMPS [SNAP]NRFSNAPyes1x14x28x55x111x14x27x54x108x
LAMMPS [Tersoff]ATOM-Time Steps/sTersoffyes2.77E+072.71E+084.95E+089.62E+081.80E+092.81E+085.18E+089.83E+081.56E+09
LAMMPS [Tersoff]NRFTersoffyes1x10x18x35x66x10x19x36x57x

MILC

Physics

Lattice Quantum Chromodynamics (LQCD) codes simulate how elemental particles are formed and bound by the “strong force” to create larger particles like protons and neutrons

VERSION

feature/gauge-action-quda_16a2d47119

ACCELERATED FEATURES

  • Staggered fermions, Krylov solvers, Gauge-link fattening

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://ngc.nvidia.com/catalog/containers/hpc:milc

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
MILCTotal Time (Sec)Apex Mediumno71,5954,7372,3471,2296893,8642,0201,1031,068
MILCNRFApex Mediumyes1x17x34x64x114x20x39x71x74x

NAMD

Molecular Dynamics

Designed for high-performance simulation of large molecular systems

VERSION

GPU, AMD CPU V 3.0a13 ; Intel CPU V 2.15a AVX512

ACCELERATED FEATURES

  • Full electrostatics with PME and most simulation features

SCALABILITY

Up to 100M atom capable, multi-GPU, single node

MORE INFORMATION

http://www.ks.uiuc.edu/Research/namd/

https://ngc.nvidia.com/catalog/containers/hpc:namd

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x RTX60002x RTX60004x RTX60008x RTX60001x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
NAMD [apoa1_npt_cuda]Ave ns/dayapoa1_npt_cudayes19.1511122344989066133266532114227455905
NAMD [apoa1_npt_cuda]NRFapoa1_npt_cudayes1x6x12x23x46x3x7x14x28x6x12x24x47x
NAMD [apoa1_nptsr_cuda]Ave ns/dayapoa1_nptsr_cudayes19.5911623547093570141282562119236473943
NAMD [apoa1_nptsr_cuda]NRFapoa1_nptsr_cudayes1x6x12x24x48x4x7x14x29x6x12x24x48x
NAMD [apoa1_nve_cuda]Ave ns/dayapoa1_nve_cudayes20.751422855711,148891793587171442865731,145
NAMD [apoa1_nve_cuda]NRFapoa1_nve_cudayes1x7x14x28x55x4x9x17x35x7x14x28x55x
NAMD [stmv_npt_cuda]Ave ns/daystmv_npt_cudayes1.87817346851021419183570
NAMD [stmv_npt_cuda]NRFstmv_npt_cudayes1x5x9x18x36x3x6x11x22x5x9x19x38x
NAMD [stmv_nptsr_cuda]Ave ns/daystmv_nptsr_cudayes1.81918367151122449183672
NAMD [stmv_nptsr_cuda]NRFstmv_nptsr_cudayes1x5x10x20x39x3x6x12x24x5x10x20x40x
NAMD [stmv_nve_cuda]Ave ns/daystmv_nve_cudayes1.9410204079613265110204080
NAMD [stmv_nve_cuda]NRFstmv_nve_cudayes1x5x10x20x41x3x7x13x26x5x10x21x41x

NV-WRFg

Numerical Weather Prediction

Numerical weather prediction system designed for both atmospheric research and operational forecasting applications

VERSION

3.8.1 NCAR (CPU) / 3.8.1 WRFg 10_28 (GPU)

ACCELERATED FEATURES

  • Dynamics modules
  • Several Physics modules

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

https://wrfg.net/wrfg-description/

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)4x V100 SXM2 32GB4x V100S PCIe 32GB
NV-WRFgSeconds / TimestampsConus_2.5k_JAno60.620.68
NV-WRFgNRFConus_2.5k_JAyes1x10x9x

Quantum Espresso

Material Science (Quantum Chemistry)

An Open-source suite of computer codes for electronic structure calculations and materials modeling at the nanoscale

VERSION

V7.0 CPU; V7.1 GPU

ACCELERATED FEATURES

  • linear algebra (matrix multiply)
  • explicit computational kernels
  • 3D FFTs

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://www.quantum-espresso.org

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
Quantum EspresssoTotal CPU Time (Sec)AUSURF112-jRno71827013382582601308869
Quantum EspresssoNRFAUSURF112-jRyes1x3x6x10x14x3x6x9x12x

RELION

Microscopy

Stand-alone computer program that employs an empirical Bayesianapproach to refinement of (multiple) 3D reconstructions or 2D class averages in electron cryo-microscopy (cryo-EM)

VERSION

3.1.3

ACCELERATED FEATURES

  • Reduced memory requirements; high-resolution cryo-EM structure determination in a matter of day on a single workstation

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

https://www2.mrc-lmb.cam.ac.uk/relion/index.php/Download_%26_install

https://ngc.nvidia.com/catalog/containers/hpc:relion

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB
Relion [Plasmodium Ribosome]Total Wall Clock (Sec)MB numbers Plasmodium Ribosime on Relion-3.0no12,7423,4172,0953,4432,083
Relion [Plasmodium Ribosome]NRFMB numbers Plasmodium Ribosime on Relion-3.0yes1x4x6x4x6x

RTM

Geoscience

Reverse time migration (RTM) modeling is a critical component in the seismic processing workflow of oil and gas exploration

VERSION

nvidia_2021_05

ACCELERATED FEATURES

  • Batch algorithm

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://www.tsunamidevelopment.com/assets/rtm.pdf

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
RTM [Isotropic Radius 4]Mcells/sIsotropic Radius 4yes11,31838,09175,978152,022303,98646,03791,790183,515367,252
RTM [Isotropic Radius 4]NRFIsotropic Radius 4yes1x3x7x13x27x4x8x16x32x
RTM [TTI Radius 8 1-pass]Mcells/sTTI Radius 8 1-passyes3,7738,53816,88533,07065,7329,27618,30436,39372,591
RTM [TTI Radius 8 1-pass]NRFTTI Radius 8 1-passyes1x2x4x9x17x2x5x10x19x
RTM [TTI RX 2Pass mgpu]Mcells/sTTI RX 2Pass mgpuyes3,7737,16514,20328,17756,2358,49116,87133,54766,849
RTM [TTI RX 2Pass mgpu]NRFTTI RX 2Pass mgpuyes1x2x4x7x15x2x4x9x18x

SPECFEM3D

Geoscience

Simulates Seismic wave propagation

VERSION

devel_fef2ace9

ACCELERATED FEATURES

  • OpenCL and CUDA hardware accelerators, based on an automatic source-to-source transformation library

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://geodynamics.org/cig/software/specfem3d/

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)1x V100 SXM2 32GB2x V100 SXM2 32GB4x V100 SXM2 32GB8x V100 SXM2 32GB1x V100S PCIe 32GB2x V100S PCIe 32GB4x V100S PCIe 32GB8x V100S PCIe 32GB
SPECFEM3DTotal Time (Sec)four_material_simple_modelno1,268159824425131683723
SPECFEM3DNRFfour_material_simple_modelyes1x9x18x33x58x11x21x39x63x

Geoscience

CPU Server: Dual Xeon Gold 6240@2.60GHz | GPU Server: Dual Xeon Gold 6240@2.60GHz with 4x NVIDIA T4 PCIe | SPECFEM3D Benchmark: four_material_simple_model, CUDA Version 11.8

Microscopy and Molecular Dynamics

CPU Server: Dual Xeon Gold 6240@2.60GHz, GPU Server: Dual Xeon Gold 6240@2.60GHz with 4x NVIDIA T4 PCIe | AMBER Benchmark: DC-STMV_NPT, CUDA Version: 11.8 | Gromacs Benchmark: STMV, CUDA Version: 11.8 | NAMD Benchmark: apoa1_nve_cuda, CUDA Version: 11.8 | Relion Benchmark: Plasmodium Ribosome (2D), CUDA Version: 11.4.2

Physics

CPU Server: Dual Xeon Gold 6240@2.60GHz, GPU Server: Dual Xeon Gold 6240@2.60GHz with 4x NVIDIA T4 PCIe | Chroma Benchmark: szscl21_24_128, CUDA Version: 11.3.1 | GTC Benchmark: moi#proc.in, CUDA Version: 11.8 | MILC Benchmark: Apex Medium, CUDA Version: 11.8

Detailed T4 application performance data is located below in alphabetical order.


AMBER

Molecular Dynamics

Suite of programs to simulate molecular dynamics on biomolecule

VERSION

22.0-AT_22.3

ACCELERATED FEATURES

  • PMEMD Explicit Solvent and GB Implicit Solvent

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

http://ambermd.org/GPUSupport.php

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)2x T4 PCIe4x T4 PCIe8x T4 PCIe
AMBER [PME-Cellulose_NPT_4fs]ns/dayDC-Cellulose_NPTyes4.1361121245
AMBER [PME-Cellulose_NPT_4fs]NRFDC-Cellulose_NPTyes1x15x29x59x
AMBER [PME-Cellulose_NVE_4fs]ns/dayDC-Cellulose_NVEyes4.1262123248
AMBER [PME-Cellulose_NVE_4fs]NRFDC-Cellulose_NVEyes1x15x30x60x
AMBER [PME-FactorIX_NPT_4fs]ns/dayDC-FactorIX_NPTyes20.712856031,213
AMBER [PME-FactorIX_NPT_4fs]NRFDC-FactorIX_NPTyes1x14x29x59x
AMBER [PME-FactorIX_NVE_4fs]ns/dayDC-FactorIX_NVEyes20.952926161,202
AMBER [PME-FactorIX_NVE_4fs]NRFDC-FactorIX_NVEyes1x14x29x57x
AMBER [PME-JAC_NPT_4fs]ns/dayDC-JAC_NPTyes84.611,2452,3654,491
AMBER [PME-JAC_NPT_4fs]NRFDC-JAC_NPTyes1x15x28x53x
AMBER [PME-JAC_NVE_4fs]ns/dayDC-JAC_NVEyes85.161,2592,5044,979
AMBER [PME-JAC_NVE_4fs]NRFDC-JAC_NVEyes1x15x29x58x
AMBER [PME-STMV_NPT_4fs]ns/dayDC-STMV_NPTyes1.38214283
AMBER [PME-STMV_NPT_4fs]NRFDC-STMV_NPTyes1x15x30x60x
AMBER [FEP-GTI_Complex 1fs]ns/dayFEP-GTI_Complexyes9.89107213427
AMBER [FEP-GTI_Complex 1fs]NRFFEP-GTI_Complexyes1x11x22x43x

Chroma

Physics

Lattice Quantum Chromodynamics (LQCD)

VERSION

V 2021.08

ACCELERATED FEATURES

  • Wilson-clover fermions, Krylov solvers, Domain-decomposition

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

http://jeffersonlab.github.io/chroma/

https://ngc.nvidia.com/catalog/containers/hpc:chroma

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)2x T4 PCIe4x T4 PCIe8x T4 PCIe
ChromaTotal Time (Sec)szscl21_24_128no1,1151174026
ChromaNRFszscl21_24_128yes1x10x28x44x

GROMACS

Molecular Dynamics

Simulation of biochemical molecules with complicated bond interactions

VERSION

2022.3

ACCELERATED FEATURES

  • Implicit (5x), Explicit (2x) Solvent

SCALABILITY

Multi-GPU, Single Node

MORE INFORMATION

http://www.gromacs.org

https://ngc.nvidia.com/catalog/containers/hpc:gromacs

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)2x T4 PCIe4x T4 PCIe
GROMACS [ADH Dodec]ns/dayADH Dodecyes67163238
GROMACS [ADH Dodec]NRFADH Dodecyes1x3x5x
GROMACS [STMV]ns/daySTMVyes4-20
GROMACS [STMV]NRFSTMVyes1x-5x

GTC

Physics

GTC is used for Gyrokinetic Particle Simulation of Turbulent Transport in Burning Plasmas

VERSION

V 4.5 Updated

ACCELERATED FEATURES

  • Push, shift, and collision

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)2x T4 PCIe4x T4 PCIe8x T4 PCIe
GTCMpush/Secmoi#proc.inyes35236466893
GTCNRFmoi#proc.inyes1x7x14x26x

MILC

Physics

Lattice Quantum Chromodynamics (LQCD) codes simulate how elemental particles are formed and bound by the “strong force” to create larger particles like protons and neutrons

VERSION

feature/gauge-action-quda_16a2d47119

ACCELERATED FEATURES

  • Staggered fermions, Krylov solvers, Gauge-link fattening

SCALABILITY

Multi-GPU and Multi-Node

MORE INFORMATION

https://ngc.nvidia.com/catalog/containers/hpc:milc

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)2x T4 PCIe4x T4 PCIe8x T4 PCIe
MILCTotal Time (Sec)Apex Mediumno71,5957,5633,8982,135
MILCNRFApex Mediumyes1x10x20x37x

NAMD

Molecular Dynamics

Designed for high-performance simulation of large molecular systems

VERSION

GPU, AMD CPU V 3.0a13 ; Intel CPU V 2.15a AVX512

ACCELERATED FEATURES

  • Full electrostatics with PME and most simulation features

SCALABILITY

Up to 100M atom capable, multi-GPU, single node

MORE INFORMATION

http://www.ks.uiuc.edu/Research/namd/

https://ngc.nvidia.com/catalog/containers/hpc:namd

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)2x T4 PCIe4x T4 PCIe8x T4 PCIe
NAMD [apoa1_npt_cuda]Ave ns/dayapoa1_npt_cudayes19.1557113229
NAMD [apoa1_npt_cuda]NRFapoa1_npt_cudayes1x3x6x12x
NAMD [apoa1_nptsr_cuda]Ave ns/dayapoa1_nptsr_cudayes19.5959117239
NAMD [apoa1_nptsr_cuda]NRFapoa1_nptsr_cudayes1x3x6x12x
NAMD [apoa1_nve_cuda]Ave ns/dayapoa1_nve_cudayes20.7575149303
NAMD [apoa1_nve_cuda]NRFapoa1_nve_cudayes1x4x7x15x
NAMD [stmv_npt_cuda]Ave ns/daystmv_npt_cudayes1.87-917
NAMD [stmv_npt_cuda]NRFstmv_npt_cudayes1x-5x9x
NAMD [stmv_nptsr_cuda]Ave ns/daystmv_nptsr_cudayes1.815917
NAMD [stmv_nptsr_cuda]NRFstmv_nptsr_cudayes1x3x5x10x
NAMD [stmv_nve_cuda]Ave ns/daystmv_nve_cudayes1.94-1020
NAMD [stmv_nve_cuda]NRFstmv_nve_cudayes1x-5x10x

RELION

Microscopy

Stand-alone computer program that employs an empirical Bayesianapproach to refinement of (multiple) 3D reconstructions or 2D class averages in electron cryo-microscopy (cryo-EM)

VERSION

3.1.3

ACCELERATED FEATURES

  • Reduced memory requirements; high-resolution cryo-EM structure determination in a matter of day on a single workstation

SCALABILITY

Multi-GPU and Single Node

MORE INFORMATION

https://www2.mrc-lmb.cam.ac.uk/relion/index.php/Download_%26_install

https://ngc.nvidia.com/catalog/containers/hpc:relion

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)2x T4 PCIe4x T4 PCIe
Relion [Plasmodium Ribosome]Total Wall Clock (Sec)MB numbers Plasmodium Ribosime on Relion-3.0no12,7423,5862,549
Relion [Plasmodium Ribosome]NRFMB numbers Plasmodium Ribosime on Relion-3.0yes1x4x5x

SPECFEM3D

Geoscience

Simulates Seismic wave propagation

VERSION

devel_fef2ace9

ACCELERATED FEATURES

  • OpenCL and CUDA hardware accelerators, based on an automatic source-to-source transformation library

SCALABILITY

Multi-GPU and Single-Node

MORE INFORMATION

https://geodynamics.org/cig/software/specfem3d/

ApplicationMetricTest ModulesBigger is betterDual Cascade Lake 6240 (CPU-Only)2x T4 PCIe4x T4 PCIe8x T4 PCIe
SPECFEM3DTotal Time (Sec)four_material_simple_modelno1,26823912264
SPECFEM3DNRFfour_material_simple_modelyes1x5x12x23x