Molecular Dynamics

NVIDIA GPU Benchmarks AMBER 22

February 7, 2023
9 min read
EXX-Blog-NVIDIA-Ampere-Benchmark-for-Amber22.jpg
Updated: 02/07/2023 > [NEW] NVIDIA H100 (PCIe)and RTX 4070 Ti AMBER Benchmarks
Updated: 10/18/2022 > [NEW] NVIDIA RTX 4090 AMBER Benchmarks
Last Update: 06/23/2022 > Benchmarks Uploaded

AMBER 22 GPU Benchmarks for Molecular Dynamics with NVIDIA Professional and Data Center GPUs

The following Amber 22 Benchmarks were performed on an Exxact AMBER Certified MD System using the AMBER 22 Benchmark Suite with the following GPUs:

All benchmarks were performed using a single GPU configuration using Amber 22 Update 1 & AmberTools 22 Update 1. NVIDIA CUDA 11.4 was also used for these benchmarks.

Quick AMBER GPU Benchmark takeaways

  • NVIDIA Ada Lovelace GPUs (RTX 4090 and RTX 4070Ti) outperform all Ampere models (A100, RTX 3090, RTX 3080) by a long shot.
    • NVIDIA RTX 4090 is a definite winner as the single most powerful GPU in our tests.
    • The upgrade to an RTX 4070Ti shows considerable performance gain from the RTX 3090
  • NVIDIA H100 is on par as 2nd most powerful (behind the RTX 4090) winning in only a couple of tests. However, the H100 offers far more scalability due to its data center nature! Leverage up to 8x NVIDIA H100s in a server or 4x in a workstation for unparalleled performance, something you cannot do with the 4090.
  • For the larger simulations, such as STMV Production NPT 4fs, the H100's larger memory capacity, and the RTX 4090's higher clock speed pulls away from the others.
  • For smaller simulations, the RTX 4070Ti showed excellent performance, a leg up on even the NVIDIA A100.

Interested in getting faster results?
Learn more about the only AMBER Certified GPU Systems starting around $6,000


Exxact Workstation System Specs:

Make/Model Supermicro AS -4124GS-TN
Nodes 1
Processor / Count 2x AMD EPYC 7552
Total Logical Cores 48
Memory 512GB DDR4
Storage 2.84TB NVMe SSD
OS Centos 7
CUDA Version 11.4
AMBER Version 22

GPU Benchmark Overview

Benchmark RTX 4090 H100 PCIeRTX 4070 TiA100 PCIe RTX A6000 RTX A5500 RTX A5000 RTX A4500 RTX A4000 A10 RTX 3090 RTX 3080 RTX 3070 RTX 6000
JAC Production NVE 4fs 1659.42 1479.321322.641199.22 1101.29 1061.73 1008.05 935.33 810 895.05 1196.5 1101.24 950.17 1034.88
JAC Production NPT 4fs 1618.45 1424.901262.401194.5 1084.37 1042.13 992.14 911.08 803.02 886.04 1157.76 1086.21 930.3 1004.03
JAC Production NVE 2fs 883.23 779.95701.09611.08 586.09 561.62 535.01 491.62 429.67 470.51 632.19 585.81 502.13 540.17
JAC Production NPT 2fs 842.69 701.09666.18610.09 560.05 535.28 505.58 469.85 412.73 455.36 595.28 557.6 479.15 515.86
FactorIX Production NVE 2fs 466.44 389.18301.03271.36 256.1 231.31 214.13 189.02 154.45 185.45 264.78 234.58 179.07 217.25
FactorIX Production NPT 2fs 433.24 357.88279.19252.87 241.63 215.41 206.78 181.35 150.12 180.45 248.65 217.5 170.09 206
Cellulose Production NVE 2fs 129.63 119.2769.3085.23 59.52 52.7 47.09 41.26 31.26 38.45 63.23 53.44 37.41 47.41
Cellulose Production NPT 2fs 119.04 108.9164.6577.98 55.5 49.88 45.71 39.48 30.34 36.72 58.3 49.69 35.75 45.24
STMV Production NPT 4fs 78.90 70.1537.3152.02 37.01 33.58 30.87 26.67 20.27 24.24 38.65 32.18 23.89 28.49
TRPCage GB 2fs 1482.22 1413.281519.471040.61 1166.26 1124.98 1235.49 1188.03 1244.75 1096.59 1225.53 1332.27 1375.35 1189.25
Myoglobin GB 2fs 929.62 1094.48757.91661.22 650.48 602.16 586.42 518.8 492.48 584.93 621.73 619.67 539.21 600.83
Nucleosome GB 2fs 36.90 37.6821.3429.66 20.37 15.23 15.6 13.47 11.02 14.49 21.08 17.72 12.76 16.81

AMBER 22 GPU Benchmark: JAC Production NVE 4fs

JAC Production NVE 4FS AMBER Benchmark

AMBER 22 GPU Benchmark: JAC Production NPT 4fs

JAC Production NPT 4FS AMBER Benchmark

AMBER 22 GPU Benchmark: JAC Production NVE 2fs

JAC Production NVE 2FS AMBER Benchmark

AMBER 22 GPU Benchmark: JAC Production NPT 2fs

JAC Production NPT 2FS AMBER Benchmark

AMBER 22 GPU Benchmark: FactorIX Production NVE 2fs

FactorIX Production NVE 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: FactorIX Production NPT 2fs

FactorIX Production NPT 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: Cellulose Production NVE 2fs

Cellulose Production NVE 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: Cellulose Production NPT 2fs

Cellulose Production NPT 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: STMV Production NPT 4fs

STMV Production NPT 4fs AMBER Benchmark

AMBER 22 GPU Benchmark: TRPCage GB 2fs

TRPCage GB 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: Myoglobin GB 2fs

Myoglobin GB 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: Nucleosome GB 2fs

Nucleosome GB 2fs AMBER Benchmark

Note about AMBER Benchmarks (From Dave Cerutti)

We take as benchmarks four periodic systems spanning a range of system sizes and compositions. The smallest Dihydrofolate Reductase (DHFR) case is a 159-residue protein in water, weighing in at 23,588 atoms. Next, from the human blood clotting system, Factor IX is a 379-residue protein also in a box of water, totaling 90,906 atoms. The larger cellulose system, with 408,609 atoms, has a greater content of macromolecules in it: the repeating sugar polymer constitutes roughly a sixth of the atoms in the system. Finally, the very large simulation of satellite tobacco mosaic virus (STMV), a gargantuan 1,067,095 atom system, also has an appreciable macromolecule content but is otherwise another collection of proteins in water. (source http://ambermd.org/GPUPerformance.php)

What is AMBER Molecular Dynamics Package?

AMBER is a molecular dynamics software package that simulates molecular mechanical force fields. AMBER (Assisted Model Building with Energy Refinement) is a family of force fields for molecular dynamics of biomolecules originally developed by Peter Kollman’s group at the University of California, San Francisco. The AMBER MD software package is maintained by active collaboration between David Case at Rutgers University, Tom Cheatham at the University of Utah, Adrian Roitberg at the University of Florida, Ken Merz at Michigan State University, Carlos Simmerling at Stony Brook University, Ray Luo at UC Irvine, and Junmei Wang at Encysive Pharmaceuticals.


Have any questions?
Contact Exxact Today


EXX-Blog-NVIDIA-Ampere-Benchmark-for-Amber22.jpg
Molecular Dynamics

NVIDIA GPU Benchmarks AMBER 22

February 7, 20239 min read
Updated: 02/07/2023 > [NEW] NVIDIA H100 (PCIe)and RTX 4070 Ti AMBER Benchmarks
Updated: 10/18/2022 > [NEW] NVIDIA RTX 4090 AMBER Benchmarks
Last Update: 06/23/2022 > Benchmarks Uploaded

AMBER 22 GPU Benchmarks for Molecular Dynamics with NVIDIA Professional and Data Center GPUs

The following Amber 22 Benchmarks were performed on an Exxact AMBER Certified MD System using the AMBER 22 Benchmark Suite with the following GPUs:

All benchmarks were performed using a single GPU configuration using Amber 22 Update 1 & AmberTools 22 Update 1. NVIDIA CUDA 11.4 was also used for these benchmarks.

Quick AMBER GPU Benchmark takeaways

  • NVIDIA Ada Lovelace GPUs (RTX 4090 and RTX 4070Ti) outperform all Ampere models (A100, RTX 3090, RTX 3080) by a long shot.
    • NVIDIA RTX 4090 is a definite winner as the single most powerful GPU in our tests.
    • The upgrade to an RTX 4070Ti shows considerable performance gain from the RTX 3090
  • NVIDIA H100 is on par as 2nd most powerful (behind the RTX 4090) winning in only a couple of tests. However, the H100 offers far more scalability due to its data center nature! Leverage up to 8x NVIDIA H100s in a server or 4x in a workstation for unparalleled performance, something you cannot do with the 4090.
  • For the larger simulations, such as STMV Production NPT 4fs, the H100's larger memory capacity, and the RTX 4090's higher clock speed pulls away from the others.
  • For smaller simulations, the RTX 4070Ti showed excellent performance, a leg up on even the NVIDIA A100.

Interested in getting faster results?
Learn more about the only AMBER Certified GPU Systems starting around $6,000


Exxact Workstation System Specs:

Make/Model Supermicro AS -4124GS-TN
Nodes 1
Processor / Count 2x AMD EPYC 7552
Total Logical Cores 48
Memory 512GB DDR4
Storage 2.84TB NVMe SSD
OS Centos 7
CUDA Version 11.4
AMBER Version 22

GPU Benchmark Overview

Benchmark RTX 4090 H100 PCIeRTX 4070 TiA100 PCIe RTX A6000 RTX A5500 RTX A5000 RTX A4500 RTX A4000 A10 RTX 3090 RTX 3080 RTX 3070 RTX 6000
JAC Production NVE 4fs 1659.42 1479.321322.641199.22 1101.29 1061.73 1008.05 935.33 810 895.05 1196.5 1101.24 950.17 1034.88
JAC Production NPT 4fs 1618.45 1424.901262.401194.5 1084.37 1042.13 992.14 911.08 803.02 886.04 1157.76 1086.21 930.3 1004.03
JAC Production NVE 2fs 883.23 779.95701.09611.08 586.09 561.62 535.01 491.62 429.67 470.51 632.19 585.81 502.13 540.17
JAC Production NPT 2fs 842.69 701.09666.18610.09 560.05 535.28 505.58 469.85 412.73 455.36 595.28 557.6 479.15 515.86
FactorIX Production NVE 2fs 466.44 389.18301.03271.36 256.1 231.31 214.13 189.02 154.45 185.45 264.78 234.58 179.07 217.25
FactorIX Production NPT 2fs 433.24 357.88279.19252.87 241.63 215.41 206.78 181.35 150.12 180.45 248.65 217.5 170.09 206
Cellulose Production NVE 2fs 129.63 119.2769.3085.23 59.52 52.7 47.09 41.26 31.26 38.45 63.23 53.44 37.41 47.41
Cellulose Production NPT 2fs 119.04 108.9164.6577.98 55.5 49.88 45.71 39.48 30.34 36.72 58.3 49.69 35.75 45.24
STMV Production NPT 4fs 78.90 70.1537.3152.02 37.01 33.58 30.87 26.67 20.27 24.24 38.65 32.18 23.89 28.49
TRPCage GB 2fs 1482.22 1413.281519.471040.61 1166.26 1124.98 1235.49 1188.03 1244.75 1096.59 1225.53 1332.27 1375.35 1189.25
Myoglobin GB 2fs 929.62 1094.48757.91661.22 650.48 602.16 586.42 518.8 492.48 584.93 621.73 619.67 539.21 600.83
Nucleosome GB 2fs 36.90 37.6821.3429.66 20.37 15.23 15.6 13.47 11.02 14.49 21.08 17.72 12.76 16.81

AMBER 22 GPU Benchmark: JAC Production NVE 4fs

JAC Production NVE 4FS AMBER Benchmark

AMBER 22 GPU Benchmark: JAC Production NPT 4fs

JAC Production NPT 4FS AMBER Benchmark

AMBER 22 GPU Benchmark: JAC Production NVE 2fs

JAC Production NVE 2FS AMBER Benchmark

AMBER 22 GPU Benchmark: JAC Production NPT 2fs

JAC Production NPT 2FS AMBER Benchmark

AMBER 22 GPU Benchmark: FactorIX Production NVE 2fs

FactorIX Production NVE 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: FactorIX Production NPT 2fs

FactorIX Production NPT 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: Cellulose Production NVE 2fs

Cellulose Production NVE 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: Cellulose Production NPT 2fs

Cellulose Production NPT 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: STMV Production NPT 4fs

STMV Production NPT 4fs AMBER Benchmark

AMBER 22 GPU Benchmark: TRPCage GB 2fs

TRPCage GB 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: Myoglobin GB 2fs

Myoglobin GB 2fs AMBER Benchmark

AMBER 22 GPU Benchmark: Nucleosome GB 2fs

Nucleosome GB 2fs AMBER Benchmark

Note about AMBER Benchmarks (From Dave Cerutti)

We take as benchmarks four periodic systems spanning a range of system sizes and compositions. The smallest Dihydrofolate Reductase (DHFR) case is a 159-residue protein in water, weighing in at 23,588 atoms. Next, from the human blood clotting system, Factor IX is a 379-residue protein also in a box of water, totaling 90,906 atoms. The larger cellulose system, with 408,609 atoms, has a greater content of macromolecules in it: the repeating sugar polymer constitutes roughly a sixth of the atoms in the system. Finally, the very large simulation of satellite tobacco mosaic virus (STMV), a gargantuan 1,067,095 atom system, also has an appreciable macromolecule content but is otherwise another collection of proteins in water. (source http://ambermd.org/GPUPerformance.php)

What is AMBER Molecular Dynamics Package?

AMBER is a molecular dynamics software package that simulates molecular mechanical force fields. AMBER (Assisted Model Building with Energy Refinement) is a family of force fields for molecular dynamics of biomolecules originally developed by Peter Kollman’s group at the University of California, San Francisco. The AMBER MD software package is maintained by active collaboration between David Case at Rutgers University, Tom Cheatham at the University of Utah, Adrian Roitberg at the University of Florida, Ken Merz at Michigan State University, Carlos Simmerling at Stony Brook University, Ray Luo at UC Irvine, and Junmei Wang at Encysive Pharmaceuticals.


Have any questions?
Contact Exxact Today