NAMD CUDA

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. This version of the NAMD test profile uses CUDA GPU acceleration; the non-CUDA version of this test profile is pts/namd.

To run this test with the Phoronix Test Suite, the basic command is: phoronix-test-suite benchmark namd-cuda.

Project Site

ks.uiuc.edu

Test Created

22 December 2018

Last Updated

25 January 2025

Test Maintainer

Michael Larabel

Test Type

Processor

Average Install Time

4 Seconds

Average Run Time

8 Minutes, 35 Seconds

Accolades

20k+ Downloads + Recently Updated Test Profile

Supported Platforms

Supported Architectures

x86_64

* Uploading of benchmark result data to OpenBenchmarking.org is always optional (opt-in) via the Phoronix Test Suite for users wishing to share their results publicly.
** Data based on those opting to upload their test results to OpenBenchmarking.org and users enabling the opt-in anonymous statistics reporting while running benchmarks from an Internet-connected platform.
*** Test profile page view reporting began March 2021.
Data updated weekly as of 29 January 2025.

Revision History

pts/namd-cuda-1.2.0 [View Source] Sat, 25 Jan 2025 10:29:57 GMT
Update against NAMD 3.0.1 upstream.

pts/namd-cuda-1.1.1 [View Source] Fri, 18 Sep 2020 13:22:37 GMT
TestType should be Graphics not Processor, typo when spinning off from namd test profile.

pts/namd-cuda-1.1.0 [View Source] Thu, 27 Aug 2020 15:53:41 GMT
Update against upstream NAMD 2.14.

pts/namd-cuda-1.0.0 [View Source] Sat, 22 Dec 2018 09:28:34 GMT
Initial commit of CUDA version of NAMD benchmark.

Suites Using This Test

NVIDIA GPU Compute

Performance Metrics

Analyze Test Configuration:

NAMD CUDA 3.0.1

Input: STMV with 1,066,628 Atoms

OpenBenchmarking.org metrics for this test profile configuration based on 51 public results since 25 January 2025 with the latest data as of 28 January 2025.

Below is an overview of the generalized performance for components where there is sufficient statistically significant data based upon user-uploaded results. It is important to keep in mind particularly in the Linux/open-source space there can be vastly different OS configurations, with this overview intended to offer just general guidance as to the performance expectations.

Component

Percentile Rank

# Compatible Public Results

ns/day (Average)

ASUS NVIDIA GeForce RTX 5090

86th

3.997 ^{+/- 0.084}

ASUS NVIDIA GeForce RTX 5080

86th

3.983 ^{+/- 0.076}

Mid-Tier

75th

< 3.564

ASUS NVIDIA GeForce RTX 4090

58th

3.524 ^{+/- 0.049}

ASUS NVIDIA GeForce RTX 4080

58th

3.509 ^{+/- 0.058}

ASUS NVIDIA GeForce RTX 4080 SUPER

54th

3.475 ^{+/- 0.031}

Median

50th

3.464

ASUS NVIDIA GeForce RTX 3080

35th

3.444 ^{+/- 0.005}

ASUS NVIDIA GeForce RTX 3090

31st

3.426 ^{+/- 0.044}

ASUS NVIDIA GeForce RTX 4070 Ti SUPER

31st

3.419 ^{+/- 0.059}

Low-Tier

25th

< 3.393

ASUS NVIDIA GeForce RTX 4070

15th

3.343 ^{+/- 0.058}

ASUS NVIDIA GeForce RTX 4070 SUPER

7th

3.262 ^{+/- 0.078}

Detailed Performance Overview

Based on OpenBenchmarking.org data, the selected test / test configuration (NAMD CUDA 3.0.1 - Input: STMV with 1,066,628 Atoms) has an average run-time of 2 minutes. By default this test profile is set to run at least 3 times but may increase if the standard deviation exceeds pre-defined defaults or other calculations deem additional runs necessary for greater statistical accuracy of the result.

Notable Instruction Set Usage

Notable instruction set extensions supported by this test, based on an automatic analysis by the Phoronix Test Suite / OpenBenchmarking.org analytics engine.

Instruction Set

Support

Instructions Detected

SSE2 (SSE2)

Used by default on supported hardware.

MOVDQA CVTSD2SS SUBSD MULSD ADDSD CVTTSD2SI CVTSS2SD CVTPD2PS MOVDQU MOVD PSRLDQ CVTSI2SD DIVSD MOVHPD UNPCKLPD COMISD SQRTSD PSHUFD PUNPCKLQDQ PUNPCKHQDQ MINSD MAXSD UCOMISD MULPD CVTPS2PD ADDPD UNPCKHPD CMPLTSD CVTDQ2PD DIVPD SUBPD CMPLTPD MOVMSKPD PADDQ PSUBQ CVTDQ2PS SQRTPD CMPEQPD CVTTPD2DQ CMPNLTSD CMPEQSD CMPNEQSD CMPLESD CMPLEPD PMULUDQ MAXPD MINPD MOVAPD PSHUFLW CVTSD2SI ANDPD XORPD ORPD ANDNPD MOVLPD CMPNLESD SHUFPD CMPUNORDPD CMPNLEPD CMPNLTPD CVTPS2DQ PSLLDQ MOVNTDQ MOVNTI

SSE3 (SSE3)

Used by default on supported hardware.

MOVDDUP LDDQU

SSSE3 (SSSE3)

Used by default on supported hardware.

PALIGNR PMADDUBSW PHADDD

SSE 4.2 (SSE4_2)

Used by default on supported hardware.
Found on Intel processors since at least 2010.
Found on AMD processors since Bulldozer (2011).

PCMPISTRM PCMPISTRI

Advanced Vector Extensions (AVX)

Used by default on supported hardware.
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).

VINSERTF128 VZEROUPPER VEXTRACTF128 VBROADCASTSS VBROADCASTSD VPERM2F128 VMASKMOVPS VPERMILPD

Advanced Vector Extensions 2 (AVX2)

Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Excavator (2016).

VPBROADCASTQ VGATHERQPD VEXTRACTI128 VPBROADCASTD

Advanced Vector Extensions 512 (AVX512)

Used by default on supported hardware.

(ZMM REGISTER USE)

FMA (FMA)

Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).

VFNMADD213SD VFMADD213SD VFMADD231SD VFMSUB213SD VFNMADD231SD VFMADD132SD VFNMADD132SD VFMSUB213SS VFMADD213SS VFMADD231SS VFNMADD213SS VFMADD213PD VFNMADD231PD VFNMADD132PD VFMSUB213PD VFNMADD213PD VFMADD231PD VFMADD132PD VFMADD213PS VFNMADD213PS VFNMADD132PS

Last automated analysis: 18 January 2022

This test profile binary relies on the shared libraries libm.so.6, libpthread.so.0, libdl.so.2, librt.so.1, libz.so.1, libc.so.6.

Tested CPU Architectures

This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.

CPU Architecture

Kernel Identifier

Verified On

Intel / AMD x86 64-bit

x86_64

(Many Processors)

Recent Test Results

Compare

NAMD NVIDIA GeForce RTX 5090 1 System - 6 Benchmark Results	Intel Core Ultra 9 285K - ASUS ROG MAXIMUS Z890 HERO - Intel Device ae7f Ubuntu 24.10 - 6.11.0-13-generic - GNOME Shell 47.0
NVIDIA NAMD 1 System - 2 Benchmark Results	Intel Core Ultra 9 285K - ASUS ROG MAXIMUS Z890 HERO - Intel Device ae7f Ubuntu 24.10 - 6.11.0-13-generic - GNOME Shell 47.0
nvidia rtx 5090 compute benchmarks 3 Systems - 94 Benchmark Results	Intel Core Ultra 9 285K - ASUS ROG MAXIMUS Z890 HERO - Intel Device ae7f Ubuntu 24.10 - 6.11.0-13-generic - GNOME Shell 47.0
2025-01-10-1611 10 Systems - 29 Benchmark Results	AMD Ryzen 5 5600X 6-Core - ASUS PRIME A520M-K - AMD Starship SystemRescue 11.01 - 6.6.30-1-lts - Xfce 4.18
cuda 1 System - 1 Benchmark Result	AMD Ryzen 9 5900X 12-Core - 32GB - 0GB Virtual Disk + 9GB Virtual Disk + 1100GB Virtual Disk Ubuntu 22.04 - 5.15.153.1-microsoft-standard-WSL2 - Wayland
test_002 1 System - 113 Benchmark Results	AMD Ryzen 9 7900X3D 12-Core - ASUS ProArt B650-CREATOR - AMD Device 14d8 Ubuntu 24.04 - 6.8.0-47-generic - GNOME Shell 46.0
cuda-test-namd 1 System - 1 Benchmark Result	Intel Core i9-13900TE - Neousys SEMIL-2000 SML-2000 - Intel Alder Lake-S PCH Ubuntu 20.04 - 5.15.0-117-generic - GNOME Shell 3.36.9
bbbbbb 1 System - 116 Benchmark Results	AMD Ryzen 7 3700X 8-Core - ASUS TUF GAMING X570-PLUS - AMD Starship RockyLinux 9.4 - 6.1.102-1.el9.elrepo.x86_64 - KDE Plasma 5.27.11