NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes.

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

Project Site

nas.nasa.gov

Test Created

6 December 2010

Last Updated

14 October 2021

Test Maintainer

Michael Larabel 

Test Type

Processor

Average Install Time

34 Seconds

Average Run Time

1 Minute, 30 Seconds

Test Dependencies

C/C++ Compiler Toolchain + Fortran + OpenMPI

Accolades

300k+ Downloads + 5k+ Public Benchmark Results

Supported Platforms


Public Result Uploads *Reported Test Completions **Reported Installs **Test Profile Page Views ***OpenBenchmarking.orgEventsNAS Parallel Benchmarks Popularity Statisticspts/npb2010.122011.052011.102012.032012.082013.012013.062013.112014.042014.092015.022015.072015.122016.052016.102017.032017.082018.012018.062018.112019.042019.092020.022020.072020.122021.052021.102022.032022.082023.012023.062023.112024.042024.0980K160K240K320K400K
* 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 22 November 2024.
IS.D7.1%EP.C10.9%BT.C11.1%CG.C10.7%LU.C13.1%FT.C9.7%MG.C11.2%SP.C6.8%SP.B9.1%EP.D10.2%Test / Class Option PopularityOpenBenchmarking.org

Revision History

pts/npb-1.4.5   [View Source]   Thu, 14 Oct 2021 14:32:39 GMT
Pull in fixes from skeevy420. Fixes: https://github.com/phoronix-test-suite/phoronix-test-suite/pull/552

pts/npb-1.4.4   [View Source]   Sat, 22 May 2021 17:40:59 GMT
Add sp.c, adjust process count per https://www.phoronix.com/forums/forum/phoronix/phoronix-test-suite/1257554-how-to-enable-verbose-output#post1257618

pts/npb-1.4.2   [View Source]   Thu, 21 Jan 2021 12:22:20 GMT
Build fix for GCC 10 gfortran/

pts/npb-1.4.1   [View Source]   Sat, 07 Mar 2020 12:22:08 GMT
Add --alow-run-as-root, ended up being missed until now.

pts/npb-1.4.0   [View Source]   Wed, 28 Aug 2019 11:43:04 GMT
Update against upstream NPB 3.4, add new test cases.

pts/npb-1.3.1   [View Source]   Tue, 15 Jan 2019 11:37:52 GMT
Update against upstream NPB 3.1.1

pts/npb-1.3.0   [View Source]   Fri, 09 Nov 2018 12:39:01 GMT
Use physical core count rather than logical cores to avoid MPI breaking on high core count systems with SMT.

pts/npb-1.2.4   [View Source]   Sat, 09 Sep 2017 10:30:50 GMT
ft.B not ft.C size

pts/npb-1.2.3   [View Source]   Sat, 09 Sep 2017 10:15:47 GMT
Update MPI handling, add some larger test sizes

pts/npb-1.2.2   [View Source]   Thu, 25 Aug 2016 13:51:56 GMT
Update CFLAGS handling

pts/npb-1.2.1   [View Source]   Thu, 27 Nov 2014 18:42:33 GMT
MG.B and IS.D do not build / run properly on modern systems.

pts/npb-1.2.0   [View Source]   Tue, 05 Nov 2013 22:57:21 GMT
Working on new version of NPB test that makes use of some of the HPCC test profile MPI improvements and other multi-core/cluster work for better benchmarking. Seems to have MPI rank errors right now though for NPB on this build.

pts/npb-1.1.1   [View Source]   Sun, 10 Jun 2012 19:11:43 GMT
Remove tests not in MPI NPB version.

pts/npb-1.1.0   [View Source]   Sun, 10 Jun 2012 16:56:25 GMT
Switch to the MPI version of NPB benchmarks.

pts/npb-1.0.0   [View Source]   Mon, 06 Dec 2010 15:00:08 GMT
Initial import into OpenBenchmarking.org

Suites Using This Test

Multi-Core

HPC - High Performance Computing

CPU Massive

Server CPU Tests

MPI Benchmarks


Performance Metrics

Analyze Test Configuration:

NAS Parallel Benchmarks 3.4

Test / Class: EP.C

OpenBenchmarking.org metrics for this test profile configuration based on 2,504 public results since 28 August 2019 with the latest data as of 23 November 2024.

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
Total Mop/s (Average)
100th
4
27554 +/- 160
100th
11
17285 +/- 1180
100th
9
12901 +/- 59
100th
4
10753 +/- 182
100th
23
9554 +/- 374
98th
26
9232 +/- 190
98th
10
8914 +/- 610
97th
18
8385 +/- 199
95th
4
7896 +/- 65
94th
33
7748 +/- 743
93rd
9
7084 +/- 136
91st
9
6275 +/- 922
91st
6
6271 +/- 83
90th
27
6085 +/- 146
89th
4
5814 +/- 281
87th
17
5046 +/- 99
85th
19
4856 +/- 141
84th
4
4704 +/- 96
83rd
3
4610 +/- 88
83rd
8
4563 +/- 80
82nd
16
4472 +/- 118
82nd
15
4358 +/- 88
82nd
4
4351 +/- 338
81st
9
4158 +/- 79
81st
4
4121 +/- 16
80th
5
3976 +/- 20
80th
9
3893 +/- 39
79th
11
3846 +/- 30
79th
15
3773 +/- 64
78th
18
3669 +/- 71
78th
6
3661 +/- 122
77th
6
3304 +/- 15
76th
5
3259 +/- 15
Mid-Tier
75th
< 3190
75th
4
3187 +/- 279
75th
18
3154 +/- 138
74th
15
3102 +/- 156
71st
9
2917 +/- 46
71st
27
2913 +/- 432
70th
6
2853 +/- 96
68th
5
2693 +/- 10
68th
20
2610 +/- 317
67th
4
2386 +/- 20
66th
6
2373 +/- 14
66th
5
2324 +/- 14
65th
21
2303 +/- 28
62nd
5
2122 +/- 3
62nd
15
2109 +/- 40
60th
20
1978 +/- 243
60th
12
1902 +/- 228
59th
4
1898 +/- 40
59th
45
1864 +/- 31
58th
12
1849 +/- 53
57th
5
1811 +/- 9
57th
15
1787 +/- 22
56th
14
1766 +/- 10
54th
4
1626 +/- 56
54th
17
1623 +/- 238
53rd
16
1593 +/- 32
53rd
20
1585 +/- 50
53rd
4
1582 +/- 46
52nd
5
1576 +/- 5
51st
11
1529 +/- 65
51st
14
1518 +/- 49
Median
50th
1514
48th
36
1456 +/- 18
48th
10
1449 +/- 16
47th
7
1414 +/- 5
47th
6
1409 +/- 9
45th
10
1355 +/- 31
45th
4
1337 +/- 70
45th
15
1313 +/- 61
44th
5
1250 +/- 33
43rd
4
1215 +/- 26
43rd
12
1200 +/- 32
43rd
7
1194 +/- 17
43rd
7
1193 +/- 5
42nd
10
1178 +/- 38
42nd
7
1172 +/- 3
41st
11
1163 +/- 18
41st
5
1159 +/- 6
41st
5
1156 +/- 66
41st
4
1153 +/- 34
39th
9
1100 +/- 2
38th
9
1078 +/- 37
38th
8
1049 +/- 19
37th
4
1041 +/- 53
36th
15
1002 +/- 15
34th
5
956 +/- 29
33rd
9
936 +/- 24
33rd
12
917 +/- 44
33rd
8
909 +/- 14
32nd
4
900 +/- 30
32nd
3
888 +/- 4
32nd
4
885 +/- 4
31st
5
869 +/- 2
31st
7
859 +/- 4
31st
5
859 +/- 62
30th
3
839 +/- 4
30th
8
829 +/- 93
30th
3
829 +/- 9
29th
10
822 +/- 102
28th
4
782 +/- 1
26th
5
693 +/- 34
26th
10
690 +/- 18
Low-Tier
25th
< 678
25th
6
676 +/- 5
25th
6
659 +/- 42
24th
3
657 +/- 6
24th
7
627 +/- 56
23rd
10
603 +/- 17
22nd
5
598 +/- 8
22nd
12
589 +/- 24
22nd
6
585 +/- 31
21st
7
584 +/- 9
21st
6
579 +/- 4
21st
8
568 +/- 6
20th
4
546 +/- 38
18th
13
526 +/- 4
18th
4
526 +/- 4
17th
3
511 +/- 4
17th
8
503 +/- 10
17th
12
502 +/- 68
16th
5
495 +/- 12
16th
3
494 +/- 3
16th
3
480 +/- 5
15th
7
477 +/- 13
15th
3
438 +/- 9
14th
9
432 +/- 25
14th
3
426 +/- 55
12th
6
371 +/- 6
11th
8
369 +/- 53
11th
3
358 +/- 21
9th
8
282 +/- 1
9th
4
275 +/- 23
8th
3
260 +/- 1
8th
5
241 +/- 28
7th
4
233 +/- 4
4th
18
134 +/- 4
OpenBenchmarking.orgDistribution Of Public Results - Test / Class: EP.C2504 Results Range From 4 To 27693 Total Mop/s4558111216662220277433283882443649905544609866527206776083148868942299761053011084116381219212746133001385414408149621551616070166241717817732182861884019394199482050221056216102216422718232722382624380249342548826042265962715027704100200300400500

Based on OpenBenchmarking.org data, the selected test / test configuration (NAS Parallel Benchmarks 3.4 - Test / Class: EP.C) 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.

OpenBenchmarking.orgMinutesTime Required To Complete BenchmarkTest / Class: EP.CRun-Time3691215Min: 1 / Avg: 1.38 / Max: 10

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 1%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsTest / Class: EP.CDeviation3691215Min: 0 / Avg: 0.96 / Max: 7

Does It Scale Well With Increasing Cores?

Yes, based on the automated analysis of the collected public benchmark data, this test / test settings does generally scale well with increasing CPU core counts. Data based on publicly available results for this test / test settings, separated by vendor, result divided by the reference CPU clock speed, grouped by matching physical CPU core count, and normalized against the smallest core count tested from each vendor for each CPU having a sufficient number of test samples and statistically significant data.

AMDIntelOpenBenchmarking.orgRelative Core Scaling To BaseNAS Parallel Benchmarks CPU Core ScalingTest / Class: EP.C468101214162432485664961281020304050

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)
Loongson LoongArch 64-bit
loongarch64
Loongson-3A5000LL
Intel / AMD x86 32-bit
i686
(Many Processors)
ARMv8 64-bit
aarch64
ARMv8 16-Core, ARMv8 32-Core, ARMv8 64-Core, ARMv8 8-Core, ARMv8 Cortex-A53 4-Core, ARMv8 Cortex-A55 4-Core, ARMv8 Cortex-A57 4-Core, ARMv8 Cortex-A72, ARMv8 Cortex-A72 16-Core, ARMv8 Cortex-A72 4-Core, ARMv8 Cortex-A72 6-Core, ARMv8 Cortex-A72 8-Core, ARMv8 Cortex-A76 4-Core, ARMv8 Neoverse-N1, ARMv8 Neoverse-N1 4-Core, ARMv8 Neoverse-N1 64-Core, ARMv8 Neoverse-N1 80-Core, ARMv8 Neoverse-V1, ARMv8 Neoverse-V1 4-Core, ARMv8 Neoverse-V2, ARMv8 rev 0 8-Core, Ampere ARMv8 Neoverse-N1 160-Core, Ampere ARMv8 Neoverse-N1 256-Core, Ampere Altra ARMv8 Neoverse-N1 160-Core, Ampere eMAG ARMv8 32-Core, AmpereOne 192-Core, AmpereOne 72-Core, Apple M2

Recent Test Results

OpenBenchmarking.org Results Compare

Most Popular Test Results

OpenBenchmarking.org Results Compare

16 Systems - 119 Benchmark Results

Intel Xeon Gold 5220R - GIGABYTE MD61-SC2-00 v01000100 - Intel Sky Lake-E DMI3 Registers

Ubuntu 20.04 - 5.4.0-18-generic - GNOME Shell 3.36.0

3 Systems - 24 Benchmark Results

Intel Core i3-10100 - Gigabyte B460M DS3H - Intel Device 9b63

Ubuntu 20.04 - 5.9.0-050900rc7daily20201002-generic - GNOME Shell 3.36.3

3 Systems - 9 Benchmark Results

2 x Intel Xeon Platinum 8280 - GIGABYTE MD61-SC2-00 v01000100 - Intel Sky Lake-E DMI3 Registers

Ubuntu 19.04 - 5.3.0-999-generic - GNOME Shell 3.32.2

3 Systems - 34 Benchmark Results

AMD Ryzen 7 1700 Eight-Core - MSI B350 TOMAHAWK - AMD 17h

Ubuntu 20.10 - 5.11.0-rc1-phx - GNOME Shell 3.38.1

4 Systems - 30 Benchmark Results

Intel Core i7-10700T - Logic Supply RXM-181 - Intel Comet Lake PCH

Ubuntu 20.10 - 5.8.0-38-generic - GNOME Shell 3.38.1

16 Systems - 333 Benchmark Results

AMD Ryzen 7 5800X 8-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2

8 Systems - 439 Benchmark Results

Intel Core i5-11600K - ASUS ROG MAXIMUS XIII HERO - Intel Device 43ef

Ubuntu 21.04 - 5.12.0-051200rc3daily20210315-generic - GNOME Shell 3.38.3

3 Systems - 143 Benchmark Results

AMD EPYC 7742 64-Core - AMD DAYTONA_X - AMD Starship

Ubuntu 20.04 - 5.4.0-31-generic - GNOME Shell 3.36.1

3 Systems - 101 Benchmark Results

Intel Core i9-10980XE - ASRock X299 Steel Legend - Intel Sky Lake-E DMI3 Registers

Clear Linux OS 34530 - 5.10.31-1033.native - GNOME Shell 3.38.4

2 Systems - 59 Benchmark Results

AMD Ryzen 7 3700X 8-Core - MSI MEG X570 GODLIKE - AMD Device 1480

Clear Linux OS 31480 - 5.3.8-854.native - GNOME Shell 3.34.1

5 Systems - 62 Benchmark Results

Ampere Altra ARMv8 Neoverse-N1 - WIWYNN Mt.Jade - Ampere Computing LLC Device e100

Ubuntu 20.04 - 5.11.0-051100-generic-64k - GNOME Shell 3.36.4

3 Systems - 173 Benchmark Results

AMD Ryzen Threadripper 3970X 32-Core - 52GB - 2 x 275GB Virtual Disk

Ubuntu 20.04 - 4.19.104-microsoft-standard - X Server

3 Systems - 376 Benchmark Results

2 x AMD EPYC 7F72 24-Core - Supermicro H11DSi-NT v2.00 - AMD Starship

Ubuntu 20.10 - 5.10.9-051009-generic - GNOME Shell 3.38.1

Find More Test Results