Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test.

To run this test with the Phoronix Test Suite, the basic command is: phoronix-test-suite benchmark graph500.

Project Site

graph500.org

Source Repository

github.com

Test Created

28 January 2022

Last Updated

29 January 2022

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

5 Seconds

Average Run Time

34 Minutes, 37 Seconds

Test Dependencies

C/C++ Compiler Toolchain + OpenMPI

Accolades

5k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page ViewsOpenBenchmarking.orgEventsGraph500 Popularity Statisticspts/graph5002022.012022.022022.032022.042022.052022.062022.072022.082022.092022.102022.112022.122023.012023.022023.032023.042023.052023.062023.072023.082023.092023.102023.112023.122024.012024.022024.0313002600390052006500
* 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.
Data updated weekly as of 2 March 2024.

Revision History

pts/graph500-1.0.1   [View Source]   Sat, 29 Jan 2022 11:06:02 GMT
Add PROCS_PER_NODE_NOT_POWER_OF_TWO handling to detect otherwise the program fails to run for non power of 2 CPU core counts.

pts/graph500-1.0.0   [View Source]   Fri, 28 Jan 2022 07:16:09 GMT
Initial commit of Graph500, long overdue...

Suites Using This Test

HPC - High Performance Computing


Performance Metrics

Analyze Test Configuration:

Graph500 3.0

Scale: 26

OpenBenchmarking.org metrics for this test profile configuration based on 661 public results since 28 January 2022 with the latest data as of 4 March 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
sssp median_TEPS (Average)
100th
18
763451889 +/- 34156366
97th
15
617984000 +/- 28872974
95th
29
599056714 +/- 46353259
90th
18
496178611 +/- 34397377
89th
20
481322263 +/- 18716429
84th
13
407990154 +/- 11862849
84th
6
402644333 +/- 32217631
82nd
5
380707800 +/- 13023747
81st
14
377258214 +/- 2895847
79th
7
368908571 +/- 16402782
77th
13
357670692 +/- 7317443
Mid-Tier
75th
< 354905000
71st
23
330989739 +/- 18943171
71st
11
330394455 +/- 3859265
66th
15
311922533 +/- 15201224
65th
18
310018444 +/- 17767504
65th
41
308534756 +/- 31938642
52nd
8
283291375 +/- 16511699
52nd
6
281195500 +/- 4224695
Median
50th
275002000
49th
9
271577111 +/- 10299537
49th
24
270935875 +/- 29812973
47th
6
268589000 +/- 705467
46th
4
267899000 +/- 2808000
43rd
18
262063556 +/- 19210989
43rd
6
262060000 +/- 13799322
42nd
19
261698737 +/- 9967228
39th
4
254262750 +/- 17861973
38th
8
252618250 +/- 36842034
38th
15
250495533 +/- 10754330
38th
3
250443667 +/- 11430370
38th
3
248282000 +/- 11698271
34th
8
228313000 +/- 1739078
32nd
10
224132100 +/- 1708299
31st
4
223171500 +/- 12313149
30th
4
215074750 +/- 8443500
28th
11
209719455 +/- 10108181
26th
6
201369000 +/- 5456854
26th
4
200128250 +/- 8116420
Low-Tier
25th
< 197386000
25th
3
196539333 +/- 1466470
23rd
5
186677600 +/- 2220376
22nd
8
179964250 +/- 1300586
21st
4
176858000 +/- 974000
20th
3
166108000 +/- 14048664
18th
12
162940417 +/- 835504
18th
6
159731000 +/- 21038042
17th
3
157047667 +/- 3051296
17th
3
156510667 +/- 173117
13th
4
123755500 +/- 457839
11th
4
117185000 +/- 1572343
10th
3
113232000 +/- 1841170
9th
9
102174556 +/- 1284813
8th
3
96798067 +/- 1103602
7th
4
95091475 +/- 992340
7th
3
92662233 +/- 960570
6th
3
91456067 +/- 979949
6th
5
82937580 +/- 11461092
5th
4
77768400 +/- 4210385
3rd
4
61164150 +/- 4971920
2nd
4
50707825 +/- 239293
OpenBenchmarking.orgDistribution Of Public Results - Scale: 26650 Results Range From 43201700 To 805128000 sssp median_TEPS432017005844022673678752889172781041558041193943301346328561498713821651099081803484341955869602108254862260640122413025382565410642717795902870181163022566423174951683327336943479722203632107463784492723936877984089263244241648504394033764546419024698804284851189545003574805155960065308345325460730585613115845765501105917886366070271626222656886375042146527427406679812666832197926984583187136968447289353707441738967594124227746509487898894748051280001326395265

Based on OpenBenchmarking.org data, the selected test / test configuration (Graph500 3.0 - Scale: 26) has an average run-time of 18 minutes. By default this test profile is set to run at least 1 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 BenchmarkScale: 26Run-Time1122334455Min: 5 / Avg: 17.3 / Max: 56

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.

OpenBenchmarking.orgRelative Core Scaling To BaseGraph500 CPU Core ScalingScale: 26163264961282.064.126.188.2410.3

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.
 
MOVD SUBSD MOVAPD ADDSD MULSD CVTTSD2SI DIVSD MOVUPD DIVPD COMISD UCOMISD CVTSI2SD UNPCKLPD SUBPD MULPD UNPCKHPD SQRTSD CVTSS2SD MOVDQA PUNPCKLQDQ CVTSD2SS
Requires passing a supported compiler/build flag (verified with targets: sandybridge, skylake, tigerlake, cascadelake, sapphirerapids, alderlake, znver2, znver3).
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).

 
VINSERTF128 VZEROUPPER VEXTRACTF128 VBROADCASTSD VBROADCASTSS
Requires passing a supported compiler/build flag (verified with targets: skylake, tigerlake, cascadelake, sapphirerapids, alderlake, znver2, znver3).
Found on Intel processors since Haswell (2013).
Found on AMD processors since Excavator (2016).

 
VPBROADCASTQ VPERM2I128 VPERMQ VINSERTI128 VPBROADCASTD
FMA (FMA)
Requires passing a supported compiler/build flag (verified with targets: skylake, tigerlake, cascadelake, sapphirerapids, alderlake, znver2, znver3).
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).

 
VFMADD231SD VFMADD132SD
Advanced Vector Extensions 512 (AVX512)
Requires passing a supported compiler/build flag (verified with targets: cascadelake, sapphirerapids).
 
(ZMM REGISTER USE)
The test / benchmark does honor compiler flag changes.
Last automated analysis: 29 January 2022

This test profile binary relies on the shared libraries libm.so.6, libmpi.so.40, libc.so.6, libopen-rte.so.40, libopen-pal.so.40, libhwloc.so.15, libz.so.1, libudev.so.1.

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)
ARMv8 64-bit
aarch64
ARMv8 Neoverse-N1, ARMv8 Neoverse-N1 128-Core, ARMv8 Neoverse-N1 32-Core, ARMv8 Neoverse-V1, ARMv8 Neoverse-V2 72-Core, Ampere ARMv8 Neoverse-N1 128-Core, Ampere ARMv8 Neoverse-N1 160-Core, Ampere ARMv8 Neoverse-N1 256-Core

Recent Test Results

OpenBenchmarking.org Results Compare

6 Systems - 10 Benchmark Results

ARMv8 Neoverse-V2 - Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB - 1 x 480GB DRAM-6400MT

Ubuntu 22.04 - 6.5.0-1007-NVIDIA-64k - NVIDIA

1 System - 125 Benchmark Results

2 x INTEL XEON PLATINUM 8592+ - Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS - Intel Device 1bce

Ubuntu 23.10 - 6.5.0-17-generic - GCC 13.2.0

1 System - 1253 Benchmark Results

3 Systems - 39 Benchmark Results

AMD Ryzen Threadripper 7980X 64-Cores - ASUS Pro WS TRX50-SAGE WIFI - AMD Device 14a4

Ubuntu 23.10 - 6.5.0-9-generic - GNOME Shell 45.0

1 System - 650 Benchmark Results

1 System - 543 Benchmark Results

AMD Ryzen Threadripper PRO 5995WX 64-Cores - ASRock WRX80 Creator - AMD Starship

Ubuntu 22.04 - 6.2.0-33-generic - GNOME Shell 42.9

Find More Test Results