High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC.

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

Project Site

hpcg-benchmark.org

Source Repository

github.com

Test Created

26 December 2013

Last Updated

15 June 2023

Test Maintainer

Michael Larabel 

Test Type

Processor

Average Install Time

12 Seconds

Average Run Time

9 Hours, 6 Minutes, 7 Seconds

Test Dependencies

C/C++ Compiler Toolchain + Fortran + OpenMPI

Accolades

150k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsHigh Performance Conjugate Gradient Popularity Statisticspts/hpcg2013.122014.042014.082014.122015.042015.082015.122016.042016.082016.122017.042017.082017.122018.042018.082018.122019.042019.082019.122020.042020.082020.122021.042021.082021.122022.042022.082022.122023.042023.082023.122024.0413K26K39K52K65K
* 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 21 April 2024.
160 160 16014.3%192 192 1927.8%104 104 10450.5%144 144 14427.3%X Y Z Option PopularityOpenBenchmarking.org
6086.3%180013.7%RT Option PopularityOpenBenchmarking.org

Revision History

pts/hpcg-1.3.0   [View Source]   Thu, 15 Jun 2023 17:40:04 GMT
Update parameters.

pts/hpcg-1.2.1   [View Source]   Fri, 10 Jan 2020 19:09:20 GMT
Add --allow-run-as-root

pts/hpcg-1.2.0   [View Source]   Fri, 10 Jan 2020 19:07:59 GMT
Update against upstream HPCG 3.1.

pts/hpcg-1.1.1   [View Source]   Fri, 13 Oct 2017 17:29:18 GMT
Various cleanups

pts/hpcg-1.1.0   [View Source]   Sat, 12 Aug 2017 22:16:43 GMT
Rework, update to v3.0 upstream test

pts/hpcg-1.0.2   [View Source]   Mon, 03 Apr 2017 11:09:33 GMT
add -lstdc++ to LINKFLAGS

pts/hpcg-1.0.1   [View Source]   Thu, 25 Aug 2016 13:53:21 GMT
Update CFLAGS handling

pts/hpcg-1.0.0   [View Source]   Thu, 26 Dec 2013 00:43:12 GMT
Initial commit of HPCG - High Performance Conjugate Gradient test.

Suites Using This Test

Multi-Core

HPC - High Performance Computing

CPU Massive

MPI Benchmarks


Performance Metrics

Analyze Test Configuration:

High Performance Conjugate Gradient 3.1

OpenBenchmarking.org metrics for this test profile configuration based on 2,102 public results since 10 January 2020 with the latest data as of 24 April 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
GFLOP/s (Average)
99th
4
45.3 +/- 0.1
98th
9
44.9 +/- 0.4
97th
9
43.9 +/- 1.3
91st
9
38.5 +/- 0.5
91st
8
38.4 +/- 0.5
90th
42
38.0 +/- 0.3
87th
10
37.1 +/- 0.6
86th
5
36.9 +/- 0.2
86th
42
36.9 +/- 0.3
86th
6
36.8 +/- 0.4
85th
28
36.7 +/- 1.9
84th
7
36.6 +/- 1.1
82nd
5
35.2 +/- 0.2
82nd
37
34.7 +/- 4.2
82nd
3
34.5 +/- 1.0
82nd
4
34.4 +/- 0.3
81st
9
34.0 +/- 0.5
81st
4
33.7 +/- 0.9
81st
5
33.6 +/- 0.4
80th
6
33.3 +/- 0.3
79th
5
31.9 +/- 0.2
79th
11
31.6 +/- 1.3
79th
5
31.5 +/- 3.5
79th
4
31.2 +/- 0.8
78th
17
31.0 +/- 1.1
77th
26
29.7 +/- 4.3
77th
3
29.5 +/- 3.5
76th
3
28.6 +/- 0.4
Mid-Tier
75th
< 28.4
75th
5
28.0 +/- 2.2
69th
3
20.1 +/- 0.1
67th
3
19.7 +/- 1.3
63rd
18
19.1 +/- 0.1
62nd
6
18.9 +/- 0.5
62nd
20
18.9 +/- 1.6
62nd
4
18.8 +/- 0.1
62nd
22
18.8 +/- 1.2
62nd
10
18.4 +/- 1.8
61st
11
18.2 +/- 0.1
60th
10
17.9 +/- 0.2
60th
3
17.8 +/- 0.1
57th
11
17.4 +/- 0.1
55th
26
17.0 +/- 0.6
54th
16
16.7 +/- 0.8
54th
10
16.6 +/- 0.1
53rd
5
16.4 +/- 0.1
53rd
3
16.1 +/- 0.6
53rd
4
15.9 +/- 0.3
51st
14
15.3 +/- 0.5
51st
13
15.3 +/- 0.2
51st
8
15.2 +/- 0.1
Median
50th
15.2
50th
19
15.2 +/- 2.2
49th
8
14.8 +/- 0.1
49th
4
14.8 +/- 0.1
49th
6
14.4 +/- 1.2
47th
5
13.4 +/- 0.1
47th
5
13.3 +/- 0.3
46th
6
12.3 +/- 1.3
44th
3
11.4 +/- 1.4
41st
20
10.0 +/- 0.6
37th
11
9.0 +/- 0.1
36th
8
8.7 +/- 0.5
34th
5
8.2 +/- 1.0
33rd
10
8.1 +/- 0.9
33rd
15
8.1 +/- 0.1
32nd
16
7.8 +/- 0.2
32nd
5
7.6 +/- 0.7
31st
18
7.5 +/- 0.8
27th
3
5.9
26th
5
5.8 +/- 0.6
Low-Tier
25th
< 5.5
25th
5
5.4 +/- 0.2
24th
22
5.2 +/- 0.2
20th
26
4.9 +/- 0.1
19th
17
4.7 +/- 0.4
18th
8
4.7 +/- 0.6
18th
43
4.6 +/- 0.7
16th
5
4.5 +/- 0.1
16th
8
4.4 +/- 0.3
16th
14
4.4 +/- 0.4
14th
5
4.3 +/- 0.4
13th
4
4.2 +/- 0.1
12th
5
4.2 +/- 0.4
11th
10
4.0 +/- 0.1
10th
6
3.9 +/- 0.6
9th
5
3.7 +/- 0.1
8th
4
3.3 +/- 0.1
8th
4
3.3 +/- 0.1
7th
3
3.0 +/- 0.3
5th
3
2.5 +/- 0.1
OpenBenchmarking.orgDistribution Of Public Results2102 Results Range From 0 To 102 GFLOP/s918273645546372819099108160320480640800

Based on OpenBenchmarking.org data, the selected test / test configuration (High Performance Conjugate Gradient 3.1) has an average run-time of 10 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 BenchmarkRun-Time714212835Min: 5 / Avg: 10.09 / Max: 33

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.2%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsDeviation246810Min: 0 / Avg: 0.17 / Max: 5

Does It Scale Well With Increasing Cores?

No, based on the automated analysis of the collected public benchmark data, this test / test settings does not 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.

IntelAMDOpenBenchmarking.orgRelative Core Scaling To BaseHigh Performance Conjugate Gradient CPU Core Scaling468101216243248641283691215

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)
IBM POWER (PowerPC) 64-bit
ppc64le
POWER9 4-Core, POWER9 44-Core, POWER9 8-Core
Loongson LoongArch 64-bit
loongarch64
Loongson-3A5000
ARMv8 64-bit
aarch64
ARMv8, ARMv8 Cortex-A72, ARMv8 Cortex-A72 16-Core, ARMv8 Neoverse-N1, ARMv8 Neoverse-N1 32-Core, ARMv8 Neoverse-N1 64-Core, ARMv8 Neoverse-N1 80-Core, ARMv8 Neoverse-V1, ARMv8 rev 0 8-Core, Ampere ARMv8 Neoverse-N1 128-Core, Ampere ARMv8 Neoverse-N1 160-Core, Ampere ARMv8 Neoverse-N1 256-Core, Ampere Altra ARMv8 Neoverse-N1 160-Core, Ampere Altra ARMv8 Neoverse-N1 64-Core, Ampere Altra ARMv8 Neoverse-N1 80-Core, Apple M2

Recent Test Results

OpenBenchmarking.org Results Compare

20 Systems - 119 Benchmark Results

AMD EPYC 7K83 64-Core - Supermicro H12SSL-i v1.01 - AMD Starship

Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1

19 Systems - 119 Benchmark Results

2 x AMD EPYC 7V13 64-Core - Supermicro H12DSi-N6 v1.02 - AMD Starship

Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1

18 Systems - 119 Benchmark Results

AMD EPYC 7K83 64-Core - Supermicro H12SSL-i v1.01 - AMD Starship

Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1

17 Systems - 119 Benchmark Results

AMD EPYC 7R32 48-Core - Supermicro H11SSL-i v2.00 - AMD Starship

Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1

1 System - 157 Benchmark Results

AMD Ryzen 5 5600G - MSI B450M MORTAR MAX - AMD Renoir

NixOS 23.11 - 6.1.65 - GCC 12.3.0

1 System - 157 Benchmark Results

AMD Ryzen 5 5600G - MSI B450M MORTAR MAX - AMD Renoir

NixOS 23.11 - 6.1.65 - GCC 12.3.0

3 Systems - 72 Benchmark Results

ARMv8 Neoverse-N1 - Amazon EC2 c6g.4xlarge - Amazon Device 0200

Amazon Linux 2 - 5.10.109-104.500.amzn2.aarch64 - GCC 7.3.1 20180712

17 Systems - 119 Benchmark Results

AMD EPYC 7K83 64-Core - Supermicro H12SSL-i v1.01 - AMD Starship

Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1

Find More Test Results