HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing.

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

Project Site

icl.utk.edu

Source Repository

github.com

Test Created

18 June 2023

Last Updated

27 October 2023

Test Maintainer

Michael Larabel 

Test Type

Processor

Average Install Time

42 Seconds

Average Run Time

1 Minute, 50 Seconds

Test Dependencies

C/C++ Compiler Toolchain + Fortran + OpenMPI + CMake + FFTW

Accolades

10k+ Downloads

Supported Platforms

Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page ViewsOpenBenchmarking.orgEventsHeFFTe - Highly Efficient FFT for Exascale Popularity Statisticspts/heffte2023.062023.072023.082023.092023.102023.112023.122024.012024.022024.032024.042024.052024.062024.072024.082024.092024.102024.112024.1210002000300040005000
* 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 23 December 2024.
c2c48.0%r2c52.0%Test Option PopularityOpenBenchmarking.org
Stock47.4%FFTW52.6%Backend Option PopularityOpenBenchmarking.org
double25.9%float28.6%double-long22.3%float-long23.1%Precision Option PopularityOpenBenchmarking.org
12833.7%25630.8%10247.1%51228.4%X Y Z Option PopularityOpenBenchmarking.org

Revision History

pts/heffte-1.1.0   [View Source]   Fri, 27 Oct 2023 15:16:02 GMT
Update against HeFFTe 2.4 upstream.

pts/heffte-1.0.0   [View Source]   Sun, 18 Jun 2023 09:51:50 GMT
Initial commit of HeFFTe benchmark.


Performance Metrics

Analyze Test Configuration:

HeFFTe - Highly Efficient FFT for Exascale 2.4

Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128

OpenBenchmarking.org metrics for this test profile configuration based on 115 public results since 27 October 2023 with the latest data as of 29 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
GFLOP/s (Average)
AMD EPYC 9575F 64-Core
98th
4
332 +/- 1
Intel Xeon Platinum 8480
97th
3
322 +/- 5
AMD EPYC 9655P 96-Core
93rd
3
252 +/- 1
2 x AMD EPYC 9684X 96-Core
90th
4
208 +/- 2
AMD Ryzen Threadripper 7970X 32-Cores
82nd
4
188 +/- 7
AMD EPYC 9334 32-Core
82nd
8
188 +/- 2
Mid-Tier
75th
< 185
Intel Core i9-14900K
74th
6
182 +/- 2
2 x Intel Xeon Platinum 8490H
68th
3
175 +/- 1
2 x Intel Xeon Max 9480
65th
4
158 +/- 6
AMD EPYC 4584PX 16-Core
59th
4
139
AMD Ryzen 9 7950X 16-Core
58th
3
136 +/- 1
Median
50th
128
AMD EPYC 4564P 16-Core
49th
5
127 +/- 1
Intel Core i5-14600K
48th
4
118 +/- 16
AMD EPYC 4484PX 12-Core
48th
4
114
AMD EPYC 4464P 12-Core
45th
3
108
AMD Ryzen Threadripper 3990X 64-Core
40th
3
92
AMD EPYC 7551 32-Core
35th
3
87
Intel Xeon E E-2488
31st
4
85
AMD EPYC 4364P 8-Core
28th
4
77 +/- 2
Low-Tier
25th
< 76
AMD EPYC 4344P 8-Core
23rd
3
76
AMD EPYC 4244P 6-Core
23rd
3
76
Intel Core i9-10980XE
21st
4
55
AMD EPYC 4124P 4-Core
16th
4
42 +/- 4
AMD Ryzen 7 7840U
13th
5
35 +/- 3
AMD Ryzen 7 PRO 6850U
11th
4
32
AMD Ryzen 9 5900HX
7th
4
17 +/- 1
Detailed Performance Overview
OpenBenchmarking.orgDistribution Of Public Results - Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128115 Results Range From 11 To 333 GFLOP/s1129476583101119137155173191209227245263281299317335510152025

Based on OpenBenchmarking.org data, the selected test / test configuration (HeFFTe - Highly Efficient FFT for Exascale 2.4 - Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128) 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: r2c - Backend: FFTW - Precision: float - X Y Z: 128Run-Time246810Min: 1 / Avg: 1 / Max: 1

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 1.7%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsTest: r2c - Backend: FFTW - Precision: float - X Y Z: 128Deviation3691215Min: 0 / Avg: 1.66 / Max: 9

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-3A6000

Recent Test Results

OpenBenchmarking.org Results Compare

73 Systems - 527 Benchmark Results

2 x Intel Xeon E5-2680 v4 - Intel S2600CW - Intel Xeon E7 v4

Arch Linux - 6.9.7-arch1-1 - GCC 14.1.1 20240522
Find More Test Results