FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions.

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

Project Site

fftw.org

Test Created

22 January 2015

Last Updated

16 August 2017

Test Maintainer

Michael Larabel 

Test Type

Processor

Average Install Time

2 Minutes, 42 Seconds

Average Run Time

8 Minutes, 3 Seconds

Test Dependencies

C/C++ Compiler Toolchain

Accolades

100k+ Downloads

Supported Platforms


Public Result UploadsReported Installs*Test Completions*OpenBenchmarking.orgEventsFFTW Popularity Statisticspts/fftw2015.012015.032015.052015.072015.092015.112016.012016.032016.052016.072016.092016.112017.012017.032017.052017.072017.092017.112018.012018.032018.052018.072018.092018.112019.012019.032019.052019.072019.092019.112020.012020.032020.052020.072020.092020.112021.012021.035K10K15K20K25K
* 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 current as of Thu, 04 Mar 2021 11:19:51 GMT.
Float + SSE51.1%Stock48.9%Build Option PopularityOpenBenchmarking.org
2D FFT Size 3211.8%2D FFT Size 409640.9%1D FFT Size 3221.8%1D FFT Size 409625.5%Size Option PopularityOpenBenchmarking.org

Revision History

pts/fftw-1.2.0   [View Source]   Wed, 16 Aug 2017 10:29:55 GMT
Update against fftw 3.3.6, add AVX2/AVX512 enables

pts/fftw-1.1.0   [View Source]   Sat, 24 Jan 2015 12:28:44 GMT
Switch to using Mflops as a scale.

pts/fftw-1.0.0   [View Source]   Thu, 22 Jan 2015 11:35:11 GMT
Initial commit of fftw.

Suites Using This Test

C/C++ Compiler Tests

CPU Massive

Scientific Computing

HPC - High Performance Computing


Performance Metrics

Analyze Test Configuration:

FFTW 3.3.6

Build: Float + SSE - Size: 2D FFT Size 4096

OpenBenchmarking.org metrics for this test profile configuration based on 1,045 public results since 16 August 2017 with the latest data as of 19 February 2021.

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
# Matching Public Results
Mflops (Average)
99th
22
31304 +/- 794
99th
7
31171 +/- 353
98th
5
29965 +/- 723
95th
19
27395 +/- 1119
95th
7
27120 +/- 1109
94th
3
26366 +/- 586
93rd
16
24865 +/- 1852
92nd
9
24230 +/- 2250
92nd
8
24188 +/- 2629
88th
4
22290 +/- 3181
86th
4
21070 +/- 1668
86th
8
20926 +/- 547
86th
4
20881 +/- 1536
84th
5
20526 +/- 2273
84th
32
20477 +/- 1813
82nd
6
19907 +/- 1868
80th
5
19319 +/- 2171
79th
3
19208 +/- 1178
79th
15
19113 +/- 1722
77th
14
18895 +/- 1080
77th
3
18734 +/- 456
76th
8
18484 +/- 557
Mid-Tier
75th
< 18460
74th
31
18327 +/- 1085
72nd
3
18019 +/- 1352
70th
4
17830 +/- 1639
69th
6
17755 +/- 251
68th
3
17576 +/- 1101
67th
8
17492 +/- 633
66th
3
17327 +/- 281
65th
5
17221 +/- 570
64th
9
17161 +/- 1602
64th
3
17084 +/- 239
64th
19
17064 +/- 1138
60th
10
16733 +/- 1472
59th
7
16508 +/- 1296
57th
9
16224 +/- 1439
56th
3
16186 +/- 1323
53rd
7
15779 +/- 1356
53rd
7
15771 +/- 1353
53rd
13
15761 +/- 1295
53rd
5
15759 +/- 1279
52nd
4
15703 +/- 621
52nd
3
15698 +/- 952
51st
7
15622 +/- 1491
51st
18
15594 +/- 1013
51st
8
15496 +/- 1271
51st
4
15494 +/- 948
Median
50th
15389
50th
5
15386 +/- 836
50th
6
15375 +/- 772
50th
7
15366 +/- 1024
50th
6
15311 +/- 872
47th
6
15142 +/- 1061
47th
6
15100 +/- 1205
46th
4
15039 +/- 1188
43rd
5
14933 +/- 1601
40th
5
14747 +/- 371
36th
3
14473 +/- 840
35th
9
14371 +/- 290
35th
7
14342 +/- 476
26th
17
13107 +/- 313
Low-Tier
25th
< 13017
25th
7
12997 +/- 1906
24th
22
12849 +/- 520
24th
3
12832 +/- 380
23rd
3
12719 +/- 1487
23rd
4
12710 +/- 999
21st
3
12344 +/- 492
21st
6
12245 +/- 334
18th
5
11362 +/- 1114
18th
3
11169 +/- 393
16th
5
10693 +/- 268
16th
13
10636 +/- 148
13th
6
10016 +/- 352
12th
3
8666 +/- 143
9th
4
6188 +/- 88
8th
5
5192 +/- 387
7th
3
4810 +/- 106
5th
29
3558 +/- 23
OpenBenchmarking.orgDistribution Of Public Results - Build: Float + SSE - Size: 2D FFT Size 40961045 Results Range From 110 To 32774 Mflops11076414182072272633804034468853425996665073047958861292669920105741122811882125361319013844144981515215806164601711417768184221907619730203842103821692223462300023654243082496225616262702692427578282322888629540301943084831502321563281020406080100

Based on OpenBenchmarking.org data, the selected test / test configuration (FFTW 3.3.6 - Build: Float + SSE - Size: 2D FFT Size 4096) has an average run-time of 16 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 BenchmarkBuild: Float + SSE - Size: 2D FFT Size 4096Run-Time1326395265Min: 1 / Avg: 15.91 / Max: 65

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.9%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsBuild: Float + SSE - Size: 2D FFT Size 4096Deviation246810Min: 0 / Avg: 0.94 / Max: 6

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 BaseFFTW CPU Core ScalingBuild: Float + SSE - Size: 2D FFT Size 4096468121620243248640.450.91.351.82.25

Recent Test Results

OpenBenchmarking.org Results Compare

1 System - 8 Benchmark Results

8 x Intel Xeon E5-2440 0 - Intel 440BX - Intel 440BX

CentOS Stream 8 - 4.18.0-277.el8.x86_64 - GCC 8.4.1 20200928 + Clang 11.0.0

1 System - 8 Benchmark Results

8 x Intel Xeon E5-2440 0 - Intel 440BX - Intel 440BX

CentOS Stream 8 - 4.18.0-277.el8.x86_64 - GCC 8.4.1 20200928 + Clang 11.0.0

1 System - 4 Benchmark Results

8 x Intel Xeon E5-2440 0 - Intel 440BX - Intel 440BX

CentOS Stream 8 - 4.18.0-277.el8.x86_64 - GCC 8.4.1 20200928 + Clang 11.0.0

1 System - 7 Benchmark Results

8 x Intel Xeon E5-2440 0 - Intel 440BX - Intel 440BX

CentOS Stream 8 - 4.18.0-277.el8.x86_64 - GCC 8.4.1 20200928 + Clang 11.0.0

2 Systems - 119 Benchmark Results

AMD EPYC 7F52 16-Core - Supermicro Super Server 0123456789 - AMD [AMD] Starship

FreeBSD - 13.0-BETA1 - Clang 11.0.1

5 Systems - 131 Benchmark Results

AMD EPYC 7F52 16-Core - Supermicro Super Server 0123456789 - AMD [AMD] Starship

FreeBSD - 12.2-RELEASE - Clang 10.0.1

4 Systems - 131 Benchmark Results

Intel Core i7-10700T - Insyde CometLake TBD by OEM - Intel

FreeBSD - 12.2-RELEASE - Clang 10.0.1

3 Systems - 156 Benchmark Results

Intel Xeon E-2278GEL - Logic Supply RXM-181 TBD by OEM - Intel

FreeBSD - 12.2-RELEASE - Clang 10.0.1

2 Systems - 156 Benchmark Results

Intel Xeon E-2278GEL - Logic Supply RXM-181 TBD by OEM - Intel

FreeBSD - 13.0-BETA1 - Clang 11.0.1

5 Systems - 159 Benchmark Results

Intel Xeon E-2278GEL - Logic Supply RXM-181 TBD by OEM - Intel

FreeBSD - 12.2-RELEASE - Clang 10.0.1

4 Systems - 198 Benchmark Results

Intel Xeon E-2278GEL - Logic Supply RXM-181 TBD by OEM - Intel

FreeBSD - 12.2-RELEASE - Clang 10.0.1

1 System - 32 Benchmark Results

POWER9 - PowerNV C1P9S01 REV 1.01 - 64GB

VoidLinux rolling - 5.10.12_1 - Xfce 4.16

Most Popular Test Results

OpenBenchmarking.org Results Compare

12 Systems - 593 Benchmark Results

Intel Core i5-10600K - ASUS PRIME Z490M-PLUS - Intel Comet Lake PCH

Ubuntu 20.04 - 5.8.0-050800daily20200622-generic - GNOME Shell 3.36.2

3 Systems - 301 Benchmark Results

Intel Core i5-4670 - MSI B85M-P33 - Intel 4th Gen Core DRAM

Ubuntu 20.04 - 5.4.0-40-generic - GNOME Shell 3.36.3

1 System - 248 Benchmark Results

AMD Ryzen 9 3900X 12-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Device 1480

Ubuntu 18.04 - 5.2.0-999-generic - GNOME Shell 3.28.3

6 Systems - 1421 Benchmark Results

Unknown - Marvell Armada 3720 Board - 2048MB

Ubuntu 16.04 - 4.4.52-armada-17.06.2-g12feccb - GCC 5.4.0 20160609

3 Systems - 56 Benchmark Results

AMD Ryzen 5 2400G with Radeon Vega - Gigabyte AX370-Gaming 5 - AMD Device 15d0

Ubuntu 17.10 - 4.15.1-041501-generic - GNOME Shell 3.26.2

2 Systems - 123 Benchmark Results

Intel Core i7-8700K - ASUS TUF Z370-PLUS GAMING - Intel 8th Gen Core

Clear Linux OS 29920 - 5.1.9-781.native - GNOME Shell 3.32.2

1 System - 263 Benchmark Results

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

Ubuntu 18.04 - 5.2.0-999-generic - GNOME Shell 3.28.4

2 Systems - 403 Benchmark Results

Intel Core i9-10900K - Gigabyte Z490 AORUS MASTER - Intel Comet Lake PCH

Ubuntu 20.04 - 5.4.0-48-generic - GNOME Shell 3.36.4

1 System - 62 Benchmark Results

ICT Loongson-3A R3 - Unknown - AMD RS780 + SB7x0

Loongnix 1.0 - 3.10.84-16.fc21.loongson.mips64el - MATE 1.8.1

5 Systems - 77 Benchmark Results

AMD Ryzen Threadripper 1950X 16-Core - Gigabyte X399 AORUS Gaming 7 - AMD Device 1450

Ubuntu 17.04 - 4.13.0-999-generic - Unity 7.5.0

Find More Test Results