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, 41 Seconds

Average Run Time

8 Minutes, 3 Seconds

Test Dependencies

C/C++ Compiler Toolchain

Accolades

100k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsFFTW Popularity Statisticspts/fftw2015.012015.042015.072015.102016.012016.042016.072016.102017.012017.042017.072017.102018.012018.042018.072018.102019.012019.042019.072019.102020.012020.042020.072020.102021.012021.045K10K15K20K25K
* 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 current as of 14 June 2021.
Float + SSE51.3%Stock48.7%Build Option PopularityOpenBenchmarking.org
2D FFT Size 3211.5%2D FFT Size 409641.0%1D FFT Size 3221.1%1D FFT Size 409626.4%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 1,117 public results since 16 August 2017 with the latest data as of 4 June 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
# Compatible Public Results
Mflops (Average)
99th
11
31453 +/- 477
99th
28
31266 +/- 836
98th
3
30894 +/- 562
97th
18
30668 +/- 2662
96th
9
30085 +/- 530
93rd
23
27470 +/- 1208
93rd
12
27355 +/- 1686
93rd
7
27120 +/- 1109
91st
3
26366 +/- 586
89th
16
24865 +/- 1852
89th
12
24498 +/- 1979
88th
8
24188 +/- 2629
87th
6
23759 +/- 1005
84th
4
22290 +/- 3181
82nd
4
21070 +/- 1668
82nd
8
20926 +/- 547
82nd
4
20881 +/- 1536
80th
5
20526 +/- 2273
80th
32
20477 +/- 1813
78th
6
19907 +/- 1868
76th
5
19319 +/- 2171
Mid-Tier
75th
< 19235
75th
3
19208 +/- 1178
75th
15
19113 +/- 1722
74th
14
18895 +/- 1080
73rd
3
18734 +/- 456
72nd
8
18484 +/- 557
71st
31
18327 +/- 1085
69th
3
18019 +/- 1352
66th
4
17830 +/- 1639
66th
6
17755 +/- 251
65th
3
17576 +/- 1101
64th
8
17492 +/- 633
63rd
3
17327 +/- 281
62nd
5
17221 +/- 570
61st
9
17161 +/- 1602
61st
3
17084 +/- 239
60th
19
17064 +/- 1138
60th
12
16961 +/- 1454
56th
7
16508 +/- 1296
54th
9
16224 +/- 1439
54th
3
16186 +/- 1323
Median
50th
15791
50th
7
15771 +/- 1353
50th
13
15761 +/- 1295
50th
5
15759 +/- 1279
50th
4
15703 +/- 621
50th
3
15698 +/- 952
49th
7
15622 +/- 1491
49th
18
15594 +/- 1013
49th
8
15496 +/- 1271
49th
4
15494 +/- 948
48th
6
15375 +/- 772
48th
7
15366 +/- 1024
47th
6
15311 +/- 872
47th
6
15286 +/- 787
45th
6
15142 +/- 1061
45th
6
15100 +/- 1205
44th
4
15039 +/- 1188
41st
5
14933 +/- 1601
40th
10
14858 +/- 1851
38th
5
14747 +/- 371
35th
3
14473 +/- 840
33rd
9
14371 +/- 290
33rd
7
14342 +/- 476
Low-Tier
25th
< 13240
25th
17
13107 +/- 313
25th
7
12997 +/- 1906
23rd
22
12849 +/- 520
23rd
3
12832 +/- 380
22nd
3
12719 +/- 1487
22nd
4
12710 +/- 999
20th
3
12344 +/- 492
20th
6
12245 +/- 334
17th
5
11362 +/- 1114
17th
3
11169 +/- 393
15th
5
10693 +/- 268
15th
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 40961117 Results Range From 95 To 32774 Mflops95749140320572711336540194673532759816635728979438597925199051055911213118671252113175138291448315137157911644517099177531840719061197152036921023216772233122985236392429324947256012625526909275632821728871295253017930833314873214132795306090120150

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 17 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-Time1428425670Min: 1 / Avg: 16.25 / Max: 74

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 RunsBuild: Float + SSE - Size: 2D FFT Size 4096Deviation246810Min: 0 / Avg: 0.96 / 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 4096468121620243248640.46880.93761.40641.87522.344

Recent Test Results

OpenBenchmarking.org Results Compare

8 Systems - 195 Benchmark Results

AMD EPYC - Hetzner vServer v20171111 - 1 x 8000 MB RAM QEMU

Debian 11 - 5.12.8-xanmod1 - GCC 10.2.1 20210110

7 Systems - 195 Benchmark Results

AMD EPYC - Hetzner vServer v20171111 - 1 x 8000 MB RAM QEMU

Debian 11 - 5.12.8-xanmod1-cacule - GCC 10.2.1 20210110

10 Systems - 16 Benchmark Results

Intel Core i3-3110M - LENOVO - Intel 3rd Gen Core DRAM

Calculate - 5.10.32-calculate - MATE 1.24.1

6 Systems - 195 Benchmark Results

AMD EPYC - Hetzner vServer v20171111 - 1 x 8000 MB RAM QEMU

Debian 10 - 4.19.0-16-amd64 - GCC 8.3.0

5 Systems - 195 Benchmark Results

AMD EPYC - Hetzner vServer v20171111 - 1 x 8000 MB RAM QEMU

Debian 11 - 5.12.8-051208-lowlatency - GCC 10.2.1 20210110

4 Systems - 195 Benchmark Results

AMD EPYC - Hetzner vServer v20171111 - 1 x 8000 MB RAM QEMU

Debian 10 - 4.19.0-16-amd64 - GCC 8.3.0

3 Systems - 195 Benchmark Results

AMD EPYC - Hetzner vServer v20171111 - 1 x 8000 MB RAM QEMU

Debian 10 - 4.19.0-16-amd64 - GCC 8.3.0

1 System - 38 Benchmark Results

2 x Intel Xeon E5-2630 v4 - Supermicro X10DRT-H v1.02 - Intel Xeon E7 v4

Debian 10 - 4.19.0-16-amd64 - GCC 8.3.0

2 Systems - 195 Benchmark Results

AMD EPYC - Hetzner vServer v20171111 - 1 x 8000 MB RAM QEMU

Debian 11 - 5.12.8-051208-generic - GCC 10.2.1 20210110

11 Systems - 454 Benchmark Results

AMD Ryzen 9 5900X 12-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

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

1 System - 32 Benchmark Results

2 x Intel Xeon E5-2630 0 - Supermicro X9DR3-F - Intel Xeon E5

Ubuntu 20.04 - 5.8.0-41-generic - X Server 1.20.9

1 System - 190 Benchmark Results

AMD EPYC - Hetzner vServer v20171111 - 1 x 8000 MB RAM QEMU

Debian 10 - 4.19.0-16-amd64 - GCC 8.3.0

Most Popular Test Results

OpenBenchmarking.org Results Compare

12 Systems - 593 Benchmark Results

AMD Ryzen 9 5900X 12-Core - ASRock X570 Taichi - AMD Starship

Fedora 33 - 5.8.16-300.fc33.x86_64 - GNOME Shell 3.38.1

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 - 301 Benchmark Results

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

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

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

3 Systems - 56 Benchmark Results

AMD Ryzen 3 2200G with Radeon Vega - Gigabyte AX370-Gaming 5 - AMD Device 15d0

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

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

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

2 Systems - 1708 Benchmark Results

Intel Core i3-10100 - ASUS PRIME Z490M-PLUS - Intel Comet Lake PCH

Ubuntu 20.04 - 5.7.0-rc6-amd-energy - GNOME Shell 3.36.2

Find More Test Results