oneDNN Benchmark - OpenBenchmarking.org

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative.

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

Revision History

pts/onednn-1.6.1 [View Source] Sun, 20 Dec 2020 09:58:16 GMT
This test profile builds and works fine on macOS so enable it (MacOSX).

pts/onednn-1.6.0 [View Source] Wed, 09 Dec 2020 13:47:31 GMT
Update against oneDNN 2.0 upstream.

pts/onednn-1.5.0 [View Source] Wed, 17 Jun 2020 16:26:39 GMT
Initial commit of oneDNN test profile based on Intel oneDNN 1.5, forked from existing mkl-dnn test profile that is named from MKL-DNN before it was renamed to DNNL and then oneDNN. So create new test profile to match Intel naming convention.

Performance Metrics

oneDNN 1.5

Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.org metrics for this test profile configuration based on 514 public results since 17 June 2020 with the latest data as of 8 December 2020.

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

ms (Average)

2 x Intel Xeon Gold 6258R

100th

0.4

2 x Intel Xeon Gold 6250

97th

0.4

2 x Intel Xeon Gold 6230R

97th

0.4

Intel Core i9-10980XE

94th

0.5

2 x Intel Xeon Gold 6138

88th

0.9

Intel Xeon Gold 5218

87th

1.0 ^{+/- 0.1}

2 x Intel Xeon Silver 4210R

86th

1.1

2 x Intel Xeon Silver 4215R

86th

1.1

2 x Intel Xeon Silver 4210

85th

1.2

Intel Xeon Silver 4216

84th

1.3

Intel Xeon Silver 4214R

82nd

1.5

Intel Core i7-7900X

82nd

1.5

Intel Xeon Gold 5217

80th

1.6

AMD Ryzen Threadripper 3970X 32-Core

79th

1.7

2 x AMD EPYC 7542 32-Core

78th

1.8

2 x AMD EPYC 7502 32-Core

77th

1.8

AMD EPYC 7662 64-Core

76th

1.8

Mid-Tier

75th

> 1.8

2 x AMD EPYC 7F72 24-Core

75th

1.9

2 x AMD EPYC 7532 32-Core

73rd

1.9

2 x AMD EPYC 7452 32-Core

72nd

1.9

Intel Xeon Silver 4215R

71st

2.0

AMD EPYC 7642 48-Core

71st

2.0

2 x AMD EPYC 7402 24-Core

69th

2.0

2 x AMD EPYC 7F52 16-Core

68th

2.0

AMD EPYC 7552 48-Core

66th

2.1

AMD EPYC 7542 32-Core

65th

2.1

AMD EPYC 7702 64-Core

64th

2.1

2 x AMD EPYC 7642 48-Core

63rd

2.1

AMD EPYC 7502 32-Core

62nd

2.2 ^{+/- 0.1}

AMD EPYC 7502P 32-Core

62nd

2.2

2 x AMD EPYC 7742 64-Core

60th

2.2 ^{+/- 0.1}

2 x AMD EPYC 7552 48-Core

58th

2.2 ^{+/- 0.1}

2 x AMD EPYC 7352 24-Core

58th

2.2

2 x AMD EPYC 7282 16-Core

56th

2.3

AMD EPYC 7452 32-Core

55th

2.4

AMD EPYC 7532 32-Core

54th

2.4

AMD Ryzen 9 5900X 12-Core

52nd

2.7 ^{+/- 0.1}

Median

50th

2.8

AMD Ryzen 9 5950X 16-Core

50th

2.8

AMD Ryzen 7 5800X 8-Core

47th

3.8 ^{+/- 0.1}

AMD Ryzen 9 3900X 12-Core

45th

4.1

AMD Ryzen Threadripper 3960X 24-Core

43rd

4.7

AMD Ryzen 5 5600X 6-Core

42nd

5.0 ^{+/- 0.1}

AMD EPYC 7F52 16-Core

39th

5.6

Intel Xeon E-2288G

38th

5.6

AMD EPYC 7272 12-Core

37th

5.8

AMD EPYC 7F72 24-Core

36th

5.8

Intel Core i5-10600K

34th

6.0

AMD Ryzen 7 3800XT 8-Core

31st

6.1 ^{+/- 0.2}

AMD EPYC 7302P 16-Core

31st

6.1 ^{+/- 0.1}

AMD EPYC 7402P 24-Core

31st

6.2 ^{+/- 0.2}

AMD EPYC 7282 16-Core

29th

6.3

AMD Ryzen 7 3700X 8-Core

28th

6.4 ^{+/- 0.3}

AMD EPYC 7352 24-Core

26th

7.2

Low-Tier

25th

> 7.2

AMD EPYC 7F32 8-Core

24th

8.0

2 x AMD EPYC 7272 12-Core

22nd

8.1 ^{+/- 0.1}

Intel Core i7-7700K

22nd

8.2

2 x AMD EPYC 7F32 8-Core

20th

8.2 ^{+/- 0.1}

2 x AMD EPYC 7262 8-Core

20th

8.3 ^{+/- 0.8}

AMD EPYC 7262 8-Core

19th

8.4

2 x AMD EPYC 7252 8-Core

17th

8.7

AMD EPYC 7232P 8-Core

15th

9.2 ^{+/- 0.5}

AMD Ryzen 5 4500U

14th

9.3 ^{+/- 0.4}

AMD EPYC 7252 8-Core

13th

9.6

Intel Xeon E3-1280 v5

12th

10.1 ^{+/- 0.2}

Intel Xeon E3-1245 v5

12th

10.3 ^{+/- 0.1}

Intel Core i5-7600K

10th

12.2

Intel Core i7-9700TE

8th

12.8 ^{+/- 0.1}

AMD Ryzen 7 2700 Eight-Core

8th

13.1 ^{+/- 0.3}

AMD Ryzen 7 1700 Eight-Core

7th

14.8 ^{+/- 2.2}

Intel Core i7-4960X

5th

19.3 ^{+/- 0.3}

Intel Core i7-4558U

3rd

28.7 ^{+/- 0.3}

AMD Ryzen 3 3200U

1st

53.8 ^{+/- 0.5}

Based on OpenBenchmarking.org data, the selected test / test configuration (oneDNN 1.5 - Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU) 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.

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 1.2%.

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.

multi-1 1 System - 189 Benchmark Results	Intel Core i7-4790K - ASRock Z97 Pro4 - Intel 4th Gen Core DRAM Arch rolling - 5.9.10-arch1-1 - Xfce 4.14
f33-machine-learning 1 System - 41 Benchmark Results	Intel Core i7-6700 - ASUS Z170I PRO GAMING - Intel Xeon E3-1200 v5 Fedora 33 - 5.8.16-300.fc33.x86_64 - Cinnamon 4.6.7
Ryzen 9 5900X 3 Systems - 218 Benchmark Results	AMD Ryzen 9 5900X 12-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship Ubuntu 20.10 - 5.8.0-29-generic - GNOME Shell 3.38.1
Arch rolling Performance 1 System - 73 Benchmark Results	Intel Core i7-4700HQ - ASUS G750JX v1.0 - Intel Xeon E3-1200 v3 Arch rolling - 5.9.8-arch1-1 - X Server 1.20.9
AWSU20-Multicore 1 System - 214 Benchmark Results	Intel Xeon Platinum 8275CL - Amazon EC2 c5.2xlarge - Intel 440FX 82441FX PMC Ubuntu 20.04 - 5.4.0-1029-aws - GCC 9.3.0
590xx complessive 12 Systems - 383 Benchmark Results	AMD Ryzen 9 5900X 12-Core - Gigabyte B550I AORUS PRO AX - AMD Starship Ubuntu 20.04 - 5.4.0-53-generic - GNOME Shell 3.36.4
EPYC vs. Xeon Benchmarks On Ubuntu 20.10 19 Systems - 176 Benchmark Results	AMD EPYC 7502P 32-Core - ASRockRack EPYCD8 - AMD Starship Ubuntu 20.10 - 5.8.0-21-generic - GNOME Shell 3.38.0
Ryzen 9 3900XT Ubuntu 20.10 Linux 1 System - 201 Benchmark Results	AMD Ryzen 9 3900XT 12-Core - MSI MEG X570 GODLIKE - AMD Starship Ubuntu 20.10 - 5.8.0-21-generic - GNOME Shell 3.38.0
amd-ryzen-9-5900x-on-linux-ubuntu-2010 7 Systems - 349 Benchmark Results	AMD Ryzen 5 5600X 6-Core - ASRock X570 Pro4 - AMD Starship Ubuntu 20.10 - 5.8.0-26-generic - GNOME Shell 3.38.1
amd-ryzen-9-5900x-on-linux-ubuntu-2010 6 Systems - 349 Benchmark Results	AMD Ryzen 9 5900X 12-Core - ASRock X570 Pro4 - AMD Starship Ubuntu 20.10 - 5.8.0-26-generic - GNOME Shell 3.38.1
5950X Extra Featured Processor Comparison	AMD Ryzen 9 5950X 16-Core - AMD Ryzen 7 5800X 8-Core
AMD Ryzen 9 5900X On Linux Ubuntu 20.10 1 System - 282 Benchmark Results	AMD Ryzen 9 5900X 12-Core - ASRock X570 Pro4 - AMD Starship Ubuntu 20.10 - 5.8.0-26-generic - GNOME Shell 3.38.1

Core i9 Clear Linux Benchmarks 6 Systems - 136 Benchmark Results	Intel Core i9-10980XE - ASRock X299 Steel Legend - Intel Sky Lake-E DMI3 Registers Clear Linux OS 33540 - 5.7.10-972.native - GNOME Shell 3.36.4
Core i9 10900K - Ubuntu 20.04 LTS vs. Ubuntu 20.10 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
Ryzen 9 3900XT Ubuntu 20.04 LTS vs. Ubuntu 20.10 3 Systems - 406 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
Ryzen 7 1700 Summer Featured Kernel Comparison	AMD Ryzen 7 1700 Eight-Core - MSI B350 TOMAHAWK - AMD 17h Ubuntu 19.10 - 5.8.3-050803-generic - GNOME Shell 3.34.1
7700K Intel 2020 3 Systems - 202 Benchmark Results	Intel Core i7-7700K - MSI Z270-A PRO - Intel Xeon E3-1200 v6 Ubuntu 20.04 - 5.4.0-28-generic - GNOME Shell 3.36.1
Threadripper 3970X Ubuntu 20.04 LTS vs. Windows WSL/WSL2 3 Systems - 173 Benchmark Results	AMD Ryzen Threadripper 3970X 32-Core - ASUS ROG ZENITH II EXTREME - AMD Starship Ubuntu 20.04 - 5.4.0-37-generic - GNOME Shell 3.36.2
Intel Xeon On Ubuntu 20.10 Featured Processor Comparison	Intel Xeon Silver 4215R - Supermicro X11SPL-F v1.02 - Intel Sky Lake-E DMI3 Registers Ubuntu 20.10 - 5.8.0-20-generic - GNOME Shell 3.38.0
AMD Ryzen 9 3900X 6 Systems - 733 Benchmark Results	AMD Ryzen 5 3600X 6-Core - MSI X470 GAMING M7 AC - AMD Starship Ubuntu 20.04 - 5.8.0-050800daily20200622-generic - GNOME Shell 3.36.2
Xeon E3 1280 v5 Featured Kernel Comparison	Intel Xeon E3-1280 v5 - MSI Z170A SLI PLUS - Intel Xeon E3-1200 v5 Ubuntu 20.04 - 5.8.3-050803-generic - GNOME Shell 3.36.4
Core i5 10600K vs. Core i5 7600K vs. Core i5 4670 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
Xeon E3-1245 v5 Ubuntu Linux 5.4 3 Systems - 138 Benchmark Results	Intel Xeon E3-1245 v5 - MSI C236A WORKSTATION - Intel Xeon E3-1200 v5 Ubuntu 20.04 - 5.8.13-050813-generic - GNOME Shell 3.36.2
Ubuntu 20.10 Devel 5 Systems - 158 Benchmark Results	Intel Core i9-10980XE - ASRock X299 Steel Legend - Intel Sky Lake-E DMI3 Registers openSUSE Tumbleweed 20200929 - 5.8.10-1-default - KDE Plasma 5.19.5

oneDNN

Project Site

Test Created

Last Updated

Test Maintainer

Test Type

Average Install Time

Average Run Time

Test Dependencies

Accolades

Supported Platforms

Revision History

Suites Using This Test

Performance Metrics

oneDNN 1.5

Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU

Does It Scale Well With Increasing Cores?

Recent Test Results

Most Popular Test Results

User Comments