oneDNN

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.

Project Site

github.com

Test Created

17 June 2020

Last Updated

20 December 2020

Test Maintainer

Michael Larabel

Test Type

Processor

Average Install Time

8 Minutes, 38 Seconds

Average Run Time

2 Minutes, 2 Seconds

Test Dependencies

C/C++ Compiler Toolchain + CMake

Accolades

5k+ Downloads

Supported Platforms

Public Result UploadsReported Installs*Test Completions*OpenBenchmarking.orgEventsoneDNN Popularity Statisticspts/onednn2020.062020.072020.082020.092020.102020.112020.122021.014K8K12K16K20K
* 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 Tue, 26 Jan 2021 07:06:13 GMT.
Deconvolution Batch shapes_3d11.4%Recurrent Neural Network Training15.9%IP Shapes 1D11.5%Convolution Batch Shapes Auto11.5%Matrix Multiply Batch Shapes Transformer11.3%Recurrent Neural Network Inference15.6%IP Shapes 3D11.5%Deconvolution Batch shapes_1d11.4%Harness Option PopularityOpenBenchmarking.org
bf16bf16bf1613.9%u8s8f3239.8%f3246.3%Data Type Option PopularityOpenBenchmarking.org

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.

Suites Using This Test

Multi-Core

Machine Learning

Intel oneAPI

CPU Massive

Server CPU Tests

Creator Workloads

HPC - High Performance Computing


Performance Metrics

Analyze Test Configuration:

oneDNN 1.5

Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU

OpenBenchmarking.org metrics for this test profile configuration based on 618 public results since 17 June 2020 with the latest data as of 13 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)
AMD Ryzen 9 5950X 16-Core
98th
11
161 +/- 1
Intel Core i9-10980XE
96th
19
168 +/- 11
AMD Ryzen 9 5900X 12-Core
92nd
18
181 +/- 5
AMD Ryzen Threadripper 3970X 32-Core
89th
5
192 +/- 1
AMD Ryzen Threadripper 3960X 24-Core
89th
7
192 +/- 9
2 x Intel Xeon Gold 6250
88th
4
197 +/- 11
AMD Ryzen 9 3950X 16-Core
87th
6
200 +/- 7
AMD Ryzen 7 5800X 8-Core
87th
8
203 +/- 3
Intel Core i7-7900X
87th
3
203 +/- 2
AMD Ryzen 9 3900X 12-Core
82nd
11
215 +/- 12
AMD EPYC 7F72 24-Core
80th
6
227 +/- 1
AMD EPYC 7F52 16-Core
78th
5
230
Mid-Tier
75th
> 233
AMD EPYC 7302P 16-Core
73rd
10
245 +/- 16
AMD Ryzen 7 3700X 8-Core
72nd
5
247 +/- 5
AMD EPYC 7542 32-Core
71st
4
251
AMD EPYC 7502P 32-Core
69th
10
255 +/- 11
AMD Ryzen 7 3800XT 8-Core
68th
7
257 +/- 8
AMD EPYC 7282 16-Core
68th
5
260
2 x Intel Xeon Gold 6138
66th
4
263 +/- 13
AMD EPYC 7402P 24-Core
66th
11
265 +/- 36
AMD EPYC 7452 32-Core
63rd
5
277
2 x Intel Xeon Gold 6230R
62nd
3
283 +/- 25
AMD Ryzen 5 5600X 6-Core
62nd
8
283 +/- 4
2 x Intel Xeon Silver 4214R
61st
4
289
AMD EPYC 7532 32-Core
60th
5
290
2 x Intel Xeon Platinum 8280
60th
8
300 +/- 40
AMD EPYC 7352 24-Core
59th
5
306
AMD EPYC 7642 48-Core
58th
5
309
2 x AMD EPYC 7252 8-Core
58th
5
309 +/- 2
2 x Intel Xeon Gold 6258R
57th
4
310 +/- 42
AMD Ryzen 5 3600X 6-Core
56th
5
314 +/- 6
2 x Intel Xeon Silver 4210R
56th
3
314 +/- 2
Intel Xeon Silver 4216
55th
7
319 +/- 8
Intel Xeon E-2288G
53rd
7
325 +/- 4
AMD Ryzen Threadripper 3990X 64-Core
52nd
3
326 +/- 3
2 x AMD EPYC 7F32 8-Core
51st
7
330 +/- 4
AMD EPYC 7552 48-Core
51st
5
330
Median
50th
330
2 x Intel Xeon Silver 4215R
47th
4
335 +/- 7
AMD EPYC 7272 12-Core
47th
3
335
2 x Intel Xeon Silver 4210
45th
3
344
2 x AMD EPYC 7272 12-Core
44th
3
346 +/- 2
2 x AMD EPYC 7282 16-Core
43rd
7
351 +/- 2
Intel Xeon Silver 4214R
42nd
4
353 +/- 4
AMD EPYC 7F32 8-Core
41st
5
355
AMD EPYC 7262 8-Core
39th
3
356
Intel Core i5-10600K
39th
14
365 +/- 49
AMD EPYC 7662 64-Core
35th
5
382
Intel Xeon Gold 5217
35th
9
385 +/- 3
2 x AMD EPYC 7F52 16-Core
35th
9
386 +/- 11
AMD EPYC 7252 8-Core
34th
3
393
2 x AMD EPYC 7262 8-Core
33rd
6
399 +/- 53
2 x AMD EPYC 7352 24-Core
33rd
4
435
2 x AMD EPYC 7402 24-Core
32nd
4
440
2 x AMD EPYC 7F72 24-Core
30th
5
443 +/- 6
AMD EPYC 7702 64-Core
30th
5
443
Intel Xeon Silver 4215R
28th
4
462
Intel Core i7-7700K
26th
3
482 +/- 3
AMD Ryzen 3 3100 4-Core
26th
6
486 +/- 19
Low-Tier
25th
> 491
Intel Xeon E3-1270 v5
24th
3
515 +/- 2
2 x AMD EPYC 7542 32-Core
23rd
5
529
Intel Xeon E3-1245 v5
21st
3
559 +/- 11
2 x AMD EPYC 7502 32-Core
20th
4
566
2 x AMD EPYC 7452 32-Core
20th
5
567
Intel Core i7-5775C
19th
4
569 +/- 30
Intel Xeon E3-1280 v5
18th
3
577 +/- 4
2 x AMD EPYC 7532 32-Core
18th
5
578
AMD Ryzen 7 2700 Eight-Core
16th
3
598 +/- 8
AMD Ryzen 5 4500U
16th
6
607 +/- 88
Intel Core i7-9700TE
16th
4
642 +/- 56
Intel Xeon E3-1260L v5
14th
3
693 +/- 1
AMD Ryzen 5 2600 Six-Core
13th
3
732 +/- 17
Intel Core i7-6700HQ
13th
3
746 +/- 23
Intel Core i5-7600K
12th
3
778
2 x AMD EPYC 7642 48-Core
11th
4
801
2 x AMD EPYC 7552 48-Core
10th
6
807 +/- 61
AMD Ryzen 3 1300X
9th
3
861 +/- 3
Intel Core i7-4960X
5th
3
1520 +/- 2
Intel Core i7-4558U
4th
3
1565 +/- 79
Intel Core i5-5300U
4th
3
1572 +/- 50
AMD Ryzen 3 3200U
2nd
3
2768 +/- 81
OpenBenchmarking.orgDistribution Of Public Results - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU618 Results Range From 147 To 124814 ms14726415135762910123126171511117605200992259325087275813007532569350633755740051425454503947533500275252155015575096000362497649916748569979724737496777461799558244984943874378993192425949199741399907102401104895107389109883112377114871117365119859122353124847130260390520650

Based on OpenBenchmarking.org data, the selected test / test configuration (oneDNN 1.5 - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU) has an average run-time of 3 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 BenchmarkHarness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPURun-Time48121620Min: 1 / Avg: 3.07 / Max: 14

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 RunsHarness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUDeviation3691215Min: 0 / Avg: 0.98 / Max: 9

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 BaseoneDNN CPU Core ScalingHarness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU468121620243248641.83.65.47.29

Recent Test Results

OpenBenchmarking.org Results Compare

13 Systems - 593 Benchmark Results

AMD Ryzen Threadripper PRO 3975WX 32-Cores - LENOVO 1046 - AMD Starship

Ubuntu 20.04 - 5.6.0-1036-oem - GNOME Shell 3.36.4

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

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

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

3 Systems - 178 Benchmark Results

AMD Ryzen 3 3100 4-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.10 - 5.8.0-29-generic - GNOME Shell 3.38.1

3 Systems - 178 Benchmark Results

AMD Ryzen 3 3100 4-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.10 - 5.8.0-29-generic - GNOME Shell 3.38.1

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

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

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

12 Systems - 224 Benchmark Results

AMD Ryzen 9 3900XT 12-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.04 - 5.9.0-050900-generic - GNOME Shell 3.36.4

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

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

Most Popular Test Results

OpenBenchmarking.org Results Compare

3 Systems - 268 Benchmark Results

Intel Core i5-2520M - HP 161C - Intel 2nd Generation Core DRAM

Ubuntu 18.04 - 4.18.0-20-generic - GNOME Shell 3.28.3

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

11 Systems - 217 Benchmark Results

Intel Core i5-10600K - Gigabyte Z490 AORUS MASTER - Intel Comet Lake PCH

Ubuntu 20.04 - 5.9.0-050900-generic - GNOME Shell 3.36.4

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

2 Systems - 403 Benchmark Results

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

Ubuntu 20.10 - 5.8.0-22-generic - GNOME Shell 3.38.0

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

5 Systems - 68 Benchmark Results

AMD Ryzen 9 3900X 12-Core - MSI MPG X570 GAMING PLUS - AMD Starship

Debian testing - 5.7.10-xanmod1 - X Server 1.20.8

3 Systems - 202 Benchmark Results

Intel Core i7-7700K - MSI Z270-A PRO - Intel Xeon E3-1200 v6

Ubuntu 20.04 - 5.9.0-050900rc8daily20201011-generic - GNOME Shell 3.36.4

3 Systems - 173 Benchmark Results

AMD Ryzen Threadripper 3970X 32-Core - 64GB - 931GB

Ubuntu 20.04 - 4.4.0-19041-Microsoft - GCC 9.3.0

12 Systems - 229 Benchmark Results

Intel Core i5-10600K - Gigabyte Z490 AORUS MASTER - Intel Comet Lake PCH

Ubuntu 20.04 - 5.9.0-050900-generic - GNOME Shell 3.36.4
Find More Test Results

OpenBenchmarking.org Community User Comments

Post A Comment