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, 59 Seconds

Average Run Time

2 Minutes, 2 Seconds

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 Fri, 22 Jan 2021 18:34:28 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 Inference15.7%IP Shapes 3D11.5%Deconvolution Batch shapes_1d11.4%Harness Option PopularityOpenBenchmarking.org
bf16bf16bf1614.0%u8s8f3240.1%f3245.8%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: IP Batch All - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.org metrics for this test profile configuration based on 505 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)
Mid-Tier
75th
> 11
Median
50th
17
27th
10
28 +/- 1
Low-Tier
25th
> 34
16th
11
46 +/- 5
11th
3
59 +/- 2
1st
3
374 +/- 8
OpenBenchmarking.orgDistribution Of Public Results - Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU505 Results Range From 4 To 3201 ms46813219626032438845251658064470877283690096410281092115612201284134814121476154016041668173217961860192419882052211621802244230823722436250025642628269227562820288429483012307631403204100200300400500

Based on OpenBenchmarking.org data, the selected test / test configuration (oneDNN 1.5 - Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU) has an average run-time of 4 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: IP Batch All - Data Type: u8s8f32 - Engine: CPURun-Time3691215Min: 1 / Avg: 3.1 / Max: 10

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.5%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsHarness: IP Batch All - Data Type: u8s8f32 - Engine: CPUDeviation3691215Min: 0 / Avg: 0.54 / Max: 12

Recent Test Results

OpenBenchmarking.org Results Compare

3 Systems - 74 Benchmark Results

2 x AMD EPYC 7601 32-Core - Dell 02MJ3T - AMD 17h

Ubuntu 19.10 - 5.9.0-050900rc6daily20200922-generic - GNOME Shell 3.34.1

2 Systems - 129 Benchmark Results

AMD Ryzen 9 5950X 16-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 20.10 - 5.11.0-051100rc2daily20210108-generic - GNOME Shell 3.38.1

3 Systems - 191 Benchmark Results

AMD Ryzen 3 2200G - ASUS PRIME B350M-E - AMD Raven

Ubuntu 20.10 - 5.8.0-38-generic - GNOME Shell 3.38.1

4 Systems - 104 Benchmark Results

AMD Ryzen 5 2400G - MSI B350M GAMING PRO - AMD Raven

Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1

4 Systems - 61 Benchmark Results

Intel Core i9-7960X - MSI X299 SLI PLUS - Intel Sky Lake-E DMI3 Registers

Ubuntu 20.04 - 5.4.0-58-generic - X Server 1.20.8

3 Systems - 113 Benchmark Results

Intel Core i9-7980XE - ASUS PRIME X299-A - Intel Sky Lake-E DMI3 Registers

Ubuntu 20.10 - 5.8.0-36-generic - GNOME Shell 3.38.1

3 Systems - 253 Benchmark Results

Intel Core i9-10885H - HP 8736 - Intel Comet Lake PCH

Ubuntu 20.04 - 5.6.0-1034-oem - GNOME Shell 3.36.4

4 Systems - 210 Benchmark Results

POWER9 - PowerNV T2P9D01 REV 1.01 - 64GB

Ubuntu 20.10 - 5.9.10-050910-generic - X Server

1 System - 219 Benchmark Results

AMD EPYC 7302P 16-Core - Supermicro H11SSL-i v2.00 - AMD Starship

Ubuntu 20.04 - 5.4.0-42-generic - GNOME Shell 3.36.4

2 Systems - 183 Benchmark Results

AMD FX-8370 Eight-Core - MSI 970 GAMING - AMD RD9x0

Ubuntu 20.10 - 5.8.0-33-generic - GNOME Shell 3.38.1

Most Popular Test Results

Find More Test Results

OpenBenchmarking.org Community User Comments

Post A Comment