oneDNN MKL-DNN

This is a test of the Intel oneDNN (formerly DNNL / Deep Neural Network Library / MKL-DNN) 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.

The pts/mkl-dnn test profile has been succeeded by the pts/onednn test profile to match the naming convetion used by Intel following their renaming to oneDNN. Run pts/onednn test profile to use the latest version of Intel oneDNN benchmark.

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

Project Site

github.com

Test Created

16 April 2019

Last Updated

17 June 2020

Test Maintainer

Michael Larabel

Test Type

Processor

Average Install Time

3 Minutes, 29 Seconds

Average Run Time

8 Minutes, 21 Seconds

Test Dependencies

C/C++ Compiler Toolchain + CMake

Accolades

20k+ Downloads

Supported Platforms

* 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 31 July 2021.

Revision History

pts/mkl-dnn-1.3.1 [View Source] Wed, 17 Jun 2020 16:31:48 GMT
NOTICE: The pts/mkl-dnn test profile has been succeeded by the pts/onednn test profile to match the naming convetion used by Intel following their renaming to oneDNN. Run pts/onednn test profile to use the latest version of Intel oneDNN benchmark

pts/mkl-dnn-1.3.0 [View Source] Thu, 09 Apr 2020 18:14:05 GMT
Fix as did not mean to expose f16 option.

pts/mkl-dnn-1.2.0 [View Source] Thu, 09 Apr 2020 18:10:17 GMT
Update against oneDNN 1.3 sources.

pts/mkl-dnn-1.1.1 [View Source] Thu, 03 Oct 2019 19:35:40 GMT
Update data types.

pts/mkl-dnn-1.1.0 [View Source] Thu, 03 Oct 2019 16:09:23 GMT
Update against MKL-DNN DNNL 1.1.

pts/mkl-dnn-1.0.2 [View Source] Thu, 18 Apr 2019 20:44:30 GMT
Fixes per reported test argument reporting and setting of OMP env vars.

pts/mkl-dnn-1.0.1 [View Source] Wed, 17 Apr 2019 09:20:39 GMT
MKLDNN_ARCH_OPT_FLAGS="-O3 $CXXFLAGS"

pts/mkl-dnn-1.0.0 [View Source] Tue, 16 Apr 2019 20:44:47 GMT
Initial commit of Intel MKL-DNN benchdnn benchmark.

Performance Metrics

Analyze Test Configuration:

oneDNN MKL-DNN 1.3

Harness: Deconvolution Batch deconv_1d - Data Type: f32

OpenBenchmarking.org metrics for this test profile configuration based on 169 public results since 9 April 2020 with the latest data as of 13 July 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

ms (Average)

AMD Ryzen Threadripper 3970X 32-Core

95th

AMD Ryzen Threadripper 3990X 64-Core

92nd

AMD EPYC 7402P 24-Core

76th

Mid-Tier

75th

> 2

AMD EPYC 7F52 16-Core

73rd

AMD Ryzen 9 3950X 16-Core

69th

AMD Ryzen 9 5900X 12-Core

67th

Intel Core i9-10900K

58th

AMD Ryzen 7 5800X 8-Core

51st

Median

50th

AMD Ryzen 5 5600X 6-Core

41st

Intel Core i5-10600K

38th

AMD EPYC 7232P 8-Core

34th

Low-Tier

25th

> 8

Intel Core i3-10100

24th

Intel Core i7-6820HQ

13th

Based on OpenBenchmarking.org data, the selected test / test configuration (oneDNN MKL-DNN 1.3 - Harness: Deconvolution Batch deconv_1d - Data Type: f32) 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 0.8%.

Notable Instruction Set Usage

Notable instruction set extensions supported by this test, based on an automatic analysis by the Phoronix Test Suite / OpenBenchmarking.org analytics engine.

Instruction Set

Support

Instructions Detected

Advanced Vector Extensions (AVX)

Used by default on supported hardware.
Found on Intel processors since Sandy Bridge (2011).
Found on AMD processors since Bulldozer (2011).

VZEROUPPER VBROADCASTSS VEXTRACTF128 VINSERTF128 VMASKMOVPS VPERM2F128 VBROADCASTSD

Advanced Vector Extensions 2 (AVX2)

Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Excavator (2016).

VINSERTI128 VPBROADCASTQ VEXTRACTI128 VPBROADCASTD VPSRAVD VPMASKMOVQ VPSLLVD VPERM2I128 VPSRLVQ VPERMQ VPBLENDD VPSLLVQ

FMA (FMA)

Used by default on supported hardware.
Found on Intel processors since Haswell (2013).
Found on AMD processors since Bulldozer (2011).

VFMADD231SS VFMADD132SS VFMADD132PS VFMADD231PS VFMADD213PS VFMADD213SS VFNMSUB231SS VFNMADD132SS VFNMSUB132SS VFNMADD231SS VFNMADD231PS VFMSUB231SS VFMADD132PD VFMADD132SD VFNMADD213SS VFMADD231SD VFMADD231PD VFMADD213PD VFMSUB231SD VFNMSUB231PS VFNMADD132PS VFMSUB231PS

Last automated analysis: 10 May 2021

This test profile binary relies on the shared libraries libdnnl.so.1, libm.so.6, libgomp.so.1, libc.so.6, libpthread.so.0, libdl.so.2.

redhat144 3 Systems - 272 Benchmark Results	2 x AMD EPYC 7543 32-Core - HPE ProLiant DL385 Gen10 Plus v2 - AMD Starship Red Hat Enterprise Linux 7.9 - 3.10.0-1160.31.1.el7.x86_64 - GNOME Shell 3.28.3
testing-server-memory 1 System - 99 Benchmark Results	Intel Xeon E5-2697 v3 - ASUS SABERTOOTH X99 - Intel Xeon E7 v3 Slackware 14.2 x86_64 - 5.13.0 - KDE Plasma 5.22.2
testing-server-memory 1 System - 99 Benchmark Results	Intel Xeon E5-2697 v3 - ASUS SABERTOOTH X99 - Intel Xeon E7 v3 Slackware 14.2 x86_64 - 5.13.0 - KDE Plasma 5.22.2
redhat144 1 System - 272 Benchmark Results	2 x Intel Xeon E5-2697 v2 - HP ProLiant BL460c Gen8 - Intel Xeon E7 v2 RedHatEnterpriseServer 7.9 - 3.10.0-1160.25.1.el7.x86_64 - X Server 1.20.4
supermicro_0603 1 System - 56 Benchmark Results	2 x Intel Xeon E5-2640 v4 - Supermicro X10DRG-O+-CPU v1.00 - Intel Xeon E7 v4 Ubuntu 16.04 - 4.15.0-142-generic - X Server 1.19.6
mem_result 2 Systems - 58 Benchmark Results	2 x Intel Xeon Silver 4214 - GIGABYTE MR91-FS0-A1 v01000100 - Intel Sky Lake-E DMI3 Registers Ubuntu 16.04 - 4.4.0-131-generic - GCC 5.4.0 20160609
2021-05-31-1212 1 System - 10 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
server-memory-20210506 1 System - 57 Benchmark Results	AMD EPYC 7402P 24-Core - GIGABYTE MZ22-G20-00 v01000100 - AMD Device 1480 Ubuntu 16.04 - 4.15.0-142-generic - Unity 7.4.5
server-memory-ubuntu-0529 1 System - 58 Benchmark Results	AMD EPYC 7402P 24-Core - GIGABYTE MZ22-G20-00 v01000100 - AMD Device 1480 Ubuntu 16.04 - 4.15.0-142-generic - Unity 7.4.5
Xeon & EPYC Tests 13 Systems - 119 Benchmark Results	Intel Xeon Platinum 8280 - GIGABYTE MD61-SC2-00 v01000100 - Intel Sky Lake-E DMI3 Registers Ubuntu 20.04 - 5.4.0-18-generic - GNOME Shell 3.36.0
Xeon & EPYC Tests 13 Systems - 119 Benchmark Results	AMD EPYC 7R32 48-Core - Supermicro H11SSL-i v2.00 - AMD Starship Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1
Xeon & EPYC Tests 13 Systems - 119 Benchmark Results	2 x Intel Xeon Platinum 8375C - Supermicro X12DPi-N6 v1.00 - Intel Device 0998 Ubuntu 19.10 - 5.3.0-64-generic - GNOME Shell 3.34.1

Core i9 10900K vs. Ryzen 9 3900X/3950X Linux Benchmarks Featured Processor Comparison	AMD Ryzen 9 3950X 16-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship Ubuntu 20.04 - 5.7.0-999-generic - GNOME Shell 3.36.1
Pop OS 20.04 vs. Ubuntu 20.04 Benchmarks 2 Systems - 269 Benchmark Results	AMD Ryzen Threadripper 3990X 64-Core - System76 Thelio Major - AMD Starship Ubuntu 20.04 - 5.4.0-29-generic - GNOME Shell 3.36.1
Intel Core i3 10100 vs. AMD Ryzen 3 3300X Benchmarks 2 Systems - 1708 Benchmark Results	AMD Ryzen 3 3300X 4-Core - ASRock X570 Pro4 - AMD Starship Ubuntu 20.04 - 5.7.0-rc6-amd-energy - GNOME Shell 3.36.2
Spring 2020 Linux Distros On Ryzen Threadripper 3970X 8 Systems - 246 Benchmark Results	AMD Ryzen Threadripper 3970X 32-Core - ASUS ROG ZENITH II EXTREME - AMD Starship openSUSE Tumbleweed 20200422 - 5.6.4-1-default - KDE Plasma 5.18.4
i5 11600k 4 Systems - 179 Benchmark Results	Intel Core i5-11600K - ASUS ROG MAXIMUS XIII HERO - Intel Device 43ef Ubuntu 20.04 - 5.10.13-051013-lowlatency - GNOME Shell 3.36.4
Dell Latitude E5470 (1.22.3 BIOS) On Fedora 33 1 System - 3 Benchmark Results	Intel Core i7-6820HQ - Dell Latitude E5470 - Intel Xeon E3-1200 v5 Fedora 33 - 5.8.14-300.fc33.x86_64 - GNOME Shell 3.38.1
5900x processor suite 2 Systems - 154 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
2020-12-25-1510 1 System - 10 Benchmark Results	2 x Intel Xeon E5-2680 v2 - Supermicro X9DRW v0123456789 - Intel Xeon E7 v2 Peppermint 10 - 5.0.0-37-generic - LXDE
Fedora 33 Benchmarks Featured OpenGL Comparison	Intel Core i7-6820HQ - Dell Latitude E5470 - Intel Xeon E3-1200 v5 Fedora 33 - 5.8.14-300.fc33.x86_64 - GNOME Shell 3.38.1
Intel Core i3 10100 vs. Core i5 10600K vs. AMD Ryzen 3 3300X Benchmarks 3 Systems - 777 Benchmark Results	AMD Ryzen 3 3300X 4-Core - ASRock X570 Pro4 - AMD Starship Ubuntu 20.04 - 5.7.0-rc6-amd-energy - GNOME Shell 3.36.2
Core i9 10900K vs. Ryzen 9 3900X/3950X Linux Benchmarks 5 Systems - 385 Benchmark Results	2 x Intel Xeon E5-2670 0 - Supermicro X9DRD-iF - Intel Xeon E5 Debian 10 - 4.19.0-9-amd64 - GCC 8.3.0
mem_result 2 Systems - 58 Benchmark Results	2 x Intel Xeon Silver 4214 - GIGABYTE MR91-FS0-A1 v01000100 - Intel Sky Lake-E DMI3 Registers Ubuntu 16.04 - 4.4.0-131-generic - GCC 5.4.0 20160609