ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo.

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

Project Site

onnxruntime.ai

Source Repository

github.com

Test Created

16 January 2021

Last Updated

30 March 2022

Test Maintainer

Michael Larabel

Test Type

System

Average Install Time

15 Minutes, 23 Seconds

Average Run Time

5 Minutes, 18 Seconds

Test Dependencies

Python + Git + C/C++ Compiler Toolchain + CMake

Accolades

10k+ 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 23 May 2022.

Revision History

pts/onnx-1.5.0 [View Source] Wed, 30 Mar 2022 14:24:29 GMT
Add standard/sequential and parallel executor option.

pts/onnx-1.4.0 [View Source] Sat, 26 Mar 2022 18:00:24 GMT
Update against ONNX 1.11 upstream, switch to parallel executor, add some new models too.

pts/onnx-1.3.0 [View Source] Fri, 03 Dec 2021 19:38:42 GMT
Update against upstream ONNX-Runtime 1.10.

pts/onnx-1.2.1 [View Source] Sat, 30 Oct 2021 05:02:16 GMT
Add cmake as necessary external dependency.

pts/onnx-1.2.0 [View Source] Fri, 29 Oct 2021 17:00:07 GMT
Update against ONNX 1.9.1 upstream. Changes based on https://github.com/phoronix-test-suite/phoronix-test-suite/pull/560 while also needing to adjust the XML options for removal of bertsquad. Closes: https://github.com/phoronix-test-suite/phoronix-test-suite/pull/560

pts/onnx-1.1.0 [View Source] Mon, 23 Aug 2021 19:03:17 GMT
Update against ONNX 1.8.2 upstream due to prior version now having build problems on newer distributions.

pts/onnx-1.0.1 [View Source] Sun, 17 Jan 2021 08:51:00 GMT
Increase run time limit to help lower deviation on laptops.

pts/onnx-1.0.0 [View Source] Sat, 16 Jan 2021 20:09:33 GMT
Initial commit of Microsoft ONNX Runtime.

Suites Using This Test

Machine Learning

HPC - High Performance Computing

Performance Metrics

Analyze Test Configuration:

ONNX Runtime 1.11

Model: GPT-2 - Device: CPU - Executor: Standard

OpenBenchmarking.org metrics for this test profile configuration based on 209 public results since 30 March 2022 with the latest data as of 26 May 2022.

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

Inferences Per Minute (Average)

AMD EPYC 7373X 16-Core

99th

16995 ^{+/- 576}

2 x AMD EPYC 75F3 32-Core

91st

11777 ^{+/- 1404}

AMD EPYC 75F3 32-Core

89th

11139 ^{+/- 616}

Intel Core i9-12900K

84th

11077 ^{+/- 41}

AMD EPYC 7773X 64-Core

78th

10437 ^{+/- 1230}

2 x Intel Xeon Platinum 8380

76th

10196 ^{+/- 1178}

Mid-Tier

75th

< 10081

Intel Core i9-10980XE

68th

9187 ^{+/- 470}

AMD EPYC 7763 64-Core

65th

8608 ^{+/- 44}

AMD Ryzen 7 5800X3D 8-Core

64th

8355 ^{+/- 414}

AMD Ryzen 9 5900X 12-Core

55th

7571 ^{+/- 400}

Median

50th

7205

AMD Ryzen 9 5950X 16-Core

49th

7121 ^{+/- 351}

Intel Core i5-12400

49th

7092 ^{+/- 186}

Intel Xeon Silver 4216

48th

7025 ^{+/- 811}

AMD Ryzen 7 5800X 8-Core

45th

6839 ^{+/- 43}

Intel Core i7-1165G7

40th

6485 ^{+/- 105}

Intel Core i7-1185G7

38th

6379 ^{+/- 8}

AMD Ryzen 7 5700G

37th

6223 ^{+/- 279}

Intel Core i7-5960X

35th

5976 ^{+/- 565}

AMD Ryzen 7 3800XT 8-Core

31st

5577 ^{+/- 26}

2 x AMD EPYC 7763 64-Core

30th

5518 ^{+/- 249}

AMD Ryzen 9 5900HX

27th

5339 ^{+/- 41}

Low-Tier

25th

< 5285

AMD Ryzen 7 PRO 5850U

25th

5235 ^{+/- 57}

AMD EPYC 7F32 8-Core

22nd

4904 ^{+/- 266}

Ampere ARMv8 Neoverse-N1 256-Core

21st

4790 ^{+/- 641}

Intel Core i7-1065G7

17th

4497 ^{+/- 225}

Intel Core i7-10700T

14th

4318 ^{+/- 66}

AMD Ryzen 7 4700U

14th

4287 ^{+/- 24}

AMD Ryzen 5 4500U

10th

4037 ^{+/- 17}

Apple M1

9th

3980 ^{+/- 4}

Intel Core i7-8565U

6th

3334 ^{+/- 119}

AMD Ryzen 7 4800U

5th

2878 ^{+/- 12}

ARMv8 Cortex-A72 4-Core

2nd

520 ^{+/- 17}

Based on OpenBenchmarking.org data, the selected test / test configuration (ONNX Runtime 1.11 - Model: GPT-2 - Device: CPU - Executor: Standard) has an average run-time of 12 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 0.6%.

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

SSE2 (SSE2)

Used by default on supported hardware.

MOVDQA PUNPCKLQDQ MOVDQU CVTSI2SD DIVSD MOVAPD COMISD UNPCKLPD MULSD CVTTSD2SI ADDSD SUBSD MOVUPD MOVD PUNPCKHQDQ PSUBQ PSHUFD PSRLDQ UCOMISD CVTSS2SD PADDQ ANDPD CVTSD2SS DIVPD MULPD SUBPD PMULUDQ ADDPD SQRTSD CVTPS2PD MINPD MAXPD CVTTPD2DQ CVTDQ2PD CMPLTPD PSHUFLW MAXSD MINSD XORPD MOVLPD SQRTPD CVTTPS2DQ CVTDQ2PS ANDNPD ORPD CVTPD2PS CMPLESD UNPCKHPD CMPLEPD SHUFPD MOVHPD CVTPS2DQ

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).

VBROADCASTSD VINSERTF128 VZEROUPPER VBROADCASTSS VMASKMOVPS VEXTRACTF128 VZEROALL VPERM2F128 VPERMILPS

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).

VPBROADCASTD VPMASKMOVD VEXTRACTI128 VINSERTI128 VPERM2I128 VPERMD VPBROADCASTW VPERMQ VPBROADCASTQ VPMASKMOVQ VPBROADCASTB VPSLLVD VPSRAVD VPSRLVD VPSLLVQ VPSRLVQ VPERMPD VGATHERQPD VPGATHERDQ VPGATHERQQ

AVX Vector Neural Network Instructions (AVX-VNNI)

Used by default on supported hardware.

VPDPBUSDS

FMA (FMA)

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

VFMADD231PD VFMADD213PD VFMADD231PS VFMADD213PS VFMADD132SS VFMADD132PS VFMADD132SD VFMADD213SS VFMADD132PD VFNMADD231PD VFMADD231SS VFNMADD213PS VFNMADD132PS VFNMADD213SS VFNMADD132SS VFNMADD231PS VFNMADD132PD VFNMADD132SD VFMSUB132SS VFMSUB132SD VFMADD231SD VFMADD213SD VFNMADD213PD VFNMADD213SD VFNMADD231SS VFNMADD231SD

The test / benchmark does honor compiler flag changes.

Last automated analysis: 10 May 2021

This test profile binary relies on the shared libraries libonnxruntime.so.1.6.0, libdl.so.2, libpthread.so.0, libc.so.6, libgomp.so.1, libm.so.6.

Tested CPU Architectures

This benchmark has been successfully tested on the below mentioned architectures. The CPU architectures listed is where successful OpenBenchmarking.org result uploads occurred, namely for helping to determine if a given test is compatible with various alternative CPU architectures.

CPU Architecture

Kernel Identifier

Verified On

Intel / AMD x86 64-bit

x86_64

(Many Processors)

ARMv8 64-bit

aarch64

ARMv8 Cortex-A72, ARMv8 Cortex-A72 4-Core, ARMv8 Neoverse-N1, ARMv8 Neoverse-V1, Ampere ARMv8 Neoverse-N1 256-Core, Apple M1

Amazon EC2 Graviton3 Benchmark Comparison 5 Systems - 94 Benchmark Results	Intel Xeon Platinum 8375C - Amazon EC2 c6i.4xlarge - Intel 440FX 82441FX PMC Ubuntu 22.04 - 5.15.0-1004-aws - GCC 11.2.0
Amazon EC2 c7g.4xlarge Graviton3 Tests 3 Systems - 102 Benchmark Results	ARMv8 Cortex-A72 - Amazon EC2 a1.4xlarge - Amazon Device 0200 Ubuntu 22.04 - 5.15.0-1004-aws - GCC 11.2.0
Amazon EC2 c7g.4xlarge AWS Graviton3 3 Systems - 101 Benchmark Results	ARMv8 Neoverse-N1 - Amazon EC2 c6g.4xlarge - Amazon Device 0200 Ubuntu 22.04 - 5.15.0-1004-aws - GCC 11.2.0
Amazon EC2 c7g.4xlarge AWS Graviton3 2 Systems - 101 Benchmark Results	ARMv8 Neoverse-V1 - Amazon EC2 c7g.4xlarge - Amazon Device 0200 Ubuntu 22.04 - 5.15.0-1004-aws - GCC 11.2.0
Amazon EC2 c7g.4xlarge Graviton3 Tests 2 Systems - 102 Benchmark Results	ARMv8 Cortex-A72 - Amazon EC2 a1.4xlarge - Amazon Device 0200 Ubuntu 22.04 - 5.15.0-1004-aws - GCC 11.2.0
Amazon EC2 c7g.4xlarge Graviton3 1 System - 106 Benchmark Results	ARMv8 Neoverse-V1 - Amazon EC2 c7g.4xlarge - Amazon Device 0200 Ubuntu 22.04 - 5.15.0-1004-aws - GCC 11.2.0
whiskey may 3 Systems - 77 Benchmark Results	Intel Core i7-8565U - Dell 0KTW76 - Intel Cannon Point-LP Ubuntu 21.10 - 5.13.0-27-generic - GNOME Shell 40.5
Linux Servers RHEL 8.6 2 Systems - 203 Benchmark Results	2 x AMD EPYC 7773X 64-Core - AMD DAYTONA_X - AMD Starship Red Hat Enterprise Linux 8.6 - 4.18.0-372.9.1.el8.x86_64 - GNOME Shell 3.32.2
cyrixws 1 System - 12 Benchmark Results
AMD Ryzen 7 5800X3D Linux Benchmarks 4 Systems - 541 Benchmark Results	AMD Ryzen 7 5800X 8-Core - ASRock X570 Pro4 - AMD Starship Ubuntu 22.04 - 5.17.4-051704-generic - GNOME Shell 42.0
Clear Linux 36260 8 Systems - 126 Benchmark Results	2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998 Clear Linux OS 36260 - 5.17.4-1139.native - GNOME Shell 42.0
Clear Linux 36260 7 Systems - 126 Benchmark Results	2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998 CentOS Stream 9 - 5.14.0-85.el9.x86_64 - GNOME Shell 40.10
Clear Linux 36260 6 Systems - 125 Benchmark Results	2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998 Ubuntu 22.04 - 5.15.0-27-generic - GNOME Shell 42.0
AMD Ryzen 7 5800X3D Linux Benchmarks 3 Systems - 541 Benchmark Results	AMD Ryzen 7 5800X3D 8-Core - ASRock X570 Pro4 - AMD Starship Ubuntu 22.04 - 5.17.4-051704-generic - GNOME Shell 42.0
Clear Linux 36260 5 Systems - 183 Benchmark Results	2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998 AlmaLinux 8.5 - 4.18.0-348.23.1.el8_5.x86_64 - GNOME Shell 3.32.2

10980XE onednn onnx 4 Systems - 51 Benchmark Results	Intel Core i9-10980XE - ASRock X299 Steel Legend - Intel Sky Lake-E DMI3 Registers Ubuntu 22.04 - 5.15.0-17-generic - GNOME Shell 40.5
AMD Ryzen 5800X, 5800X3D, 5950X Linux Benchmarks 3 Systems - 531 Benchmark Results	AMD Ryzen 9 5950X 16-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship Ubuntu 22.04 - 5.17.4-051704-generic - GNOME Shell 42.0
apple m1 onednn onnx java 4 Systems - 37 Benchmark Results	Apple M1 - Apple Mac mini - 8GB Arch Linux ARM - 5.17.0-rc7-asahi-next-20220310-5-1-ARCH - KDE Plasma 5.24.3
icelake onx onednn 3 Systems - 36 Benchmark Results	Intel Core i7-1065G7 - Dell 06CDVY - Intel Ice Lake-LP DRAM Ubuntu 21.10 - 5.13.0-35-generic - GNOME Shell 40.5
core-i5-12400-april 4 Systems - 82 Benchmark Results	Intel Core i5-12400 - ASRock B660M-HDV - Intel Device 7aa7 Ubuntu 22.04 - 5.15.0-18-generic - GNOME Shell 41.3
tgl onnx onednn 3 Systems - 36 Benchmark Results	Intel Core i7-1185G7 - Dell 0DXP1F - Intel Tiger Lake-LP Ubuntu 22.04 - 5.17.0-051700rc7daily20220309-generic - GNOME Shell 41.3
new 4500U 3 Systems - 36 Benchmark Results	AMD Ryzen 5 4500U - LENOVO LNVNB161216 - AMD Renoir Ubuntu 21.10 - 5.16.0-051600rc8daily20220108-generic - GNOME Shell 40.5
epyc-75f3-new 4 Systems - 48 Benchmark Results	2 x AMD EPYC 75F3 32-Core - ASRockRack ROME2D16-2T - AMD Starship Ubuntu 21.10 - 5.17.0-051700rc4daily20220219-generic - GNOME Shell 40.5
onnx 5950X 5 Systems - 12 Benchmark Results	AMD Ryzen 9 5950X 16-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship Ubuntu 22.04 - 5.17.0-phx - GNOME Shell
onednn onnx alderlake 4 Systems - 36 Benchmark Results	Intel Core i9-12900K - ASUS ROG STRIX Z690-E GAMING WIFI - Intel Device 7aa7 Ubuntu 21.10 - 5.17.0-phx - GNOME Shell 40.5
onednn onnx threadripper 4 Systems - 36 Benchmark Results	AMD Ryzen Threadripper 3990X 64-Core - Gigabyte TRX40 AORUS PRO WIFI - AMD Starship Pop 21.10 - 5.17.0-rc1-sched-core-phx - GNOME Shell 40.5
april amd 3 Systems - 71 Benchmark Results	AMD Ryzen 7 3800XT 8-Core - MSI X370 XPOWER GAMING TITANIUM - AMD Starship Debian 11 - 5.10.0-13-amd64 - X Server 1.20.11
AMD Ryzen 7 5800X3D Linux Benchmarks 3 Systems - 541 Benchmark Results	AMD Ryzen 7 5800X3D 8-Core - ASRock X570 Pro4 - AMD Starship Ubuntu 22.04 - 5.17.4-051704-generic - GNOME Shell 42.0
Clear Linux 36260 4 Systems - 183 Benchmark Results	2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998 Ubuntu 22.04 - 5.15.0-27-generic - GNOME Shell 42.0
Clear Linux 36260 3 Systems - 183 Benchmark Results	2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Device 0998 Ubuntu 22.04 - 5.15.0-27-generic - GNOME Shell 42.0