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, 30 Seconds

Average Run Time

5 Minutes, 18 Seconds

Test Dependencies

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

Accolades

10k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsONNX Runtime Popularity Statisticspts/onnx2021.012021.022021.032021.042021.052021.062021.072021.082021.092021.102021.112021.122022.012022.022022.032022.042022.052022.062022.072022.082022.092022.102022.112K4K6K8K10K
* 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 22 November 2022.
fcn-resnet101-1115.3%yolov416.4%bertsquad-1216.1%super-resolution-1015.8%ArcFace ResNet-10017.3%GPT-219.0%Model Option PopularityOpenBenchmarking.org
Standard71.1%Parallel28.9%Executor Option PopularityOpenBenchmarking.org

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: yolov4 - Device: CPU - Executor: Standard

OpenBenchmarking.org metrics for this test profile configuration based on 406 public results since 30 March 2022 with the latest data as of 13 November 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)
93rd
20
680 +/- 14
92nd
15
679 +/- 93
88th
4
644 +/- 51
83rd
8
606 +/- 4
78th
3
530 +/- 2
76th
11
526 +/- 8
Mid-Tier
75th
< 526
62nd
4
454 +/- 2
61st
6
446 +/- 16
61st
4
444 +/- 37
57th
4
424 +/- 5
55th
6
419 +/- 12
52nd
5
402 +/- 45
Median
50th
365
46th
4
322 +/- 37
41st
5
305 +/- 9
36th
7
295 +/- 14
32nd
9
287 +/- 3
31st
3
286 +/- 28
28th
4
277 +/- 8
Low-Tier
25th
< 271
22nd
5
264 +/- 24
21st
3
260 +/- 9
17th
20
253 +/- 7
16th
8
251 +/- 20
11th
6
199 +/- 1
9th
3
189 +/- 7
7th
5
176 +/- 3
5th
3
159 +/- 8
5th
6
155 +/- 16
3rd
4
90
OpenBenchmarking.orgDistribution Of Public Results - Model: yolov4 - Device: CPU - Executor: Standard406 Results Range From 14 To 850 Inferences Per Minute1443721011301591882172462753043333623914204494785075365655946236526817107397687978268551224364860

Based on OpenBenchmarking.org data, the selected test / test configuration (ONNX Runtime 1.11 - Model: yolov4 - 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.

OpenBenchmarking.orgMinutesTime Required To Complete BenchmarkModel: yolov4 - Device: CPU - Executor: StandardRun-Time612182430Min: 6 / Avg: 11.13 / Max: 24

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 RunsModel: yolov4 - Device: CPU - Executor: StandardDeviation3691215Min: 0 / Avg: 1.03 / Max: 12

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.

OpenBenchmarking.orgRelative Core Scaling To BaseONNX Runtime CPU Core ScalingModel: yolov4 - Device: CPU - Executor: Standard6816641280.82271.64542.46813.29084.1135

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
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
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 4-Core, Ampere ARMv8 Neoverse-N1 256-Core, Apple M1

Recent Test Results

OpenBenchmarking.org Results Compare

5 Systems - 215 Benchmark Results

Intel Core i9-13900K - ASUS PRIME Z790-P WIFI - Intel Device 7a27

CentOS Stream 9 - 5.14.0-183.el9.x86_64 - GNOME Shell 40.10

4 Systems - 215 Benchmark Results

Intel Core i9-13900K - ASUS PRIME Z790-P WIFI - Intel Device 7a27

Fedora Linux 37 - 6.0.7-301.fc37.x86_64 - GNOME Shell 43.0

2 Systems - 384 Benchmark Results

Intel Core i9-13900K - ASUS PRIME Z790-P WIFI - Intel Device 7a27

Clear Linux OS 37600 - 6.0.7-1207.native - GNOME Shell 43.0

1 System - 384 Benchmark Results

Intel Core i9-13900K - ASUS PRIME Z790-P WIFI - Intel Device 7a27

Ubuntu 22.10 - 5.19.0-23-generic - GNOME Shell 43.0

1 System - 380 Benchmark Results

Intel Core i9-13900K - ASUS PRIME Z790-P WIFI - Intel Device 7a27

Ubuntu 22.10 - 5.19.0-23-generic - GNOME Shell 43.0

1 System - 351 Benchmark Results

Intel Core i5-13600K - ASUS PRIME Z790-P WIFI - Intel Device 7a27

Ubuntu 22.10 - 5.19.0-23-generic - GNOME Shell 43.0

1 System - 704 Benchmark Results

Intel Core i9-11900K - ASUS ROG MAXIMUS XIII HERO - Intel Tiger Lake-H

Ubuntu 22.10 - 5.19.0-21-generic - GNOME Shell 43.0

1 System - 100 Benchmark Results

AMD Ryzen 5 7600X 6-Core - ASUS ROG CROSSHAIR X670E HERO - AMD Device 14d8

Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2

3 Systems - 357 Benchmark Results

AMD Ryzen 7 7700X 8-Core - ASUS ROG CROSSHAIR X670E HERO - AMD Device 14d8

Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2

3 Systems - 357 Benchmark Results

4 Systems - 537 Benchmark Results

AMD Ryzen 9 7950X 16-Core - ASUS ROG CROSSHAIR X670E HERO - AMD Device 14d8

Fedora Linux 36 - 6.0.0-0.rc5.20220914git3245cb65fd91.39.vanilla.1.fc36.x86_64 - GNOME Shell 42.4

4 Systems - 361 Benchmark Results

AMD Ryzen 9 7950X 16-Core - ASUS ROG CROSSHAIR X670E HERO - AMD Device 14d8

Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2

13 Systems - 333 Benchmark Results

Intel Core i5-12600K - ASUS ROG STRIX Z690-E GAMING WIFI - Intel Device 7aa7

Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2

5 Systems - 105 Benchmark Results

2 x Intel Xeon Platinum 8380 - HPE ProLiant DL380 Gen10 Plus - Intel Device 0998

Clear Linux OS 37000 - 5.15.0-47-generic - X Server

Most Popular Test Results

OpenBenchmarking.org Results Compare

13 Systems - 333 Benchmark Results

AMD Ryzen 9 7900X 12-Core - ASUS ROG CROSSHAIR X670E HERO - AMD Device 14d8

Ubuntu 22.04 - 6.0.0-060000rc1daily20220820-generic - GNOME Shell 42.2

3 Systems - 531 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

7 Systems - 293 Benchmark Results

AMD Ryzen 5 5500U - NB01 NL5xNU - AMD Renoir

Pop 22.04 - 5.17.5-76051705-generic - GNOME Shell 42.1

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

4 Systems - 171 Benchmark Results

AMD Ryzen 5 5600G - Gigabyte A520M DS3H - AMD Renoir

Ubuntu 22.04 - 5.15.0-41-generic - GNOME Shell 42.2

4 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

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

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

3 Systems - 178 Benchmark Results

2 x Intel Xeon Platinum 8280 - GIGABYTE MD61-SC2-00 v01000100 - Intel Sky Lake-E DMI3 Registers

Ubuntu 21.04 - 5.11.0-40-generic - GNOME Shell 3.38.4

3 Systems - 541 Benchmark Results

2 x Intel Xeon E5-2620 v2 - Dell 0WN7Y6 - Intel Xeon E7 v2

Linuxmint 20.3 - 5.13.0-40-generic - X Server 1.20.13

Find More Test Results