XNNPACK

XNNPACK is a Google library for high efficiency floating-point neural network inference operators across mobile / server / web use. XNNPACK is used by machine learning frameworks like TensorFlow, PyTorch, ONNX Runtime, MediaPipe, and others. This test profile uses XNNPACK with its bench-models benchmark and testing all available CPU threads.

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

Project Site

github.com

Source Repository

github.com

Test Created

11 August 2024

Last Updated

15 October 2024

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

5 Minutes, 20 Seconds

Average Run Time

11 Minutes, 9 Seconds

Test Dependencies

CMake + C/C++ Compiler Toolchain

Accolades

Recently Updated Test Profile

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page ViewsOpenBenchmarking.orgEventsXNNPACK Popularity Statisticspts/xnnpack2024.082024.092024.10400800120016002000
* 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.
Data updated weekly as of 16 October 2024.
FP32MobileNetV3Large11.1%FP32MobileNetV3Small11.1%QU8MobileNetV3Large11.3%FP16MobileNetV211.1%FP32MobileNetV211.1%QU8MobileNetV3Small11.1%FP16MobileNetV3Small11.1%FP16MobileNetV3Large11.1%QU8MobileNetV211.3%Model Option PopularityOpenBenchmarking.org

Revision History

pts/xnnpack-1.1.0   [View Source]   Tue, 15 Oct 2024 15:30:38 GMT
Update against XNNPACK upstream, switch to new benchmark.

pts/xnnpack-1.0.0   [View Source]   Sun, 11 Aug 2024 10:34:29 GMT
Add XNNPACK benchmark.

Suites Using This Test

Machine Learning

HPC - High Performance Computing


Performance Metrics

Analyze Test Configuration:

XNNPACK 2cd86b

Model: QU8MobileNetV3Large

OpenBenchmarking.org metrics for this test profile configuration based on 202 public results since 11 August 2024 with the latest data as of 16 October 2024.

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
us (Average)
95th
4
960 +/- 67
89th
11
1101 +/- 11
87th
4
1110 +/- 138
83rd
14
1129 +/- 20
79th
4
1172 +/- 16
Mid-Tier
75th
> 1224
67th
6
1798 +/- 81
66th
7
1826 +/- 95
62nd
6
2155 +/- 4
59th
4
2287 +/- 2
56th
3
2406 +/- 24
52nd
7
2770 +/- 127
Median
50th
2864
46th
4
3040 +/- 9
43rd
10
3468 +/- 451
37th
4
5154 +/- 132
36th
4
6019 +/- 38
Low-Tier
25th
> 9463
25th
8
9549 +/- 137
23rd
4
9653 +/- 762
22nd
4
10112 +/- 628
17th
8
14042 +/- 418
12th
4
20767 +/- 309
10th
4
29917 +/- 3495
OpenBenchmarking.orgDistribution Of Public Results - Model: QU8MobileNetV3Large202 Results Range From 600 To 687200 us600143322806441796555286926082992967241104561241881379201516521653841791161928482065802203122340442477762615082752402889723027043164363301683439003576323713643850963988284125604262924400244537564674884812204949525086845224165361485498805636125773445910766048086185406322726460046597366734686872004080120160200

Based on OpenBenchmarking.org data, the selected test / test configuration (XNNPACK 2cd86b - Model: QU8MobileNetV3Large) has an average run-time of 22 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: QU8MobileNetV3LargeRun-Time1020304050Min: 14 / Avg: 21.31 / Max: 49

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-A76 4-Core, ARMv8 Neoverse-N1 128-Core, ARMv8 Neoverse-V2, ARMv8 Neoverse-V2 72-Core, AmpereOne 192-Core

Recent Test Results

OpenBenchmarking.org Results Compare

3 Systems - 27 Benchmark Results

ARMv8 Neoverse-V2 - Pegatron JIMBO P4352 - 1 x 480GB LPDDR5-6400MT

Ubuntu 24.04 - 6.8.0-45-generic-64k - NVIDIA

2 Systems - 147 Benchmark Results

ARMv8 Neoverse-V2 - Pegatron JIMBO P4352 - 1 x 480GB LPDDR5-6400MT

Ubuntu 24.04 - 6.8.0-45-generic-64k - NVIDIA

1 System - 147 Benchmark Results

ARMv8 Neoverse-V2 - Pegatron JIMBO P4352 - 1 x 480GB LPDDR5-6400MT

Ubuntu 24.04 - 6.8.0-45-generic-64k - NVIDIA

6 Systems - 344 Benchmark Results

Intel Core i7-1185G7 - Dell XPS 13 9310 0DXP1F - Intel Tiger Lake-LP

Ubuntu 24.10 - 6.11.0-rc6-phx - GNOME Shell

2 Systems - 55 Benchmark Results

Intel Core i7-1280P - MSI Prestige 14Evo A12M MS-14C6 - Intel Alder Lake PCH

Ubuntu 24.04 - 6.10.0-061000rc4daily20240621-generic - GNOME Shell 46.0

2 Systems - 137 Benchmark Results

AMD Ryzen 5 9600X 6-Core - ASUS ROG STRIX X670E-E GAMING WIFI - AMD Device 14d8

Ubuntu 24.04 - 6.10.0-phx - GNOME Shell 46.0

3 Systems - 120 Benchmark Results

2 x AMD EPYC 7773X 64-Core - AMD DAYTONA_X - AMD Starship

Ubuntu 24.04 - 6.8.0-41-generic - GNOME Shell 46.0

4 Systems - 116 Benchmark Results

2 x AMD EPYC 7303 16-Core - AMD DAYTONA_X - AMD Starship

Ubuntu 24.04 - 6.8.0-31-generic - GNOME Shell 46.0

1 System - 1043 Benchmark Results

2 Systems - 81 Benchmark Results

ARMv8 Neoverse-V2 - Amazon EC2 r8g.48xlarge - Amazon Device 0200

Ubuntu 24.04 - 6.8.0-41-generic-64k - GCC 13.2.0

4 Systems - 40 Benchmark Results

ARMv8 Neoverse-N1 - GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 - Ampere Computing LLC Altra PCI Root Complex A

Ubuntu 24.04 - 6.8.0-11-generic - GCC 13.2.0

3 Systems - 106 Benchmark Results

Intel Core i9-10980XE - ASRock X299 Steel Legend - Intel Sky Lake-E DMI3 Registers

Ubuntu 22.04 - 6.5.0-35-generic - GNOME Shell 42.9

2 Systems - 41 Benchmark Results

Intel Core Ultra 7 155H - MTL Swift SFG14-72T Coral_MTH - Intel Device 7e7f

Ubuntu 24.04 - 6.10.0-061000rc4daily20240621-generic - GNOME Shell 46.0

Most Popular Test Results

OpenBenchmarking.org Results Compare

2 Systems - 41 Benchmark Results

Intel Core Ultra 7 155H - MTL Swift SFG14-72T Coral_MTH - Intel Device 7e7f

Ubuntu 24.04 - 6.10.0-061000rc4daily20240621-generic - GNOME Shell 46.0

2 Systems - 62 Benchmark Results

AMD Ryzen 7 3800XT 8-Core - MSI X370 XPOWER GAMING TITANIUM - AMD Starship

Debian 12 - 6.1.0-22-amd64 - X Server 1.20.11

2 Systems - 62 Benchmark Results

AMD Ryzen 7 3800XT 8-Core - MSI X370 XPOWER GAMING TITANIUM - AMD Starship

Debian 12 - 6.1.0-22-amd64 - X Server 1.20.11

2 Systems - 41 Benchmark Results

Intel Core Ultra 7 155H - MTL Swift SFG14-72T Coral_MTH - Intel Device 7e7f

Ubuntu 24.04 - 6.10.0-061000rc4daily20240621-generic - GNOME Shell 46.0

3 Systems - 86 Benchmark Results

Intel Core i7-1185G7 - Dell XPS 13 9310 0DXP1F - Intel Tiger Lake-LP

Ubuntu 24.04 - 6.10.0-061000rc4daily20240621-generic - GNOME Shell 46.0

5 Systems - 26 Benchmark Results

AMD Ryzen Threadripper 3990X 64-Core - Gigabyte TRX40 AORUS PRO WIFI - AMD Starship

Pop 22.04 - 6.8.0-76060800daily20240311-generic - GNOME Shell 42.5

3 Systems - 34 Benchmark Results

Intel Core Ultra 7 155H - Framework Laptop 13 - Intel Device 7e7f

Ubuntu 24.04 - 6.10.0-061000rc4daily20240621-generic - GNOME Shell 46.0

4 Systems - 26 Benchmark Results

Intel Core i9-14900K - ASUS PRIME Z790-P WIFI - Intel Raptor Lake-S PCH

Ubuntu 24.04 - 6.10.0-061000rc6daily20240706-generic - GNOME Shell 46.0

3 Systems - 14 Benchmark Results

AMD Ryzen AI 9 365 - ASUS Zenbook S 16 UM5606WA_UM5606WA UM5606WA v1.0 - AMD Device 1507

Ubuntu 24.04 - 6.10.0-phx - GNOME Shell 46.0

3 Systems - 106 Benchmark Results

Intel Core i9-10980XE - ASRock X299 Steel Legend - Intel Sky Lake-E DMI3 Registers

Ubuntu 22.04 - 6.5.0-35-generic - GNOME Shell 42.9

4 Systems - 48 Benchmark Results

AMD Ryzen 9 7950X 16-Core - ASUS ROG STRIX X670E-E GAMING WIFI - AMD Device 14d8

Ubuntu 24.04 - 6.10.0-phx - GNOME Shell 46.0

4 Systems - 16 Benchmark Results

AMD Ryzen Threadripper 7980X 64-Cores - System76 Thelio Major - AMD Device 14a4

Pop 24.04 - 6.9.3-76060903-generic - COSMIC 0.1.0

2 Systems - 81 Benchmark Results

Intel Xeon Silver 4216 - TYAN S7100AG2NR - Intel Sky Lake-E DMI3 Registers

Debian 12 - 6.1.0-11-amd64 - X Server

Find More Test Results