TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics.

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

Project Site

tensorflow.org

Source Repository

github.com

Test Created

6 February 2017

Last Updated

6 January 2024

Test Maintainer

Michael Larabel 

Test Type

System

Average Install Time

1 Minute, 6 Seconds

Average Run Time

1 Minute, 51 Seconds

Test Dependencies

Python

Accolades

80k+ Downloads

Supported Platforms


Public Result Uploads *Reported Installs **Reported Test Completions **Test Profile Page Views ***OpenBenchmarking.orgEventsTensorflow Popularity Statisticspts/tensorflow2017.022017.052017.082017.112018.022018.052018.082018.112019.022019.052019.082019.112020.022020.052020.082020.112021.022021.052021.082021.112022.022022.052022.082022.112023.022023.052023.082023.112024.025K10K15K20K25K
* 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 updated weekly as of 18 March 2024.
25610.8%111.3%51210.1%3220.9%6422.4%1624.4%Batch Size Option PopularityOpenBenchmarking.org
GoogLeNet21.8%AlexNet22.1%VGG-1610.5%ResNet-5045.6%Model Option PopularityOpenBenchmarking.org

Revision History

pts/tensorflow-2.1.1   [View Source]   Sat, 06 Jan 2024 17:48:46 GMT
Add NVIDIA GPU CUDA option.

pts/tensorflow-2.1.0   [View Source]   Tue, 28 Mar 2023 16:38:47 GMT
Update against TensorFlow 2.12 upstream to work with newer distros / Python.

pts/tensorflow-2.0.0   [View Source]   Fri, 07 Oct 2022 12:18:59 GMT
Update this, get it going against TF 2.10 upstream...

pts/tensorflow-1.1.0   [View Source]   Fri, 06 Mar 2020 07:23:10 GMT
Rework test, increase max steps to 1000

pts/tensorflow-1.0.0   [View Source]   Mon, 06 Feb 2017 18:08:28 GMT
Initial commit of TensorFlow benchmark

Suites Using This Test

Machine Learning

HPC - High Performance Computing

CPU Massive


Performance Metrics

Analyze Test Configuration:

TensorFlow 2.12

Device: CPU - Batch Size: 64 - Model: ResNet-50

OpenBenchmarking.org metrics for this test profile configuration based on 530 public results since 28 March 2023 with the latest data as of 13 March 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
images/sec (Average)
92nd
15
99 +/- 10
84th
6
86 +/- 11
Mid-Tier
75th
< 78
Median
50th
35
39th
9
27 +/- 2
34th
7
23 +/- 2
28th
3
20 +/- 1
Low-Tier
25th
< 18
15th
9
13 +/- 1
OpenBenchmarking.orgDistribution Of Public Results - Device: CPU - Batch Size: 64 - Model: ResNet-50529 Results Range From 0 To 113 images/sec10203040506070809010011012020406080100

Based on OpenBenchmarking.org data, the selected test / test configuration (TensorFlow 2.12 - Device: CPU - Batch Size: 64 - Model: ResNet-50) has an average run-time of 14 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 BenchmarkDevice: CPU - Batch Size: 64 - Model: ResNet-50Run-Time20406080100Min: 3 / Avg: 13.18 / Max: 98

Based on public OpenBenchmarking.org results, the selected test / test configuration has an average standard deviation of 0.1%.

OpenBenchmarking.orgPercent, Fewer Is BetterAverage Deviation Between RunsDevice: CPU - Batch Size: 64 - Model: ResNet-50Deviation246810Min: 0 / Avg: 0.14 / Max: 2

Does It Scale Well With Increasing Cores?

No, based on the automated analysis of the collected public benchmark data, this test / test settings does not 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.

IntelAMDOpenBenchmarking.orgRelative Core Scaling To BaseTensorflow CPU Core ScalingDevice: CPU - Batch Size: 64 - Model: ResNet-504681214163264962.775.548.3111.0813.85

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)

Recent Test Results

OpenBenchmarking.org Results Compare

2 Systems - 298 Benchmark Results

Intel Core i7-8700 - ASUS PRIME Z370-P II - 32GB ddr4-3200

Ubuntu 23.10 - 6.5.0-15-generic - KDE Plasma 5.27.8

3 Systems - 298 Benchmark Results

Intel Core i7-8700 - ASUS PRIME Z370-P II - 32GB ddr4-3200

Ubuntu 23.10 - 6.5.0-15-generic - KDE Plasma 5.27.8

1 System - 341 Benchmark Results

AMD Ryzen 9 7950X 16-Core - ASUS ProArt X670E-CREATOR WIFI - AMD Device 14d8

Pop 22.04 - 6.6.10-76060610-generic - GNOME Shell 42.5

1 System - 1 Benchmark Result

Intel Pentium N3700 - AMI Aptio CRB - Intel Atom

Debian 12 - 6.1.0-18-amd64 - GCC 12.2.0

1 System - 2 Benchmark Results

2 x Intel Xeon E5-2696 v4 - ASUS Z10PE-D8 WS - Intel Xeon E7 v4

Ubuntu 22.04 - 6.5.0-21-generic - X Server 1.21.1.4

1 System - 27 Benchmark Results

Intel Core Ultra 7 155H - 16GB - 0GB Virtual Disk + 4GB Virtual Disk + 2 x 1100GB Virtual Disk

Ubuntu 22.04 - 5.15.146.1-microsoft-standard-WSL2 - Wayland

1 System - 26 Benchmark Results

Intel Core Ultra 7 155H - 16GB - 0GB Virtual Disk + 4GB Virtual Disk + 1100GB Virtual Disk

Ubuntu 22.04 - 5.15.146.1-microsoft-standard-WSL2 - Wayland

4 Systems - 125 Benchmark Results

2 x INTEL XEON PLATINUM 8592+ - Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS - Intel Device 1bce

Fedora Linux 39 - 6.7.6-200.fc39.x86_64 - GCC 13.2.1 20231205

3 Systems - 125 Benchmark Results

2 x INTEL XEON PLATINUM 8592+ - Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS - Intel Device 1bce

CentOS Stream 9 - 5.14.0-419.el9.x86_64 - GNOME Shell 40.10

2 Systems - 390 Benchmark Results

ARMv8 Cortex-A76 - Mixtile Blade 3 v1.0.1 - 16GB

Ubuntu 22.04 - 5.10.160-rockchip - GNOME Shell 42.9

1 System - 6 Benchmark Results

ARMv8 Cortex-A72 - Texas Instruments J721E SK - 2560MB

Ubuntu 22.04.4 LTS - 6.1.46-g5892b80d6b - overlayfs

1 System - 183 Benchmark Results

Intel Atom C3708 - Kontron Europe COMe-bDV7 E2 v2.0.1 - 32GB

Ubuntu 22.04.4 LTS - 4.18.0-448.el8.x86_64 - overlayfs

1 System - 103 Benchmark Results

ARMv8 Cortex-A72 - Texas Instruments AM69 SK - 28GB

Ubuntu 22.04.4 LTS - 6.1.46-g5892b80d6b - GCC 11.4.0

1 System - 6 Benchmark Results

ARMv8 Cortex-A72 - Texas Instruments AM69 SK - 28GB

Ubuntu 22.04.4 LTS - 6.1.46-g5892b80d6b - GCC 11.4.0

1 System - 6 Benchmark Results

ARMv8 Cortex-A72 - Texas Instruments AM69 SK - 28GB

Ubuntu 22.04.4 LTS - 6.1.46-g5892b80d6b - GCC 11.4.0

Most Popular Test Results

OpenBenchmarking.org Results Compare

3 Systems - 131 Benchmark Results

AMD Ryzen 7 5800X3D 8-Core - ASUS ROG CROSSHAIR VIII HERO - AMD Starship

Ubuntu 22.04 - 5.17.0-1019-oem - GNOME Shell 42.2

4 Systems - 215 Benchmark Results

AMD EPYC 7343 16-Core - Supermicro H12SSL-i v1.02 - 8 x 64 GB DDR4-3200MT

AlmaLinux 9.1 - 5.14.0-162.12.1.el9_1.x86_64 - GCC 11.3.1 20220421

5 Systems - 203 Benchmark Results

AMD EPYC 9654 96-Core - AMD Titanite_4G - AMD Device 14a4

Ubuntu 23.04 - 5.19.0-21-generic - GNOME Shell 43.1

4 Systems - 132 Benchmark Results

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

Ubuntu 22.04 - 6.2.0-phx - GNOME Shell 42.5

3 Systems - 231 Benchmark Results

2 x Intel Xeon Platinum 8380 - Intel M50CYP2SB2U - Intel Ice Lake IEH

Ubuntu 22.10 - 6.2.0-rc5-phx-dodt - GNOME Shell 43.0

2 Systems - 93 Benchmark Results

AMD Ryzen 7 7800X3D 8-Core - ASUS ROG CROSSHAIR X670E HERO - AMD Device 14d8

Ubuntu 23.04 - 6.2.8-060208-generic - GNOME Shell 44.0

3 Systems - 16 Benchmark Results

Intel Core i7-1165G7 - Dell 0GG9PT - Intel Tiger Lake-LP

Ubuntu 22.10 - 5.19.0-35-generic - GNOME Shell 43.0

3 Systems - 197 Benchmark Results

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

Ubuntu 22.04 - 5.15.0-47-generic - GNOME Shell 42.4

2 Systems - 120 Benchmark Results

AMD EPYC 9B14 - Google Compute Engine c3d-standard-60 - Intel 440FX 82441FX PMC

Ubuntu 22.04 - 6.2.0-1014-gcp - 1.3.238

3 Systems - 46 Benchmark Results

AMD Ryzen 7 4700U - LENOVO LNVNB161216 - AMD Renoir

Ubuntu 22.04 - 5.19.0-35-generic - GNOME Shell 42.2

3 Systems - 120 Benchmark Results

ARMv8 Neoverse-N1 - Amazon EC2 c6g.16xlarge - Amazon Device 0200

Ubuntu 22.04 - 5.19.0-1025-aws - 1.3.238

3 Systems - 28 Benchmark Results

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

Ubuntu 22.04 - 5.19.0-35-generic - GNOME Shell 42.2

Find More Test Results