rpi tensorflow lite + renaissance

ARMv8 Cortex-A72 testing with a BCM2835 Raspberry Pi 400 Rev 1.0 and V3D 4.2 4GB on Debian 11 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2205215-NE-RPITENSOR11
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
A
May 19 2022
  2 Hours, 32 Minutes
B
May 20 2022
  2 Hours, 34 Minutes
C
May 20 2022
  2 Hours, 32 Minutes
D
May 20 2022
  2 Hours, 33 Minutes
Invert Hiding All Results Option
  2 Hours, 33 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

A

Kernel Notes: snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1
Processor Notes: Scaling Governor: cpufreq-dt ondemand
Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable + srbds: Not affected + tsx_async_abort: Not affected

B

C

D

Processor: ARMv8 Cortex-A72 @ 1.80GHz (4 Cores), Motherboard: BCM2835 Raspberry Pi 400 Rev 1.0, Chipset: Broadcom BCM2711, Memory: 4096MB, Disk: 128GB SF128, Graphics: V3D 4.2 4GB, Monitor: DELL P2210H

OS: Debian 11, Kernel: 5.10.92-v8+ (aarch64), Desktop: LXDE 0.10.1, Display Server: X Server 1.20.11, OpenGL: 2.1 Mesa 20.3.5, Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1920x1080

rpi tensorflow lite + renaissanceOpenBenchmarking.orgPhoronix Test SuiteARMv8 Cortex-A72 @ 1.80GHz (4 Cores)BCM2835 Raspberry Pi 400 Rev 1.0Broadcom BCM27114096MB128GB SF128V3D 4.2 4GBDELL P2210HDebian 115.10.92-v8+ (aarch64)LXDE 0.10.1X Server 1.20.112.1 Mesa 20.3.5GCC 10.2.1 20210110ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionRpi Tensorflow Lite + Renaissance BenchmarksSystem Logs- snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1- Scaling Governor: cpufreq-dt ondemand- OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable + srbds: Not affected + tsx_async_abort: Not affected

ABCDResult OverviewPhoronix Test Suite100%103%106%108%111%RenaissanceRenaissanceRenaissanceRenaissanceRenaissanceRenaissanceRenaissanceRenaissanceRenaissanceTensorFlow LiteRenaissanceTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteRenaissanceScala DottyF.H.RApache Spark BayesI.M.D.SSavina Reactors.IOA.U.C.TA.S.PALS Movie LensApache Spark ALSI.R.VG.A.U.J.FInception V4SqueezeNetMobilenet QuantNASNet MobileMobilenet FloatRand Forest

rpi tensorflow lite + renaissancerenaissance: Scala Dottyrenaissance: Rand Forestrenaissance: ALS Movie Lensrenaissance: Apache Spark ALSrenaissance: Apache Spark Bayesrenaissance: Savina Reactors.IOrenaissance: Apache Spark PageRankrenaissance: Finagle HTTP Requestsrenaissance: In-Memory Database Shootoutrenaissance: Akka Unbalanced Cobwebbed Treerenaissance: Genetic Algorithm Using Jenetics + Futurestensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2ABCD8147.23930.738291.528846.384660.230773.729838.029083.925012.861177.57694.376627.812208601258116738023331.410767807684.73938.137821.328654.489558.531303.329640.128183.224030.960337.47697.475910.5122811012652267033.223284.810884508023.63944.237686.428508.686508.730281.230394.227385.524494.362137.87596.676472.9121603012633267246.62342710949507321.83935.137441.729100.789144.330354.630293.927984.923715.461219.87639.57612512267201258186737023368.41086870OpenBenchmarking.org

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Scala DottyABCD2K4K6K8K10K8147.27684.78023.67321.8MIN: 5301.91 / MAX: 16917.29MIN: 5231.49 / MAX: 22318.45MIN: 5267.49 / MAX: 21854.85MIN: 5073.31 / MAX: 22809.97

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Random ForestABCD80016002400320040003930.73938.13944.23935.1MIN: 3295.47 / MAX: 6927.09MIN: 3293.74 / MAX: 6983.39MIN: 3347.93 / MAX: 6875.5MIN: 3232.62 / MAX: 6420.48

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: ALS Movie LensABCD8K16K24K32K40K38291.537821.337686.437441.7MIN: 36929.46 / MAX: 47229.61MIN: 35867.85 / MAX: 47450.84MIN: 36132.69 / MAX: 46249.34MIN: 35895.61 / MAX: 47359.73

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Apache Spark ALSABCD6K12K18K24K30K28846.328654.428508.629100.7MIN: 27682.2 / MAX: 30758.63MIN: 27398.51 / MAX: 29995.58MIN: 27552.39 / MAX: 30920.89MIN: 28026.41 / MAX: 30919.56

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Apache Spark BayesABCD20K40K60K80K100K84660.289558.586508.789144.3MIN: 75026.79 / MAX: 84660.24MIN: 77990.75MIN: 76379.82MIN: 79804.46

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Savina Reactors.IOABCD7K14K21K28K35K30773.731303.330281.230354.6MIN: 30773.69 / MAX: 39679.21MAX: 42176.33MAX: 38955.78MAX: 39403.44

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Apache Spark PageRankABCD7K14K21K28K35K29838.029640.130394.230293.9MIN: 28408.49 / MAX: 31908.75MIN: 28465.16 / MAX: 32235.57MIN: 29438.16 / MAX: 33698.59MIN: 29416.81 / MAX: 32567.6

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Finagle HTTP RequestsABCD6K12K18K24K30K29083.928183.227385.527984.9MIN: 25726.24 / MAX: 34517.4MIN: 24641.47 / MAX: 37293.74MIN: 23777.71 / MAX: 33718.65MIN: 24640.53 / MAX: 34197.2

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: In-Memory Database ShootoutABCD5K10K15K20K25K25012.824030.924494.323715.4MIN: 20961.04 / MAX: 29854.89MIN: 21118.36 / MAX: 27203.7MIN: 21825.68 / MAX: 28178.68MIN: 21326.03 / MAX: 29360.42

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Akka Unbalanced Cobwebbed TreeABCD13K26K39K52K65K61177.560337.462137.861219.8MIN: 51500.06MIN: 50029.66MIN: 51762.74 / MAX: 62137.82MIN: 50843.02 / MAX: 61219.83

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.14Test: Genetic Algorithm Using Jenetics + FuturesABCD160032004800640080007694.37697.47596.67639.5MIN: 7550.37 / MAX: 7954.49MIN: 7609.76 / MAX: 7864.36MIN: 7495.22 / MAX: 7689.86MIN: 7452.02 / MAX: 7775.21

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: SqueezeNetABCD16K32K48K64K80K76627.875910.576472.976125.0

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4ABCD300K600K900K1200K1500K1220860122811012160301226720

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet MobileABCD30K60K90K120K150K125811126522126332125818

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet FloatABCD14K28K42K56K70K67380.067033.267246.667370.0

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet QuantABCD5K10K15K20K25K23331.423284.823427.023368.4

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2ABCD200K400K600K800K1000K1076780108845010949501086870

A

Kernel Notes: snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1
Processor Notes: Scaling Governor: cpufreq-dt ondemand
Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 19 May 2022 19:07 by user pi.

B

Kernel Notes: snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1
Processor Notes: Scaling Governor: cpufreq-dt ondemand
Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 20 May 2022 04:17 by user pi.

C

Kernel Notes: snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1
Processor Notes: Scaling Governor: cpufreq-dt ondemand
Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 20 May 2022 07:30 by user pi.

D

Processor: ARMv8 Cortex-A72 @ 1.80GHz (4 Cores), Motherboard: BCM2835 Raspberry Pi 400 Rev 1.0, Chipset: Broadcom BCM2711, Memory: 4096MB, Disk: 128GB SF128, Graphics: V3D 4.2 4GB, Monitor: DELL P2210H

OS: Debian 11, Kernel: 5.10.92-v8+ (aarch64), Desktop: LXDE 0.10.1, Display Server: X Server 1.20.11, OpenGL: 2.1 Mesa 20.3.5, Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: snd_bcm2835.enable_compat_alsa=0 snd_bcm2835.enable_hdmi=1
Processor Notes: Scaling Governor: cpufreq-dt ondemand
Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 20 May 2022 19:51 by user pi.