tensorflow lite AMD EPYC Naples

AMD EPYC 7551 32-Core testing with a GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS) and ASPEED on Debian 10 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 2008231-NE-TENSORFLO46
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
Run 1
August 23 2020
  22 Minutes
Run 2
August 23 2020
  19 Minutes
Run 3
August 23 2020
  19 Minutes
Invert Hiding All Results Option
  20 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):

Run 1

Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8001227
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Run 2

Run 3

Processor: AMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads), Motherboard: GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS), Chipset: AMD 17h, Memory: 32GB, Disk: Samsung SSD 960 EVO 500GB, Graphics: ASPEED, Network: Realtek RTL8111/8168/8411 + 2 x Broadcom NetXtreme II BCM57810 10

OS: Debian 10, Kernel: 4.19.0-10-amd64 (x86_64), Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1024x768

tensorflow lite AMD EPYC NaplesOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads)GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS)AMD 17h32GBSamsung SSD 960 EVO 500GBASPEEDRealtek RTL8111/8168/8411 + 2 x Broadcom NetXtreme II BCM57810 10Debian 104.19.0-10-amd64 (x86_64)GCC 8.3.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionTensorflow Lite AMD EPYC Naples PerformanceSystem Logs- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8001227- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Run 1Run 2Run 3Result OverviewPhoronix Test Suite100%101%101%102%TensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteTensorFlow LiteNASNet MobileInception V4I.R.VMobilenet FloatSqueezeNetMobilenet Quant

tensorflow lite AMD EPYC Naplestensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2Run 1Run 2Run 3101974132798712914160701.564204.21189023101308134930313275961760.764450.61184100101970135377312989361331.564073.31205527OpenBenchmarking.org

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. 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 2020-08-23Model: SqueezeNetRun 1Run 2Run 320K40K60K80K100KSE +/- 512.84, N = 3SE +/- 584.21, N = 3SE +/- 874.47, N = 3101974101308101970
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetRun 1Run 2Run 320K40K60K80K100KMin: 101074 / Avg: 101974.33 / Max: 102850Min: 100523 / Avg: 101308 / Max: 102450Min: 100544 / Avg: 101970.33 / Max: 103560

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Run 1Run 2Run 3300K600K900K1200K1500KSE +/- 2152.75, N = 3SE +/- 4431.01, N = 3SE +/- 3096.28, N = 3132798713493031353773
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Run 1Run 2Run 3200K400K600K800K1000KMin: 1323960 / Avg: 1327986.67 / Max: 1331320Min: 1342610 / Avg: 1349303.33 / Max: 1357680Min: 1350200 / Avg: 1353773.33 / Max: 1359940

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileRun 1Run 2Run 330K60K90K120K150KSE +/- 1829.92, N = 6SE +/- 1020.13, N = 3SE +/- 932.88, N = 3129141132759129893
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileRun 1Run 2Run 320K40K60K80K100KMin: 121247 / Avg: 129140.67 / Max: 134259Min: 131054 / Avg: 132759.33 / Max: 134582Min: 128029 / Avg: 129892.67 / Max: 130901

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatRun 1Run 2Run 313K26K39K52K65KSE +/- 268.57, N = 3SE +/- 715.27, N = 3SE +/- 330.49, N = 360701.561760.761331.5
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatRun 1Run 2Run 311K22K33K44K55KMin: 60320 / Avg: 60701.47 / Max: 61219.7Min: 60817.2 / Avg: 61760.73 / Max: 63163.7Min: 60670.5 / Avg: 61331.47 / Max: 61665.7

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantRun 1Run 2Run 314K28K42K56K70KSE +/- 96.54, N = 3SE +/- 299.92, N = 3SE +/- 51.47, N = 364204.264450.664073.3
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantRun 1Run 2Run 311K22K33K44K55KMin: 64014.3 / Avg: 64204.17 / Max: 64329.5Min: 63860.4 / Avg: 64450.6 / Max: 64838.5Min: 63970.4 / Avg: 64073.33 / Max: 64125.9

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Run 1Run 2Run 3300K600K900K1200K1500KSE +/- 9565.47, N = 3SE +/- 2247.87, N = 3SE +/- 13168.81, N = 3118902311841001205527
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Run 1Run 2Run 3200K400K600K800K1000KMin: 1173230 / Avg: 1189023.33 / Max: 1206270Min: 1181380 / Avg: 1184100 / Max: 1188560Min: 1188450 / Avg: 1205526.67 / Max: 1231430

Run 1

Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8001227
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 August 2020 13:18 by user root.

Run 2

Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8001227
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 August 2020 13:42 by user root.

Run 3

Processor: AMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads), Motherboard: GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS), Chipset: AMD 17h, Memory: 32GB, Disk: Samsung SSD 960 EVO 500GB, Graphics: ASPEED, Network: Realtek RTL8111/8168/8411 + 2 x Broadcom NetXtreme II BCM57810 10

OS: Debian 10, Kernel: 4.19.0-10-amd64 (x86_64), Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1024x768

Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8001227
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 23 August 2020 14:03 by user root.