tensorflow-lite_Sep04-2020

Intel Core i7-10875H testing with a Notebook PCX0DX (1.07.05LAM BIOS) and NVIDIA GeForce RTX 2080 Super with Max-Q Design 8GB on Ubuntu 20.04 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 2009046-NE-TENSORFLO17
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Sep04
September 04 2020
  38 Minutes
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):

Sep04

Processor: Intel Core i7-10875H @ 5.10GHz (8 Cores / 16 Threads), Motherboard: Notebook PCX0DX (1.07.05LAM BIOS), Chipset: Intel Comet Lake PCH, Memory: 64GB, Disk: 1000GB Samsung SSD 970 EVO Plus 1TB + 1000GB Samsung SSD 860, Graphics: NVIDIA GeForce RTX 2080 Super with Max-Q Design 8GB (300/405MHz), Audio: Realtek ALC1220, Network: Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX201

OS: Ubuntu 20.04, Kernel: 5.4.0-42-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: NVIDIA 450.57, Compiler: GCC 9.3.0 + CUDA 10.2, File-System: ext4, Screen Resolution: 1920x1080

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

tensorflow-lite_Sep04-2020OpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-10875H @ 5.10GHz (8 Cores / 16 Threads)Notebook PCX0DX (1.07.05LAM BIOS)Intel Comet Lake PCH64GB1000GB Samsung SSD 970 EVO Plus 1TB + 1000GB Samsung SSD 860NVIDIA GeForce RTX 2080 Super with Max-Q Design 8GB (300/405MHz)Realtek ALC1220Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX201Ubuntu 20.045.4.0-42-generic (x86_64)GNOME Shell 3.36.4X Server 1.20.8NVIDIA 450.57GCC 9.3.0 + CUDA 10.2ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionTensorflow-lite_Sep04-2020 BenchmarksSystem Logs- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8- itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

tensorflow-lite_Sep04-2020tensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2Sep0455264292960175662124403694331338416527OpenBenchmarking.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: SqueezeNetSep04120K240K360K480K600KSE +/- 50553.40, N = 12552642

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Sep042M4M6M8M10MSE +/- 1944.41, N = 39296017

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileSep04120K240K360K480K600KSE +/- 663.88, N = 3566212

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatSep0490K180K270K360K450KSE +/- 533.90, N = 3440369

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantSep0490K180K270K360K450KSE +/- 291.21, N = 3433133

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Sep042M4M6M8M10MSE +/- 14119.76, N = 38416527

Sep04

Processor: Intel Core i7-10875H @ 5.10GHz (8 Cores / 16 Threads), Motherboard: Notebook PCX0DX (1.07.05LAM BIOS), Chipset: Intel Comet Lake PCH, Memory: 64GB, Disk: 1000GB Samsung SSD 970 EVO Plus 1TB + 1000GB Samsung SSD 860, Graphics: NVIDIA GeForce RTX 2080 Super with Max-Q Design 8GB (300/405MHz), Audio: Realtek ALC1220, Network: Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX201

OS: Ubuntu 20.04, Kernel: 5.4.0-42-generic (x86_64), Desktop: GNOME Shell 3.36.4, Display Server: X Server 1.20.8, Display Driver: NVIDIA 450.57, Compiler: GCC 9.3.0 + CUDA 10.2, File-System: ext4, Screen Resolution: 1920x1080

Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 4 September 2020 22:01 by user galapagos.