msi-tensorlite

Intel Core i7-9750H testing with a MSI MS-17E2 (E17E2IMS.10D BIOS) and MSI NVIDIA GeForce RTX 2070 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 2111286-TJ-MSITENSOR68
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
Performance Per
Dollar
Date
Run
  Test
  Duration
msi-tensorlite
November 28 2021
  1 Hour, 9 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):


msi-tensorliteOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-9750H @ 4.50GHz (6 Cores / 12 Threads)MSI MS-17E2 (E17E2IMS.10D BIOS)Intel Cannon Lake PCH32GB2 x 1000GB Samsung SSD 970 EVO Plus 1TB + 8002GB Backup+ Desk + 2000GB Seagate ST2000LX001-1RG1MSI NVIDIA GeForce RTX 2070 8GBRealtek ALC1220Qualcomm Atheros Killer E2500 + Intel-AC 9560Ubuntu 20.045.4.0-89-generic (x86_64)Xfce 4.14X Server 1.20.11NVIDIA 460.91.034.6.0OpenCL 1.2 CUDA 11.2.1621.2.145GCC 9.3.0 + CUDA 11.4ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionMsi-tensorlite BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: intel_pstate powersave - CPU Microcode: 0xea - Thermald 1.9.1- itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected

msi-tensorlitetensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2msi-tensorlite44624568005534316233160013205536593418OpenBenchmarking.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: SqueezeNetmsi-tensorlite100K200K300K400K500KSE +/- 4489.09, N = 15446245

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4msi-tensorlite1.5M3M4.5M6M7.5MSE +/- 63815.07, N = 36800553

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet Mobilemsi-tensorlite90K180K270K360K450KSE +/- 4736.39, N = 15431623

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Floatmsi-tensorlite70K140K210K280K350KSE +/- 1355.31, N = 3316001

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet Quantmsi-tensorlite70K140K210K280K350KSE +/- 478.29, N = 3320553

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2msi-tensorlite1.4M2.8M4.2M5.6M7MSE +/- 147967.25, N = 96593418