tf-lite-7

Intel Xeon W3690 testing with a Dell 09KPNV (A11 BIOS) and NVIDIA Quadro P1000 4GB on VoidLinux rolling 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 2412047-NE-TFLITE77691
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
tensorflow-lite-7
December 04 2024
  19 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):


tf-lite-7OpenBenchmarking.orgPhoronix Test SuiteIntel Xeon W3690 (6 Cores)Dell 09KPNV (A11 BIOS)Intel 5520/5500/X58 + ICH10R12GB250GB INTENSO SSD + 500GB Samsung SSD 850NVIDIA Quadro P1000 4GBAnalog Devices AD1984ABroadcom NetXtreme BCM5761 PCIeVoidLinux rolling6.6.63_1 (x86_64)X Server 1.21.1.14NVIDIAGCC 13.2.0ext4ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDisplay ServerDisplay DriverCompilerFile-SystemTf-lite-7 BenchmarksSystem Logs- Transparent Huge Pages: madvise- CPU Microcode: 0x10- gather_data_sampling: Not affected + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT disabled + mds: Vulnerable: Clear buffers attempted no microcode; SMT disabled + meltdown: Mitigation of PTI + mmio_stale_data: Unknown: No mitigations + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

tf-lite-7tensorflow-lite: SqueezeNettensorflow-lite: Inception V4tensorflow-lite: NASNet Mobiletensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: Inception ResNet V2tensorflow-lite-716941.124103128637.912822.6301778227883OpenBenchmarking.org

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: SqueezeNettensorflow-lite-74K8K12K16K20KSE +/- 2.23, N = 316941.1

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception V4tensorflow-lite-750K100K150K200K250KSE +/- 172.07, N = 3241031

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: NASNet Mobiletensorflow-lite-76K12K18K24K30KSE +/- 21.28, N = 328637.9

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Floattensorflow-lite-73K6K9K12K15KSE +/- 4.20, N = 312822.6

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Mobilenet Quanttensorflow-lite-760K120K180K240K300KSE +/- 1.67, N = 3301778

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2022-05-18Model: Inception ResNet V2tensorflow-lite-750K100K150K200K250KSE +/- 34.44, N = 3227883