tensorflowlite-sq Intel Pentium N3700 testing with a AMI Aptio CRB (5.11 BIOS) and Intel Atom/Celeron/Pentium x5-E8000/J3xxx/N3xxx IGP on Debian 12 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2403139-NE-TENSORFLO76 .
tensorflowlite-sq Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Compiler File-System Screen Resolution tflsq Intel Pentium N3700 @ 2.40GHz (4 Cores) AMI Aptio CRB (5.11 BIOS) Intel Atom/Celeron/Pentium 8GB SHAREVDI 128GB S Intel Atom/Celeron/Pentium x5-E8000/J3xxx/N3xxx IGP (700MHz) Intel Atom/Celeron/Pentium SB220Q 4 x Intel I225-V Debian 12 6.1.0-18-amd64 (x86_64) GCC 12.2.0 ext4 1920x1080 OpenBenchmarking.org - Transparent Huge Pages: always - Scaling Governor: intel_cpufreq schedutil - CPU Microcode: 0x368 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Mitigation of Clear buffers; SMT disabled + meltdown: Mitigation of PTI + mmio_stale_data: Unknown: No mitigations + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Not affected + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
tensorflowlite-sq tensorflow-lite: SqueezeNet Standard Error Standard Deviation tflsq 89903.1 54.22 0.10% OpenBenchmarking.org
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: SqueezeNet tflsq 20K 40K 60K 80K 100K SE +/- 54.22, N = 3 89903.1
Phoronix Test Suite v10.8.4