pytorch.txt ARMv8 Cortex-A78E testing with a NVIDIA Jetson Orin NX Engineering Developer Kit (36.3.0-gcid-36191598 BIOS) and Orin on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2408262-NE-PYTORCHTX65 .
pytorch.txt Processor Motherboard Memory Disk Graphics Network OS Kernel Desktop Display Server Display Driver Vulkan Compiler File-System Screen Resolution all of them ARMv8 Cortex-A78E @ 1.98GHz (8 Cores) NVIDIA Jetson Orin NX Engineering Developer Kit (36.3.0-gcid-36191598 BIOS) 16GB 128GB FORESEE XP1000F128G Orin Realtek RTL8111/8168/8411 Ubuntu 22.04 5.15.136-tegra (aarch64) GNOME Shell 42.9 X Server 1.21.1.4 NVIDIA 1.3.251 GCC 11.4.0 + CUDA 12.2 ext4 6582x1234 OpenBenchmarking.org - Transparent Huge Pages: always - Scaling Governor: tegra194 performance - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of CSV2 but not BHB + srbds: Not affected + tsx_async_abort: Not affected
pytorch.txt tensorflow-lite: SqueezeNet tensorflow-lite: Inception V4 tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Float tensorflow-lite: Mobilenet Quant tensorflow-lite: Inception ResNet V2 all of them 8886.22 128466 22370.4 6848.70 3307.88 117511 OpenBenchmarking.org
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: SqueezeNet all of them 2K 4K 6K 8K 10K SE +/- 30.83, N = 3 8886.22
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception V4 all of them 30K 60K 90K 120K 150K SE +/- 310.94, N = 3 128466
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: NASNet Mobile all of them 5K 10K 15K 20K 25K SE +/- 161.30, N = 3 22370.4
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float all of them 1500 3000 4500 6000 7500 SE +/- 50.47, N = 3 6848.70
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Quant all of them 700 1400 2100 2800 3500 SE +/- 4.64, N = 3 3307.88
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 all of them 30K 60K 90K 120K 150K SE +/- 57.20, N = 3 117511
Phoronix Test Suite v10.8.5