tflite ARMv8 Cortex-A78E testing with a NVIDIA Jetson Orin Nano 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/2408268-NE-TFLITE59672&grr .
tflite 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 @ 1.51GHz (6 Cores) NVIDIA Jetson Orin Nano Developer Kit (36.3.0-gcid-36191598 BIOS) 8GB 1000GB Western Digital WD_BLACK SN770 1TB Orin Realtek RTL8111/8168/8411 + Realtek RTL8822CE 802.11ac PCIe 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
tflite tensorflow-lite: Inception V4 tensorflow-lite: Inception ResNet V2 tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Float tensorflow-lite: SqueezeNet tensorflow-lite: Mobilenet Quant all of them 201982 185122 30431.5 10103.6 14598.6 5164.66 OpenBenchmarking.org
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception V4 all of them 40K 80K 120K 160K 200K SE +/- 373.30, N = 3 201982
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 all of them 40K 80K 120K 160K 200K SE +/- 76.78, N = 3 185122
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: NASNet Mobile all of them 7K 14K 21K 28K 35K SE +/- 251.51, N = 3 30431.5
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float all of them 2K 4K 6K 8K 10K SE +/- 39.85, N = 3 10103.6
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: SqueezeNet all of them 3K 6K 9K 12K 15K SE +/- 43.56, N = 3 14598.6
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Quant all of them 1100 2200 3300 4400 5500 SE +/- 29.50, N = 3 5164.66
Phoronix Test Suite v10.8.5