atomicrulez_ubuntu_2310_tensorflow-lite Intel Core i9-10850K testing with a ASUS ROG MAXIMUS XII APEX (2701 BIOS) and NVIDIA GeForce RTX 3090 Ti 24GB on Ubuntu 23.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2310010-MICH-ATOMICR74&gru .
atomicrulez_ubuntu_2310_tensorflow-lite Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution i9-10850K Intel Core i9-10850K @ 5.30GHz (10 Cores / 20 Threads) ASUS ROG MAXIMUS XII APEX (2701 BIOS) Intel Comet Lake PCH 64GB 280GB INTEL SSDPE21D280GA NVIDIA GeForce RTX 3090 Ti 24GB Realtek ALC1220 ROG PG259QN Intel I225-V + Intel Comet Lake PCH CNVi WiFi Ubuntu 23.10 6.5.0-5-generic (x86_64) GNOME Shell 45.0 X Server 1.21.1.7 NVIDIA 535.104.05 4.6.0 OpenCL 3.0 CUDA 12.2.138 GCC 13.2.0 + CUDA 12.0 ext4 1920x1080 OpenBenchmarking.org - Transparent Huge Pages: madvise - Scaling Governor: intel_pstate powersave (EPP: performance) - CPU Microcode: 0xf8 - Thermald 2.5.4 - gather_data_sampling: Mitigation of Microcode + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected
atomicrulez_ubuntu_2310_tensorflow-lite tensorflow-lite: SqueezeNet tensorflow-lite: Inception V4 tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Float tensorflow-lite: Mobilenet Quant tensorflow-lite: Inception ResNet V2 i9-10850K 2228.05 38862.9 8770.57 1960.94 2980.00 31925.3 OpenBenchmarking.org
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: SqueezeNet i9-10850K 500 1000 1500 2000 2500 SE +/- 8.97, N = 3 2228.05
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception V4 i9-10850K 8K 16K 24K 32K 40K SE +/- 431.57, N = 5 38862.9
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: NASNet Mobile i9-10850K 2K 4K 6K 8K 10K SE +/- 13.25, N = 3 8770.57
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float i9-10850K 400 800 1200 1600 2000 SE +/- 17.24, N = 15 1960.94
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Quant i9-10850K 600 1200 1800 2400 3000 SE +/- 26.69, N = 3 2980.00
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 i9-10850K 7K 14K 21K 28K 35K SE +/- 198.63, N = 3 31925.3
Phoronix Test Suite v10.8.5