tf AMD Ryzen 7 5800X 8-Core testing with a MSI B450-A PRO MAX (MS-7B86) v4.0 (M.C0 BIOS) and ASUS NVIDIA GeForce GTX 1650 SUPER 4GB on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2104062-HA-TF303717716 .
tf Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution run_1 AMD Ryzen 7 5800X 8-Core (8 Cores / 16 Threads) MSI B450-A PRO MAX (MS-7B86) v4.0 (M.C0 BIOS) AMD Starship/Matisse 16GB 500GB CT500MX500SSD1 ASUS NVIDIA GeForce GTX 1650 SUPER 4GB NVIDIA TU116 HD Audio DELL U2311H Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX200 Ubuntu 20.10 5.8.0-48-generic (x86_64) GNOME Shell 3.38.2 X Server 1.20.9 NVIDIA 460.39 4.6.0 OpenCL 1.2 CUDA 11.2.136 1.2.155 GCC 10.2.0 + CUDA 11.0 ext4 1920x1080 OpenBenchmarking.org - Transparent Huge Pages: madvise - CPU Microcode: 0xa201009 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
tf tensorflow-lite: SqueezeNet tensorflow-lite: Inception V4 tensorflow-lite: NASNet Mobile tensorflow-lite: Mobilenet Float tensorflow-lite: Mobilenet Quant tensorflow-lite: Inception ResNet V2 run_1 168755 2452263 143815 114047 124933 2219593 OpenBenchmarking.org
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet run_1 40K 80K 120K 160K 200K SE +/- 395.23, N = 3 168755
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 run_1 500K 1000K 1500K 2000K 2500K SE +/- 1610.89, N = 3 2452263
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile run_1 30K 60K 90K 120K 150K SE +/- 405.81, N = 3 143815
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float run_1 20K 40K 60K 80K 100K SE +/- 93.68, N = 3 114047
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant run_1 30K 60K 90K 120K 150K SE +/- 57.82, N = 3 124933
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 run_1 500K 1000K 1500K 2000K 2500K SE +/- 1779.57, N = 3 2219593
Phoronix Test Suite v10.8.4