tflit3970X tflote AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (0702 BIOS) and NVIDIA TITAN RTX 24GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2008236-PTS-TFLIT39748&grr&sor .
tflit3970X tflote Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution Run 1 Run 2 Run 3 AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads) ASUS ROG ZENITH II EXTREME (0702 BIOS) AMD Starship/Matisse 64GB 1000GB Corsair Force MP600 NVIDIA TITAN RTX 24GB (1920/6500MHz) NVIDIA TU102 HD Audio ASUS MG28U Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.4.0-42-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.8 NVIDIA 450.36.06 4.6.0 OpenCL 1.2 CUDA 11.0.185 GCC 9.3.0 + CUDA 11.0 ext4 3840x2160 NVIDIA TITAN RTX 24GB (495/405MHz) NVIDIA TITAN RTX 24GB (555/810MHz) OpenBenchmarking.org Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025 Security Details - 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 STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
tflit3970X tflote tensorflow-lite: NASNet Mobile tensorflow-lite: Inception V4 tensorflow-lite: Inception ResNet V2 tensorflow-lite: SqueezeNet tensorflow-lite: Mobilenet Float tensorflow-lite: Mobilenet Quant Run 1 Run 2 Run 3 96109.5 886049 782026 66685.4 42836.1 43487.5 97256.4 876734 786424 66080.2 43240.4 43886.8 97208.5 878291 787311 65815.1 43241.4 43704.9 OpenBenchmarking.org
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Run 1 Run 3 Run 2 20K 40K 60K 80K 100K SE +/- 1129.61, N = 6 SE +/- 1090.58, N = 7 SE +/- 987.16, N = 8 96109.5 97208.5 97256.4
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Run 2 Run 3 Run 1 200K 400K 600K 800K 1000K SE +/- 428.12, N = 3 SE +/- 739.04, N = 3 SE +/- 12451.28, N = 3 876734 878291 886049
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Run 1 Run 2 Run 3 200K 400K 600K 800K 1000K SE +/- 813.54, N = 3 SE +/- 1182.87, N = 3 SE +/- 1412.73, N = 3 782026 786424 787311
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Run 3 Run 2 Run 1 14K 28K 42K 56K 70K SE +/- 311.37, N = 3 SE +/- 160.47, N = 3 SE +/- 647.95, N = 3 65815.1 66080.2 66685.4
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Run 1 Run 2 Run 3 9K 18K 27K 36K 45K SE +/- 270.60, N = 3 SE +/- 194.72, N = 3 SE +/- 168.71, N = 3 42836.1 43240.4 43241.4
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Run 1 Run 3 Run 2 9K 18K 27K 36K 45K SE +/- 52.49, N = 3 SE +/- 47.28, N = 3 SE +/- 27.18, N = 3 43487.5 43704.9 43886.8
Phoronix Test Suite v10.8.4