TensorFlow Lite AMD Ryzen Threadripper AMD Ryzen Threadripper 3960X 24-Core testing with a MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) and Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2008237-FI-TENSORFLO23&sor&grs .
TensorFlow Lite AMD Ryzen Threadripper Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution TR 3960X Vet 2 Vet 3 AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads) MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) AMD Starship/Matisse 32GB 1000GB Sabrent Rocket 4.0 1TB Sapphire AMD Radeon RX 5500/5500M / Pro 5500M 4GB (1900/875MHz) AMD Navi 10 HDMI 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 3.36.3 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 20.0.8 (LLVM 10.0.0) GCC 9.3.0 ext4 3840x2160 GNOME Shell 3.36.4 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
TensorFlow Lite AMD Ryzen Threadripper tensorflow-lite: SqueezeNet tensorflow-lite: Mobilenet Float tensorflow-lite: Mobilenet Quant tensorflow-lite: Inception V4 tensorflow-lite: NASNet Mobile tensorflow-lite: Inception ResNet V2 TR 3960X Vet 2 Vet 3 76058.7 51035.5 52131.1 1137923 86858.3 1007423 75628.9 51344.7 52306.2 1136157 86852.5 1007393 75472.6 51110.6 52160.5 1134943 86655.8 1006490 OpenBenchmarking.org
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Vet 3 Vet 2 TR 3960X 16K 32K 48K 64K 80K SE +/- 295.88, N = 3 SE +/- 329.17, N = 3 SE +/- 97.87, N = 3 75472.6 75628.9 76058.7
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float TR 3960X Vet 3 Vet 2 11K 22K 33K 44K 55K SE +/- 148.03, N = 3 SE +/- 192.51, N = 3 SE +/- 73.95, N = 3 51035.5 51110.6 51344.7
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant TR 3960X Vet 3 Vet 2 11K 22K 33K 44K 55K SE +/- 72.23, N = 3 SE +/- 104.73, N = 3 SE +/- 124.19, N = 3 52131.1 52160.5 52306.2
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Vet 3 Vet 2 TR 3960X 200K 400K 600K 800K 1000K SE +/- 881.67, N = 3 SE +/- 1424.48, N = 3 SE +/- 688.10, N = 3 1134943 1136157 1137923
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Vet 3 Vet 2 TR 3960X 20K 40K 60K 80K 100K SE +/- 271.25, N = 3 SE +/- 118.06, N = 3 SE +/- 144.60, N = 3 86655.8 86852.5 86858.3
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Vet 3 Vet 2 TR 3960X 200K 400K 600K 800K 1000K SE +/- 1302.93, N = 3 SE +/- 761.50, N = 3 SE +/- 450.42, N = 3 1006490 1007393 1007423
Phoronix Test Suite v10.8.5