Core i9 10900K TensorFlow Lite Intel Core i9-10900K testing with a Gigabyte Z490 AORUS MASTER (F3 BIOS) and Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2008231-SYST-COREI9100&rdt .
Core i9 10900K TensorFlow Lite Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution Go 1 Go 2 Go 3 Intel Core i9-10900K @ 5.30GHz (10 Cores / 20 Threads) Gigabyte Z490 AORUS MASTER (F3 BIOS) Intel Comet Lake PCH 16GB Samsung SSD 970 EVO 250GB Gigabyte AMD Radeon RX 5500/5500M / Pro 5500M 8GB (1890/875MHz) Realtek ALC1220 DELL P2415Q Intel Device 15f3 + Intel Wi-Fi 6 AX201 Ubuntu 20.04 5.8.1-050801-generic (x86_64) GNOME Shell 3.36.3 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 20.2.0-devel (git-ef67218 2020-07-07 focal-oibaf-ppa) (LLVM 10.0.1) OpenCL 1.1 Mesa 20.2.0-devel (git-c977567db6) 1.2.131 GCC 9.3.0 ext4 3840x2160 OpenBenchmarking.org Processor Details - Scaling Governor: intel_pstate powersave - CPU Microcode: 0xc8 Security Details - itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Core i9 10900K 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 Go 1 Go 2 Go 3 167615 2379273 147414 114294 118651 2141807 167543 2375430 147181 114256 117317 2141663 167560 2374960 147213 114078 117410 2141327 OpenBenchmarking.org
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Go 1 Go 2 Go 3 40K 80K 120K 160K 200K SE +/- 25.12, N = 3 SE +/- 34.11, N = 3 SE +/- 15.56, N = 3 167615 167543 167560
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Go 1 Go 2 Go 3 500K 1000K 1500K 2000K 2500K SE +/- 3903.95, N = 3 SE +/- 11.55, N = 3 SE +/- 260.83, N = 3 2379273 2375430 2374960
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Go 1 Go 2 Go 3 30K 60K 90K 120K 150K SE +/- 66.02, N = 3 SE +/- 89.66, N = 3 SE +/- 144.80, N = 3 147414 147181 147213
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Go 1 Go 2 Go 3 20K 40K 60K 80K 100K SE +/- 141.41, N = 3 SE +/- 86.19, N = 3 SE +/- 50.71, N = 3 114294 114256 114078
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Go 1 Go 2 Go 3 30K 60K 90K 120K 150K SE +/- 1241.85, N = 3 SE +/- 141.34, N = 3 SE +/- 210.41, N = 3 118651 117317 117410
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Go 1 Go 2 Go 3 500K 1000K 1500K 2000K 2500K SE +/- 140.99, N = 3 SE +/- 37.12, N = 3 SE +/- 61.19, N = 3 2141807 2141663 2141327
Phoronix Test Suite v10.8.4