Tensorflow-Lite_FLOAT Intel Core i7-9750H testing with a Dell 0F7T8V (1.14.0 BIOS) and NVIDIA GeForce RTX 2070 with Max-Q Design 8GB on EndeavourOS rolling via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2304136-EIRI-230412085&rdt .
Tensorflow-Lite_FLOAT Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution RTX-2070MQ_UHD-630_i7-9750H RTX-2070MQ_UHD-630_i7-9750H-Xanmod Intel Core i7-9750H @ 4.50GHz (6 Cores / 12 Threads) Dell 0F7T8V (1.14.0 BIOS) Intel Cannon Lake PCH 32GB 2000GB Samsung SSD 970 EVO Plus 2TB + 1000GB CT1000MX500SSD1 NVIDIA GeForce RTX 2070 with Max-Q Design 8GB Realtek ALC3204 Realtek Device 2502 + Intel-AC 9260 EndeavourOS rolling 6.2.10-arch1-1 (x86_64) KDE Plasma 5.27.4 X Server 1.21.1.8 NVIDIA 530.41.03 4.6.0 OpenCL 3.0 + OpenCL 3.0 CUDA 12.1.98 GCC 12.2.1 20230201 + Clang 15.0.7 + LLVM 15.0.7 + CUDA 12.1 ext4 1920x1080 6.2.10-x64v1-xanmod1-1 (x86_64) OpenBenchmarking.org Kernel Details - RTX-2070MQ_UHD-630_i7-9750H: Transparent Huge Pages: always - RTX-2070MQ_UHD-630_i7-9750H-Xanmod: Transparent Huge Pages: madvise Processor Details - RTX-2070MQ_UHD-630_i7-9750H: Scaling Governor: intel_pstate powersave (EPP: performance) - CPU Microcode: 0xf0 - RTX-2070MQ_UHD-630_i7-9750H-Xanmod: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf0 Security Details - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: vulnerable + mds: Vulnerable; SMT vulnerable + meltdown: Vulnerable + mmio_stale_data: Vulnerable + retbleed: Vulnerable + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled PBRSB-eIBRS: Not affected + srbds: Vulnerable + tsx_async_abort: Not affected
Tensorflow-Lite_FLOAT tensorflow-lite: Mobilenet Float Difference Standard Error Standard Deviation RTX-2070MQ_UHD-630_i7-9750H RTX-2070MQ_UHD-630_i7-9750H-Xanmod 4422.46 1.08x 56.20 2.20% 4812.70 1.00x 12.44 0.45% OpenBenchmarking.org
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float RTX-2070MQ_UHD-630_i7-9750H RTX-2070MQ_UHD-630_i7-9750H-Xanmod 1000 2000 3000 4000 5000 SE +/- 56.20, N = 3 SE +/- 12.44, N = 3 4422.46 4812.70
Phoronix Test Suite v10.8.5