litert Ryzen 7 9800X3D AMD Ryzen 7 9800X3D 8-Core testing with a ASRock X870E Taichi (3.09.AS03 BIOS) and AMD Radeon RX 7900 GRE 16GB on Ubuntu 24.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2411063-PTS-LITERTRY63&sor&grw .
litert Ryzen 7 9800X3D Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution Run 1 Run 2 Run 3 Run 4 AMD Ryzen 7 9800X3D 8-Core @ 5.27GHz (8 Cores / 16 Threads) ASRock X870E Taichi (3.09.AS03 BIOS) AMD Device 14d8 2 x 16GB DDR5-6000MT/s F5-6000J2836G16G 2000GB Corsair MP700 PRO AMD Radeon RX 7900 GRE 16GB AMD Navi 31 HDMI/DP DELL U2723QE Realtek Device 8126 + MEDIATEK Device 0717 Ubuntu 24.04 6.10.0-phx (x86_64) GNOME Shell 46.0 X Server + Wayland 4.6 Mesa 24.2~git2406040600.8112d4~oibaf~n (git-8112d44 2024-06-04 noble-oibaf-ppa) (LLVM 17.0.6 DRM 3.57) GCC 13.2.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Processor Details - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xb404023 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
litert Ryzen 7 9800X3D litert: Quantized COCO SSD MobileNet v1 litert: Mobilenet Quant litert: Inception ResNet V2 litert: Mobilenet Float litert: NASNet Mobile litert: Inception V4 litert: SqueezeNet litert: DeepLab V3 Run 1 Run 2 Run 3 Run 4 1252.07 744.188 14569.6 721.061 5372.17 17514.8 1160.02 1304.52 1246.92 748.334 14574.7 725.302 5429.64 17512.0 1158.96 1307.47 1255.82 740.880 14598.0 726.579 5386.01 17531.1 1162.13 1318.59 1246.74 741.328 14620.7 723.586 5358.58 17517.7 1163.65 1361.51 OpenBenchmarking.org
LiteRT Model: Quantized COCO SSD MobileNet v1 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Quantized COCO SSD MobileNet v1 Run 4 Run 2 Run 1 Run 3 300 600 900 1200 1500 SE +/- 2.57, N = 3 SE +/- 4.68, N = 3 SE +/- 1.95, N = 3 SE +/- 4.03, N = 3 1246.74 1246.92 1252.07 1255.82
LiteRT Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Quant Run 3 Run 4 Run 1 Run 2 160 320 480 640 800 SE +/- 2.10, N = 3 SE +/- 2.89, N = 3 SE +/- 4.97, N = 3 SE +/- 1.67, N = 3 740.88 741.33 744.19 748.33
LiteRT Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception ResNet V2 Run 1 Run 2 Run 3 Run 4 3K 6K 9K 12K 15K SE +/- 26.94, N = 3 SE +/- 16.44, N = 3 SE +/- 9.20, N = 3 SE +/- 11.15, N = 3 14569.6 14574.7 14598.0 14620.7
LiteRT Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Mobilenet Float Run 1 Run 4 Run 2 Run 3 160 320 480 640 800 SE +/- 0.85, N = 3 SE +/- 1.21, N = 3 SE +/- 1.37, N = 3 SE +/- 0.51, N = 3 721.06 723.59 725.30 726.58
LiteRT Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: NASNet Mobile Run 4 Run 1 Run 3 Run 2 1200 2400 3600 4800 6000 SE +/- 8.05, N = 3 SE +/- 25.17, N = 3 SE +/- 13.10, N = 3 SE +/- 9.53, N = 3 5358.58 5372.17 5386.01 5429.64
LiteRT Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: Inception V4 Run 2 Run 1 Run 4 Run 3 4K 8K 12K 16K 20K SE +/- 11.00, N = 3 SE +/- 6.93, N = 3 SE +/- 144.50, N = 3 SE +/- 46.03, N = 3 17512.0 17514.8 17517.7 17531.1
LiteRT Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: SqueezeNet Run 2 Run 1 Run 3 Run 4 300 600 900 1200 1500 SE +/- 1.86, N = 3 SE +/- 1.98, N = 3 SE +/- 3.78, N = 3 SE +/- 1.70, N = 3 1158.96 1160.02 1162.13 1163.65
LiteRT Model: DeepLab V3 OpenBenchmarking.org Microseconds, Fewer Is Better LiteRT 2024-10-15 Model: DeepLab V3 Run 1 Run 2 Run 3 Run 4 300 600 900 1200 1500 SE +/- 9.61, N = 3 SE +/- 11.58, N = 3 SE +/- 15.19, N = 4 SE +/- 6.95, N = 3 1304.52 1307.47 1318.59 1361.51
Phoronix Test Suite v10.8.5