novvy AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (1603 BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 22.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads), Motherboard: ASUS ROG ZENITH II EXTREME (1603 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: Samsung SSD 980 PRO 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 6.2.0-32-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.49), Vulkan: 1.2.204, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3840x2160 b: Processor: AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads), Motherboard: ASUS ROG ZENITH II EXTREME (1603 BIOS), Chipset: AMD Starship/Matisse, Memory: 64GB, Disk: Samsung SSD 980 PRO 500GB, Graphics: AMD Radeon RX 5700 8GB (1750/875MHz), Audio: AMD Navi 10 HDMI Audio, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 OS: Ubuntu 22.04, Kernel: 6.2.0-32-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.49), Vulkan: 1.2.204, Compiler: GCC 11.4.0, File-System: ext4, Screen Resolution: 3840x2160 C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 8MB MB/s > Higher Is Better a . 14524.6 |================================================================== b . 14553.4 |================================================================== C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 16MB MB/s > Higher Is Better a . 14681.1 |================================================================= b . 15007.0 |================================================================== C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 32MB MB/s > Higher Is Better a . 13648.4 |================================================================= b . 13927.4 |================================================================== C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 64MB MB/s > Higher Is Better a . 11647.2 |================================================================== b . 11499.4 |================================================================= C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 8MB MB/s > Higher Is Better a . 11333.4 |================================================================== b . 10921.7 |================================================================ C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 128MB MB/s > Higher Is Better a . 9128.9 |=================================================================== b . 8600.5 |=============================================================== C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 256MB MB/s > Higher Is Better a . 6794.6 |=================================================================== b . 6173.9 |============================================================= C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 8MB MB/s > Higher Is Better a . 12902.5 |================================================================== b . 12733.1 |================================================================= C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 16MB MB/s > Higher Is Better a . 11117.3 |================================================================== b . 10930.2 |================================================================= C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 32MB MB/s > Higher Is Better a . 10114.3 |================================================================== b . 9830.1 |================================================================ C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 64MB MB/s > Higher Is Better a . 8272.0 |=================================================================== b . 7935.6 |================================================================ C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 16MB MB/s > Higher Is Better a . 13502.4 |================================================================== b . 13204.9 |================================================================= C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 32MB MB/s > Higher Is Better a . 12653.7 |================================================================== b . 12401.9 |================================================================= C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 64MB MB/s > Higher Is Better a . 10766.7 |================================================================== b . 10607.5 |================================================================= C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 128MB MB/s > Higher Is Better a . 6839.2 |=================================================================== b . 6452.2 |=============================================================== C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 256MB MB/s > Higher Is Better a . 5388.7 |=================================================================== b . 4975.7 |============================================================== C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 128MB MB/s > Higher Is Better a . 8726.0 |=================================================================== b . 8241.7 |=============================================================== C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 256MB MB/s > Higher Is Better a . 6511.1 |=================================================================== b . 5971.1 |============================================================= QuantLib 1.32 Configuration: Multi-Threaded MFLOPS > Higher Is Better a . 110940.4 |================================================================= b . 111297.1 |================================================================= QuantLib 1.32 Configuration: Single-Threaded MFLOPS > Higher Is Better a . 2935.3 |================================================================== b . 2962.1 |=================================================================== CloverLeaf 1.3 Input: clover_bm Seconds < Lower Is Better a . 26.36 |================================================================= b . 27.46 |==================================================================== CloverLeaf 1.3 Input: clover_bm16 Seconds < Lower Is Better a . 1297.63 |================================================================== b . 1307.50 |================================================================== CloverLeaf 1.3 Input: clover_bm64_short Seconds < Lower Is Better a . 150.81 |=================================================================== b . 151.11 |=================================================================== QMCPACK 3.17.1 Input: H4_ae Total Execution Time - Seconds < Lower Is Better a . 14.70 |==================================================================== b . 14.49 |=================================================================== QMCPACK 3.17.1 Input: Li2_STO_ae Total Execution Time - Seconds < Lower Is Better a . 132.36 |=================================================================== b . 132.12 |=================================================================== QMCPACK 3.17.1 Input: LiH_ae_MSD Total Execution Time - Seconds < Lower Is Better a . 113.41 |=================================================================== b . 110.56 |================================================================= QMCPACK 3.17.1 Input: simple-H2O Total Execution Time - Seconds < Lower Is Better a . 27.06 |==================================================================== b . 26.90 |==================================================================== QMCPACK 3.17.1 Input: O_ae_pyscf_UHF Total Execution Time - Seconds < Lower Is Better a . 195.27 |=================================================================== b . 195.12 |=================================================================== QMCPACK 3.17.1 Input: FeCO6_b3lyp_gms Total Execution Time - Seconds < Lower Is Better a . 172.30 |=================================================================== b . 172.23 |=================================================================== easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 240 Seconds < Lower Is Better a . 3.321 |=================================================================== b . 3.395 |==================================================================== easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200 Seconds < Lower Is Better a . 148.24 |================================================================= b . 153.82 |=================================================================== easyWave r34 Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400 Seconds < Lower Is Better a . 412.54 |================================================================= b . 428.29 |=================================================================== Embree 4.3 Binary: Pathtracer - Model: Crown Frames Per Second > Higher Is Better a . 38.09 |==================================================================== b . 38.04 |==================================================================== Embree 4.3 Binary: Pathtracer ISPC - Model: Crown Frames Per Second > Higher Is Better a . 33.83 |==================================================================== b . 33.77 |==================================================================== Embree 4.3 Binary: Pathtracer - Model: Asian Dragon Frames Per Second > Higher Is Better a . 38.06 |==================================================================== b . 37.51 |=================================================================== Embree 4.3 Binary: Pathtracer - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 33.62 |==================================================================== b . 33.18 |=================================================================== Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Frames Per Second > Higher Is Better a . 36.70 |==================================================================== b . 36.40 |=================================================================== Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Frames Per Second > Higher Is Better a . 31.65 |==================================================================== b . 31.28 |=================================================================== Intel Open Image Denoise 2.1 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better a . 1.14 |===================================================================== b . 1.14 |===================================================================== Intel Open Image Denoise 2.1 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only Images / Sec > Higher Is Better a . 1.14 |===================================================================== b . 1.14 |===================================================================== Intel Open Image Denoise 2.1 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only Images / Sec > Higher Is Better a . 0.57 |===================================================================== b . 0.57 |===================================================================== OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC Items / Sec > Higher Is Better a . 554 |====================================================================== b . 552 |====================================================================== OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU Scalar Items / Sec > Higher Is Better a . 311 |====================================================================== b . 311 |====================================================================== Timed Gem5 Compilation 23.0.1 Time To Compile Seconds < Lower Is Better a . 301.84 |=================================================================== b . 291.05 |================================================================= oneDNN 3.3 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1.51732 |================================================================== b . 1.40003 |============================================================= oneDNN 3.3 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 5.30723 |================================================================== b . 5.30471 |================================================================== oneDNN 3.3 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.35399 |================================================================ b . 1.39743 |================================================================== oneDNN 3.3 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 0.972836 |================================================================= b . 0.970336 |================================================================= oneDNN 3.3 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 6.75167 |================================================================== b . 6.79235 |================================================================== oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 5.59343 |================================================================== b . 5.55480 |================================================================== oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 2.74341 |================================================================== b . 2.74744 |================================================================== oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 7.3594 |=================================================================== b . 7.3635 |=================================================================== oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.54036 |================================================================== b . 1.55034 |================================================================== oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1.54437 |================================================================= b . 1.56101 |================================================================== oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 3894.96 |================================================================== b . 3914.95 |================================================================== oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU ms < Lower Is Better a . 1090.13 |================================================================== b . 1094.58 |================================================================== oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 3938.81 |================================================================== b . 3925.64 |================================================================== oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU ms < Lower Is Better a . 1097.99 |================================================================== b . 1101.56 |================================================================== oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 3924.43 |================================================================== b . 3935.10 |================================================================== oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU ms < Lower Is Better a . 1101.21 |================================================================== b . 1094.99 |================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 4191 |===================================================================== b . 4196 |===================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 4289 |===================================================================== b . 4299 |===================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 4963 |===================================================================== b . 4981 |===================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 73331 |==================================================================== b . 73227 |==================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 140574 |=================================================================== b . 140056 |=================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 75018 |==================================================================== b . 74992 |==================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 143476 |=================================================================== b . 143606 |=================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 85890 |==================================================================== b . 86000 |==================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 165158 |=================================================================== b . 165029 |=================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 1057 |===================================================================== b . 1058 |===================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 1081 |===================================================================== b . 1076 |===================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 1251 |===================================================================== b . 1252 |===================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 16836 |==================================================================== b . 16814 |==================================================================== OSPRay Studio 0.13 Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 40015 |==================================================================== b . 40024 |==================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 17147 |==================================================================== b . 17193 |==================================================================== OSPRay Studio 0.13 Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 40607 |==================================================================== b . 40704 |==================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 20005 |==================================================================== b . 19971 |==================================================================== OSPRay Studio 0.13 Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU ms < Lower Is Better a . 46279 |==================================================================== b . 46238 |==================================================================== Cpuminer-Opt 23.5 Algorithm: Magi kH/s > Higher Is Better a . 973.65 |=================================================================== b . 969.25 |=================================================================== Cpuminer-Opt 23.5 Algorithm: scrypt kH/s > Higher Is Better a . 335.46 |=================================================================== b . 335.25 |=================================================================== Cpuminer-Opt 23.5 Algorithm: Deepcoin kH/s > Higher Is Better a . 11310 |==================================================================== b . 11310 |==================================================================== Cpuminer-Opt 23.5 Algorithm: Ringcoin kH/s > Higher Is Better a . 4585.89 |================================================================== b . 4575.65 |================================================================== Cpuminer-Opt 23.5 Algorithm: Blake-2 S kH/s > Higher Is Better a . 206350 |=================================================================== b . 206270 |=================================================================== Cpuminer-Opt 23.5 Algorithm: Garlicoin kH/s > Higher Is Better a . 1440.1 |=================================================================== b . 1431.7 |=================================================================== Cpuminer-Opt 23.5 Algorithm: Skeincoin kH/s > Higher Is Better a . 49520 |==================================================================== b . 49200 |==================================================================== Cpuminer-Opt 23.5 Algorithm: Myriad-Groestl kH/s > Higher Is Better a . 16380 |==================================================================== b . 16390 |==================================================================== Cpuminer-Opt 23.5 Algorithm: LBC, LBRY Credits kH/s > Higher Is Better a . 21810 |==================================================================== b . 21810 |==================================================================== Cpuminer-Opt 23.5 Algorithm: Quad SHA-256, Pyrite kH/s > Higher Is Better a . 75090 |==================================================================== b . 75110 |==================================================================== Cpuminer-Opt 23.5 Algorithm: Triple SHA-256, Onecoin kH/s > Higher Is Better a . 106820 |=================================================================== b . 106780 |=================================================================== OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a . 8.98 |===================================================================== b . 8.98 |===================================================================== OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a . 1769.17 |================================================================== b . 1768.09 |================================================================== OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a . 63.37 |==================================================================== b . 62.81 |=================================================================== OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a . 252.40 |=================================================================== b . 254.29 |=================================================================== OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better a . 63.23 |==================================================================== b . 63.29 |==================================================================== OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU ms < Lower Is Better a . 252.67 |=================================================================== b . 252.37 |=================================================================== OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a . 465.19 |=================================================================== b . 466.04 |=================================================================== OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a . 34.33 |==================================================================== b . 34.27 |==================================================================== OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 11.43 |==================================================================== b . 11.42 |==================================================================== OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 1394.76 |================================================================== b . 1397.89 |================================================================== OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU FPS > Higher Is Better a . 2556.07 |================================================================== b . 2559.91 |================================================================== OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU ms < Lower Is Better a . 6.24 |===================================================================== b . 6.23 |===================================================================== OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU FPS > Higher Is Better a . 81.55 |==================================================================== b . 81.71 |==================================================================== OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU ms < Lower Is Better a . 196.00 |=================================================================== b . 195.62 |=================================================================== OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 900.08 |=================================================================== b . 902.81 |=================================================================== OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 17.76 |==================================================================== b . 17.71 |==================================================================== OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better a . 851.68 |=================================================================== b . 847.73 |=================================================================== OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better a . 18.76 |==================================================================== b . 18.85 |==================================================================== OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU FPS > Higher Is Better a . 2914.91 |================================================================== b . 2907.71 |================================================================== OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU ms < Lower Is Better a . 5.48 |===================================================================== b . 5.49 |===================================================================== OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU FPS > Higher Is Better a . 406.48 |=================================================================== b . 400.92 |================================================================== OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU ms < Lower Is Better a . 39.32 |=================================================================== b . 39.86 |==================================================================== OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a . 94.09 |==================================================================== b . 93.13 |=================================================================== OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a . 169.89 |================================================================== b . 171.57 |=================================================================== OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 1134.72 |================================================================== b . 1133.46 |================================================================== OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 28.18 |==================================================================== b . 28.21 |==================================================================== OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a . 1139.38 |================================================================== b . 1147.76 |================================================================== OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a . 14.02 |==================================================================== b . 13.92 |==================================================================== OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU FPS > Higher Is Better a . 333.33 |=================================================================== b . 330.63 |================================================================== OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU ms < Lower Is Better a . 95.92 |=================================================================== b . 96.70 |==================================================================== OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a . 27213.10 |================================================================= b . 27049.12 |================================================================= OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a . 1.16 |==================================================================== b . 1.17 |===================================================================== OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU FPS > Higher Is Better a . 358.24 |================================================================== b . 364.05 |=================================================================== OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU ms < Lower Is Better a . 89.24 |==================================================================== b . 87.83 |=================================================================== OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a . 39083.44 |================================================================= b . 38988.78 |================================================================= OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a . 0.81 |===================================================================== b . 0.81 |=====================================================================