ffhgf AMD Ryzen 5 5500U testing with a NB01 TUXEDO Aura 15 Gen2 NL5xNU (1.07.11RTR1 BIOS) and AMD Lucienne 512MB on Tuxedo 22.04 via the Phoronix Test Suite. a: Processor: AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads), Motherboard: NB01 TUXEDO Aura 15 Gen2 NL5xNU (1.07.11RTR1 BIOS), Chipset: AMD Renoir/Cezanne, Memory: 2 x 8GB DDR4-3200MT/s Samsung M471A1K43DB1-CWE, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Lucienne 512MB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX200 OS: Tuxedo 22.04, Kernel: 6.0.0-1010-oem (x86_64), Desktop: KDE Plasma 5.26.5, Display Server: X Server 1.21.1.3, OpenGL: 4.6 Mesa 22.3.7 (LLVM 14.0.0 DRM 3.48), Vulkan: 1.3.230, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1920x1080 b: Processor: AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads), Motherboard: NB01 TUXEDO Aura 15 Gen2 NL5xNU (1.07.11RTR1 BIOS), Chipset: AMD Renoir/Cezanne, Memory: 2 x 8GB DDR4-3200MT/s Samsung M471A1K43DB1-CWE, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Lucienne 512MB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX200 OS: Tuxedo 22.04, Kernel: 6.0.0-1010-oem (x86_64), Desktop: KDE Plasma 5.26.5, Display Server: X Server 1.21.1.3, OpenGL: 4.6 Mesa 22.3.7 (LLVM 14.0.0 DRM 3.48), Vulkan: 1.3.230, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1920x1080 c: Processor: AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads), Motherboard: NB01 TUXEDO Aura 15 Gen2 NL5xNU (1.07.11RTR1 BIOS), Chipset: AMD Renoir/Cezanne, Memory: 2 x 8GB DDR4-3200MT/s Samsung M471A1K43DB1-CWE, Disk: Samsung SSD 970 EVO Plus 500GB, Graphics: AMD Lucienne 512MB (1800/400MHz), Audio: AMD Renoir Radeon HD Audio, Network: Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX200 OS: Tuxedo 22.04, Kernel: 6.0.0-1010-oem (x86_64), Desktop: KDE Plasma 5.26.5, Display Server: X Server 1.21.1.3, OpenGL: 4.6 Mesa 22.3.7 (LLVM 14.0.0 DRM 3.48), Vulkan: 1.3.230, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1920x1080 JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 80 MP/s > Higher Is Better a . 17.59 |==================================================================== b . 17.51 |==================================================================== c . 17.61 |==================================================================== JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 90 MP/s > Higher Is Better a . 16.21 |==================================================================== b . 16.19 |==================================================================== c . 16.28 |==================================================================== JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 80 MP/s > Higher Is Better a . 17.45 |==================================================================== b . 17.45 |==================================================================== c . 17.53 |==================================================================== JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 90 MP/s > Higher Is Better a . 16.51 |==================================================================== b . 16.49 |==================================================================== c . 16.49 |==================================================================== JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 100 MP/s > Higher Is Better a . 6.880 |==================================================================== b . 6.880 |==================================================================== c . 6.897 |==================================================================== JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 100 MP/s > Higher Is Better a . 6.808 |==================================================================== b . 6.812 |==================================================================== c . 6.815 |==================================================================== JPEG-XL Decoding libjxl 0.10.1 CPU Threads: 1 MP/s > Higher Is Better a . 54.82 |=================================================================== b . 55.06 |=================================================================== c . 55.73 |==================================================================== JPEG-XL Decoding libjxl 0.10.1 CPU Threads: All MP/s > Higher Is Better a . 191.40 |================================================================= b . 197.72 |=================================================================== c . 197.64 |=================================================================== srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Total Mbps > Higher Is Better a . 2124.4 |=================================================================== b . 2110.1 |=================================================================== c . 2116.7 |=================================================================== srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Thread Mbps > Higher Is Better a . 314.8 |==================================================================== b . 302.6 |================================================================= c . 307.0 |================================================================== SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 2.060 |=================================================================== b . 2.073 |==================================================================== c . 2.077 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 16.29 |=================================================================== b . 16.46 |==================================================================== c . 16.48 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 43.43 |================================================================= b . 45.38 |==================================================================== c . 45.44 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 45.11 |=================================================================== b . 45.65 |==================================================================== c . 45.47 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 7.495 |=================================================================== b . 7.555 |==================================================================== c . 7.569 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 51.48 |=================================================================== b . 52.06 |==================================================================== c . 52.16 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 202.30 |================================================================== b . 206.83 |=================================================================== c . 204.57 |================================================================== SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 245.38 |================================================================= b . 250.82 |=================================================================== c . 252.60 |=================================================================== Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression Seconds < Lower Is Better a . 14.58 |==================================================================== b . 14.51 |==================================================================== c . 14.49 |==================================================================== Primesieve 12.1 Length: 1e12 Seconds < Lower Is Better a . 37.34 |==================================================================== b . 36.22 |================================================================== c . 36.28 |================================================================== Primesieve 12.1 Length: 1e13 Seconds < Lower Is Better a . 473.57 |=================================================================== b . 464.65 |================================================================== c . 463.00 |================================================================== oneDNN 3.4 Harness: IP Shapes 1D - Engine: CPU ms < Lower Is Better a . 7.22621 |================================================================= b . 7.32690 |================================================================== c . 7.19520 |================================================================= oneDNN 3.4 Harness: IP Shapes 3D - Engine: CPU ms < Lower Is Better a . 14.39 |==================================================================== b . 14.34 |==================================================================== c . 14.29 |==================================================================== oneDNN 3.4 Harness: Convolution Batch Shapes Auto - Engine: CPU ms < Lower Is Better a . 22.49 |==================================================================== b . 22.58 |==================================================================== c . 22.59 |==================================================================== oneDNN 3.4 Harness: Deconvolution Batch shapes_1d - Engine: CPU ms < Lower Is Better a . 11.76 |================================================================== b . 12.09 |==================================================================== c . 11.52 |================================================================= oneDNN 3.4 Harness: Deconvolution Batch shapes_3d - Engine: CPU ms < Lower Is Better a . 11.72 |=================================================================== b . 11.93 |==================================================================== c . 11.67 |=================================================================== oneDNN 3.4 Harness: Recurrent Neural Network Training - Engine: CPU ms < Lower Is Better a . 6067.92 |================================================================== b . 6016.25 |================================================================= c . 6024.94 |================================================================== oneDNN 3.4 Harness: Recurrent Neural Network Inference - Engine: CPU ms < Lower Is Better a . 3135.38 |================================================================== b . 3110.94 |================================================================= c . 3118.61 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 4.3724 |================================================================== b . 4.4546 |=================================================================== c . 4.4236 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 681.91 |=================================================================== b . 670.45 |================================================================== c . 672.11 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 4.3416 |=================================================================== b . 4.3352 |=================================================================== c . 4.3490 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 230.32 |=================================================================== b . 230.66 |=================================================================== c . 229.93 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 101.43 |=================================================================== b . 101.56 |=================================================================== c . 101.71 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 29.53 |==================================================================== b . 29.49 |==================================================================== c . 29.45 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 85.91 |=================================================================== b . 86.71 |==================================================================== c . 86.83 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 11.63 |==================================================================== b . 11.52 |=================================================================== c . 11.51 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 50.03 |================================================================== b . 51.54 |==================================================================== c . 50.62 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 59.90 |==================================================================== b . 58.17 |================================================================== c . 59.21 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 46.55 |==================================================================== b . 46.77 |==================================================================== c . 46.72 |==================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 21.47 |==================================================================== b . 21.37 |==================================================================== c . 21.39 |==================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 312.38 |================================================================== b . 314.95 |=================================================================== c . 314.54 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 9.5805 |=================================================================== b . 9.5031 |================================================================== c . 9.5153 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 220.43 |=================================================================== b . 217.64 |================================================================== c . 221.31 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 4.5244 |================================================================== b . 4.5824 |=================================================================== c . 4.5062 |================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream items/sec > Higher Is Better Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 50.65 |=================================================================== b . 51.30 |==================================================================== c . 51.31 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 59.15 |==================================================================== b . 58.45 |=================================================================== c . 58.40 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 46.70 |==================================================================== b . 46.64 |==================================================================== c . 46.77 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 21.40 |==================================================================== b . 21.43 |==================================================================== c . 21.37 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 24.92 |=================================================================== b . 25.18 |==================================================================== c . 25.01 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 120.27 |=================================================================== b . 118.96 |================================================================== c . 119.90 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 23.10 |==================================================================== b . 23.11 |==================================================================== c . 23.06 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 43.28 |==================================================================== b . 43.27 |==================================================================== c . 43.35 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 40.87 |==================================================================== b . 40.95 |==================================================================== c . 40.89 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 73.35 |==================================================================== b . 73.18 |==================================================================== c . 73.30 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 37.44 |==================================================================== b . 37.53 |==================================================================== c . 37.51 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 26.70 |==================================================================== b . 26.64 |==================================================================== c . 26.65 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 4.7151 |=================================================================== b . 4.7167 |=================================================================== c . 4.7347 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 634.54 |=================================================================== b . 633.89 |=================================================================== c . 632.75 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 4.7614 |=================================================================== b . 4.7630 |=================================================================== c . 4.7761 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 210.01 |=================================================================== b . 209.94 |=================================================================== c . 209.36 |=================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 51.41 |==================================================================== b . 51.19 |==================================================================== c . 51.14 |==================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 58.31 |==================================================================== b . 58.55 |==================================================================== c . 58.60 |==================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 39.03 |==================================================================== b . 39.02 |==================================================================== c . 39.09 |==================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 25.61 |==================================================================== b . 25.61 |==================================================================== c . 25.57 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 4.5018 |=================================================================== b . 4.4900 |=================================================================== c . 4.4900 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 665.18 |=================================================================== b . 665.49 |=================================================================== c . 666.74 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 4.3554 |=================================================================== b . 4.3580 |=================================================================== c . 4.3291 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 229.59 |=================================================================== b . 229.45 |=================================================================== c . 230.98 |=================================================================== Google Draco 1.5.6 Model: Lion ms < Lower Is Better a . 6409 |===================================================================== b . 6315 |==================================================================== c . 6400 |===================================================================== Google Draco 1.5.6 Model: Church Facade ms < Lower Is Better a . 9515 |=================================================================== b . 9536 |=================================================================== c . 9766 |===================================================================== OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a . 1.45 |===================================================================== b . 1.44 |===================================================================== c . 1.45 |===================================================================== OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a . 2740.33 |================================================================== b . 2748.14 |================================================================== c . 2752.56 |================================================================== OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a . 14.83 |==================================================================== b . 14.56 |================================================================== c . 14.90 |==================================================================== OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a . 269.72 |================================================================== b . 274.43 |=================================================================== c . 268.20 |================================================================= OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better a . 14.71 |==================================================================== b . 14.57 |=================================================================== c . 14.51 |=================================================================== OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU ms < Lower Is Better a . 271.53 |================================================================== b . 274.00 |=================================================================== c . 275.49 |=================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a . 102.94 |================================================================== b . 103.79 |=================================================================== c . 103.13 |=================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a . 38.82 |==================================================================== b . 38.50 |=================================================================== c . 38.74 |==================================================================== OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 1.71 |===================================================================== b . 1.62 |================================================================= c . 1.62 |================================================================= OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 2321.44 |============================================================== b . 2456.33 |================================================================== c . 2437.33 |================================================================= OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU FPS > Higher Is Better a . 378.86 |=================================================================== b . 376.67 |=================================================================== c . 376.30 |=================================================================== OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU ms < Lower Is Better a . 10.53 |==================================================================== b . 10.59 |==================================================================== c . 10.60 |==================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU FPS > Higher Is Better a . 23.86 |==================================================================== b . 23.97 |==================================================================== c . 23.94 |==================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU ms < Lower Is Better a . 167.55 |=================================================================== b . 166.76 |=================================================================== c . 166.96 |=================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 141.94 |=================================================================== b . 140.29 |================================================================== c . 140.41 |================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 28.16 |=================================================================== b . 28.49 |==================================================================== c . 28.46 |==================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better a . 131.99 |=================================================================== b . 131.82 |=================================================================== c . 132.29 |=================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better a . 30.28 |==================================================================== b . 30.32 |==================================================================== c . 30.22 |==================================================================== OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU FPS > Higher Is Better a . 459.92 |=================================================================== b . 458.71 |=================================================================== c . 453.71 |================================================================== OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU ms < Lower Is Better a . 8.69 |==================================================================== b . 8.71 |==================================================================== c . 8.80 |===================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU FPS > Higher Is Better a . 70.33 |==================================================================== b . 70.31 |==================================================================== c . 70.01 |==================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU ms < Lower Is Better a . 56.83 |==================================================================== b . 56.84 |==================================================================== c . 57.09 |==================================================================== OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a . 17.17 |==================================================================== b . 17.27 |==================================================================== c . 17.26 |==================================================================== OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a . 232.78 |=================================================================== b . 231.30 |=================================================================== c . 231.39 |=================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 188.24 |=================================================================== b . 188.05 |=================================================================== c . 187.42 |=================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 31.85 |==================================================================== b . 31.89 |==================================================================== c . 32.00 |==================================================================== OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a . 191.40 |=================================================================== b . 191.00 |=================================================================== c . 190.23 |=================================================================== OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a . 20.87 |==================================================================== b . 20.92 |==================================================================== c . 21.00 |==================================================================== OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU FPS > Higher Is Better a . 221.74 |=================================================================== b . 221.65 |=================================================================== c . 221.88 |=================================================================== OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU ms < Lower Is Better a . 18.01 |==================================================================== b . 18.02 |==================================================================== c . 18.00 |==================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU FPS > Higher Is Better a . 60.91 |=================================================================== b . 61.46 |==================================================================== c . 61.48 |==================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU ms < Lower Is Better a . 98.43 |==================================================================== b . 97.56 |=================================================================== c . 97.51 |=================================================================== OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU FPS > Higher Is Better a . 212.60 |=================================================================== b . 212.76 |=================================================================== c . 211.95 |=================================================================== OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU ms < Lower Is Better a . 18.79 |==================================================================== b . 18.78 |==================================================================== c . 18.85 |==================================================================== OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a . 3160.64 |================================================================== b . 3147.58 |================================================================== c . 3154.67 |================================================================== OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a . 1.88 |===================================================================== b . 1.89 |===================================================================== c . 1.88 |===================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU FPS > Higher Is Better a . 65.59 |==================================================================== b . 65.61 |==================================================================== c . 65.60 |==================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU ms < Lower Is Better a . 91.44 |==================================================================== b . 91.39 |==================================================================== c . 91.41 |==================================================================== OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a . 5051.32 |================================================================== b . 5066.06 |================================================================== c . 5032.95 |================================================================== OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a . 1.18 |===================================================================== b . 1.17 |==================================================================== c . 1.18 |===================================================================== WavPack Audio Encoding 5.7 WAV To WavPack Seconds < Lower Is Better a . 7.692 |=================================================================== b . 7.578 |================================================================== c . 7.794 |==================================================================== Chaos Group V-RAY 6.0 Mode: CPU vsamples > Higher Is Better a . 7052 |===================================================================== b . 7019 |===================================================================== c . 7052 |=====================================================================