kdlkf AMD EPYC 8534P 64-Core testing with a AMD Cinnabar (RCB1009C BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite. a: Processor: AMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 23.10, Kernel: 6.5.0-15-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.7, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200 b: Processor: AMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 23.10, Kernel: 6.5.0-15-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.7, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200 c: Processor: AMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe OS: Ubuntu 23.10, Kernel: 6.5.0-15-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.7, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200 JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 80 MP/s > Higher Is Better a . 42.81 |================================================================= b . 40.41 |============================================================= c . 45.02 |==================================================================== JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 90 MP/s > Higher Is Better a . 36.94 |============================================================ b . 41.75 |==================================================================== c . 37.53 |============================================================= JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 80 MP/s > Higher Is Better a . 40.43 |=============================================================== b . 43.88 |==================================================================== c . 40.66 |=============================================================== JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 90 MP/s > Higher Is Better a . 39.59 |==================================================================== b . 38.18 |================================================================== c . 38.07 |================================================================= JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 100 MP/s > Higher Is Better a . 29.42 |==================================================================== b . 29.50 |==================================================================== c . 29.55 |==================================================================== JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 100 MP/s > Higher Is Better a . 30.19 |==================================================================== b . 30.03 |==================================================================== c . 29.92 |=================================================================== JPEG-XL Decoding libjxl 0.10.1 CPU Threads: 1 MP/s > Higher Is Better a . 49.66 |==================================================================== b . 49.68 |==================================================================== c . 49.75 |==================================================================== JPEG-XL Decoding libjxl 0.10.1 CPU Threads: All MP/s > Higher Is Better a . 551.29 |=================================================================== b . 546.96 |================================================================== c . 536.44 |================================================================= srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Total Mbps > Higher Is Better a . 21012.2 |================================================================== b . 21055.5 |================================================================== c . 20479.7 |================================================================ srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Thread Mbps > Higher Is Better a . 545.7 |=========================================================== b . 628.9 |==================================================================== c . 630.9 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 7.000 |==================================================================== b . 7.005 |==================================================================== c . 6.925 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 71.24 |==================================================================== b . 68.58 |================================================================= c . 69.50 |================================================================== SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 165.28 |=================================================================== b . 165.01 |=================================================================== c . 165.22 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a . 167.56 |=================================================================== b . 166.21 |================================================================== c . 165.24 |================================================================== SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 18.75 |=================================================================== b . 18.76 |=================================================================== c . 19.07 |==================================================================== SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 142.85 |================================================================== b . 142.25 |================================================================== c . 145.06 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 507.36 |=================================================================== b . 499.83 |================================================================== c . 509.75 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a . 577.70 |================================================================== b . 582.51 |=================================================================== c . 565.04 |================================================================= Stockfish 16.1 Chess Benchmark Nodes Per Second > Higher Is Better a . 98973914 |========================================================= b . 110763828 |================================================================ c . 97292518 |======================================================== Timed Linux Kernel Compilation 6.8 Build: defconfig Seconds < Lower Is Better a . 44.30 |==================================================================== b . 44.41 |==================================================================== c . 44.39 |==================================================================== Timed Linux Kernel Compilation 6.8 Build: allmodconfig Seconds < Lower Is Better a . 391.24 |=================================================================== b . 391.93 |=================================================================== c . 391.03 |=================================================================== Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression Seconds < Lower Is Better a . 2.016558 |============================================================ b . 2.170377 |================================================================= c . 2.057670 |============================================================== Primesieve 12.1 Length: 1e12 Seconds < Lower Is Better a . 3.556 |==================================================================== b . 3.554 |==================================================================== c . 3.531 |==================================================================== Primesieve 12.1 Length: 1e13 Seconds < Lower Is Better a . 42.90 |==================================================================== b . 42.76 |==================================================================== c . 42.84 |==================================================================== oneDNN 3.4 Harness: IP Shapes 1D - Engine: CPU ms < Lower Is Better a . 0.796392 |================================================================= b . 0.791773 |================================================================ c . 0.802263 |================================================================= oneDNN 3.4 Harness: IP Shapes 3D - Engine: CPU ms < Lower Is Better a . 0.990182 |================================================================= b . 0.992488 |================================================================= c . 0.991900 |================================================================= oneDNN 3.4 Harness: Convolution Batch Shapes Auto - Engine: CPU ms < Lower Is Better a . 1.18235 |================================================================== b . 1.18126 |================================================================== c . 1.17292 |================================================================= oneDNN 3.4 Harness: Deconvolution Batch shapes_1d - Engine: CPU ms < Lower Is Better a . 8.73308 |================================================================== b . 8.78255 |================================================================== c . 8.75546 |================================================================== oneDNN 3.4 Harness: Deconvolution Batch shapes_3d - Engine: CPU ms < Lower Is Better a . 1.45255 |================================================================== b . 1.45945 |================================================================== c . 1.45433 |================================================================== oneDNN 3.4 Harness: Recurrent Neural Network Training - Engine: CPU ms < Lower Is Better a . 746.67 |================================================================== b . 752.48 |=================================================================== c . 745.41 |================================================================== oneDNN 3.4 Harness: Recurrent Neural Network Inference - Engine: CPU ms < Lower Is Better a . 455.02 |=================================================================== b . 457.83 |=================================================================== c . 457.71 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 35.62 |==================================================================== b . 35.74 |==================================================================== c . 35.62 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 881.71 |=================================================================== b . 883.06 |=================================================================== c . 883.40 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 29.72 |==================================================================== b . 29.71 |==================================================================== c . 29.72 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 33.64 |==================================================================== b . 33.64 |==================================================================== c . 33.63 |==================================================================== 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 . 1442.79 |================================================================== b . 1439.29 |================================================================== c . 1440.70 |================================================================== 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 . 22.15 |==================================================================== b . 22.20 |==================================================================== c . 22.18 |==================================================================== 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 . 202.10 |================================================================== b . 203.93 |=================================================================== c . 201.04 |================================================================== 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 . 4.9422 |=================================================================== b . 4.8985 |================================================================== c . 4.9685 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 476.83 |=================================================================== b . 476.81 |=================================================================== c . 476.88 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 66.99 |==================================================================== b . 66.99 |==================================================================== c . 67.04 |==================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 187.28 |=================================================================== b . 187.20 |=================================================================== c . 187.46 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 5.3331 |=================================================================== b . 5.3354 |=================================================================== c . 5.3276 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 3769.72 |================================================================== b . 3790.80 |================================================================== c . 3797.24 |================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 8.4671 |=================================================================== b . 8.4216 |=================================================================== c . 8.4068 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 823.78 |=================================================================== b . 820.60 |=================================================================== c . 796.35 |================================================================= Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 1.2101 |================================================================= b . 1.2147 |================================================================= c . 1.2517 |=================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 2.8545 |=================================================================== b . 2.8315 |================================================================== c . 2.8225 |================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 9727.68 |================================================================= b . 9786.06 |================================================================== c . 9824.21 |================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 14.38 |==================================================================== b . 14.35 |==================================================================== c . 14.36 |==================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 69.50 |==================================================================== b . 69.64 |==================================================================== c . 69.62 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 477.05 |=================================================================== b . 476.53 |=================================================================== c . 476.82 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 66.97 |==================================================================== b . 67.01 |==================================================================== c . 66.99 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 186.97 |=================================================================== b . 187.00 |=================================================================== c . 186.67 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 5.3423 |=================================================================== b . 5.3412 |=================================================================== c . 5.3508 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 213.94 |=================================================================== b . 212.47 |=================================================================== c . 213.20 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 149.25 |=================================================================== b . 150.07 |=================================================================== c . 149.61 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 154.50 |=================================================================== b . 154.04 |=================================================================== c . 154.41 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 6.4656 |=================================================================== b . 6.4846 |=================================================================== c . 6.4692 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 314.47 |=================================================================== b . 315.29 |=================================================================== c . 314.48 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 101.53 |=================================================================== b . 101.31 |=================================================================== c . 101.63 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 136.97 |================================================================== b . 137.78 |=================================================================== c . 138.06 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 7.2927 |=================================================================== b . 7.2496 |=================================================================== c . 7.2356 |================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 62.35 |==================================================================== b . 62.30 |==================================================================== c . 62.39 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 509.31 |=================================================================== b . 508.60 |=================================================================== c . 507.72 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 44.11 |==================================================================== b . 44.07 |==================================================================== c . 44.06 |==================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 22.65 |==================================================================== b . 22.67 |==================================================================== c . 22.67 |==================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 685.23 |=================================================================== b . 686.68 |=================================================================== c . 683.77 |=================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 46.62 |==================================================================== b . 46.53 |==================================================================== c . 46.72 |==================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 64.49 |==================================================================== b . 64.42 |==================================================================== c . 64.01 |=================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 15.49 |=================================================================== b . 15.51 |==================================================================== c . 15.61 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better a . 35.76 |==================================================================== b . 35.59 |==================================================================== c . 35.68 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better a . 882.34 |=================================================================== b . 883.11 |=================================================================== c . 882.87 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better a . 29.75 |==================================================================== b . 29.74 |==================================================================== c . 29.76 |==================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better a . 33.60 |==================================================================== b . 33.61 |==================================================================== c . 33.60 |==================================================================== Google Draco 1.5.6 Model: Lion ms < Lower Is Better a . 6301 |===================================================================== b . 6258 |===================================================================== c . 6255 |==================================================================== Google Draco 1.5.6 Model: Church Facade ms < Lower Is Better a . 8195 |===================================================================== b . 8069 |==================================================================== c . 8162 |===================================================================== OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better a . 29.64 |==================================================================== b . 29.59 |==================================================================== c . 29.60 |==================================================================== OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU ms < Lower Is Better a . 1077.23 |================================================================== b . 1076.61 |================================================================== c . 1076.35 |================================================================== OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better a . 217.12 |=================================================================== b . 216.75 |=================================================================== c . 216.84 |=================================================================== OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better a . 147.21 |=================================================================== b . 147.48 |=================================================================== c . 147.42 |=================================================================== OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better a . 216.99 |=================================================================== b . 217.07 |=================================================================== c . 216.93 |=================================================================== OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU ms < Lower Is Better a . 147.33 |=================================================================== b . 147.26 |=================================================================== c . 147.35 |=================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better a . 1332.49 |================================================================== b . 1330.83 |================================================================== c . 1332.74 |================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better a . 23.96 |==================================================================== b . 23.99 |==================================================================== c . 23.96 |==================================================================== OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 56.39 |==================================================================== b . 56.45 |==================================================================== c . 56.51 |==================================================================== OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 564.47 |=================================================================== b . 564.47 |=================================================================== c . 564.32 |=================================================================== OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU FPS > Higher Is Better a . 6930.15 |================================================================== b . 6920.51 |================================================================== c . 6927.90 |================================================================== OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU ms < Lower Is Better a . 4.60 |===================================================================== b . 4.61 |===================================================================== c . 4.60 |===================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU FPS > Higher Is Better a . 556.51 |=================================================================== b . 546.67 |================================================================== c . 545.93 |================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU ms < Lower Is Better a . 57.43 |=================================================================== b . 58.46 |==================================================================== c . 58.54 |==================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 3015.55 |================================================================== b . 2988.49 |================================================================= c . 3012.81 |================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 10.59 |=================================================================== b . 10.69 |==================================================================== c . 10.60 |=================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better a . 2966.79 |================================================================== b . 2968.32 |================================================================== c . 2969.13 |================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better a . 21.55 |==================================================================== b . 21.54 |==================================================================== c . 21.53 |==================================================================== OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU FPS > Higher Is Better a . 9773.24 |================================================================== b . 9793.26 |================================================================== c . 9779.93 |================================================================== OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU ms < Lower Is Better a . 6.53 |===================================================================== b . 6.52 |===================================================================== c . 6.53 |===================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU FPS > Higher Is Better a . 1051.90 |================================================================== b . 1054.53 |================================================================== c . 1049.11 |================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU ms < Lower Is Better a . 30.38 |==================================================================== b . 30.30 |==================================================================== c . 30.46 |==================================================================== OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better a . 331.17 |=================================================================== b . 331.65 |=================================================================== c . 331.63 |=================================================================== OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better a . 96.50 |==================================================================== b . 96.35 |==================================================================== c . 96.38 |==================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better a . 5678.12 |================================================================== b . 5685.06 |================================================================== c . 5681.48 |================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better a . 11.26 |==================================================================== b . 11.24 |==================================================================== c . 11.25 |==================================================================== OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better a . 2974.20 |================================================================== b . 2945.11 |================================================================= c . 2934.13 |================================================================= OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better a . 10.73 |=================================================================== b . 10.84 |==================================================================== c . 10.88 |==================================================================== OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU FPS > Higher Is Better a . 3817.87 |================================================================== b . 3825.64 |================================================================== c . 3828.30 |================================================================== OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU ms < Lower Is Better a . 16.53 |==================================================================== b . 16.51 |==================================================================== c . 16.49 |==================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU FPS > Higher Is Better a . 1541.43 |================================================================== b . 1540.00 |================================================================== c . 1525.91 |================================================================= OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU ms < Lower Is Better a . 41.49 |=================================================================== b . 41.53 |=================================================================== c . 41.91 |==================================================================== OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU FPS > Higher Is Better a . 3927.60 |================================================================== b . 3916.92 |================================================================== c . 3921.98 |================================================================== OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU ms < Lower Is Better a . 8.13 |===================================================================== b . 8.15 |===================================================================== c . 8.14 |===================================================================== OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better a . 68063.14 |================================================================= b . 68303.49 |================================================================= c . 68152.88 |================================================================= OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better a . 0.77 |===================================================================== b . 0.77 |===================================================================== c . 0.77 |===================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU FPS > Higher Is Better a . 1616.79 |================================================================== b . 1621.11 |================================================================== c . 1621.25 |================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU ms < Lower Is Better a . 39.55 |==================================================================== b . 39.45 |==================================================================== c . 39.45 |==================================================================== OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better a . 86126.49 |================================================================= b . 86415.41 |================================================================= c . 85841.12 |================================================================= OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better a . 0.58 |===================================================================== b . 0.58 |===================================================================== c . 0.58 |===================================================================== WavPack Audio Encoding 5.7 WAV To WavPack Seconds < Lower Is Better a . 6.067 |==================================================================== b . 6.066 |==================================================================== c . 6.059 |==================================================================== Chaos Group V-RAY 6.0 Mode: CPU vsamples > Higher Is Better a . 92008 |==================================================================== b . 92099 |==================================================================== c . 91007 |===================================================================