n1n1 ARMv8 Neoverse-N1 testing with a GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite. a: Processor: ARMv8 Neoverse-N1 @ 3.00GHz (128 Cores), Motherboard: GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS), Chipset: Ampere Computing LLC Altra PCI Root Complex A, Memory: 16 x 32 GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE, Disk: 800GB Micron_7450_MTFDKBA800TFS, Graphics: ASPEED, Monitor: VGA HDMI, Network: 2 x Intel I350 OS: Ubuntu 23.10, Kernel: 6.5.0-15-generic (aarch64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1024x768 aa: Processor: ARMv8 Neoverse-N1 @ 3.00GHz (128 Cores), Motherboard: GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS), Chipset: Ampere Computing LLC Altra PCI Root Complex A, Memory: 16 x 32 GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE, Disk: 800GB Micron_7450_MTFDKBA800TFS, Graphics: ASPEED, Monitor: VGA HDMI, Network: 2 x Intel I350 OS: Ubuntu 23.10, Kernel: 6.5.0-15-generic (aarch64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1024x768 b: Processor: ARMv8 Neoverse-N1 @ 3.00GHz (128 Cores), Motherboard: GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS), Chipset: Ampere Computing LLC Altra PCI Root Complex A, Memory: 16 x 32 GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE, Disk: 800GB Micron_7450_MTFDKBA800TFS, Graphics: ASPEED, Monitor: VGA HDMI, Network: 2 x Intel I350 OS: Ubuntu 23.10, Kernel: 6.5.0-15-generic (aarch64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1024x768 c: Processor: ARMv8 Neoverse-N1 @ 3.00GHz (128 Cores), Motherboard: GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS), Chipset: Ampere Computing LLC Altra PCI Root Complex A, Memory: 16 x 32 GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE, Disk: 800GB Micron_7450_MTFDKBA800TFS, Graphics: ASPEED, Monitor: VGA HDMI, Network: 2 x Intel I350 OS: Ubuntu 23.10, Kernel: 6.5.0-15-generic (aarch64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1024x768 Google Draco 1.5.6 Model: Lion ms < Lower Is Better aa . 7351 |==================================================================== b .. 7320 |==================================================================== c .. 7332 |==================================================================== Google Draco 1.5.6 Model: Church Facade ms < Lower Is Better aa . 10100 |=================================================================== b .. 9847 |================================================================= c .. 9848 |================================================================= JPEG-XL Decoding libjxl 0.10.1 CPU Threads: 1 MP/s > Higher Is Better a .. 27.24 |=================================================================== aa . 27.15 |================================================================== b .. 27.42 |=================================================================== c .. 27.40 |=================================================================== JPEG-XL Decoding libjxl 0.10.1 CPU Threads: All MP/s > Higher Is Better a .. 558.57 |================================================================= aa . 523.02 |============================================================= b .. 564.89 |================================================================== c .. 542.10 |=============================================================== JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 80 MP/s > Higher Is Better a .. 43.10 |=================================================================== aa . 40.28 |=============================================================== b .. 41.31 |================================================================ c .. 41.35 |================================================================ JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 90 MP/s > Higher Is Better a .. 39.25 |================================================================== aa . 37.90 |================================================================ b .. 39.67 |=================================================================== c .. 39.25 |================================================================== JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 80 MP/s > Higher Is Better a .. 39.27 |=================================================================== aa . 38.92 |================================================================== b .. 37.77 |================================================================ c .. 39.32 |=================================================================== JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 90 MP/s > Higher Is Better a .. 37.59 |=================================================================== aa . 37.42 |================================================================== b .. 37.79 |=================================================================== c .. 35.84 |================================================================ JPEG-XL libjxl 0.10.1 Input: PNG - Quality: 100 MP/s > Higher Is Better a .. 29.60 |=================================================================== aa . 29.24 |================================================================== b .. 29.49 |=================================================================== c .. 29.54 |=================================================================== JPEG-XL libjxl 0.10.1 Input: JPEG - Quality: 100 MP/s > Higher Is Better a .. 31.67 |=================================================================== aa . 31.12 |================================================================== b .. 31.62 |=================================================================== c .. 31.62 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 33.42 |================================================================== b .. 33.71 |=================================================================== c .. 33.68 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 1844.12 |================================================================= b .. 1834.83 |================================================================= c .. 1833.45 |================================================================= Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 26.09 |================================================================== b .. 25.95 |================================================================== c .. 26.33 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 38.32 |=================================================================== b .. 38.52 |=================================================================== c .. 37.96 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 1149.47 |================================================================= b .. 1144.80 |================================================================= c .. 1144.77 |================================================================= Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 55.03 |=================================================================== b .. 55.26 |=================================================================== c .. 55.24 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 132.18 |================================================================== b .. 132.99 |================================================================== c .. 131.48 |================================================================= Neural Magic DeepSparse 1.7 Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 7.5520 |================================================================== b .. 7.5061 |================================================================= c .. 7.5924 |================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 474.90 |================================================================= b .. 475.82 |================================================================= c .. 479.99 |================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 132.95 |================================================================== b .. 132.74 |================================================================== c .. 131.52 |================================================================= Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 133.53 |================================================================== b .. 134.00 |================================================================== c .. 133.49 |================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 7.4741 |================================================================== b .. 7.4484 |================================================================== c .. 7.4767 |================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 2678.24 |================================================================= b .. 2688.96 |================================================================= c .. 2630.33 |================================================================ Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 23.50 |================================================================== b .. 23.41 |================================================================== c .. 23.91 |=================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 315.75 |================================================================== b .. 312.46 |================================================================= c .. 316.35 |================================================================== Neural Magic DeepSparse 1.7 Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 3.1508 |================================================================= b .. 3.1835 |================================================================== c .. 3.1449 |================================================================= Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 2.2602 |================================================================= b .. 2.2754 |================================================================== c .. 2.2836 |================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 21332.89 |================================================================ b .. 21231.56 |================================================================ c .. 21169.30 |================================================================ Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 12.93 |=================================================================== b .. 12.90 |=================================================================== c .. 12.96 |=================================================================== Neural Magic DeepSparse 1.7 Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 77.30 |=================================================================== b .. 77.49 |=================================================================== c .. 77.12 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 476.36 |================================================================== b .. 478.64 |================================================================== c .. 478.37 |================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 132.54 |================================================================== b .. 131.95 |================================================================== c .. 131.86 |================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 133.62 |================================================================== b .. 133.63 |================================================================== c .. 133.89 |================================================================== Neural Magic DeepSparse 1.7 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 7.4691 |================================================================== b .. 7.4692 |================================================================== c .. 7.4540 |================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 202.64 |================================================================== b .. 202.15 |================================================================== c .. 201.02 |================================================================= Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 310.51 |================================================================== b .. 311.17 |================================================================== c .. 312.79 |================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 112.53 |================================================================== b .. 112.83 |================================================================== c .. 112.85 |================================================================== Neural Magic DeepSparse 1.7 Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 8.8709 |================================================================== b .. 8.8483 |================================================================== c .. 8.8461 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 345.11 |================================================================== b .. 346.67 |================================================================== c .. 339.90 |================================================================= Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 182.88 |================================================================= b .. 181.90 |================================================================= c .. 185.72 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 109.95 |================================================================= b .. 109.48 |================================================================= c .. 111.16 |================================================================== Neural Magic DeepSparse 1.7 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 9.0819 |================================================================== b .. 9.1198 |================================================================== c .. 8.9820 |================================================================= Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 46.61 |=================================================================== b .. 46.72 |=================================================================== c .. 46.68 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 1337.59 |================================================================= b .. 1335.35 |================================================================= c .. 1333.72 |================================================================= Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 30.60 |=================================================================== b .. 30.72 |=================================================================== c .. 30.67 |=================================================================== Neural Magic DeepSparse 1.7 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 32.66 |=================================================================== b .. 32.53 |=================================================================== c .. 32.58 |=================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 438.71 |================================================================== b .. 439.60 |================================================================== c .. 438.25 |================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 143.83 |================================================================== b .. 143.48 |================================================================== c .. 143.60 |================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 50.60 |=================================================================== b .. 50.73 |=================================================================== c .. 50.65 |=================================================================== Neural Magic DeepSparse 1.7 Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 19.75 |=================================================================== b .. 19.69 |=================================================================== c .. 19.73 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream items/sec > Higher Is Better aa . 33.53 |=================================================================== b .. 33.58 |=================================================================== c .. 33.67 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream ms/batch < Lower Is Better aa . 1840.37 |================================================================= b .. 1835.26 |================================================================= c .. 1836.79 |================================================================= Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream items/sec > Higher Is Better aa . 26.25 |=================================================================== b .. 26.35 |=================================================================== c .. 26.20 |=================================================================== Neural Magic DeepSparse 1.7 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream ms/batch < Lower Is Better aa . 38.07 |=================================================================== b .. 37.94 |=================================================================== c .. 38.15 |=================================================================== oneDNN 3.4 Harness: IP Shapes 1D - Engine: CPU ms < Lower Is Better aa . 4.84065 |================================================================ b .. 4.88015 |================================================================= c .. 4.88858 |================================================================= oneDNN 3.4 Harness: IP Shapes 3D - Engine: CPU ms < Lower Is Better aa . 2.15582 |================================================================= b .. 2.15178 |================================================================= c .. 2.14878 |================================================================= oneDNN 3.4 Harness: Convolution Batch Shapes Auto - Engine: CPU ms < Lower Is Better aa . 4.29470 |================================================================= b .. 4.28036 |================================================================= c .. 4.28461 |================================================================= oneDNN 3.4 Harness: Deconvolution Batch shapes_1d - Engine: CPU ms < Lower Is Better aa . 20.93 |=================================================================== b .. 20.43 |================================================================= c .. 20.89 |=================================================================== oneDNN 3.4 Harness: Deconvolution Batch shapes_3d - Engine: CPU ms < Lower Is Better aa . 2.79626 |================================================================= b .. 2.78238 |================================================================= c .. 2.80386 |================================================================= oneDNN 3.4 Harness: Recurrent Neural Network Training - Engine: CPU ms < Lower Is Better aa . 3738.39 |================================================================= b .. 3737.15 |================================================================= c .. 3738.53 |================================================================= oneDNN 3.4 Harness: Recurrent Neural Network Inference - Engine: CPU ms < Lower Is Better aa . 1460.94 |================================================================= b .. 1461.00 |================================================================= c .. 1469.65 |================================================================= OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU FPS > Higher Is Better aa . 2.84 |==================================================================== b .. 2.84 |==================================================================== c .. 2.84 |==================================================================== OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU ms < Lower Is Better aa . 10877.53 |================================================================ b .. 10891.93 |================================================================ c .. 10876.70 |================================================================ OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU FPS > Higher Is Better aa . 14.77 |=================================================================== b .. 14.77 |=================================================================== c .. 14.73 |=================================================================== OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU ms < Lower Is Better aa . 2150.30 |================================================================= b .. 2151.85 |================================================================= c .. 2157.45 |================================================================= OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU FPS > Higher Is Better aa . 14.73 |=================================================================== b .. 14.84 |=================================================================== c .. 14.80 |=================================================================== OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU ms < Lower Is Better aa . 2156.87 |================================================================= b .. 2140.20 |================================================================ c .. 2146.07 |================================================================= OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU FPS > Higher Is Better aa . 222.86 |================================================================== b .. 223.85 |================================================================== c .. 222.78 |================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU ms < Lower Is Better aa . 143.42 |================================================================== b .. 142.79 |================================================================== c .. 143.48 |================================================================== OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU FPS > Higher Is Better aa . 2.74 |==================================================================== b .. 2.75 |==================================================================== c .. 2.75 |==================================================================== OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU ms < Lower Is Better aa . 11232.43 |================================================================ b .. 11206.13 |================================================================ c .. 11196.54 |================================================================ OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU FPS > Higher Is Better aa . 676.59 |================================================================== b .. 664.78 |================================================================= c .. 670.19 |================================================================= OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU ms < Lower Is Better aa . 47.28 |================================================================== b .. 48.10 |=================================================================== c .. 47.72 |================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU FPS > Higher Is Better aa . 65.60 |=================================================================== b .. 65.49 |=================================================================== c .. 65.60 |=================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU ms < Lower Is Better aa . 486.11 |================================================================== b .. 486.90 |================================================================== c .. 486.11 |================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU FPS > Higher Is Better aa . 89.35 |=================================================================== b .. 89.19 |=================================================================== c .. 89.30 |=================================================================== OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU ms < Lower Is Better aa . 357.86 |================================================================== b .. 358.50 |================================================================== c .. 357.41 |================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU FPS > Higher Is Better aa . 293.47 |================================================================= b .. 297.48 |================================================================== c .. 294.58 |================================================================= OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU ms < Lower Is Better aa . 108.97 |================================================================== b .. 107.50 |================================================================= c .. 108.56 |================================================================== OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU FPS > Higher Is Better aa . 333.15 |================================================================== b .. 329.97 |================================================================= c .. 331.77 |================================================================== OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU ms < Lower Is Better aa . 95.98 |================================================================== b .. 96.90 |=================================================================== c .. 96.38 |=================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU FPS > Higher Is Better aa . 34.90 |=================================================================== b .. 34.79 |=================================================================== c .. 34.88 |=================================================================== OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU ms < Lower Is Better aa . 913.41 |================================================================== b .. 915.17 |================================================================== c .. 913.21 |================================================================== OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU FPS > Higher Is Better aa . 40.11 |=================================================================== b .. 40.15 |=================================================================== c .. 40.21 |=================================================================== OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU ms < Lower Is Better aa . 794.06 |================================================================== b .. 793.31 |================================================================== c .. 792.00 |================================================================== OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU FPS > Higher Is Better aa . 217.95 |================================================================= b .. 221.47 |================================================================== c .. 219.27 |================================================================= OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU ms < Lower Is Better aa . 146.71 |================================================================== b .. 144.38 |================================================================= c .. 145.82 |================================================================== OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU FPS > Higher Is Better aa . 204.69 |================================================================= b .. 205.33 |================================================================= c .. 207.24 |================================================================== OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU ms < Lower Is Better aa . 156.22 |================================================================== b .. 155.74 |================================================================== c .. 154.30 |================================================================= OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU FPS > Higher Is Better aa . 164.82 |================================================================== b .. 164.75 |================================================================== c .. 164.79 |================================================================== OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU ms < Lower Is Better aa . 193.84 |================================================================== b .. 193.93 |================================================================== c .. 193.87 |================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU FPS > Higher Is Better aa . 163.95 |================================================================== b .. 163.98 |================================================================== c .. 164.13 |================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU ms < Lower Is Better aa . 194.88 |================================================================== b .. 194.84 |================================================================== c .. 194.65 |================================================================== OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU FPS > Higher Is Better aa . 142.60 |================================================================== b .. 142.58 |================================================================== c .. 142.54 |================================================================== OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU ms < Lower Is Better aa . 224.22 |================================================================== b .. 224.22 |================================================================== c .. 224.31 |================================================================== OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU FPS > Higher Is Better aa . 1402.51 |================================================================= b .. 1402.97 |================================================================= c .. 1403.65 |================================================================= OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU ms < Lower Is Better aa . 22.80 |=================================================================== b .. 22.79 |=================================================================== c .. 22.78 |=================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU FPS > Higher Is Better aa . 147.76 |================================================================== b .. 147.08 |================================================================== c .. 146.90 |================================================================== OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU ms < Lower Is Better aa . 216.18 |================================================================== b .. 217.16 |================================================================== c .. 217.41 |================================================================== OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU FPS > Higher Is Better aa . 1462.94 |================================================================= b .. 1473.23 |================================================================= c .. 1460.72 |================================================================ OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU ms < Lower Is Better aa . 21.86 |=================================================================== b .. 21.71 |================================================================== c .. 21.89 |=================================================================== Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression Seconds < Lower Is Better aa . 2.413553 |=============================================================== b .. 2.439338 |================================================================ c .. 2.438631 |================================================================ Primesieve 12.1 Length: 1e12 Seconds < Lower Is Better aa . 2.911 |=================================================================== b .. 2.872 |================================================================== c .. 2.893 |=================================================================== Primesieve 12.1 Length: 1e13 Seconds < Lower Is Better aa . 42.31 |=================================================================== b .. 42.44 |=================================================================== c .. 42.29 |=================================================================== srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Total Mbps > Higher Is Better a .. 14099.8 |================================================================= aa . 13936.1 |================================================================ b .. 13999.6 |================================================================= srsRAN Project 23.10.1-20240219 Test: PUSCH Processor Benchmark, Throughput Total Mbps > Higher Is Better a . 1602.1 |=================================================================== srsRAN Project 23.10.1-20240219 Test: PDSCH Processor Benchmark, Throughput Thread Mbps > Higher Is Better a .. 175.8 |=================================================================== aa . 175.7 |=================================================================== srsRAN Project 23.10.1-20240219 Test: PUSCH Processor Benchmark, Throughput Thread Mbps > Higher Is Better a . 46.7 |===================================================================== Stockfish 16.1 Chess Benchmark Nodes Per Second > Higher Is Better a .. 59028775 |================================================================ aa . 59449725 |================================================================ b .. 51901853 |======================================================== c .. 53514996 |========================================================== SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 2.652 |=================================================================== aa . 2.644 |=================================================================== b .. 2.650 |=================================================================== c .. 2.650 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 24.95 |=================================================================== aa . 24.93 |=================================================================== b .. 25.01 |=================================================================== c .. 24.95 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 74.68 |=================================================================== aa . 74.47 |================================================================== b .. 75.17 |=================================================================== c .. 75.02 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K Frames Per Second > Higher Is Better a .. 74.90 |=================================================================== aa . 74.90 |=================================================================== b .. 74.96 |=================================================================== c .. 74.60 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 8.914 |=================================================================== aa . 8.925 |=================================================================== b .. 8.921 |=================================================================== c .. 8.926 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 56.90 |=================================================================== aa . 57.14 |=================================================================== b .. 57.03 |=================================================================== c .. 56.79 |=================================================================== SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 265.74 |================================================================== aa . 264.98 |================================================================== b .. 265.44 |================================================================== c .. 264.28 |================================================================== SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 1080p Frames Per Second > Higher Is Better a .. 364.40 |================================================================== aa . 363.35 |================================================================== b .. 365.10 |================================================================== c .. 363.61 |================================================================== Timed Linux Kernel Compilation 6.8 Build: defconfig Seconds < Lower Is Better a .. 94.27 |=================================================================== aa . 92.76 |================================================================== b .. 94.43 |=================================================================== c .. 94.50 |=================================================================== Timed Linux Kernel Compilation 6.8 Build: allmodconfig Seconds < Lower Is Better aa . 348.02 |================================================================== b .. 350.29 |================================================================== c .. 349.92 |================================================================== WavPack Audio Encoding 5.7 WAV To WavPack Seconds < Lower Is Better aa . 25.20 |=================================================================== b .. 25.21 |=================================================================== c .. 25.20 |===================================================================