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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2403174-NE-N1N13670960
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

C/C++ Compiler Tests 2 Tests
CPU Massive 6 Tests
Creator Workloads 7 Tests
Encoding 2 Tests
HPC - High Performance Computing 3 Tests
Imaging 2 Tests
Machine Learning 3 Tests
Multi-Core 7 Tests
Intel oneAPI 2 Tests
Python Tests 2 Tests
Server CPU Tests 4 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 17
  15 Minutes
aa
March 17
  7 Hours, 43 Minutes
b
March 17
  2 Hours, 32 Minutes
c
March 17
  2 Hours, 15 Minutes
Invert Hiding All Results Option
  3 Hours, 11 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

n1n1 , "JPEG-XL libjxl 0.10.1 - Input: PNG - Quality: 80", Higher Results Are Better "a", "aa",39.706,40.738,40.393 "b", "c", "JPEG-XL libjxl 0.10.1 - Input: PNG - Quality: 90", Higher Results Are Better "a", "aa",38.915,38.941,32.816,38.754,33.331,38.752,39.128,39.066,38.939,39.103,38.582,35.772,38.855,38.868,38.608 "b", "c", "JPEG-XL libjxl 0.10.1 - Input: JPEG - Quality: 80", Higher Results Are Better "a", "aa",39.152,38.862,38.749 "b", "c", "JPEG-XL libjxl 0.10.1 - Input: JPEG - Quality: 90", Higher Results Are Better "a", "aa",35.451,38.118,39.039,38.751,37.711,36.519,39.667,35.446,36.613,35.162,37.975,39.049,40.38,35.796,35.551 "b", "c", "JPEG-XL libjxl 0.10.1 - Input: PNG - Quality: 100", Higher Results Are Better "a", "aa",29.269,29.295,29.151 "b", "c", "JPEG-XL libjxl 0.10.1 - Input: JPEG - Quality: 100", Higher Results Are Better "a", "aa",31.129,31.117,31.117 "b", "c", "JPEG-XL Decoding libjxl 0.10.1 - CPU Threads: 1", Higher Results Are Better "a", "aa",27.132,27.144,27.181 "b", "c", "JPEG-XL Decoding libjxl 0.10.1 - CPU Threads: All", Higher Results Are Better "a", "aa",525.517,519.158,524.381 "b", "c", "srsRAN Project 23.10.1-20240219 - Test: PDSCH Processor Benchmark, Throughput Total", Higher Results Are Better "a", "aa",13954.2,13854.9,13999.1 "b", "srsRAN Project 23.10.1-20240219 - Test: PUSCH Processor Benchmark, Throughput Total", Higher Results Are Better "a", "srsRAN Project 23.10.1-20240219 - Test: PDSCH Processor Benchmark, Throughput Thread", Higher Results Are Better "a", "aa",175.6,175.7,175.7 "srsRAN Project 23.10.1-20240219 - Test: PUSCH Processor Benchmark, Throughput Thread", Higher Results Are Better "a", "SVT-AV1 2.0 - Encoder Mode: Preset 4 - Input: Bosphorus 4K", Higher Results Are Better "a", "aa",2.648,2.636,2.647 "b", "c", "SVT-AV1 2.0 - Encoder Mode: Preset 8 - Input: Bosphorus 4K", Higher Results Are Better "a", "aa",24.922,24.912,24.947 "b", "c", "SVT-AV1 2.0 - Encoder Mode: Preset 12 - Input: Bosphorus 4K", Higher Results Are Better "a", "aa",74.597,74.885,73.924 "b", "c", "SVT-AV1 2.0 - Encoder Mode: Preset 13 - Input: Bosphorus 4K", Higher Results Are Better "a", "aa",74.567,75.219,74.915 "b", "c", "SVT-AV1 2.0 - Encoder Mode: Preset 4 - Input: Bosphorus 1080p", Higher Results Are Better "a", "aa",8.926,8.907,8.943 "b", "c", "SVT-AV1 2.0 - Encoder Mode: Preset 8 - Input: Bosphorus 1080p", Higher Results Are Better "a", "aa",57.215,57.175,57.016 "b", "c", "SVT-AV1 2.0 - Encoder Mode: Preset 12 - Input: Bosphorus 1080p", Higher Results Are Better "a", "aa",264.887,264.991,265.056 "b", "c", "SVT-AV1 2.0 - Encoder Mode: Preset 13 - Input: Bosphorus 1080p", Higher Results Are Better "a", "aa",362.211,363.99,363.86 "b", "c", "Stockfish 16.1 - Chess Benchmark", Higher Results Are Better "a", "aa",69125864,59571638,59338275,57221418,53054878,54439774,60239452,55353821,65066627,62363322,52770867,64850761 "b", "c", "Timed Linux Kernel Compilation 6.8 - Build: defconfig", Lower Results Are Better "a", "aa",94.569,91.858,91.854 "b", "c", "Timed Linux Kernel Compilation 6.8 - Build: allmodconfig", Lower Results Are Better "aa",349.356,347.555,347.144 "b", "c", "Parallel BZIP2 Compression 1.1.13 - FreeBSD-13.0-RELEASE-amd64-memstick.img Compression", Lower Results Are Better "aa",2.413644,2.416125,2.41089 "b", "c", "Primesieve 12.1 - Length: 1e12", Lower Results Are Better "aa",2.916,2.905,2.912 "b", "c", "Primesieve 12.1 - Length: 1e13", Lower Results Are Better "aa",42.201,42.438,42.275 "b", "c", "oneDNN 3.4 - Harness: IP Shapes 1D - Engine: CPU", Lower Results Are Better "aa",4.86044,4.83517,4.82634 "b", "c", "oneDNN 3.4 - Harness: IP Shapes 3D - Engine: CPU", Lower Results Are Better "aa",2.15843,2.15522,2.15381 "b", "c", "oneDNN 3.4 - Harness: Convolution Batch Shapes Auto - Engine: CPU", Lower Results Are Better "aa",4.32434,4.29197,4.2678 "b", "c", "oneDNN 3.4 - Harness: Deconvolution Batch shapes_1d - Engine: CPU", Lower Results Are Better "aa",21.0625,20.5372,21.1769 "b", "c", "oneDNN 3.4 - Harness: Deconvolution Batch shapes_3d - Engine: CPU", Lower Results Are Better "aa",2.75255,2.77722,3.00306,2.7737,2.76656,2.77428,2.79424,2.77245,2.77091,2.79051,2.78974,2.78994 "b", "c", "oneDNN 3.4 - Harness: Recurrent Neural Network Training - Engine: CPU", Lower Results Are Better "aa",3736.24,3735.94,3742.99 "b", "c", "oneDNN 3.4 - Harness: Recurrent Neural Network Inference - Engine: CPU", Lower Results Are Better "aa",1459.45,1468,1455.38 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",33.4478,33.3717,33.4367 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",1840.803,1846.8904,1844.6805 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",25.9217,26.2941,26.0456 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",38.5596,38.0133,38.3758 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",1150.5278,1144.1049,1153.7846 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",55.0269,55.2084,54.843 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",132.0089,132.7117,131.8342 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",7.5621,7.5218,7.5721 "b", "c", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",475.3001,472.4256,476.9672 "b", "c", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",132.7014,133.7216,132.4346 "b", "c", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",133.6249,133.6617,133.3036 "b", "c", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",7.469,7.4665,7.4869 "b", "c", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",2680.2349,2688.4148,2666.065 "b", "c", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",23.5203,23.4003,23.5911 "b", "c", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",316.1404,316.8063,314.2882 "b", "c", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",3.1469,3.1404,3.1651 "b", "c", "Neural Magic DeepSparse 1.7 - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",2.2489,2.2575,2.2742 "b", "c", "Neural Magic DeepSparse 1.7 - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",21417.907,21352.672,21228.1003 "b", "c", "Neural Magic DeepSparse 1.7 - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",12.9703,12.9053,12.9138 "b", "c", "Neural Magic DeepSparse 1.7 - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",77.0606,77.4489,77.3983 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",475.6256,474.7699,478.6717 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",132.7019,133.0297,131.8958 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",133.78,133.8013,133.2841 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",7.4607,7.4585,7.4881 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",203.0745,201.9769,202.8562 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",310.0856,311.5314,309.9217 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",112.2511,112.8215,112.5275 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",8.8931,8.8485,8.8711 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",345.5208,345.1388,344.6644 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",182.7388,182.871,183.0269 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",108.2672,110.5076,111.0821 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",9.2219,9.0352,8.9885 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",46.474,46.831,46.5309 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",1340.0294,1331.2606,1341.4853 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",30.5973,30.583,30.6081 "b", "c", "Neural Magic DeepSparse 1.7 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",32.6588,32.6736,32.6468 "b", "c", "Neural Magic DeepSparse 1.7 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",438.3678,439.5519,438.2195 "b", "c", "Neural Magic DeepSparse 1.7 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",143.9565,143.7015,143.8372 "b", "c", "Neural Magic DeepSparse 1.7 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",50.4684,50.5848,50.7396 "b", "c", "Neural Magic DeepSparse 1.7 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",19.7964,19.7505,19.6908 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "aa",33.606,33.4867,33.5084 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "aa",1841.7245,1840.9711,1838.4074 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream", Higher Results Are Better "aa",26.2951,26.2545,26.2097 "b", "c", "Neural Magic DeepSparse 1.7 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream", Lower Results Are Better "aa",38.0118,38.0704,38.1357 "b", "c", "Google Draco 1.5.6 - Model: Lion", Lower Results Are Better "aa",7350,7355,7349 "b", "c", "Google Draco 1.5.6 - Model: Church Facade", Lower Results Are Better "aa",10088,10109,10103 "b", "c", "OpenVINO 2024.0 - Model: Face Detection FP16 - Device: CPU", Higher Results Are Better "aa",2.84,2.85,2.83 "b", "c", "OpenVINO 2024.0 - Model: Face Detection FP16 - Device: CPU", Lower Results Are Better "aa",10892.13,10842.87,10897.58 "b", "c", "OpenVINO 2024.0 - Model: Person Detection FP16 - Device: CPU", Higher Results Are Better "aa",14.77,14.79,14.76 "b", "c", "OpenVINO 2024.0 - Model: Person Detection FP16 - Device: CPU", Lower Results Are Better "aa",2150.44,2148.17,2152.28 "b", "c", "OpenVINO 2024.0 - Model: Person Detection FP32 - Device: CPU", Higher Results Are Better "aa",14.76,14.73,14.7 "b", "c", "OpenVINO 2024.0 - Model: Person Detection FP32 - Device: CPU", Lower Results Are Better "aa",2152.53,2157.31,2160.77 "b", "c", "OpenVINO 2024.0 - Model: Vehicle Detection FP16 - Device: CPU", Higher Results Are Better "aa",222.67,222.93,222.98 "b", "c", "OpenVINO 2024.0 - Model: Vehicle Detection FP16 - Device: CPU", Lower Results Are Better "aa",143.54,143.37,143.35 "b", "c", "OpenVINO 2024.0 - Model: Face Detection FP16-INT8 - Device: CPU", Higher Results Are Better "aa",2.75,2.74,2.74 "b", "c", "OpenVINO 2024.0 - Model: Face Detection FP16-INT8 - Device: CPU", Lower Results Are Better "aa",11218.49,11250.12,11228.67 "b", "c", "OpenVINO 2024.0 - Model: Face Detection Retail FP16 - Device: CPU", Higher Results Are Better "aa",689.94,679.09,660.75 "b", "c", "OpenVINO 2024.0 - Model: Face Detection Retail FP16 - Device: CPU", Lower Results Are Better "aa",46.35,47.09,48.4 "b", "c", "OpenVINO 2024.0 - Model: Road Segmentation ADAS FP16 - Device: CPU", Higher Results Are Better "aa",65.8,65.39,65.6 "b", "c", "OpenVINO 2024.0 - Model: Road Segmentation ADAS FP16 - Device: CPU", Lower Results Are Better "aa",484.59,487.65,486.1 "b", "c", "OpenVINO 2024.0 - Model: Vehicle Detection FP16-INT8 - Device: CPU", Higher Results Are Better "aa",89.39,89.36,89.3 "b", "c", "OpenVINO 2024.0 - Model: Vehicle Detection FP16-INT8 - Device: CPU", Lower Results Are Better "aa",357.69,357.84,358.06 "b", "c", "OpenVINO 2024.0 - Model: Weld Porosity Detection FP16 - Device: CPU", Higher Results Are Better "aa",292.87,293.81,293.73 "b", "c", "OpenVINO 2024.0 - Model: Weld Porosity Detection FP16 - Device: CPU", Lower Results Are Better "aa",109.19,108.84,108.87 "b", "c", "OpenVINO 2024.0 - Model: Face Detection Retail FP16-INT8 - Device: CPU", Higher Results Are Better "aa",331.94,333.57,333.94 "b", "c", "OpenVINO 2024.0 - Model: Face Detection Retail FP16-INT8 - Device: CPU", Lower Results Are Better "aa",96.33,95.87,95.74 "b", "c", "OpenVINO 2024.0 - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU", Higher Results Are Better "aa",34.87,34.92,34.92 "b", "c", "OpenVINO 2024.0 - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU", Lower Results Are Better "aa",914.38,912.89,912.96 "b", "c", "OpenVINO 2024.0 - Model: Machine Translation EN To DE FP16 - Device: CPU", Higher Results Are Better "aa",40.01,40.16,40.16 "b", "c", "OpenVINO 2024.0 - Model: Machine Translation EN To DE FP16 - Device: CPU", Lower Results Are Better "aa",795.93,793.11,793.15 "b", "c", "OpenVINO 2024.0 - Model: Weld Porosity Detection FP16-INT8 - Device: CPU", Higher Results Are Better "aa",218.19,218.06,217.6 "b", "c", "OpenVINO 2024.0 - Model: Weld Porosity Detection FP16-INT8 - Device: CPU", Lower Results Are Better "aa",146.56,146.63,146.95 "b", "c", "OpenVINO 2024.0 - Model: Person Vehicle Bike Detection FP16 - Device: CPU", Higher Results Are Better "aa",205.99,204.18,203.9 "b", "c", "OpenVINO 2024.0 - Model: Person Vehicle Bike Detection FP16 - Device: CPU", Lower Results Are Better "aa",155.24,156.6,156.82 "b", "c", "OpenVINO 2024.0 - Model: Noise Suppression Poconet-Like FP16 - Device: CPU", Higher Results Are Better "aa",164.8,164.78,164.87 "b", "c", "OpenVINO 2024.0 - Model: Noise Suppression Poconet-Like FP16 - Device: CPU", Lower Results Are Better "aa",193.81,193.78,193.92 "b", "c", "OpenVINO 2024.0 - Model: Handwritten English Recognition FP16 - Device: CPU", Higher Results Are Better "aa",163.95,164.06,163.85 "b", "c", "OpenVINO 2024.0 - Model: Handwritten English Recognition FP16 - Device: CPU", Lower Results Are Better "aa",194.87,194.76,195.02 "b", "c", "OpenVINO 2024.0 - Model: Person Re-Identification Retail FP16 - Device: CPU", Higher Results Are Better "aa",142.45,143.25,142.1 "b", "c", "OpenVINO 2024.0 - Model: Person Re-Identification Retail FP16 - Device: CPU", Lower Results Are Better "aa",224.44,223.22,225 "b", "c", "OpenVINO 2024.0 - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU", Higher Results Are Better "aa",1408.52,1400.57,1398.45 "b", "c", "OpenVINO 2024.0 - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU", Lower Results Are Better "aa",22.71,22.83,22.87 "b", "c", "OpenVINO 2024.0 - Model: Handwritten English Recognition FP16-INT8 - Device: CPU", Higher Results Are Better "aa",146.95,149.42,146.9 "b", "c", "OpenVINO 2024.0 - Model: Handwritten English Recognition FP16-INT8 - Device: CPU", Lower Results Are Better "aa",217.33,213.75,217.45 "b", "c", "OpenVINO 2024.0 - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU", Higher Results Are Better "aa",1463.59,1465.12,1460.11 "b", "c", "OpenVINO 2024.0 - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU", Lower Results Are Better "aa",21.85,21.83,21.9 "b", "c", "WavPack Audio Encoding 5.7 - WAV To WavPack", Lower Results Are Better "aa",25.207,25.201,25.193,25.193,25.203 "b", "c",