24.03.13.Pop.2204.ML.test1

AMD Ryzen 9 7950X 16-Core testing with a ASUS ProArt X670E-CREATOR WIFI (1710 BIOS) and Zotac NVIDIA GeForce RTX 4070 Ti 12GB on Pop 22.04 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 2403157-NE-240313POP28
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Initial test 1 No water cool
March 13
  2 Days, 55 Minutes
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):

24.03.13.Pop.2204.ML.test1, "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: S3D", Higher Results Are Better "Initial test 1 No water cool",299.75,299.667,298.988 "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Triad", Higher Results Are Better "Initial test 1 No water cool",25.5227,25.5074,25.3594 "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: FFT SP", Higher Results Are Better "Initial test 1 No water cool",1290.47,1294.57,1292.55 "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: MD5 Hash", Higher Results Are Better "Initial test 1 No water cool",47.8826,47.97,47.8439 "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Reduction", Higher Results Are Better "Initial test 1 No water cool",388.834,389.087,388.88 "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: GEMM SGEMM_N", Higher Results Are Better "Initial test 1 No water cool",13553.9,12918.3,12914,13580.4,13544.8,12902.1,12970.5,13519.9,13573.5,12911.2,12943.1 "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Max SP Flops", Higher Results Are Better "Initial test 1 No water cool",43043.2,42923.3,43258.2 "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Bus Speed Download", Higher Results Are Better "Initial test 1 No water cool",26.8271,26.8267,26.8287 "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Bus Speed Readback", Higher Results Are Better "Initial test 1 No water cool",27.075,27.0706,27.0714 "SHOC Scalable HeterOgeneous Computing 2020-04-17 - Target: OpenCL - Benchmark: Texture Read Bandwidth", Higher Results Are Better "Initial test 1 No water cool",2980.04,2986.83,2990.24 "LeelaChessZero 0.30 - Backend: BLAS", Higher Results Are Better "Initial test 1 No water cool", "oneDNN 3.4 - Harness: IP Shapes 1D - Engine: CPU", Lower Results Are Better "Initial test 1 No water cool",1.10754,1.13816,1.16528,1.17996,1.17925,1.19183,1.19174,1.1909,1.19743,1.19298 "oneDNN 3.4 - Harness: IP Shapes 3D - Engine: CPU", Lower Results Are Better "Initial test 1 No water cool",4.42842,4.43024,4.40645 "oneDNN 3.4 - Harness: Convolution Batch Shapes Auto - Engine: CPU", Lower Results Are Better "Initial test 1 No water cool",7.13261,7.18438,7.18194 "oneDNN 3.4 - Harness: Deconvolution Batch shapes_1d - Engine: CPU", Lower Results Are Better "Initial test 1 No water cool",3.18255,3.01572,3.03527,3.03446,3.04095 "oneDNN 3.4 - Harness: Deconvolution Batch shapes_3d - Engine: CPU", Lower Results Are Better "Initial test 1 No water cool",2.5736,2.55359,2.56838 "oneDNN 3.4 - Harness: Recurrent Neural Network Training - Engine: CPU", Lower Results Are Better "Initial test 1 No water cool",1439.14,1454.38,1465.35 "oneDNN 3.4 - Harness: Recurrent Neural Network Inference - Engine: CPU", Lower Results Are Better "Initial test 1 No water cool",745.631,747.264,749.603 "Numpy Benchmark - ", Higher Results Are Better "Initial test 1 No water cool",689.82,709.24,714.49 "DeepSpeech 0.6 - Acceleration: CPU", Lower Results Are Better "Initial test 1 No water cool",47.19448,46.36497,47.54598 "R Benchmark - ", Lower Results Are Better "Initial test 1 No water cool", "RNNoise 2020-06-28 - ", Lower Results Are Better "Initial test 1 No water cool",13.555,13.549,14.018 "TensorFlow Lite 2022-05-18 - Model: SqueezeNet", Lower Results Are Better "Initial test 1 No water cool",1694.82,1715.52,1737.79 "TensorFlow Lite 2022-05-18 - Model: Inception V4", Lower Results Are Better "Initial test 1 No water cool",21103.3,21145.9,21169.1 "TensorFlow Lite 2022-05-18 - Model: NASNet Mobile", Lower Results Are Better "Initial test 1 No water cool",10137.9,10091.4,10068.6 "TensorFlow Lite 2022-05-18 - Model: Mobilenet Float", Lower Results Are Better "Initial test 1 No water cool",1211.91,1217.17,1213.25 "TensorFlow Lite 2022-05-18 - Model: Mobilenet Quant", Lower Results Are Better "Initial test 1 No water cool",1838.9,1874.9,1870.78 "TensorFlow Lite 2022-05-18 - Model: Inception ResNet V2", Lower Results Are Better "Initial test 1 No water cool",21648.5,21978.2,21944.4 "PyTorch 2.1 - Device: CPU - Batch Size: 1 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",64.711858838884,65.631860955446,64.073291766651 "PyTorch 2.1 - Device: CPU - Batch Size: 1 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",26.16475354352,25.702719074115,25.042387029453 "PyTorch 2.1 - Device: CPU - Batch Size: 16 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",44.385185501778,43.905799131315,43.94886442382 "PyTorch 2.1 - Device: CPU - Batch Size: 32 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",43.940460194436,43.720854803445,44.58020137558 "PyTorch 2.1 - Device: CPU - Batch Size: 64 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",44.038984049916,42.922611443836,43.092394342344 "PyTorch 2.1 - Device: CPU - Batch Size: 16 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",17.882102565423,17.545642122543,17.554248960352 "PyTorch 2.1 - Device: CPU - Batch Size: 256 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",42.754637861902,44.374276395991,43.351074437206 "PyTorch 2.1 - Device: CPU - Batch Size: 32 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",17.477419924865,17.623830726746,17.807786359048 "PyTorch 2.1 - Device: CPU - Batch Size: 512 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",42.189983618725,43.445671711731,43.100242034348 "PyTorch 2.1 - Device: CPU - Batch Size: 64 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",17.660483474135,18.046742930446,17.260643099618 "PyTorch 2.1 - Device: CPU - Batch Size: 256 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",17.744515547922,17.715305604219,17.612350590999 "PyTorch 2.1 - Device: CPU - Batch Size: 512 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",17.70271780011,17.383122128208,17.678549709277 "PyTorch 2.1 - Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",13.97033817565,14.287177043548,14.157665610718 "PyTorch 2.1 - Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",10.34943940681,10.594507736174,10.442291616623 "PyTorch 2.1 - Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",10.668632340861,10.629741581217,10.462901910319 "PyTorch 2.1 - Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",10.646037128588,10.489870015263,10.602590694286 "PyTorch 2.1 - Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",10.540819018436,10.777890651798,10.556837146017 "PyTorch 2.1 - Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",10.619947875765,10.295722418864,10.40783572655 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",382.26601702943,394.88546744974,384.03571625658 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",138.62782924803,137.79765854287,135.74444708183 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",379.61744055971,383.65420212883,378.73127063961 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",381.24630054123,374.39522475143,386.58444643698 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",380.16731400139,380.30016930681,379.48014282717 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",138.70221728766,138.54894491516,139.08603190671 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",379.44822565121,380.75460658577,380.80763942604 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",140.38609076966,137.93869559067,139.89039865427 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",376.42969302417,386.37973447233,387.85876562828 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",138.38263759725,140.3315263502,137.43233725413 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",139.69511830593,136.99054128272,139.16796911736 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152", Higher Results Are Better "Initial test 1 No water cool",140.01208981188,143.47817633196,137.72777359291 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",72.790453478063,71.698766072409,71.459028253991 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",72.258962827821,70.209463025478,69.415596601694 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",70.327276199125,70.90169164261,70.345515945627 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",70.738810052259,69.413286748942,69.25602188904 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",69.702983647133,71.397278928655,71.324938946822 "PyTorch 2.1 - Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l", Higher Results Are Better "Initial test 1 No water cool",69.87813617932,70.125305628148,69.912489442377 "TensorFlow 2.12 - Device: CPU - Batch Size: 1 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",4.74,4.75,4.73 "TensorFlow 2.12 - Device: GPU - Batch Size: 1 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",1.45,1.46,1.46 "TensorFlow 2.12 - Device: CPU - Batch Size: 1 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",13.02,12.99,12.98 "TensorFlow 2.12 - Device: CPU - Batch Size: 16 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",16.32,16,15.95 "TensorFlow 2.12 - Device: CPU - Batch Size: 32 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",16.94,16.85,16.87 "TensorFlow 2.12 - Device: CPU - Batch Size: 64 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",17.55,17.3,17.48 "TensorFlow 2.12 - Device: GPU - Batch Size: 1 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",12.57,12.57,12.61 "TensorFlow 2.12 - Device: GPU - Batch Size: 16 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",1.7,1.71,1.7 "TensorFlow 2.12 - Device: GPU - Batch Size: 32 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",1.73,1.71,1.73 "TensorFlow 2.12 - Device: GPU - Batch Size: 64 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",1.72,1.73,1.75 "TensorFlow 2.12 - Device: CPU - Batch Size: 16 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",149.11,148.75,148.29 "TensorFlow 2.12 - Device: CPU - Batch Size: 256 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",18.1,18.13,18.12 "TensorFlow 2.12 - Device: CPU - Batch Size: 32 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",224.88,224.11,224.69 "TensorFlow 2.12 - Device: CPU - Batch Size: 512 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool", "TensorFlow 2.12 - Device: CPU - Batch Size: 64 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",308.05,305.77,303.61 "TensorFlow 2.12 - Device: GPU - Batch Size: 16 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",30.32,30.66,31.03 "TensorFlow 2.12 - Device: GPU - Batch Size: 256 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool",1.77,1.77,1.76 "TensorFlow 2.12 - Device: GPU - Batch Size: 32 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",33.22,33.63,33.32 "TensorFlow 2.12 - Device: GPU - Batch Size: 512 - Model: VGG-16", Higher Results Are Better "Initial test 1 No water cool", "TensorFlow 2.12 - Device: GPU - Batch Size: 64 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",35.04,34.63,34.85 "TensorFlow 2.12 - Device: CPU - Batch Size: 1 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",47.34,46.93,47.35 "TensorFlow 2.12 - Device: CPU - Batch Size: 1 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",12.73,12.69,12.68 "TensorFlow 2.12 - Device: CPU - Batch Size: 256 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",394.69,386.95,383.56 "TensorFlow 2.12 - Device: CPU - Batch Size: 512 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",387.86,394.54,394.07 "TensorFlow 2.12 - Device: GPU - Batch Size: 1 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",12.44,12.33,12.32 "TensorFlow 2.12 - Device: GPU - Batch Size: 1 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",4.23,4.23,4.28 "TensorFlow 2.12 - Device: GPU - Batch Size: 256 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",35.77,36.01,35.67 "TensorFlow 2.12 - Device: GPU - Batch Size: 512 - Model: AlexNet", Higher Results Are Better "Initial test 1 No water cool",36.06,35.97,35.77 "TensorFlow 2.12 - Device: CPU - Batch Size: 16 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",126.4,125.65,125.45 "TensorFlow 2.12 - Device: CPU - Batch Size: 16 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",36.57,36.37,36.36 "TensorFlow 2.12 - Device: CPU - Batch Size: 32 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",122.62,122.43,122.11 "TensorFlow 2.12 - Device: CPU - Batch Size: 32 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",36.83,36.74,36.66 "TensorFlow 2.12 - Device: CPU - Batch Size: 64 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",119.3,118.92,118.9 "TensorFlow 2.12 - Device: CPU - Batch Size: 64 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",36.38,36.32,36.37 "TensorFlow 2.12 - Device: GPU - Batch Size: 16 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",15,15.13,15.16 "TensorFlow 2.12 - Device: GPU - Batch Size: 16 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",5.42,5.4,5.45 "TensorFlow 2.12 - Device: GPU - Batch Size: 32 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",15.44,15.51,15.4 "TensorFlow 2.12 - Device: GPU - Batch Size: 32 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",5.54,5.52,5.41 "TensorFlow 2.12 - Device: GPU - Batch Size: 64 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",15.58,15.56,15.69 "TensorFlow 2.12 - Device: GPU - Batch Size: 64 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",5.52,5.5,5.51 "TensorFlow 2.12 - Device: CPU - Batch Size: 256 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",117.13,116.09,115.76 "TensorFlow 2.12 - Device: CPU - Batch Size: 256 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",36.15,36.15,36.16 "TensorFlow 2.12 - Device: CPU - Batch Size: 512 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",115.87,115.62,115.62 "TensorFlow 2.12 - Device: CPU - Batch Size: 512 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool", "TensorFlow 2.12 - Device: GPU - Batch Size: 256 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",15.69,15.82,15.77 "TensorFlow 2.12 - Device: GPU - Batch Size: 256 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool",5.54,5.55,5.59 "TensorFlow 2.12 - Device: GPU - Batch Size: 512 - Model: GoogLeNet", Higher Results Are Better "Initial test 1 No water cool",15.88,15.93,15.88 "TensorFlow 2.12 - Device: GPU - Batch Size: 512 - Model: ResNet-50", Higher Results Are Better "Initial test 1 No water cool", "Neural Magic DeepSparse 1.6 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",20.3269,19.9627,19.966 "Neural Magic DeepSparse 1.6 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",392.8541,400.1259,399.7591 "Neural Magic DeepSparse 1.6 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",17.4434,17.3299,17.2983 "Neural Magic DeepSparse 1.6 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",57.3188,57.6941,57.7984 "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",895.2205,891.1507,884.197 "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",8.9211,8.9611,9.032 "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",278.0953,278.4703,278.3709 "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",3.5926,3.5877,3.5892 "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",266.1476,264.1444,262.84 "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",30.0406,30.2664,30.4176 "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",174.1316,173.5848,172.4194 "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",5.735,5.7532,5.792 "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",2048.0549,2011.3442,2036.2333 "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",3.8928,3.9643,3.915 "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",1219.9898,1214.2652,1208.4647 "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",0.8174,0.8215,0.8253 "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",111.1286,110.8889,110.9568 "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",71.9429,72.1156,72.0652 "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",90.6467,90.3295,90.0911 "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",11.0209,11.0588,11.0871 "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",26.4048,26.2964,26.3024 "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",302.504,303.7409,303.7541 "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",18.5964,18.4871,18.4593 "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",53.7635,54.0814,54.1635 "Neural Magic DeepSparse 1.6 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",267.5636,264.3345,263.7072 "Neural Magic DeepSparse 1.6 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",29.8824,30.2447,30.3203 "Neural Magic DeepSparse 1.6 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",173.9087,174.8679,172.9191 "Neural Magic DeepSparse 1.6 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",5.7427,5.7114,5.7766 "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",115.7648,113.8878,115.6846 "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",69.036,70.2002,69.0865 "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",92.7041,92.4202,92.4162 "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",10.7801,10.8131,10.8138 "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",183.4035,182.1445,182.3196 "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",43.6022,43.8845,43.8537 "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",97.4033,95.8381,96.1663 "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",10.2585,10.4273,10.3913 "Neural Magic DeepSparse 1.6 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",33.9144,33.7604,33.7538 "Neural Magic DeepSparse 1.6 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",235.8584,236.3315,236.7533 "Neural Magic DeepSparse 1.6 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",27.5487,27.5154,27.5267 "Neural Magic DeepSparse 1.6 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",36.2842,36.3288,36.3137 "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",417.8124,417.1567,416.5478 "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",19.1308,19.1635,19.1894 "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",98.0147,98.2818,97.9308 "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",10.1928,10.1651,10.2007 "Neural Magic DeepSparse 1.6 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "Initial test 1 No water cool",19.8756,20.0678,19.7869 "Neural Magic DeepSparse 1.6 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "Initial test 1 No water cool",400.4668,397.9907,402.7219 "Neural Magic DeepSparse 1.6 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream", Higher Results Are Better "Initial test 1 No water cool",17.3436,17.2761,17.2483 "Neural Magic DeepSparse 1.6 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream", Lower Results Are Better "Initial test 1 No water cool",57.6489,57.8747,57.9677 "spaCy 3.4.1 - Model: en_core_web_lg", Higher Results Are Better "Initial test 1 No water cool",18227,18616,18827 "spaCy 3.4.1 - Model: en_core_web_trf", Higher Results Are Better "Initial test 1 No water cool",2361,2464,2419 "Caffe 2020-02-13 - Model: AlexNet - Acceleration: CPU - Iterations: 100", Lower Results Are Better "Initial test 1 No water cool", "Caffe 2020-02-13 - Model: AlexNet - Acceleration: CPU - Iterations: 200", Lower Results Are Better "Initial test 1 No water cool", "Caffe 2020-02-13 - Model: AlexNet - Acceleration: CPU - Iterations: 1000", Lower Results Are Better "Initial test 1 No water cool", "Caffe 2020-02-13 - Model: GoogleNet - Acceleration: CPU - Iterations: 100", Lower Results Are Better "Initial test 1 No water cool", "Caffe 2020-02-13 - Model: GoogleNet - Acceleration: CPU - Iterations: 200", Lower Results Are Better "Initial test 1 No water cool", "Caffe 2020-02-13 - Model: GoogleNet - Acceleration: CPU - Iterations: 1000", Lower Results Are Better "Initial test 1 No water cool", "Mobile Neural Network 2.1 - Model: nasnet", Lower Results Are Better "Initial test 1 No water cool",11.108,11.377,11.416 "Mobile Neural Network 2.1 - Model: mobilenetV3", Lower Results Are Better "Initial test 1 No water cool",1.585,1.665,1.663 "Mobile Neural Network 2.1 - Model: squeezenetv1.1", Lower Results Are Better "Initial test 1 No water cool",2.452,2.599,2.575 "Mobile Neural Network 2.1 - Model: resnet-v2-50", Lower Results Are Better "Initial test 1 No water cool",12.047,12.124,12.199 "Mobile Neural Network 2.1 - Model: SqueezeNetV1.0", Lower Results Are Better "Initial test 1 No water cool",3.92,4.256,4.247 "Mobile Neural Network 2.1 - Model: MobileNetV2_224", Lower Results Are Better "Initial test 1 No water cool",3.339,3.505,3.385 "Mobile Neural Network 2.1 - Model: mobilenet-v1-1.0", Lower Results Are Better "Initial test 1 No water cool",2.527,2.397,2.445 "Mobile Neural Network 2.1 - Model: inception-v3", Lower Results Are Better "Initial test 1 No water cool",22.288,23.813,24.161 "NCNN 20230517 - Target: CPU - Model: mobilenet", Lower Results Are Better "Initial test 1 No water cool",9.66,9.95,9.78 "NCNN 20230517 - Target: CPU-v2-v2 - Model: mobilenet-v2", Lower Results Are Better "Initial test 1 No water cool",3.61,3.67,3.66 "NCNN 20230517 - Target: CPU-v3-v3 - Model: mobilenet-v3", Lower Results Are Better "Initial test 1 No water cool",3.65,3.75,3.66 "NCNN 20230517 - Target: CPU - Model: shufflenet-v2", Lower Results Are Better "Initial test 1 No water cool",3.95,3.94,3.91 "NCNN 20230517 - Target: CPU - Model: mnasnet", Lower Results Are Better "Initial test 1 No water cool",3.48,3.47,3.44 "NCNN 20230517 - Target: CPU - Model: efficientnet-b0", Lower Results Are Better "Initial test 1 No water cool",4.46,4.54,4.5 "NCNN 20230517 - Target: CPU - Model: blazeface", Lower Results Are Better "Initial test 1 No water cool",1.59,1.61,1.59 "NCNN 20230517 - Target: CPU - Model: googlenet", Lower Results Are Better "Initial test 1 No water cool",9.55,9.54,9.6 "NCNN 20230517 - Target: CPU - Model: vgg16", Lower Results Are Better "Initial test 1 No water cool",32.44,33.08,32.28 "NCNN 20230517 - Target: CPU - Model: resnet18", Lower Results Are Better "Initial test 1 No water cool",6.57,6.66,6.63 "NCNN 20230517 - Target: CPU - Model: alexnet", Lower Results Are Better "Initial test 1 No water cool",5.52,5.53,5.51 "NCNN 20230517 - Target: CPU - Model: resnet50", Lower Results Are Better "Initial test 1 No water cool",13.12,14.16,13.15 "NCNN 20230517 - Target: CPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3", Lower Results Are Better "Initial test 1 No water cool",9.66,9.95,9.78 "NCNN 20230517 - Target: CPU - Model: yolov4-tiny", Lower Results Are Better "Initial test 1 No water cool",15.95,16.94,15.95 "NCNN 20230517 - Target: CPU - Model: squeezenet_ssd", Lower Results Are Better "Initial test 1 No water cool",8.17,8.72,8.57 "NCNN 20230517 - Target: CPU - Model: regnety_400m", Lower Results Are Better "Initial test 1 No water cool",9.76,9.93,9.92 "NCNN 20230517 - Target: CPU - Model: vision_transformer", Lower Results Are Better "Initial test 1 No water cool",37.67,38.76,37.32 "NCNN 20230517 - Target: CPU - Model: FastestDet", Lower Results Are Better "Initial test 1 No water cool",4.53,4.89,4.65 "NCNN 20230517 - Target: Vulkan GPU - Model: mobilenet", Lower Results Are Better "Initial test 1 No water cool",9.34,9.32,9.42 "NCNN 20230517 - Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2", Lower Results Are Better "Initial test 1 No water cool",3.74,3.67,3.66 "NCNN 20230517 - Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3", Lower Results Are Better "Initial test 1 No water cool",3.77,3.7,3.69 "NCNN 20230517 - Target: Vulkan GPU - Model: shufflenet-v2", Lower Results Are Better "Initial test 1 No water cool",3.87,3.91,3.92 "NCNN 20230517 - Target: Vulkan GPU - Model: mnasnet", Lower Results Are Better "Initial test 1 No water cool",3.46,3.45,3.45 "NCNN 20230517 - Target: Vulkan GPU - Model: efficientnet-b0", Lower Results Are Better "Initial test 1 No water cool",4.69,4.51,4.5 "NCNN 20230517 - Target: Vulkan GPU - Model: blazeface", Lower Results Are Better "Initial test 1 No water cool",1.57,1.62,1.66 "NCNN 20230517 - Target: Vulkan GPU - Model: googlenet", Lower Results Are Better "Initial test 1 No water cool",9.84,9.62,9.6 "NCNN 20230517 - Target: Vulkan GPU - Model: vgg16", Lower Results Are Better "Initial test 1 No water cool",32.59,32.25,32.08 "NCNN 20230517 - Target: Vulkan GPU - Model: resnet18", Lower Results Are Better "Initial test 1 No water cool",6.72,6.63,6.61 "NCNN 20230517 - Target: Vulkan GPU - Model: alexnet", Lower Results Are Better "Initial test 1 No water cool",6,5.52,5.5 "NCNN 20230517 - Target: Vulkan GPU - Model: resnet50", Lower Results Are Better "Initial test 1 No water cool",13.26,13.04,13.18 "NCNN 20230517 - Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3", Lower Results Are Better "Initial test 1 No water cool",9.34,9.32,9.42 "NCNN 20230517 - Target: Vulkan GPU - Model: yolov4-tiny", Lower Results Are Better "Initial test 1 No water cool",15.87,15.77,15.89 "NCNN 20230517 - Target: Vulkan GPU - Model: squeezenet_ssd", Lower Results Are Better "Initial test 1 No water cool",8.33,8.35,8.47 "NCNN 20230517 - Target: Vulkan GPU - Model: regnety_400m", Lower Results Are Better "Initial test 1 No water cool",9.75,9.92,9.82 "NCNN 20230517 - Target: Vulkan GPU - Model: vision_transformer", Lower Results Are Better "Initial test 1 No water cool",37.83,37.22,39.3 "NCNN 20230517 - Target: Vulkan GPU - Model: FastestDet", Lower Results Are Better "Initial test 1 No water cool",4.18,4.2,4.51 "TNN 0.3 - Target: CPU - Model: DenseNet", Lower Results Are Better "Initial test 1 No water cool",2016.63,2008.764,1991.424 "TNN 0.3 - Target: CPU - Model: MobileNet v2", Lower Results Are Better "Initial test 1 No water cool",182.149,184.611,183.07 "TNN 0.3 - Target: CPU - Model: SqueezeNet v2", Lower Results Are Better "Initial test 1 No water cool",42.013,42.446,42.186 "TNN 0.3 - Target: CPU - Model: SqueezeNet v1.1", Lower Results Are Better "Initial test 1 No water cool",176.968,180.992,181.078 "PlaidML - FP16: No - Mode: Inference - Network: VGG16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool", "PlaidML - FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool", "OpenVINO 2024.0 - Model: Face Detection FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",13.39,12.88,12.7,12.63,12.57,12.51,12.54 "OpenVINO 2024.0 - Model: Face Detection FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",595.54,620.42,627.47,632.27,633.62,635.37,634.92 "OpenVINO 2024.0 - Model: Person Detection FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",75.97,77.07,76.9 "OpenVINO 2024.0 - Model: Person Detection FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",105.17,103.7,103.93 "OpenVINO 2024.0 - Model: Person Detection FP32 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",77.2,76.4,79.01 "OpenVINO 2024.0 - Model: Person Detection FP32 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",103.52,104.59,101.17 "OpenVINO 2024.0 - Model: Vehicle Detection FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",620.79,619.4,615.04 "OpenVINO 2024.0 - Model: Vehicle Detection FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",12.86,12.89,12.98 "OpenVINO 2024.0 - Model: Face Detection FP16-INT8 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",24.83,24.65,24.65 "OpenVINO 2024.0 - Model: Face Detection FP16-INT8 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",321.65,323.76,323.96 "OpenVINO 2024.0 - Model: Face Detection Retail FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",3085.08,3052.45,3050.37 "OpenVINO 2024.0 - Model: Face Detection Retail FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",2.51,2.54,2.53 "OpenVINO 2024.0 - Model: Road Segmentation ADAS FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",275.85,271.37,269.87 "OpenVINO 2024.0 - Model: Road Segmentation ADAS FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",28.95,29.42,29.59 "OpenVINO 2024.0 - Model: Vehicle Detection FP16-INT8 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",1546.32,1535.6,1532.9 "OpenVINO 2024.0 - Model: Vehicle Detection FP16-INT8 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",5.15,5.19,5.2 "OpenVINO 2024.0 - Model: Weld Porosity Detection FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",1273.4,1264.28,1262.86 "OpenVINO 2024.0 - Model: Weld Porosity Detection FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",12.54,12.63,12.65 "OpenVINO 2024.0 - Model: Face Detection Retail FP16-INT8 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",4371.22,4329.33,4306.44 "OpenVINO 2024.0 - Model: Face Detection Retail FP16-INT8 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",3.58,3.61,3.63 "OpenVINO 2024.0 - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",450.31,446.86,447.68 "OpenVINO 2024.0 - Model: Road Segmentation ADAS FP16-INT8 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",17.73,17.86,17.83 "OpenVINO 2024.0 - Model: Machine Translation EN To DE FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",122.1,121.65,122.14 "OpenVINO 2024.0 - Model: Machine Translation EN To DE FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",65.45,65.68,65.42 "OpenVINO 2024.0 - Model: Weld Porosity Detection FP16-INT8 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",2488.39,2464.23,2459.96 "OpenVINO 2024.0 - Model: Weld Porosity Detection FP16-INT8 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",6.4,6.45,6.46 "OpenVINO 2024.0 - Model: Person Vehicle Bike Detection FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",1442.64,1445.1,1438.48 "OpenVINO 2024.0 - Model: Person Vehicle Bike Detection FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",5.53,5.52,5.54 "OpenVINO 2024.0 - Model: Noise Suppression Poconet-Like FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",1387.6,1388.46,1384.72 "OpenVINO 2024.0 - Model: Noise Suppression Poconet-Like FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",11.33,11.32,11.35 "OpenVINO 2024.0 - Model: Handwritten English Recognition FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",669.88,668.14,663.85 "OpenVINO 2024.0 - Model: Handwritten English Recognition FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",23.85,23.91,24.06 "OpenVINO 2024.0 - Model: Person Re-Identification Retail FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",1790.47,1785.55,1780.43 "OpenVINO 2024.0 - Model: Person Re-Identification Retail FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",4.45,4.46,4.48 "OpenVINO 2024.0 - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",32552.74,32317.29,32337.24 "OpenVINO 2024.0 - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",0.45,0.45,0.45 "OpenVINO 2024.0 - Model: Handwritten English Recognition FP16-INT8 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",734.54,728.06,727.38 "OpenVINO 2024.0 - Model: Handwritten English Recognition FP16-INT8 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",21.75,21.94,21.96 "OpenVINO 2024.0 - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU", Higher Results Are Better "Initial test 1 No water cool",46210.59,45974.14,45893.08 "OpenVINO 2024.0 - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU", Lower Results Are Better "Initial test 1 No water cool",0.31,0.31,0.31 "Numenta Anomaly Benchmark 1.1 - Detector: KNN CAD", Lower Results Are Better "Initial test 1 No water cool",106.072,109.864,101.979,103.768,107.917,105.636,103.465,103.442,102.865 "Numenta Anomaly Benchmark 1.1 - Detector: Relative Entropy", Lower Results Are Better "Initial test 1 No water cool",8.536,8.05,8.232,8.305 "Numenta Anomaly Benchmark 1.1 - Detector: Windowed Gaussian", Lower Results Are Better "Initial test 1 No water cool",5.215,4.977,4.869,4.907,5.2,5.445,4.872,4.738,4.894,4.855,4.911,4.949,5.006,5.036,4.89 "Numenta Anomaly Benchmark 1.1 - Detector: Earthgecko Skyline", Lower Results Are Better "Initial test 1 No water cool",55.018,56.026,55.653 "Numenta Anomaly Benchmark 1.1 - Detector: Bayesian Changepoint", Lower Results Are Better "Initial test 1 No water cool",13.278,13.111,13.249 "Numenta Anomaly Benchmark 1.1 - Detector: Contextual Anomaly Detector OSE", Lower Results Are Better "Initial test 1 No water cool",25.785,25.004,25.41 "ONNX Runtime 1.17 - Model: GPT-2 - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: GPT-2 - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: yolov4 - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: yolov4 - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: T5 Encoder - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: T5 Encoder - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: bertsquad-12 - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: bertsquad-12 - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: super-resolution-10 - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: super-resolution-10 - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel", Higher Results Are Better "Initial test 1 No water cool", "ONNX Runtime 1.17 - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard", Higher Results Are Better "Initial test 1 No water cool", "AI Benchmark Alpha 0.1.2 - Device Inference Score", Higher Results Are Better "Initial test 1 No water cool", "AI Benchmark Alpha 0.1.2 - Device Training Score", Higher Results Are Better "Initial test 1 No water cool", "AI Benchmark Alpha 0.1.2 - Device AI Score", Higher Results Are Better "Initial test 1 No water cool", "Mlpack Benchmark - Benchmark: scikit_ica", Lower Results Are Better "Initial test 1 No water cool",30.011435985565,30.168902873993,30.165871858597 "Mlpack Benchmark - Benchmark: scikit_qda", Lower Results Are Better "Initial test 1 No water cool",33.811544656754,34.555150270462,33.828336715698 "Mlpack Benchmark - Benchmark: scikit_svm", Lower Results Are Better "Initial test 1 No water cool",15.204170227051,15.122441053391,15.046759128571 "Mlpack Benchmark - Benchmark: scikit_linearridgeregression", Lower Results Are Better "Initial test 1 No water cool",1.0414371490479,1.025634765625,1.0357301235199 "Scikit-Learn 1.2.2 - Benchmark: GLM", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: SAGA", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Tree", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Lasso", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Glmnet", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Sparsify", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Ward", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: MNIST Dataset", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Neighbors", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: SGD Regression", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: SGDOneClassSVM", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Lasso Path", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Isolation Forest", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Fast KMeans", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Text Vectorizers", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Hierarchical", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot OMP vs. LARS", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Feature Expansions", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: LocalOutlierFactor", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: TSNE MNIST Dataset", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Isotonic / Logistic", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Incremental PCA", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Hist Gradient Boosting", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Parallel Pairwise", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Isotonic / Pathological", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: RCV1 Logreg Convergencet", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Sample Without Replacement", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Covertype Dataset Benchmark", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Hist Gradient Boosting Adult", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Isotonic / Perturbed Logarithm", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Hist Gradient Boosting Threading", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Singular Value Decomposition", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Hist Gradient Boosting Higgs Boson", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: 20 Newsgroups / Logistic Regression", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Polynomial Kernel Approximation", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Plot Non-Negative Matrix Factorization", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Hist Gradient Boosting Categorical Only", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Kernel PCA Solvers / Time vs. N Samples", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Kernel PCA Solvers / Time vs. N Components", Lower Results Are Better "Initial test 1 No water cool", "Scikit-Learn 1.2.2 - Benchmark: Sparse Random Projections / 100 Iterations", Lower Results Are Better "Initial test 1 No water cool", "Whisper.cpp 1.4 - Model: ggml-base.en - Input: 2016 State of the Union", Lower Results Are Better "Initial test 1 No water cool",0.25841,0.14757,0.14731,0.14542,0.14513,0.14532,0.14673,0.14739,0.14695,0.14594,0.14556,0.14538,0.14505,0.14518,0.14517 "Whisper.cpp 1.4 - Model: ggml-small.en - Input: 2016 State of the Union", Lower Results Are Better "Initial test 1 No water cool",0.71017,0.32377,0.32376,0.32231,0.3259,0.32334,0.32231,0.32162,0.32219,0.32464,0.32136,0.31951,0.32224,0.32208,0.3269 "Whisper.cpp 1.4 - Model: ggml-medium.en - Input: 2016 State of the Union", Lower Results Are Better "Initial test 1 No water cool",2.05052,0.78346,0.7883,0.78205,0.78264,0.78143,0.78114,0.78183,0.78327,0.77428,0.783,0.78227,0.79268,0.77767,0.76776 "Llama.cpp b1808 - Model: llama-2-7b.Q4_0.gguf", Higher Results Are Better "Initial test 1 No water cool", "Llama.cpp b1808 - Model: llama-2-13b.Q4_0.gguf", Higher Results Are Better "Initial test 1 No water cool", "Llama.cpp b1808 - Model: llama-2-70b-chat.Q5_0.gguf", Higher Results Are Better "Initial test 1 No water cool", "Llamafile 0.6 - Test: llava-v1.5-7b-q4 - Acceleration: CPU", Higher Results Are Better "Initial test 1 No water cool", "Llamafile 0.6 - Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU", Higher Results Are Better "Initial test 1 No water cool", "Llamafile 0.6 - Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU", Higher Results Are Better "Initial test 1 No water cool", "OpenCV 4.7 - Test: DNN - Deep Neural Network", Lower Results Are Better "Initial test 1 No water cool",30072,30070,32126,30801,31884,29379,30639,28079,31581,31162,31467,28610,29669,27543,31071