mnn ncnn xeon

2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on CentOS Stream 9 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 2208133-NE-MNNNCNNXE63
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:

HPC - High Performance Computing 2 Tests
Machine Learning 2 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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
A
August 13 2022
  2 Hours, 54 Minutes
B
August 13 2022
  2 Hours, 53 Minutes
C
August 13 2022
  4 Hours, 30 Minutes
D
August 13 2022
  4 Hours, 39 Minutes
E
August 13 2022
  2 Hours, 55 Minutes
Invert Hiding All Results Option
  3 Hours, 34 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):

mnn ncnn xeon, "Mobile Neural Network 2.0 - Model: mobilenetV3", Lower Results Are Better "A",1.825,1.84,1.757 "B",1.82,1.807,1.883 "C",1.808,1.808,1.891,1.776,1.891,1.879,1.919,1.82,1.745,1.699,1.856,1.798,1.72,1.915 "D",1.806,2.077,1.857,1.88,1.795,1.843,1.817,1.872,1.907,1.901,1.848,1.901,1.801,1.812,1.856 "E",1.875,1.9,1.82 "Mobile Neural Network 2.0 - Model: squeezenetv1.1", Lower Results Are Better "A",2.235,2.517,2.199 "B",2.579,2.198,2.407 "C",2.244,2.219,2.552,2.438,2.554,2.619,2.589,2.24,2.642,2.161,2.656,2.245,2.139,2.647 "D",2.378,2.531,2.611,2.418,2.333,2.331,2.365,2.389,2.643,2.409,2.406,2.61,2.387,2.43,2.465 "E",2.577,2.619,2.363 "Mobile Neural Network 2.0 - Model: resnet-v2-50", Lower Results Are Better "A",8.872,8.983,8.491 "B",9.356,9.006,8.88 "C",8.589,8.801,8.645,8.559,8.912,8.762,8.88,8.682,9.219,8.545,9.13,8.757,8.505,8.739 "D",9.06,8.797,8.75,9.05,8.928,8.816,8.675,8.697,8.871,9.069,8.837,9.041,8.639,8.847,9.215 "E",9.151,9.245,9.2 "Mobile Neural Network 2.0 - Model: SqueezeNetV1.0", Lower Results Are Better "A",4.063,4.429,3.871 "B",4.301,4.318,4.02 "C",4.176,3.951,4.058,4.309,4.548,4.495,4.385,3.989,4.491,4.022,4.529,4.51,4.26,4.408 "D",3.999,3.989,4.288,4.368,4.343,4.427,4.018,4.203,4.22,4.04,4.214,4.394,4.212,4.388,4.178 "E",4.55,4.239,4.173 "Mobile Neural Network 2.0 - Model: MobileNetV2_224", Lower Results Are Better "A",3.69,3.343,3.212 "B",3.003,3.193,3.256 "C",3.659,3.192,2.843,3.277,3.162,3.111,3.042,3.121,3.337,3.194,3.328,3.269,3.308,3.197 "D",3.698,3.196,3.017,2.793,3.268,3.263,3.251,3.293,3.23,3.158,3.279,3.254,3.234,3.268,3.235 "E",3.264,2.927,3.216 "Mobile Neural Network 2.0 - Model: mobilenet-v1-1.0", Lower Results Are Better "A",2.21,2.27,2.203 "B",2.209,2.201,2.184 "C",2.13,2.189,2.191,2.188,2.254,2.183,2.238,2.152,2.194,2.273,2.135,1.867,2.176 "D",2.215,2.201,2.171,2.27,2.17,2.349,2.204,2.166,2.217,2.193,2.196,2.259,2.175,2.154,2.231 "E",2.211,2.256,2.185 "Mobile Neural Network 2.0 - Model: inception-v3", Lower Results Are Better "A",20.49,21.538,20.043 "B",20.996,20.445,20.995 "C",20.302,20.896,20.879,21.108,20.955,20.44,21.415,20.745,20.821,20.094,21.056,21.246,20.29,21.694 "D",20.502,20.396,21.236,21.247,20.722,20.653,20.444,20.4,20.765,21.269,20.706,21.493,20.847,20.826,20.931 "E",21.255,21.543,21.24 "NCNN 20220729 - Target: CPU - Model: mobilenet", Lower Results Are Better "A",22.12,21.33,22.28 "B",21.71,21.68,21.65 "C",22.27,22.11,22.66 "D",23.06,22.77,22.73 "E",21.94,21.54,22.08 "NCNN 20220729 - Target: CPU-v2-v2 - Model: mobilenet-v2", Lower Results Are Better "A",12.85,12.86,13.26 "B",12.89,12.77,12.76 "C",12.69,12.87,12.8 "D",12.95,12.84,12.65 "E",13.31,13.83,12.8 "NCNN 20220729 - Target: CPU-v3-v3 - Model: mobilenet-v3", Lower Results Are Better "A",12.19,12.14,11.76 "B",12.28,12.51,11.84 "C",12.15,12.36,12.25 "D",12.07,12.14,12.15 "E",12.53,11.98,12.13 "NCNN 20220729 - Target: CPU - Model: shufflenet-v2", Lower Results Are Better "A",13.57,13.56,13.28 "B",14.34,13.45,13.36 "C",13.58,13.68,13.15 "D",13.26,13.56,13.54 "E",14.09,13.2,13.59 "NCNN 20220729 - Target: CPU - Model: mnasnet", Lower Results Are Better "A",12.11,11.83,11.81 "B",12.01,11.79,12.35 "C",11.91,12.08,11.73 "D",11.49,11.91,11.83 "E",11.89,11.63,11.85 "NCNN 20220729 - Target: CPU - Model: efficientnet-b0", Lower Results Are Better "A",17.09,16.62,16.97 "B",16.85,16.75,16.4 "C",19.18,17.31,16.77 "D",15.99,16.96,16.67 "E",17.01,15.98,16.52 "NCNN 20220729 - Target: CPU - Model: blazeface", Lower Results Are Better "A",7.28,7,7.18 "B",7.73,7.08,7.21 "C",7.39,7.39,7.05 "D",6.84,7.27,7.06 "E",7.27,7.14,7.29 "NCNN 20220729 - Target: CPU - Model: googlenet", Lower Results Are Better "A",24.85,23.26,23.1 "B",22.87,22.57,22.15 "C",23.27,23.85,22.2 "D",22.67,23.69,24.2 "E",23.15,22.14,22.64 "NCNN 20220729 - Target: CPU - Model: vgg16", Lower Results Are Better "A",32.73,27.74,32.26 "B",29.15,28.92,29.08 "C",30.02,29.64,29.24 "D",30.41,30.81,32.38 "E",28.63,28.76,28.66 "NCNN 20220729 - Target: CPU - Model: resnet18", Lower Results Are Better "A",13.56,12.89,13.65 "B",13.38,12.99,13.17 "C",13.25,13.5,13.77 "D",13.12,13.42,15.08 "E",13.01,13.42,13.18 "NCNN 20220729 - Target: CPU - Model: alexnet", Lower Results Are Better "A",8.93,8.26,9.49 "B",8.83,8.37,8.34 "C",8.49,8.69,8.42 "D",9.65,8.37,9.35 "E",8.35,8.16,9.34 "NCNN 20220729 - Target: CPU - Model: resnet50", Lower Results Are Better "A",25.36,23.44,25.46 "B",24.82,24.75,23.89 "C",24.94,25.52,24.97 "D",25.17,25.16,25.49 "E",24.12,24.47,24.43 "NCNN 20220729 - Target: CPU - Model: yolov4-tiny", Lower Results Are Better "A",28.15,26.94,28.31 "B",26.98,27.02,27.75 "C",27.26,27.23,27.34 "D",27.83,27.38,26.93 "E",26.64,26.47,27.1 "NCNN 20220729 - Target: CPU - Model: squeezenet_ssd", Lower Results Are Better "A",26.14,26.27,26.6 "B",26.5,26.09,26.49 "C",26.63,26.86,28.02 "D",26.21,27.14,26.63 "E",25.94,25.75,26.19 "NCNN 20220729 - Target: CPU - Model: regnety_400m", Lower Results Are Better "A",60.08,54.58,56.77 "B",59.19,56.77,57.32 "C",59.54,58.05,56.17 "D",54.98,59.16,56.57 "E",57.54,59.2,59.29 "NCNN 20220729 - Target: CPU - Model: vision_transformer", Lower Results Are Better "A",154.79,150.92,149.62 "B",152.95,152.61,152.34 "C",153.94,151.73,152.71 "D",156.09,155,154.85 "E",155.8,155.39,156.51 "NCNN 20220729 - Target: CPU - Model: FastestDet", Lower Results Are Better "A",15.1,15.31,15.59 "B",14.75,14.81,15.38 "C",15.51,16.37,14.8 "D",14.67,15.35,14.73 "E",15.05,14.99,14.74