EPYC 7F32 Last

AMD EPYC 7F32 8-Core testing with a Supermicro H11DSi-NT v2.00 (2.1 BIOS) and llvmpipe on Ubuntu 20.04 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 2012274-HA-EPYC7F32L08
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:

Audio Encoding 4 Tests
Timed Code Compilation 2 Tests
CPU Massive 2 Tests
Creator Workloads 5 Tests
Encoding 4 Tests
HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests
Multi-Core 3 Tests
Programmer / Developer System Benchmarks 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
Run 1
December 26 2020
  1 Hour, 54 Minutes
Run 2
December 26 2020
  1 Hour, 37 Minutes
Run 3
December 27 2020
  1 Hour, 38 Minutes
Run 4
December 27 2020
  1 Hour, 37 Minutes
Invert Hiding All Results Option
  1 Hour, 42 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):

EPYC 7F32 Last, "NCNN 20201218 - Target: CPU - Model: googlenet", Lower Results Are Better "Run 1",15.93,15.47,15.55 "Run 2",15.35,15.35,15.85 "Run 3",15.45,15.55,15.45 "Run 4",16.93,16.79,15.43 "NCNN 20201218 - Target: CPU - Model: squeezenet_ssd", Lower Results Are Better "Run 1",24.57,24.41,25.61 "Run 2",24.52,24.45,24.47 "Run 3",24.43,24.48,24.47 "Run 4",25.73,25.74,24.47 "NCNN 20201218 - Target: CPU - Model: mnasnet", Lower Results Are Better "Run 1",5.99,5.9,6.53 "Run 2",5.97,5.92,5.93 "Run 3",5.94,6.01,5.96 "Run 4",5.9,6.21,5.94 "Unpacking The Linux Kernel - linux-4.15.tar.xz", Lower Results Are Better "Run 1",5.872,6.02,5.925,6.077 "Run 2",5.811,5.814,6.182,6.105,5.947 "Run 3",5.968,6.025,5.972,6.097 "Run 4",5.825,5.694,6.016,5.871 "CLOMP 1.2 - Static OMP Speedup", Higher Results Are Better "Run 1",29.8,29.8,29.7 "Run 2",29.7,29.4,29.6 "Run 3",27.8,29.7,28.9,29.5 "Run 4",29.9,29.9,29.3 "NCNN 20201218 - Target: CPU - Model: yolov4-tiny", Lower Results Are Better "Run 1",27.76,27.15,26.27 "Run 2",26.37,26.39,27.38 "Run 3",26.38,26.44,26.39 "Run 4",27.35,27.33,26.62 "oneDNN 2.0 - Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "Run 1",9.71552,9.8362,9.45098 "Run 2",9.53748,9.49696,9.8362 "Run 3",9.42583,9.42842,9.54432 "Run 4",9.39225,9.50447,9.88915 "oneDNN 2.0 - Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU", Lower Results Are Better "Run 1",6.52361,6.13298,6.15787,6.1484,6.14293 "Run 2",6.12161,6.18998,6.14305 "Run 3",6.11941,6.13406,6.12334 "Run 4",6.15007,6.21023,6.1778 "NCNN 20201218 - Target: CPU - Model: blazeface", Lower Results Are Better "Run 1",3.37,3.27,3.3 "Run 2",3.33,3.27,3.42 "Run 3",3.3,3.3,3.3 "Run 4",3.27,3.34,3.32 "oneDNN 2.0 - Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU", Lower Results Are Better "Run 1",4.93403,4.96052,5.04737 "Run 2",4.90191,4.94679,4.92142 "Run 3",4.93994,4.96201,4.96151 "Run 4",4.93454,4.96262,4.88977 "NCNN 20201218 - Target: CPU - Model: efficientnet-b0", Lower Results Are Better "Run 1",10.81,10.41,10.52 "Run 2",10.57,10.51,10.56 "Run 3",10.44,10.47,10.47 "Run 4",10.5,10.44,10.49 "oneDNN 2.0 - Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "Run 1",0.770455,0.807209,0.789226 "Run 2",0.796044,0.79034,0.800387 "Run 3",0.798562,0.789313,0.803185 "Run 4",0.790855,0.777622,0.795651 "NCNN 20201218 - Target: CPU - Model: regnety_400m", Lower Results Are Better "Run 1",32.59,31.37,32.25 "Run 2",32.5,31.93,32.15 "Run 3",32.37,32.18,32.49 "Run 4",31.71,31.74,32.64 "NCNN 20201218 - Target: CPU-v3-v3 - Model: mobilenet-v3", Lower Results Are Better "Run 1",6.61,6.75,6.62 "Run 2",6.64,6.63,6.66 "Run 3",6.62,6.65,6.6 "Run 4",6.56,6.59,6.66 "Unpacking Firefox 84.0 - Extracting: firefox-84.0.source.tar.xz", Lower Results Are Better "Run 1",20.362,20.229,20.457,20.439 "Run 2",20.353,20.348,20.304,20.088 "Run 3",20.053,20.199,20.397,20.234 "Run 4",20.259,20.08,20.289,20.213 "NCNN 20201218 - Target: CPU - Model: resnet18", Lower Results Are Better "Run 1",11.59,11.58,11.4 "Run 2",11.49,11.57,11.66 "Run 3",11.46,11.49,11.5 "Run 4",11.68,11.58,11.44 "oneDNN 2.0 - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "Run 1",3427.9,3412.04,3413.8 "Run 2",3437.73,3443.34,3444.73 "Run 3",3436.04,3449.63,3437.94 "Run 4",3414.25,3423.08,3428.51 "NCNN 20201218 - Target: CPU - Model: mobilenet", Lower Results Are Better "Run 1",20.06,19.8,19.95 "Run 2",19.78,19.77,19.87 "Run 3",19.9,19.87,19.91 "Run 4",19.9,19.96,19.79 "NCNN 20201218 - Target: CPU - Model: resnet50", Lower Results Are Better "Run 1",23.15,23,22.91 "Run 2",22.94,22.89,23.06 "Run 3",22.8,22.93,22.94 "Run 4",23.11,23.09,22.91 "oneDNN 2.0 - Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU", Lower Results Are Better "Run 1",4.92789,4.9031,5.00129 "Run 2",4.93762,5.04212,4.92494 "Run 3",5.00723,4.93438,4.93217 "Run 4",4.92833,4.98738,4.89499 "oneDNN 2.0 - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "Run 1",1709.82,1704.67,1700.41 "Run 2",1716.62,1714.37,1715.96 "Run 3",1706.24,1713.92,1718.4 "Run 4",1708.31,1722.36,1712 "Build2 0.13 - Time To Compile", Lower Results Are Better "Run 1",112.087,112.79,111.357 "Run 2",112.174,113.192,112.967 "Run 3",113.176,113.877,110.967 "Run 4",112.07,112.002,113.3 "NCNN 20201218 - Target: CPU-v2-v2 - Model: mobilenet-v2", Lower Results Are Better "Run 1",6.85,6.82,6.93 "Run 2",6.84,6.83,6.84 "Run 3",6.82,6.84,6.89 "Run 4",6.79,6.82,6.88 "oneDNN 2.0 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU", Lower Results Are Better "Run 1",1.17158,1.16157,1.16002 "Run 2",1.15372,1.16047,1.16186 "Run 3",1.15713,1.1582,1.16309 "Run 4",1.16192,1.15921,1.16357 "NCNN 20201218 - Target: CPU - Model: vgg16", Lower Results Are Better "Run 1",32.67,32.39,32.28 "Run 2",32.66,32.29,32.29 "Run 3",32.25,32.35,32.35 "Run 4",32.33,32.33,32.27 "oneDNN 2.0 - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "Run 1",1712.05,1708.72,1713.41 "Run 2",1718.08,1718.65,1717.69 "Run 3",1715.52,1717.9,1716.17 "Run 4",1708.67,1712.11,1713.07 "oneDNN 2.0 - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "Run 1",3428.76,3437.04,3422.83 "Run 2",3441.12,3440.04,3435.82 "Run 3",3433.89,3439.19,3437.27 "Run 4",3428.26,3427.4,3426.13 "oneDNN 2.0 - Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "Run 1",7.22763,7.2285,7.14387 "Run 2",7.28959,7.19642,7.17064 "Run 3",7.21506,7.24778,7.20547 "Run 4",7.19526,7.2068,7.25817 "NCNN 20201218 - Target: CPU - Model: shufflenet-v2", Lower Results Are Better "Run 1",9.61,9.56,9.67 "Run 2",9.64,9.63,9.62 "Run 3",9.58,9.61,9.62 "Run 4",9.59,9.57,9.65 "oneDNN 2.0 - Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU", Lower Results Are Better "Run 1",3.52232,3.56585,3.56001 "Run 2",3.54244,3.55962,3.55072 "Run 3",3.55304,3.55865,3.56733 "Run 4",3.54964,3.56009,3.56842 "NCNN 20201218 - Target: CPU - Model: alexnet", Lower Results Are Better "Run 1",7.58,7.57,7.58 "Run 2",7.57,7.59,7.63 "Run 3",7.59,7.59,7.61 "Run 4",7.59,7.6,7.58 "Timed Eigen Compilation 3.3.9 - Time To Compile", Lower Results Are Better "Run 1",82.91,82.847,82.891 "Run 2",82.966,82.955,82.932 "Run 3",83.045,83.131,83.03 "Run 4",82.99,82.931,83.06 "oneDNN 2.0 - Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU", Lower Results Are Better "Run 1",1708.67,1704.45,1711.76 "Run 2",1705.77,1707.04,1711.84 "Run 3",1709.33,1716.76,1707.34 "Run 4",1712.02,1717.27,1706.32 "oneDNN 2.0 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "Run 1",3.59064,3.59604,3.60556 "Run 2",3.59777,3.59551,3.59416 "Run 3",3.58933,3.59119,3.59256 "Run 4",3.59074,3.60654,3.59669 "Monkey Audio Encoding 3.99.6 - WAV To APE", Lower Results Are Better "Run 1",12.493,12.572,12.496,12.483,12.492 "Run 2",12.486,12.525,12.554,12.474,12.519 "Run 3",12.509,12.499,12.471,12.489,12.477 "Run 4",12.482,12.494,12.479,12.503,12.507 "oneDNN 2.0 - Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "Run 1",5.57965,5.58744,5.58185 "Run 2",5.58039,5.58033,5.57887 "Run 3",5.57022,5.58025,5.58533 "Run 4",5.59387,5.58573,5.58329 "Ogg Audio Encoding 1.3.4 - WAV To Ogg", Lower Results Are Better "Run 1",20.621,20.55,20.551 "Run 2",20.559,20.621,20.541 "Run 3",20.619,20.546,20.584 "Run 4",20.522,20.564,20.58 "oneDNN 2.0 - Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "Run 1",2.78528,2.78777,2.80115 "Run 2",2.78253,2.79179,2.79496 "Run 3",2.78423,2.7914,2.79446 "Run 4",2.78454,2.79148,2.80259 "oneDNN 2.0 - Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU", Lower Results Are Better "Run 1",6.41927,6.42516,6.42817 "Run 2",6.41456,6.43048,6.42083 "Run 3",6.42437,6.42288,6.42208 "Run 4",6.41124,6.41764,6.4244 "Opus Codec Encoding 1.3.1 - WAV To Opus Encode", Lower Results Are Better "Run 1",7.965,7.96,7.993,7.965,7.975 "Run 2",7.963,7.976,7.963,7.98,7.983 "Run 3",7.96,7.974,7.972,7.974,7.966 "Run 4",7.955,7.969,7.958,7.972,7.977 "WavPack Audio Encoding 5.3 - WAV To WavPack", Lower Results Are Better "Run 1",13.744,13.731,13.725,13.73,13.726 "Run 2",13.727,13.74,13.73,13.725,13.733 "Run 3",13.725,13.734,13.725,13.732,13.733 "Run 4",13.732,13.73,13.738,13.727,13.732 "oneDNN 2.0 - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU", Lower Results Are Better "Run 1",4756.58,3418.82,4776.46,3421.07,3419.63,3424.43,3423.86,3433.27,3431.33,3422.23,3423.21,3425.02,3426.62,3430.11,3433.3 "Run 2",3439.78,3433.92,3435.58 "Run 3",3421.55,3432.93,3440.01 "Run 4",3418.44,3414.93,3418.57