Tests for a future article. 2 x AMD EPYC 7601 32-Core testing with a Dell 02MJ3T (1.2.5 BIOS) and llvmpipe on Ubuntu 19.10 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 2101214-HA-AMDEPYC7619
AMD EPYC 7601 2P 2021,
"oneDNN 2.0 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"1",0.90628,0.920226,0.933221
"2",0.899441,0.901383,0.907591
"3",2.61411,2.58489,2.61197
"oneDNN 2.0 - Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"1",2.75224,2.82223,2.88637
"2",2.66103,2.65063,2.72487
"3",4.50721,4.51624,4.48046
"oneDNN 2.0 - Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"1",2.82271,2.90147,2.98479
"2",2.46908,2.56353,2.54238
"3",3.72134,3.79401,3.9182
"oneDNN 2.0 - Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"1",17.6978,17.686,17.7622
"2",16.5182,16.409,16.5366
"3",20.3909,20.5255,20.4421
"oneDNN 2.0 - Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"1",23.4518,23.1156,23.1557
"2",22.6249,22.3906,23.2057
"3",25.2978,25.1976,24.9831
"oneDNN 2.0 - Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"1",3.69289,3.39961,3.38209,3.31923,3.62481,3.49948,3.68324,3.64422,3.45198,3.49268,3.55496,3.75602,3.29516,3.63831,3.74891
"2",3.29157,3.32346,3.75702,3.3019,3.42455,3.36071,3.34151,3.25267,3.59176,3.58017,3.45062,3.38115,3.48687,3.41161,3.40379
"3",3.48682,3.57444,3.88482,3.81199,4.07891,3.71215,3.50356,3.76552,3.74015,3.54457,3.8455,3.82642,3.95181,3.93185,3.78225
"oneDNN 2.0 - Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"1",19.6937,19.7561,20.1486
"2",19.3788,19.0895,19.1836
"3",20.9102,21.3057,21.1358
"oneDNN 2.0 - Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"1",3.55301,3.61481,3.47953
"2",3.44826,3.67498,3.47494,3.45833,3.41904
"3",3.71094,3.74807,3.69001
"dav1d 0.8.1 - Video Input: Summer Nature 1080p",
Higher Results Are Better
"1",602.14,658.04,609.89,650.31,645.75,549.8,652.64,664.85,649.55,652.36,649.81,629.28,648.37,601.1,580.08
"2",659.42,673.31,675
"3",535.77,642.8,641.35,628.6,574.09,664.86,623.99,648.23,673.87,641.77,624.37,659.54,657.92,669.26,634.08
"Mobile Neural Network 1.1.1 - Model: inception-v3",
Lower Results Are Better
"1",67.363,68.702,69.69
"2",69.185,72.314,73.225
"dav1d 0.8.1 - Video Input: Chimera 1080p",
Higher Results Are Better
"1",617.14,646.24,647.71
"2",655.53,660.59,661.44
"3",662.16,624.55,620.8,631.58
"oneDNN 2.0 - Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"1",3.73334,3.92983,3.94335,3.86313
"2",3.82347,3.90353,3.7303
"3",3.98899,4.00893,3.89315
"OpenFOAM 8 - Input: Motorbike 30M",
Lower Results Are Better
"1",34.64,34.78,34.45
"2",34.1,34.09,34.5
"3",38.11,37.91,34.68,34.95,34.67,34.55,34.57,34.99,34.24,34.41,34.83,36.09,34.33,36.89,34.58
"Quantum ESPRESSO 6.7 - Input: AUSURF112",
Lower Results Are Better
"1",1732.12,1871.01,1820.6,1726.39,1723.76,1860.37,1827.56,1840.6,1764.46
"2",1763.84,1752.59,1746.21
"3",1782.95,1900.47,1793.95,1716.03,1806.07,1877.84,1797.59,1780.87,1823.24
"Timed Godot Game Engine Compilation 3.2.3 - Time To Compile",
Lower Results Are Better
"1",106.266,104.436,110.592
"2",102.282,102.913,106.817
"3",101.962,106.488,103.292
"Etcpak 0.7 - Configuration: DXT1",
Higher Results Are Better
"1",1298.842,1293.94,1297.578
"2",1322.168,1325.527,1323.7
"3",1321.077,1323.481,1322.46
"rav1e 0.4 - Speed: 10",
Higher Results Are Better
"1",2.353,2.283,2.33
"2",2.36,2.402,2.348
"3",2.32,2.356,2.331
"oneDNN 2.0 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"1",1.36902,1.37409,1.39331
"2",1.37921,1.3965,1.39097
"3",1.39821,1.40829,1.41013
"Mobile Neural Network 1.1.1 - Model: MobileNetV2_224",
Lower Results Are Better
"1",10.468,10.661,11.095
"2",11.426,10.404,10.898
"rav1e 0.4 - Speed: 1",
Higher Results Are Better
"1",0.26,0.259,0.255
"2",0.261,0.264,0.26
"3",0.261,0.264,0.259
"rav1e 0.4 - Speed: 6",
Higher Results Are Better
"1",1.017,0.999,1.031
"2",1.023,1.041,1.029
"3",1.045,1.042,1.002
"LAMMPS Molecular Dynamics Simulator 29Oct2020 - Model: Rhodopsin Protein",
Higher Results Are Better
"1",23.353,23.339,23.241
"2",23.487,23.391,23.269
"3",23.527,22.983,22.739
"Cryptsetup - PBKDF2-sha512",
Higher Results Are Better
"1",1170285,1174217,1167679
"2",1172903,1168981,1084359,1168981,1170285,1167679,1168981
"3",1168981,1168981,1167679
"Mobile Neural Network 1.1.1 - Model: SqueezeNetV1.0",
Lower Results Are Better
"1",15.119,14.77,14.976
"2",15.157,14.804,14.475
"Cryptsetup - AES-XTS 256b Encryption",
Higher Results Are Better
"1",1438.5,1443.7,1450.8
"2",1467.4,1458.5,1452.6,1450.2,1459.1,1459.1,1451.3
"3",1456.5,1451.2,1455.7
"LAMMPS Molecular Dynamics Simulator 29Oct2020 - Model: 20k Atoms",
Higher Results Are Better
"1",23.438,23.475,23.233
"2",23.367,23.576,23.253
"3",23.235,23.099,23.268
"Cryptsetup - PBKDF2-whirlpool",
Higher Results Are Better
"1",510007,511001,509017
"2",508031,508031,506069,508031,508031,508031,508031
"3",507048,504123,507048
"Cryptsetup - AES-XTS 256b Decryption",
Higher Results Are Better
"1",1444.6,1442.1,1449.4
"2",1467.3,1366.5,1450.6,1448.6,1457.2,1454.7,1453.4
"3",1455.9,1449.1,1454.3
"Cryptsetup - AES-XTS 512b Decryption",
Higher Results Are Better
"1",1273.1,1275.9,1281
"2",1294.9,1281.9,1283.5,1278.5,1287,1285.5,1283.5
"3",1286.8,1280.9,1285.2
"rav1e 0.4 - Speed: 5",
Higher Results Are Better
"1",0.77,0.792,0.778
"2",0.776,0.787,0.77
"3",0.774,0.767,0.785
"LULESH 2.0.3 - ",
Higher Results Are Better
"1",16176.33,16066.837,16035.608
"2",16079.784,15996.323,16143.152
"3",15884.605,16108.813,15978.743
"Unpacking Firefox 84.0 - Extracting: firefox-84.0.source.tar.xz",
Lower Results Are Better
"1",25.856,25.882,26.139,25.749
"2",25.66,25.804,25.782,25.768
"Cryptsetup - AES-XTS 512b Encryption",
Higher Results Are Better
"1",1278.5,1277.7,1282
"2",1294.1,1284,1283.9,1283.3,1288.8,1287.6,1285.2
"3",1287.3,1282.6,1286.2
"OpenFOAM 8 - Input: Motorbike 60M",
Lower Results Are Better
"1",339.03,338.92,338.17
"2",339.82,337.68,337.61
"3",339.2,339.55,341.38
"dav1d 0.8.1 - Video Input: Chimera 1080p 10-bit",
Higher Results Are Better
"1",139.1,138.58,137.68
"2",138.48,138.73,139.48
"3",139.34,138.86,139.18
"oneDNN 2.0 - Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"1",3.15167,3.27307,3.0276,3.24069,3.15265,3.16714
"2",3.15445,3.17841,3.21069
"3",3.16399,3.21433,3.17345
"Opus Codec Encoding 1.3.1 - WAV To Opus Encode",
Lower Results Are Better
"1",10.219,10.205,10.227,10.207,10.207
"2",10.212,10.212,10.215,10.195,10.202
"3",10.227,10.251,10.238,10.236,10.238
"ONNX Runtime 1.6 - Model: super-resolution-10 - Device: OpenMP CPU",
Higher Results Are Better
"1",2096.5,2099,2056
"2",2032,2060.5,2140
"Cryptsetup - Twofish-XTS 256b Encryption",
Higher Results Are Better
"1",316.7,317.8,317.8
"2",318.1,318.1,318.4,318.1,318.6,318.4,318.4
"3",318.2,318.3,318.3
"Cryptsetup - Serpent-XTS 256b Encryption",
Higher Results Are Better
"1",306.9,308.6,308.7
"2",308.2,305.3,309.1,308.7,309.2,309.1,308.9
"3",308.9,308.9,309
"Ogg Audio Encoding 1.3.4 - WAV To Ogg",
Lower Results Are Better
"1",26.636,26.591,26.581
"2",26.632,26.63,26.619
"3",26.645,26.671,26.678
"Cryptsetup - Twofish-XTS 512b Decryption",
Higher Results Are Better
"1",316,315.9
"2",316.6,316.5,316.8,316.5,316.7,316.9,316.5
"3",316.9,316.5,316.8
"TNN 0.2.3 - Target: CPU - Model: MobileNet v2",
Lower Results Are Better
"1",368.979,371.539,366.805
"2",369.436,369.982,369.59
"Cryptsetup - Serpent-XTS 256b Decryption",
Higher Results Are Better
"1",306.5,306.6,306.9
"2",306.4,307,307.1,306.9,307.2,307.2,306.9
"3",307.1,307.1,307.1
"Cryptsetup - Serpent-XTS 512b Encryption",
Higher Results Are Better
"1",308.7,308.5
"2",308.4,308.7,309,308.8,309,308.8
"3",
"Cryptsetup - Twofish-XTS 256b Decryption",
Higher Results Are Better
"1",316.5,316.4,316.6
"2",316.7,316.7,316.9,316.6,317,317.1,316.7
"3",317,316.7,317
"Cryptsetup - Twofish-XTS 512b Encryption",
Higher Results Are Better
"1",317.5,317.6,318.1
"2",318,318,318.1,317.9,318.3,318.3,318.2
"3",317.8,318.2
"Algebraic Multi-Grid Benchmark 1.2 - ",
Higher Results Are Better
"1",712322900,708525700,708250800
"2",710095200,709725900,709396000
"3",708583000,707917000,710140700
"Monkey Audio Encoding 3.99.6 - WAV To APE",
Lower Results Are Better
"1",18.372,18.334,18.382,18.314,18.316
"2",18.32,18.316,18.324,18.326,18.322
"3",18.332,18.34,18.344,18.333,18.333
"Cryptsetup - Serpent-XTS 512b Decryption",
Higher Results Are Better
"1",306.6,306.7
"2",306.5,306.9,307,307.3
"3",
"RELION 3.1.1 - Test: Basic - Device: CPU",
Lower Results Are Better
"1",548.48,548.742,547.915
"2",548.535,548.803,547.943
"3",547.668,547.704,548.446
"Etcpak 0.7 - Configuration: ETC1 + Dithering",
Higher Results Are Better
"1",174.268,174.324,174.258
"2",174.269,174.346,174.286
"3",174.062,174.211,174.225
"WavPack Audio Encoding 5.3 - WAV To WavPack",
Lower Results Are Better
"1",17.296,17.306,17.29,17.285,17.301
"2",17.305,17.285,17.278,17.279,17.279
"TNN 0.2.3 - Target: CPU - Model: SqueezeNet v1.1",
Lower Results Are Better
"1",333.343,333.333,333.532
"2",333.498,332.999,333.32
"Etcpak 0.7 - Configuration: ETC1",
Higher Results Are Better
"1",184.735,184.787,184.718
"2",184.732,184.664,184.674
"3",184.718,184.775,184.777
"Etcpak 0.7 - Configuration: ETC2",
Higher Results Are Better
"1",118.068,118.041,118.038
"2",118.041,118.046,118.06
"3",118.067,118.076,118.067
"Google SynthMark 20201109 - Test: VoiceMark_100",
Higher Results Are Better
"1",512.106,512.107,512.108
"2",512.055,512.057,512.105
"3",512.106,512.056,512.058
"Kripke 1.2.4 - ",
Higher Results Are Better
"1",45330920,36296890,33939030,38793770,25581770,38510970,39626950,35882640,32698920,52034560,42393820,32833500,36291960,28857630,49164730
"2",30221490,34404790,34938020,33051000,32994060,46374140,37501320,39520230,29731770,24563190,41555510,37867160
"ONNX Runtime 1.6 - Model: shufflenet-v2-10 - Device: OpenMP CPU",
Higher Results Are Better
"1",2234,2618,1434,2514.5,2604.5,2367.5,1551.5,2289,1275.5,2141,2609,2613.5
"2",1729.5,2351,2188.5,2504,2816.5,1934.5,2669,1598.5,2558,2424,2306.5,2731
"ONNX Runtime 1.6 - Model: fcn-resnet101-11 - Device: OpenMP CPU",
Higher Results Are Better
"1",52,53,55
"2",55.5,46,47,50.5,54.5,54.5,55.5,51,53,46.5,54.5,52
"ONNX Runtime 1.6 - Model: bertsquad-10 - Device: OpenMP CPU",
Higher Results Are Better
"1",58.5,57,57.5
"2",47,55.5,48.5,48,66,50.5,49.5,51,71
"ONNX Runtime 1.6 - Model: yolov4 - Device: OpenMP CPU",
Higher Results Are Better
"1",75.5,68,82,73,66.5,84,62,83.5,63,87.5,79,86.5
"2",77.5,77,60.5,74,78.5,68,61,71.5,59.5,76.5,73,77
"Mobile Neural Network 1.1.1 - Model: mobilenet-v1-1.0",
Lower Results Are Better
"1",6.56,6.817,6.905
"2",6.74,6.113,8.182
"Mobile Neural Network 1.1.1 - Model: resnet-v2-50",
Lower Results Are Better
"1",56.253,53.157,52.953
"2",57.348,50.064,51.169
"dav1d 0.8.1 - Video Input: Summer Nature 4K",
Higher Results Are Better
"1",225.06,240.58,236.39,209.32,251.4,258.5,247.81,251.35,242.15,250.5,257.27,249.35
"2",253.4,249.26,252.04
"3",255.81,199.11,254.13,250.21,253.03,252.03,248.92,253.44,254.1,261.58,247.51,253.07
"oneDNN 2.0 - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"1",3036.06,3918.17,3242.93,3937.87,4742.94,3344.61,3187.82,4241.88,3729.01,3325.75,3823.26,3706.79,3209.97,3586.79,4447.87
"2",4652.99,4604.18,3602.33,3732.16,3347.69,3847.2,3761.34,3631.52,4631.89,3324.72,3276.6,4324.71,3342.61,4808.88,3276.8
"3",3533.92,4661.31,4692.08,4714.75,4122.54,3956.19,3975.19,4137.1,3915.46,4034.64,4234.37,4147.81,3837.58,3952.18,4147.66
"oneDNN 2.0 - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"1",4592.46,4256.84,4795.34,5284.78,4373.18,5576.88,4791.34,5182.26,4693.69,4386.72,4436.96,4115.45
"2",5274.21,4668.52,4432.91,5551.98,3589.05,4595.53,4581.12,4261.51,4863.44,5398.46,3679.93,4798.51,4930.34,4674.46,3930.46
"3",4108.9,4961.79,4619.35,4245.92,4547.05,5519.73,5115.52,4878.57,5366.22,5373.72,4181.32,4600.08,4899.08,5414.77,5445.52
"oneDNN 2.0 - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"1",3517.06,3527.26,3628.37
"2",4159.55,3194.98,3864.79,3538.74,4676.29,3374.65,3203.93,3413.73,3341.05,3857.53,4021.4,3309.57,3381.38,3166.44,3202.42
"3",4249.49,3819.74,4275.77,4788.9,4200.38,4297.16,3872.95,4750.83,4379.21,4328.38,3870.38,3946.98,3555.05,4111.57,4548.25
"oneDNN 2.0 - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"1",4691.88,3442.71,3502.73,5139.98,5576.18,4096.82,3120.4,4243.1,5620.28,4806.26,5728.89,4760.47,3466.87,4294.05,4506.84
"2",3215.97,4195.06,5138.27,5452.97,4818.73,4113.62,5036.78,5600.15,3851.33,5263.29,4729.34,3679.03,4928.72,4202.91,4477.02
"3",4803.61,4855.02,3977.89,5119.68,5442.91,4561.09,4833.52,5004.92,3650.55,4314.98,5358.14,4458.64,4335.34,5430.21,3781.78
"oneDNN 2.0 - Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"1",4287.38,4075.08,3908.36,4109.97,4152.29,3645.99,4202.55,3722.17,4054.25,3772.95,3750.39,4240.92,3478.78,4018.51,3681.4
"2",4366.26,3397.61,3810.76,3511.39,3957.27,4054.15,3975.27,3516.21,3355.02,3357.74,4571.02,3431.35,4611.92,4626.94,3440.75
"3",3911.78,3914.5,4121.36,4688,4053.18,3866.37,4635.9,4078.2,3835.5,4121.81,3550.3,3827.48
"oneDNN 2.0 - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"1",4830.03,4482.24,5305.34,4295.75,4240.97,4991.37,4205.89,3712,4386.25,5002.21,4735.05,4735.04,4884.74,4823.95,3684.02
"2",4659.23,4729.17,5274.91,4083.92,4326.24,3764.53,4287.09,5416.72,3875.53,4360.29,4311.8,5100.06
"3",4410.15,5715.16,4451.75,4530.11,4700.08,5587.8,5259.38,4918.72,5036.03,5637.81,5200.17,4519.26,5316.4,4924.67,5093.11
"oneDNN 2.0 - Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"1",6.64866,7.26934,6.30304,5.46988,5.62553,6.13215,6.99382,6.84365,6.10703,5.66245,6.8641,6.00316,6.42671,7.21184,7.25793
"2",6.83589,5.7482,7.05228,6.82865,6.3057,6.86363,6.9176,6.89933,7.41281,6.48045,5.61434,6.3743,6.61315,6.38967,6.09958
"3",7.06733,7.29128,6.9153
"QMCPACK 3.10 - Input: simple-H2O",
Lower Results Are Better
"1",42.249,41.751,41.517
"2",41.681,48.2,56.688,48.545,49.768,44.521,51.35,41.555,41.66,43.372,42.935,42.193,42.634,56.806,41.821
"3",41.582,45.835,48.477,55.049,55.238,60.774,51.425,56.136,41.65,52.807,50.687,48.201
"CloverLeaf - Lagrangian-Eulerian Hydrodynamics",
Lower Results Are Better
"1",28.203080892563,30.82347202301,27.973757982254,29.093134880066,29.242066144943,28.151166915894,30.505786895752,31.990628957748,30.426919221878,30.848891973495,28.274749994278,28.865705013275,28.565698862076,30.46116900444,29.604470014572
"2",27.184356927872,29.397855997086,28.860022068024,29.559723854065,27.764235973358,28.998887062073,29.663860082626,29.502600193024,30.560847997665,28.665574073792,29.75217294693,29.519800901413,29.383412837982,30.452581882477,29.335314035416
"3",29.813720941544,28.596750974655,32.680616855621,29.52020907402,29.863306999207,30.675420045853,26.749304056168,28.281254053116,31.265856027603,27.284070968628,28.328382015228,29.377113103867,33.12101817131,32.388772964478,30.132599830627