ARMv8 Cortex-A72 testing on Ubuntu 18.04 via the Phoronix Test Suite. Tests for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1903298-HV-AMAZONEC210
Ubuntu 18.04 EC2 AMD EPYC, Intel Xeon, Amazon Graviton Compute,
"7-Zip Compression 16.02 - Compress Speed Test",
Higher Results Are Better
"m5a.2xlarge",14293,14377,14476
"m5ad.2xlarge",15004,14782,14728
"m5.2xlarge",20641,21285,21038
"m5ad.4xlarge",27954,28332,28280
"m5a.4xlarge",27966,28660,28131
"m5.4xlarge",39623,39266,40156
"a1.2xlarge",13374,13490,13431
"a1.4xlarge",25119,25385,25295
"7-Zip Compression 16.02 - Performance / Cost - Compress Speed Test",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"asmFish 2018-07-23 - 1024 Hash Memory, 26 Depth",
Higher Results Are Better
"m5a.2xlarge",7884174,8064812,7993435
"m5ad.2xlarge",8483584,8371873,8130903
"m5.2xlarge",9946481,10489158,10091632
"m5ad.4xlarge",15888338,15928640,16166683
"m5a.4xlarge",15726639,15777300,15354838
"m5.4xlarge",20733632,20304548,20777235
"a1.2xlarge",7259556,7533029,7904814
"a1.4xlarge",15698242,15966631,15564489
"asmFish 2018-07-23 - Performance / Cost - 1024 Hash Memory, 26 Depth",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"CloverLeaf - Lagrangian-Eulerian Hydrodynamics",
Lower Results Are Better
"m5a.2xlarge",5.8746819496155,5.8992831707001,5.87651014328
"m5ad.2xlarge",5.4762539863586,5.492360830307,5.4830079078674
"m5.2xlarge",3.2606301307678,3.2767469882965,3.2599999904633
"m5ad.4xlarge",4.7125091552734,4.7056179046631,4.7249329090118
"m5a.4xlarge",4.7345590591431,4.7352290153503,4.7480750083923
"m5.4xlarge",1.8657059669495,1.8636379241943,1.8706450462341
"a1.2xlarge",7.4739339351654,7.4702479839325,7.4790329933167
"a1.4xlarge",5.6799409389496,5.6791479587555,5.6854979991913
"CloverLeaf - Performance / Cost - Lagrangian-Eulerian Hydrodynamics",
Lower Results Are Better
"m5ad.4xlarge",
"Cost To Run Tests - Cost / Price Per Hour",
Lower Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"GraphicsMagick 1.3.30 - Operation: Resizing",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",179,178,178
"m5.4xlarge",182,181,181
"a1.2xlarge",131,132,132
"a1.4xlarge",
"GraphicsMagick 1.3.30 - Performance / Cost - Operation: Resizing",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"GraphicsMagick 1.3.30 - Operation: Rotate",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",138,137,137
"GraphicsMagick 1.3.30 - Performance / Cost - Operation: Rotate",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"Himeno Benchmark 3.0 - Poisson Pressure Solver",
Higher Results Are Better
"m5a.2xlarge",147.544138,135.934292,147.398259
"m5ad.2xlarge",180.425955,174.970173,225.901588
"m5.2xlarge",2169.828778,2167.523854,2164.561218
"m5ad.4xlarge",897.914832,904.019131,914.278192
"m5a.4xlarge",910.166152,908.573725,919.146265
"m5.4xlarge",2205.39802,2187.572648,2186.231737
"a1.2xlarge",486.638421,473.133634,503.117583
"a1.4xlarge",493.25857,516.032899,488.580501
"Himeno Benchmark 3.0 - Performance / Cost - Poisson Pressure Solver",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"LeelaChessZero 0.20.1 - Backend: BLAS",
Higher Results Are Better
"m5a.2xlarge",43.8782,47.4005,45.4694
"m5ad.2xlarge",47.4908,48.832,52.5997
"m5.2xlarge",134.056,134.169,133.657
"m5ad.4xlarge",78.66,72.6651,73.1997
"m5a.4xlarge",83.5591,71.7388,74.5925
"m5.4xlarge",205.648,199.551,199.713
"a1.2xlarge",41.4795,43.2404,41.7733
"a1.4xlarge",63.3439,64.643,63.8574
"LeelaChessZero 0.20.1 - Performance / Cost - Backend: BLAS",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"NAMD 2.13b1 - ATPase Simulation - 327,506 Atoms",
Lower Results Are Better
"m5a.2xlarge",7.00468,6.99776,7.12903
"m5ad.2xlarge",6.95862,6.95561,6.95826
"m5.2xlarge",5.13147,5.12219,5.13009
"m5ad.4xlarge",3.49904,3.49485,3.50002
"m5a.4xlarge",3.53126,3.52698,3.5266
"m5.4xlarge",2.56152,2.57366,2.57147
"NAMD 2.13b1 - Performance / Cost - ATPase Simulation - 327,506 Atoms",
Lower Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"OpenSSL 1.1.1 - RSA 4096-bit Performance",
Higher Results Are Better
"m5a.2xlarge",530.8,531.8,531.1
"m5ad.2xlarge",532.4,532.5,533.8
"m5.2xlarge",943.1,940.2,947
"m5ad.4xlarge",1068.8,1068.8,1069.5
"m5a.4xlarge",1064.3,1065.5,1066.1
"m5.4xlarge",1901.4,1889,1888.7
"a1.2xlarge",293.3,293.3,293.1
"a1.4xlarge",586.1,586,586.1
"OpenSSL 1.1.1 - Performance / Cost - RSA 4096-bit Performance",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.4xlarge",
"PHPBench 0.8.1 - PHP Benchmark Suite",
Higher Results Are Better
"m5a.2xlarge",323978,312731,312410
"m5ad.2xlarge",365520,361896,370530
"m5.2xlarge",502656,508831,508897
"m5ad.4xlarge",366701,366902,366172
"m5a.4xlarge",362101,367277,368708
"m5.4xlarge",508965,508741,507408
"a1.2xlarge",163754,165736,162988
"a1.4xlarge",165134,163163,166699
"PHPBench 0.8.1 - Performance / Cost - PHP Benchmark Suite",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"Primesieve 7.4 - 1e12 Prime Number Generation",
Lower Results Are Better
"m5a.2xlarge",76.8,77.139,76.967
"m5ad.2xlarge",76.19,76.18,76.544
"m5.2xlarge",62.151,62.071,62.214
"m5ad.4xlarge",38.212,38.264,38.25
"m5a.4xlarge",38.438,38.443,38.506
"m5.4xlarge",30.984,31.092,31.112
"a1.2xlarge",146.628,143.1,157.008
"a1.4xlarge",67.617,73.793,72.998
"Primesieve 7.4 - Performance / Cost - 1e12 Prime Number Generation",
Lower Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"PyBench 2018-02-16 - Total For Average Test Times",
Lower Results Are Better
"m5a.2xlarge",1971,1951,1957
"m5ad.2xlarge",
"m5.2xlarge",1360,1355,1355
"m5ad.4xlarge",1653,1670,1665
"m5a.4xlarge",1647,1664,1654
"m5.4xlarge",1346,1358,1342
"a1.2xlarge",4280,4244,4263
"a1.4xlarge",
"PyBench 2018-02-16 - Performance / Cost - Total For Average Test Times",
Lower Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"Scikit-Learn 0.17.1 - ",
Lower Results Are Better
"m5a.2xlarge",24.157283067703,24.747395038605,24.204607009888
"m5ad.2xlarge",20.796379804611,20.688592195511,20.802781105042
"m5.2xlarge",18.165956020355,18.138487100601,18.182991027832
"m5ad.4xlarge",18.779375076294,18.82966709137,18.922501087189
"m5a.4xlarge",18.886061906815,19.022589921951,18.87829208374
"m5.4xlarge",16.917167186737,16.901072978973,17.347367048264
"a1.2xlarge",38.397397041321,37.544363975525,37.476489067078
"a1.4xlarge",32.738611936569,32.687058925629,32.661782979965
"Scikit-Learn 0.17.1 - Performance / Cost - ",
Lower Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"Stockfish 9 - Total Time",
Higher Results Are Better
"m5a.2xlarge",7595985,7435655,7627561
"m5ad.2xlarge",7583866,7761514,7651581
"m5.2xlarge",9397408,9174216,9362140
"m5ad.4xlarge",15142436,15096888,15001447
"m5a.4xlarge",15281384,15440880,15162259
"m5.4xlarge",18403341,18384212,18701971
"Stockfish 9 - Performance / Cost - Total Time",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"Timed HMMer Search 2.3.2 - Pfam Database Search",
Lower Results Are Better
"m5a.2xlarge",13.011158943176,12.735769987106,13.019346952438
"m5ad.2xlarge",12.650537014008,12.586647033691,12.822763204575
"m5.2xlarge",9.0628499984741,9.0986399650574,9.089015007019
"m5ad.4xlarge",9.093279838562,9.164913892746,9.1716220378876
"m5a.4xlarge",9.1555030345917,9.2379679679871,9.2016639709473
"m5.4xlarge",6.0663180351257,6.0888180732727,6.0952799320221
"Timed HMMer Search 2.3.2 - Performance / Cost - Pfam Database Search",
Lower Results Are Better
"m5ad.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"Timed Linux Kernel Compilation 4.18 - Time To Compile",
Lower Results Are Better
"m5a.2xlarge",246.62249612808,242.54751801491,247.95258688927
"m5ad.2xlarge",242.95897698402,238.95954179764,239.04334211349
"m5.2xlarge",171.94985079765,168.76809000969,168.81332397461
"m5ad.4xlarge",128.98874092102,125.7855758667,126.07123398781
"m5a.4xlarge",129.12607216835,125.92990899086,124.94146704674
"m5.4xlarge",91.371272087097,88.532790184021,88.509011983871
"a1.2xlarge",656.93784499168,652.38042998314,660.47007918358
"a1.4xlarge",358.26283288002,397.61287903786,380.35134482384
"Timed Linux Kernel Compilation 4.18 - Performance / Cost - Time To Compile",
Lower Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"Timed MAFFT Alignment 7.392 - Multiple Sequence Alignment",
Lower Results Are Better
"m5a.2xlarge",7.0521650314331,7.0471749305725,7.0556428432465
"m5ad.2xlarge",7.6036529541016,6.2567138671875,6.9571371078491
"m5.2xlarge",4.6627559661865,4.5742969512939,4.713846206665
"m5ad.4xlarge",4.9791259765625,4.5330638885498,4.5079329013824
"m5a.4xlarge",5.0241649150848,4.4906771183014,4.9989578723907
"m5.4xlarge",3.7319738864899,3.3695511817932,3.9192199707031
"a1.2xlarge",6.9821929931641,6.945760011673,6.9197630882263
"a1.4xlarge",6.1341598033905,6.0930621623993,6.0665769577026
"Timed MAFFT Alignment 7.392 - Performance / Cost - Multiple Sequence Alignment",
Lower Results Are Better
"m5ad.4xlarge",
"TTSIOD 3D Renderer 2.3b - Phong Rendering With Soft-Shadow Mapping",
Higher Results Are Better
"m5a.2xlarge",162.48,163.61,161.426
"m5ad.2xlarge",164.829,165.292,165.15
"m5.2xlarge",152.425,152.732,153.322
"m5ad.4xlarge",251.471,250.47,250.689
"m5a.4xlarge",249.383,249.054,250.275
"m5.4xlarge",291.231,289.847,292.654
"a1.2xlarge",155.342,155.362,156.436
"a1.4xlarge",289.001,288.351,288.542
"TTSIOD 3D Renderer 2.3b - Performance / Cost - Phong Rendering With Soft-Shadow Mapping",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"Zstd Compression 1.3.4 - Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19",
Lower Results Are Better
"m5a.2xlarge",57.447679042816,58.419826984406,58.287653923035
"m5ad.2xlarge",54.605170965195,54.651081085205,54.496120929718
"m5.2xlarge",35.485122919083,35.745776891708,35.751014947891
"m5ad.4xlarge",33.463814973831,33.486117124557,33.516268014908
"m5a.4xlarge",33.656378030777,33.746127843857,33.400698900223
"m5.4xlarge",19.695312023163,19.78174996376,19.832170009613
"a1.2xlarge",61.255332946777,60.61786198616,76.095479011536
"a1.4xlarge",40.22775220871,39.6463367939,40.355349063873
"Zstd Compression 1.3.4 - Performance / Cost - Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19",
Lower Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",
"Geometric Mean Of All Test Results - Result Composite - Ubuntu 18.04 EC2 AMD EPYC, Intel Xeon, Amazon Graviton Compute",
Higher Results Are Better
"m5a.2xlarge",
"m5ad.2xlarge",
"m5.2xlarge",
"m5ad.4xlarge",
"m5a.4xlarge",
"m5.4xlarge",
"a1.2xlarge",
"a1.4xlarge",