Google Cloud c3 Sapphire Rapids vs. AMD Milan

Benchmarks by Michael Larabel 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 2303280-NE-2303286NE24
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:

Timed Code Compilation 2 Tests
C/C++ Compiler Tests 8 Tests
Compression Tests 2 Tests
CPU Massive 14 Tests
Creator Workloads 9 Tests
Cryptography 2 Tests
Database Test Suite 4 Tests
Fortran Tests 2 Tests
Game Development 4 Tests
HPC - High Performance Computing 12 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 5 Tests
Molecular Dynamics 4 Tests
MPI Benchmarks 2 Tests
Multi-Core 16 Tests
NVIDIA GPU Compute 3 Tests
Intel oneAPI 5 Tests
OpenMPI Tests 6 Tests
Programmer / Developer System Benchmarks 3 Tests
Python Tests 2 Tests
Renderers 2 Tests
Scientific Computing 4 Tests
Server 6 Tests
Server CPU Tests 9 Tests
Common Workstation 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
Disable Color Branding
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable

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
Performance Per
Dollar
Date
Run
  Test
  Duration
c3-highcpu-8 SPR
March 21 2023
  12 Hours, 6 Minutes
c2-standard-8 CLX
March 21 2023
  13 Hours
n2-standard-8 CLX
March 22 2023
  16 Hours, 1 Minute
n2-highcpu-8 CLX
March 23 2023
  14 Hours, 13 Minutes
t2d-standard-8 AMD
March 27 2023
  11 Hours, 20 Minutes
c2d-highcpu-8 AMD
March 28 2023
  11 Hours, 59 Minutes
Invert Hiding All Results Option
  13 Hours, 7 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):

Google Cloud c3 Sapphire Rapids vs. AMD Milan, "miniBUDE 20210901 - Implementation: OpenMP - Input Deck: BM1", Higher Results Are Better "c3-highcpu-8 SPR",7.544,7.547,7.547 "c2-standard-8 CLX",6.11,6.113,6.113 "n2-standard-8 CLX",5.36,5.354,5.36 "n2-highcpu-8 CLX",5.36,5.354,5.36 "t2d-standard-8 AMD",12.163,12.16,12.164 "c2d-highcpu-8 AMD",7.445,7.444,7.441 "OpenSSL 3.1 - Algorithm: SHA256", Higher Results Are Better "c3-highcpu-8 SPR",4281947650,4280427040,4289247270 "c2-standard-8 CLX",1318236220,1318139990,1318204380 "n2-standard-8 CLX",1181526990,1176520840,1177493790 "n2-highcpu-8 CLX",1177028320,1177687310,1177285210 "t2d-standard-8 AMD",6873644960,6878908980,6875829250 "c2d-highcpu-8 AMD",5828449760,5823201530,5820888360 "OpenSSL 3.1 - Algorithm: SHA512", Higher Results Are Better "c3-highcpu-8 SPR",1566293190,1569412870,1570012700 "c2-standard-8 CLX",1471625920,1463936180,1461883580 "n2-standard-8 CLX",1304972920,1314517850,1304971310 "n2-highcpu-8 CLX",1305164190,1303030630,1310476340 "t2d-standard-8 AMD",3157251310,3156488060,3162225080 "c2d-highcpu-8 AMD",1863267990,1862955150,1863833060 "OpenSSL 3.1 - Algorithm: ChaCha20", Higher Results Are Better "c3-highcpu-8 SPR",22100458700,22148601720,22025612490 "c2-standard-8 CLX",21347789480,21343870980,21348774980 "n2-standard-8 CLX",19072322220,19025187910,19067880520 "n2-highcpu-8 CLX",19065248150,19060436720,19070772840 "t2d-standard-8 AMD",26314874330,26333549360,26327437040 "c2d-highcpu-8 AMD",17279705360,17247305730,17272542280 "OpenSSL 3.1 - Algorithm: AES-128-GCM", Higher Results Are Better "c3-highcpu-8 SPR",57581204280,57658200880,57542828310 "c2-standard-8 CLX",23249333730,23228925540,23233678540 "n2-standard-8 CLX",20767058060,20761296350,20767414950 "n2-highcpu-8 CLX",20747912530,20757449660,20755288340 "t2d-standard-8 AMD",33962929080,33961322630,33920694410 "c2d-highcpu-8 AMD",18522705920,18522702920,18521860230 "OpenSSL 3.1 - Algorithm: AES-256-GCM", Higher Results Are Better "c3-highcpu-8 SPR",47913384620,48042883750,48068816350 "c2-standard-8 CLX",16950542610,16937586410,16946872870 "n2-standard-8 CLX",15140960390,15123918850,15122834770 "n2-highcpu-8 CLX",15146359470,15128363550,15126841750 "t2d-standard-8 AMD",31385526820,31489066870,31467824470 "c2d-highcpu-8 AMD",16968420280,16964662610,16973733070 "OpenSSL 3.1 - Algorithm: ChaCha20-Poly1305", Higher Results Are Better "c3-highcpu-8 SPR",15997971110,15987123000,15927249310 "c2-standard-8 CLX",10916123720,10921518690,10919813120 "n2-standard-8 CLX",9577190740,9571740880,9580608440 "n2-highcpu-8 CLX",9568054480,9560526300,9573842120 "t2d-standard-8 AMD",17522441420,17626497570,17628861240 "c2d-highcpu-8 AMD",11760020680,11759238620,11758720070 "nekRS 22.0 - Input: TurboPipe Periodic", Higher Results Are Better "c3-highcpu-8 SPR",30677600000,30503900000,30822200000 "c2-standard-8 CLX",25066000000,25211900000,25024400000 "n2-standard-8 CLX",22849500000,23064300000,22976900000 "n2-highcpu-8 CLX", "t2d-standard-8 AMD",40721000000,40881400000,40666700000 "c2d-highcpu-8 AMD",27145700000,27180500000,27019400000 "Embree 4.0.1 - Binary: Pathtracer ISPC - Model: Crown", Higher Results Are Better "c3-highcpu-8 SPR",5.8471,5.8684,5.8269 "c2-standard-8 CLX",3.9313,3.9306,3.94 "n2-standard-8 CLX",3.5006,3.4416,3.433 "n2-highcpu-8 CLX",3.4913,3.4519,3.4711 "t2d-standard-8 AMD",5.5501,5.517,5.4113 "c2d-highcpu-8 AMD",4.94,4.9222,4.9072 "Embree 4.0.1 - Binary: Pathtracer ISPC - Model: Asian Dragon", Higher Results Are Better "c3-highcpu-8 SPR",7.3731,7.3711,7.3484 "c2-standard-8 CLX",5.1353,5.1761,5.1511 "n2-standard-8 CLX",4.6076,4.5633,4.5594 "n2-highcpu-8 CLX",4.5841,4.604,4.6102 "t2d-standard-8 AMD",6.5226,6.3441,6.3851 "c2d-highcpu-8 AMD",5.842,5.8434,5.8196 "uvg266 0.4.1 - Video Input: Bosphorus 4K - Video Preset: Very Fast", Higher Results Are Better "c3-highcpu-8 SPR",6.94,7.02,7.02 "c2-standard-8 CLX",5.65,5.71,5.7 "n2-standard-8 CLX",4.92,4.97,5.01 "n2-highcpu-8 CLX",4.93,4.93,4.92 "t2d-standard-8 AMD",10.56,10.72,10.75 "c2d-highcpu-8 AMD",7.85,7.9,7.95 "uvg266 0.4.1 - Video Input: Bosphorus 4K - Video Preset: Super Fast", Higher Results Are Better "c3-highcpu-8 SPR",7.48,7.48,7.48 "c2-standard-8 CLX",6.03,6.03,6.03 "n2-standard-8 CLX",5.28,5.28,5.28 "n2-highcpu-8 CLX",5.17,5.17,5.18 "t2d-standard-8 AMD",11.31,11.38,11.39 "c2d-highcpu-8 AMD",8.16,8.14,8.12 "uvg266 0.4.1 - Video Input: Bosphorus 4K - Video Preset: Ultra Fast", Higher Results Are Better "c3-highcpu-8 SPR",9.12,9.13,9.11 "c2-standard-8 CLX",7.45,7.46,7.44 "n2-standard-8 CLX",6.53,6.51,6.48 "n2-highcpu-8 CLX",6.41,6.41,6.4 "t2d-standard-8 AMD",13.76,13.71,13.53 "c2d-highcpu-8 AMD",9.82,9.8,9.85 "uvg266 0.4.1 - Video Input: Bosphorus 1080p - Video Preset: Very Fast", Higher Results Are Better "c3-highcpu-8 SPR",31.89,32.65,32.62 "c2-standard-8 CLX",25.99,26.51,26.41 "n2-standard-8 CLX",22.51,22.93,22.98 "n2-highcpu-8 CLX",22.63,22.93,23.05 "t2d-standard-8 AMD",48.23,49.39,49.95 "c2d-highcpu-8 AMD",35.72,36.81,36.82 "uvg266 0.4.1 - Video Input: Bosphorus 1080p - Video Preset: Super Fast", Higher Results Are Better "c3-highcpu-8 SPR",34.44,34.53,34.54 "c2-standard-8 CLX",27.73,27.73,27.7 "n2-standard-8 CLX",24.13,24.18,24.15 "n2-highcpu-8 CLX",24.19,24.14,24.13 "t2d-standard-8 AMD",52.03,52.25,52.46 "c2d-highcpu-8 AMD",37.72,37.85,37.79 "uvg266 0.4.1 - Video Input: Bosphorus 1080p - Video Preset: Ultra Fast", Higher Results Are Better "c3-highcpu-8 SPR",42.25,42.22,42.24 "c2-standard-8 CLX",34.46,34.48,34.47 "n2-standard-8 CLX",30.08,29.96,30.11 "n2-highcpu-8 CLX",29.91,29.99,30 "t2d-standard-8 AMD",61.39,62.48,61.67 "c2d-highcpu-8 AMD",45.57,45.38,45.65 "miniBUDE 20210901 - Implementation: OpenMP - Input Deck: BM1", Higher Results Are Better "c3-highcpu-8 SPR",188.599,188.678,188.675 "c2-standard-8 CLX",152.76,152.813,152.821 "n2-standard-8 CLX",133.998,133.857,133.997 "n2-highcpu-8 CLX",134.009,133.853,133.988 "t2d-standard-8 AMD",304.074,303.992,304.092 "c2d-highcpu-8 AMD",186.128,186.088,186.025 "Intel Open Image Denoise 1.4.0 - Run: RT.hdr_alb_nrm.3840x2160", Higher Results Are Better "c3-highcpu-8 SPR",0.24343338445434,0.24382750666868,0.24185200592054 "c2-standard-8 CLX",0.22430527050094,0.22430275488644,0.22431885579438 "n2-standard-8 CLX",0.20145977754811,0.20172556044404,0.20172515351284 "n2-highcpu-8 CLX",0.20096907286938,0.20129513288498,0.20090003214401 "t2d-standard-8 AMD",0.29689183933401,0.29653176448261,0.2968142922018 "c2d-highcpu-8 AMD",0.16477885030501,0.16484757369099,0.16492125010308 "Intel Open Image Denoise 1.4.0 - Run: RTLightmap.hdr.4096x4096", Higher Results Are Better "c3-highcpu-8 SPR",0.11460516800545,0.11549464624567,0.11563527708525 "c2-standard-8 CLX",0.10568277413055,0.10565296171665,0.10560576522994 "n2-standard-8 CLX",0.094940614645539,0.095028128325985,0.095178268897645 "n2-highcpu-8 CLX",0.094871259700586,0.094898269055572,0.090971116670457 "t2d-standard-8 AMD",0.14789989543477,0.14826852022086,0.14851492500739 "c2d-highcpu-8 AMD",0.082532765507907,0.082523230289327,0.082511654771236 "TensorFlow 2.10 - Device: CPU - Batch Size: 16 - Model: ResNet-50", Higher Results Are Better "c3-highcpu-8 SPR",14.16,14.27,14.16 "c2-standard-8 CLX",13.35,13.34,13.3 "n2-standard-8 CLX",12.29,12.22,12.02 "n2-highcpu-8 CLX",12.13,12.2,12.2 "t2d-standard-8 AMD",10.67,10.81,10.74 "c2d-highcpu-8 AMD",8.62,8.67,8.69 "TensorFlow 2.10 - Device: CPU - Batch Size: 32 - Model: ResNet-50", Higher Results Are Better "c3-highcpu-8 SPR",14.93,14.92,14.94 "c2-standard-8 CLX",14.11,14.14,14.09 "n2-standard-8 CLX",12.82,12.96,13.06 "n2-highcpu-8 CLX",12.97,13.01,12.98 "t2d-standard-8 AMD",10.55,10.58,10.7 "c2d-highcpu-8 AMD",8.54,8.56,8.56 "TensorFlow 2.10 - Device: CPU - Batch Size: 64 - Model: ResNet-50", Higher Results Are Better "c3-highcpu-8 SPR",15.67,15.7,15.71 "c2-standard-8 CLX",14.93,15,14.44 "n2-standard-8 CLX",13.71,13.74,13.76 "n2-highcpu-8 CLX",13.69,13.72,13.69 "t2d-standard-8 AMD",10.41,10.46,10.56 "c2d-highcpu-8 AMD",8.47,8.46,8.46 "OpenVKL 1.3.1 - Benchmark: vklBenchmark ISPC", Higher Results Are Better "c3-highcpu-8 SPR",98,99,98 "c2-standard-8 CLX",70,70,70 "n2-standard-8 CLX",62,63,63 "n2-highcpu-8 CLX",80,81,81 "t2d-standard-8 AMD",76,75,74 "c2d-highcpu-8 AMD",61,62,63 "Neural Magic DeepSparse 1.3.2 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR",3.8131,3.777,3.7717 "c2-standard-8 CLX",2.9306,2.931,2.9307 "n2-standard-8 CLX",2.651,2.6647,2.6603 "n2-highcpu-8 CLX",2.6264,2.6262,2.6279 "t2d-standard-8 AMD",6.1764,6.1406,6.1663 "c2d-highcpu-8 AMD",3.4241,3.4203,3.4138 "Neural Magic DeepSparse 1.3.2 - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR",19.1751,19.207,19.1209 "c2-standard-8 CLX",15.8087,15.9625,15.9826 "n2-standard-8 CLX",15.4575,15.3886,15.2403 "n2-highcpu-8 CLX",15.106,15.0896,15.145 "t2d-standard-8 AMD",23.8926,23.7166,23.8156 "c2d-highcpu-8 AMD",13.5714,13.4728,13.5956 "Neural Magic DeepSparse 1.3.2 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR",64.8563,64.8078,64.96 "c2-standard-8 CLX",60.0386,59.9662,59.9693 "n2-standard-8 CLX",54.9984,54.9145,54.9642 "n2-highcpu-8 CLX",54.6459,54.4258,54.476 "t2d-standard-8 AMD",68.6547,68.9515,68.9591 "c2d-highcpu-8 AMD",38.1119,38.1928,38.0678 "Neural Magic DeepSparse 1.3.2 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR",33.3333,32.8117,33.1741 "c2-standard-8 CLX",29.2192,29.115,29.2007 "n2-standard-8 CLX",25.873,25.828,26.2197 "n2-highcpu-8 CLX",26.0694,25.3957,25.6159 "t2d-standard-8 AMD",51.3271,51.3554,51.3797 "c2d-highcpu-8 AMD",28.5455,28.4777,28.4454 "Neural Magic DeepSparse 1.3.2 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR",6.5425,6.5473,6.5218 "c2-standard-8 CLX",6.1951,6.1894,6.1834 "n2-standard-8 CLX",5.7552,5.7691,5.7229 "n2-highcpu-8 CLX",5.6482,5.6418,5.6542 "t2d-standard-8 AMD",8.0428,8.139,8.3145 "c2d-highcpu-8 AMD",4.5825,4.5867,4.5833 "Neural Magic DeepSparse 1.3.2 - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR",16.0563,16.4667,16.1353 "c2-standard-8 CLX",13.9423,14.0406,13.9967 "n2-standard-8 CLX",12.6218,12.8707,12.7403 "n2-highcpu-8 CLX",12.8748,12.8909,12.8771 "t2d-standard-8 AMD",26.077,26.1495,25.951 "c2d-highcpu-8 AMD",14.3408,14.3733,14.3506 "Neural Magic DeepSparse 1.3.2 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR",3.8154,3.7569,3.7356 "c2-standard-8 CLX",2.9377,2.9277,2.9402 "n2-standard-8 CLX",2.6584,2.6645,2.6561 "n2-highcpu-8 CLX",2.66,2.6629,2.6482 "t2d-standard-8 AMD",6.2087,6.1933,6.1848 "c2d-highcpu-8 AMD",3.3873,3.4134,3.3719 "Zstd Compression 1.5.4 - Compression Level: 19 - Compression Speed", Higher Results Are Better "c3-highcpu-8 SPR",10.1,10.2,10.5 "c2-standard-8 CLX",9.13,9.19,9.39 "n2-standard-8 CLX",8.29,8.31,8.12 "n2-highcpu-8 CLX",8.05,8.28,8.56,8.31,8.23 "t2d-standard-8 AMD",11.1,11,10.7 "c2d-highcpu-8 AMD",11,10.9,11.1 "Zstd Compression 1.5.4 - Compression Level: 19 - Decompression Speed", Higher Results Are Better "c3-highcpu-8 SPR",907.8,905.2,902.6 "c2-standard-8 CLX",703.8,700.8,698.8 "n2-standard-8 CLX",649.9,643,655.7 "n2-highcpu-8 CLX",644.1,642.7,640.5,637.8,639.1 "t2d-standard-8 AMD",1126.5,1136.9,1123.7 "c2d-highcpu-8 AMD",1256.5,1257.4,1246.9 "Zstd Compression 1.5.4 - Compression Level: 19, Long Mode - Compression Speed", Higher Results Are Better "c3-highcpu-8 SPR",6.5,6.5,6.5 "c2-standard-8 CLX",5.87,5.86,5.86 "n2-standard-8 CLX",5.22,4.8,4.79,5.1,5.15,5.2,5.16,5.14,5.22,5.16,5.18,5.21,5.22,5.22,5.17 "n2-highcpu-8 CLX",5.04,5.03,5.04 "t2d-standard-8 AMD",5.33,5.41,5.52 "c2d-highcpu-8 AMD",6.71,6.78,6.64 "Zstd Compression 1.5.4 - Compression Level: 19, Long Mode - Decompression Speed", Higher Results Are Better "c3-highcpu-8 SPR",909.6,907.5,904.5 "c2-standard-8 CLX",713.2,710.7,717.6 "n2-standard-8 CLX",667.5,639.1,649.9,661.7,663.5,658.7,662.2,664.9,661.6,660.4,665.6,660.4,665.8,658.4,665.4 "n2-highcpu-8 CLX",649.8,650,650.1 "t2d-standard-8 AMD",1065.9,1071.6,1089.8 "c2d-highcpu-8 AMD",1201.1,1168.3,1182.1 "7-Zip Compression 22.01 - Test: Compression Rating", Higher Results Are Better "c3-highcpu-8 SPR",36032,35385,34238,33196,33265,35420,35826,35790,35405,35925,35683,35909,35855,35548,36117 "c2-standard-8 CLX",31070,31372,30524 "n2-standard-8 CLX",28312,27913,27961 "n2-highcpu-8 CLX",27282,28798,28373,27918 "t2d-standard-8 AMD",48215,48648,48483 "c2d-highcpu-8 AMD",38469,39668,39471 "LeelaChessZero 0.28 - Backend: BLAS", Higher Results Are Better "c3-highcpu-8 SPR",1293,1283,1239 "c2-standard-8 CLX",915,894,917 "n2-standard-8 CLX",810,805,816 "n2-highcpu-8 CLX",757,778,774 "t2d-standard-8 AMD",1199,1204,1202 "c2d-highcpu-8 AMD",852,865,850 "LeelaChessZero 0.28 - Backend: Eigen", Higher Results Are Better "c3-highcpu-8 SPR",1224,1232,1206 "c2-standard-8 CLX",884,911,911 "n2-standard-8 CLX",831,818,778,810,805 "n2-highcpu-8 CLX",795,790,817 "t2d-standard-8 AMD",1045,1035,1037 "c2d-highcpu-8 AMD",742,737,749 "GROMACS 2023 - Implementation: MPI CPU - Input: water_GMX50_bare", Higher Results Are Better "c3-highcpu-8 SPR",0.778,0.779,0.775 "c2-standard-8 CLX",0.579,0.578,0.58 "n2-standard-8 CLX",0.529,0.53,0.526 "n2-highcpu-8 CLX",0.528,0.529,0.53 "t2d-standard-8 AMD",1.09,1.116,1.089 "c2d-highcpu-8 AMD",0.692,0.69,0.689 "CockroachDB 22.2 - Workload: KV, 50% Reads - Concurrency: 128", Higher Results Are Better "c3-highcpu-8 SPR",19364.1,19360.8,19239.9 "c2-standard-8 CLX",13803.5,13684.4,13565.7 "n2-standard-8 CLX",12839.3,12633.4,12624.7 "n2-highcpu-8 CLX",12710.9,12572.4,12621.9 "t2d-standard-8 AMD",19111.6,19099.8,19119.7 "c2d-highcpu-8 AMD",17306.8,17141.4,17057.1 "CockroachDB 22.2 - Workload: KV, 95% Reads - Concurrency: 128", Higher Results Are Better "c3-highcpu-8 SPR",25031.6,25136.9,24711.9 "c2-standard-8 CLX",16233,16028.4,16291.3 "n2-standard-8 CLX",15048.1,14911.4,14971 "n2-highcpu-8 CLX",15061.3,14876.1,14716.6 "t2d-standard-8 AMD",22116,22253.8,22076.6 "c2d-highcpu-8 AMD",20567.2,20651.6,20496.6 "Memcached 1.6.18 - Set To Get Ratio: 1:10", Higher Results Are Better "c3-highcpu-8 SPR",1038407.67,1048682.86,1047750.86 "c2-standard-8 CLX",717606.37,718252.63,711311.59 "n2-standard-8 CLX",640944.24,636611.65,647584.92 "n2-highcpu-8 CLX",619003.67,612873.36,612350.84 "t2d-standard-8 AMD",1216953.36,1181784.2,1202844.71 "c2d-highcpu-8 AMD",832968.69,850736.16,844787.46 "Memcached 1.6.18 - Set To Get Ratio: 1:100", Higher Results Are Better "c3-highcpu-8 SPR",1053054.96,1017311.17,1022445.7 "c2-standard-8 CLX",705307.55,706210.34,695357.89 "n2-standard-8 CLX",631919.06,616986.98,626035.95 "n2-highcpu-8 CLX",607369.27,604610.36,601110.49 "t2d-standard-8 AMD",1232775.78,1247062.82,1193813.45 "c2d-highcpu-8 AMD",830620.68,835649.15,839945.34 "MariaDB 11.0.1 - Clients: 2048", Higher Results Are Better "c3-highcpu-8 SPR",338.06626098715,328.29940906106,330.03300330033 "c2-standard-8 CLX",251.69896803423,241.08003857281,251.44581342721 "n2-standard-8 CLX",221.2389380531,208.20320632938,220.50716648291,218.19768710452,224.66861379465,220.75055187638,223.11468094601 "n2-highcpu-8 CLX",221.77866489244,216.16947686987,221.92632046161 "t2d-standard-8 AMD",322.78889606198,299.9400119976,313.67628607277,288.26751225137,305.71690614491,273.00027300027 "c2d-highcpu-8 AMD",309.78934324659,301.20481927711,303.49013657056 "MariaDB 11.0.1 - Clients: 4096", Higher Results Are Better "c3-highcpu-8 SPR",320.61558191728,317.76294884017,311.72069825436 "c2-standard-8 CLX",233.10023310023,241.7210539038,235.68230025925 "n2-standard-8 CLX",208.37674515524,209.90764063812,202.88090890647 "n2-highcpu-8 CLX",212.58503401361,216.02937999568,213.85799828914 "t2d-standard-8 AMD",276.01435274634,277.08506511499,288.93383415198,278.31895352074 "c2d-highcpu-8 AMD",288.26751225137,295.07229271171,292.14139643588 "John The Ripper 2023.03.14 - Test: bcrypt", Higher Results Are Better "c3-highcpu-8 SPR",6933,6931,6931 "c2-standard-8 CLX",6686,6686,6688 "n2-standard-8 CLX",5969,5969,5971 "n2-highcpu-8 CLX",5959,5962,5964 "t2d-standard-8 AMD",10598,10570,10587 "c2d-highcpu-8 AMD",7619,7622,7619 "John The Ripper 2023.03.14 - Test: Blowfish", Higher Results Are Better "c3-highcpu-8 SPR",6926,6933,6931 "c2-standard-8 CLX",6686,6679,6688 "n2-standard-8 CLX",5966,5969,5969 "n2-highcpu-8 CLX",5962,5957,5959 "t2d-standard-8 AMD",10634,10610,10588 "c2d-highcpu-8 AMD",7617,7622,7617 "John The Ripper 2023.03.14 - Test: MD5", Higher Results Are Better "c3-highcpu-8 SPR",768563,764928,763648 "c2-standard-8 CLX",683827,683548,683264 "n2-standard-8 CLX",599193,599603,600115 "n2-highcpu-8 CLX",598732,599296,598886 "t2d-standard-8 AMD",737715,738969,737945 "c2d-highcpu-8 AMD",436488,436684,436582 "nginx 1.23.2 - Connections: 100", Higher Results Are Better "c3-highcpu-8 SPR",36357.61,36293.45,36279.99 "c2-standard-8 CLX",25188.77,25173.87,25082.19 "n2-standard-8 CLX",22933.87,22779.83,22776.88 "n2-highcpu-8 CLX",22407.02,22546.92,22379.25 "t2d-standard-8 AMD",35062.71,35485.43,35225.18 "c2d-highcpu-8 AMD",25055.41,25026.77,24977.41 "nginx 1.23.2 - Connections: 200", Higher Results Are Better "c3-highcpu-8 SPR",35456.96,35603.09,35746.26 "c2-standard-8 CLX",24720.9,24744.89,24621.95 "n2-standard-8 CLX",22679.54,22336.57,22694.42 "n2-highcpu-8 CLX",21174.42,21637.67,21482.16 "t2d-standard-8 AMD",35574.22,34717.88,35383.02 "c2d-highcpu-8 AMD",25042.17,24904.22,24084.69 "nginx 1.23.2 - Connections: 500", Higher Results Are Better "c3-highcpu-8 SPR",35079.56,34901.13,34037.25 "c2-standard-8 CLX",21967.78,21980.64,21923.1 "n2-standard-8 CLX",20128.68,20242.54,20067.09 "n2-highcpu-8 CLX",19867.57,19805.65,19746.58 "t2d-standard-8 AMD",35039.23,35231.77,35110.79 "c2d-highcpu-8 AMD",24104.22,24328.75,24362.97 "nginx 1.23.2 - Connections: 1000", Higher Results Are Better "c3-highcpu-8 SPR",32092.98,32163.26,32099.5 "c2-standard-8 CLX",21609.49,21328.62,21400.71 "n2-standard-8 CLX",19713.96,19688.83,19648 "n2-highcpu-8 CLX",19616.29,19277.2,19360.75 "t2d-standard-8 AMD",34092.04,33991.22,34155.61 "c2d-highcpu-8 AMD",23773.68,23764.34,23737.4 "nginx 1.23.2 - Connections: 4000", Higher Results Are Better "c3-highcpu-8 SPR",32760.05,32851.88,32832.31 "c2-standard-8 CLX",21578.93,21588.59,21617.3 "n2-standard-8 CLX",20051.43,19863.12,19928.12 "n2-highcpu-8 CLX",19590.58,19393.31,19448.04 "t2d-standard-8 AMD",34486.69,32944.29,33347.34 "c2d-highcpu-8 AMD",23593.01,23883.12,23766.42 "OpenSSL 3.1 - Algorithm: RSA4096", Higher Results Are Better "c3-highcpu-8 SPR",2061.6,2061.4,2065 "c2-standard-8 CLX",1159,1158.2,1152.5 "n2-standard-8 CLX",1033,1025.8,1026.9 "n2-highcpu-8 CLX",1028.4,1035,1023 "t2d-standard-8 AMD",1764.6,1764.7,1765.8 "c2d-highcpu-8 AMD",1025.9,1025.1,1026 "PostgreSQL 15 - Scaling Factor: 100 - Clients: 800 - Mode: Read Only", Higher Results Are Better "c3-highcpu-8 SPR",305738.608104,317322.770153,312764.934778 "c2-standard-8 CLX",173636.106805,174556.147225,171759.43414 "n2-standard-8 CLX",157881.434458,158158.578538,158761.528617 "n2-highcpu-8 CLX",128478.397737,152143.701238,154342.592837,150534.748461,155593.726584,155464.248379,156043.213808,153074.874172,154766.141873,154974.840221,154747.596231,154952.725344 "t2d-standard-8 AMD",324773.433598,330358.368644,314927.215031 "c2d-highcpu-8 AMD",248522.233864,249185.670392,250763.173084 "PostgreSQL 15 - Scaling Factor: 100 - Clients: 1000 - Mode: Read Only", Higher Results Are Better "c3-highcpu-8 SPR",297902.593253,289539.14012,293734.136799 "c2-standard-8 CLX",170258.828355,171009.355757,167660.314579 "n2-standard-8 CLX",155662.300356,150117.52879,140731.342465,157519.151729,155890.639091,157740.309849,160742.012331,157256.887057,157692.009729,155895.505932,156837.099874,156268.303493 "n2-highcpu-8 CLX",149500.394225,142338.377074,145530.329977 "t2d-standard-8 AMD",326206.173851,317243.965476,319030.03051 "c2d-highcpu-8 AMD",243927.127202,240646.45512,248019.855015 "BRL-CAD 7.34 - VGR Performance Metric", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "NAMD 2.14 - ATPase Simulation - 327,506 Atoms", Lower Results Are Better "c3-highcpu-8 SPR",3.35951,3.35279,3.36107 "c2-standard-8 CLX",4.43721,4.46076,4.43806 "n2-standard-8 CLX",5.12308,5.0712,5.00689 "n2-highcpu-8 CLX",5.09083,5.03134,5.04416 "t2d-standard-8 AMD",3.10849,3.1079,3.10828 "c2d-highcpu-8 AMD",4.45538,4.46234,4.45523 "oneDNN 3.0 - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR",1.49334,1.50238,1.50439 "c2-standard-8 CLX",19.5587,19.5177,19.5097 "n2-standard-8 CLX",21.9804,22.0265,22.0687 "n2-highcpu-8 CLX",21.9802,22.0639,22.0626 "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "oneDNN 3.0 - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR",5.34688,5.34815,5.33151 "c2-standard-8 CLX",8.01859,8.04698,8.00691 "n2-standard-8 CLX",8.48507,8.50474,8.56612 "n2-highcpu-8 CLX",8.69303,8.62013,8.56596 "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "oneDNN 3.0 - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR",4.16425,4.19367,4.17328 "c2-standard-8 CLX",34.1974,34.1805,34.1899 "n2-standard-8 CLX",38.9373,38.8167,38.8612 "n2-highcpu-8 CLX",38.9525,38.9707,38.9797 "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "oneDNN 3.0 - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR",1.47037,1.46387,1.4801 "c2-standard-8 CLX",52.9452,52.9429,52.9381 "n2-standard-8 CLX",60.6888,60.5247,60.564 "n2-highcpu-8 CLX",60.5276,60.5515,60.5856 "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "oneDNN 3.0 - Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR",3.56326,3.52833,3.55673 "c2-standard-8 CLX",35.8971,35.9208,35.9312 "n2-standard-8 CLX",40.6004,40.7152,40.6469 "n2-highcpu-8 CLX",40.736,40.7447,40.8554 "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "oneDNN 3.0 - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR",4660.11,4662.39,4659.61 "c2-standard-8 CLX",5756.22,5762.86,5784.01 "n2-standard-8 CLX",6074.23,6083.46,6078.75 "n2-highcpu-8 CLX",6125.33,6117.8,6094.82 "t2d-standard-8 AMD",3978.07,3997.75,4038.21 "c2d-highcpu-8 AMD",6505.09,6495.48,6510.33 "oneDNN 3.0 - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR",2340.41,2334.3,2337.22 "c2-standard-8 CLX",2998.28,2999.33,2996.49 "n2-standard-8 CLX",3122.07,3163.55,3231.41 "n2-highcpu-8 CLX",3154.09,3165.26,3152.78 "t2d-standard-8 AMD",2104.03,2096.03,2122.1 "c2d-highcpu-8 AMD",3340.48,3328.64,3337.99 "oneDNN 3.0 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR",0.995169,0.954568,0.95722 "c2-standard-8 CLX",7.41768,7.43812,7.44199 "n2-standard-8 CLX",8.50295,8.51814,8.49924 "n2-highcpu-8 CLX",8.43561,8.44176,8.45809 "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OSPRay Studio 0.11 - Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer", Lower Results Are Better "c3-highcpu-8 SPR",20958,20955,20942 "c2-standard-8 CLX",30976,30879,30879 "n2-standard-8 CLX",36215,35748,35690 "n2-highcpu-8 CLX",35014,35332,35232 "t2d-standard-8 AMD",25134,25456,25328 "c2d-highcpu-8 AMD",31260,31429,31420 "OSPRay Studio 0.11 - Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer", Lower Results Are Better "c3-highcpu-8 SPR",25090,26175,26191 "c2-standard-8 CLX",37865,37971,37841 "n2-standard-8 CLX",61069,61450,61493 "n2-highcpu-8 CLX",61410,61059,60982 "t2d-standard-8 AMD",29864,30611,30421 "c2d-highcpu-8 AMD",37198,37163,37320 "PostgreSQL 15 - Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency", Lower Results Are Better "c3-highcpu-8 SPR",2.617,2.521,2.558 "c2-standard-8 CLX",4.607,4.583,4.658 "n2-standard-8 CLX",5.067,5.058,5.039 "n2-highcpu-8 CLX",6.227,5.258,5.183,5.314,5.142,5.146,5.127,5.226,5.169,5.162,5.17,5.163 "t2d-standard-8 AMD",2.463,2.422,2.54 "c2d-highcpu-8 AMD",3.219,3.21,3.19 "PostgreSQL 15 - Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency", Lower Results Are Better "c3-highcpu-8 SPR",3.357,3.454,3.404 "c2-standard-8 CLX",5.873,5.848,5.964 "n2-standard-8 CLX",6.424,6.661,7.106,6.348,6.415,6.34,6.221,6.359,6.341,6.415,6.376,6.399 "n2-highcpu-8 CLX",6.689,7.026,6.871 "t2d-standard-8 AMD",3.066,3.152,3.135 "c2d-highcpu-8 AMD",4.1,4.155,4.032 "Google Draco 1.5.6 - Model: Lion", Lower Results Are Better "c3-highcpu-8 SPR",7161,6578,6399,6260,6258,6251,6286,6216,6189,6212,6169,5940,5923,5940,5970 "c2-standard-8 CLX",7420,7417,7474 "n2-standard-8 CLX",8504,8260,8301 "n2-highcpu-8 CLX",8351,8397,8424 "t2d-standard-8 AMD",6070,6131,6017 "c2d-highcpu-8 AMD",5643,5582,5626 "Google Draco 1.5.6 - Model: Church Facade", Lower Results Are Better "c3-highcpu-8 SPR",7552,7580,7586 "c2-standard-8 CLX",11456,11494,11437 "n2-standard-8 CLX",12370,12296,12330 "n2-highcpu-8 CLX",12662,12733,13290,12843 "t2d-standard-8 AMD",8806,8674,8782 "c2d-highcpu-8 AMD",7395,7421,7509 "OpenCV 4.7 - Test: Core", Lower Results Are Better "c3-highcpu-8 SPR",87830,86863,87423 "c2-standard-8 CLX",147331,146334,135027,138439,134678,141205,133882,156596,137493,133524,149632,159101 "n2-standard-8 CLX",191218,195741,231668,190445,225862,216300,204252,200361,205098,215040,214855,220478 "n2-highcpu-8 CLX",208096,197119,202045,212675,195163,207136,218186,217353,216017 "t2d-standard-8 AMD",131240,87795,82110,81525,90452,81899,85936,85910,95421,93601,85506,95207,84777,89236,86037 "c2d-highcpu-8 AMD",81673,81199,79442 "OpenCV 4.7 - Test: Graph API", Lower Results Are Better "c3-highcpu-8 SPR",218103,220535,221155 "c2-standard-8 CLX",233048,237863,237647 "n2-standard-8 CLX",266071,268579,267100 "n2-highcpu-8 CLX",308224,303579,282582,280344,288234,282733,280627,286503,289628 "t2d-standard-8 AMD",210996,209206,210441 "c2d-highcpu-8 AMD",195559,199596,203254 "OpenCV 4.7 - Test: Stitching", Lower Results Are Better "c3-highcpu-8 SPR",205423,219331,215088,212317,219291,219545,212325 "c2-standard-8 CLX",250883,247593,254022 "n2-standard-8 CLX",278989,274339,282152 "n2-highcpu-8 CLX",285619,277568,280828 "t2d-standard-8 AMD",201026,194965,191477 "c2d-highcpu-8 AMD",179937,189213,187136,191135,189577 "OpenCV 4.7 - Test: Image Processing", Lower Results Are Better "c3-highcpu-8 SPR",126554,137305,134315,131682,135422,129209,121655,121639,120763,126507,128674,124236 "c2-standard-8 CLX",149111,149446,142821,147556 "n2-standard-8 CLX",178588,182730,174795 "n2-highcpu-8 CLX",169069,176258,173198 "t2d-standard-8 AMD",110733,115462,116259,115186 "c2d-highcpu-8 AMD",120315,116554,115986 "OpenCV 4.7 - Test: Object Detection", Lower Results Are Better "c3-highcpu-8 SPR",39819,39999,38190,38245,38744 "c2-standard-8 CLX",59039,56579,58550 "n2-standard-8 CLX",64684,62667,65502 "n2-highcpu-8 CLX",68289,64841,66303,65643 "t2d-standard-8 AMD",33219,29995,32494,30304,31966,31904,32456,33728,35095,34347,30605,29452,32644,30906,31093 "c2d-highcpu-8 AMD",38588,37581,36830 "Neural Magic DeepSparse 1.3.2 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR",524.469,529.4905,530.0983 "c2-standard-8 CLX",682.421,682.3242,682.3791 "n2-standard-8 CLX",754.3553,750.472,751.7501 "n2-highcpu-8 CLX",761.459,761.5197,761.035 "t2d-standard-8 AMD",644.441,646.8738,644.954 "c2d-highcpu-8 AMD",583.9932,584.3825,585.3038 "Neural Magic DeepSparse 1.3.2 - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR",104.2698,104.0962,104.5645 "c2-standard-8 CLX",126.2483,125.2466,124.9289 "n2-standard-8 CLX",129.2199,129.8313,131.0037 "n2-highcpu-8 CLX",132.3161,132.4864,131.8509 "t2d-standard-8 AMD",167.0995,168.1768,167.7337 "c2d-highcpu-8 AMD",147.3354,148.1836,146.9194 "Neural Magic DeepSparse 1.3.2 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR",30.8038,30.8268,30.7549 "c2-standard-8 CLX",33.265,33.3073,33.3049 "n2-standard-8 CLX",36.3189,36.3739,36.3412 "n2-highcpu-8 CLX",36.5554,36.7028,36.6695 "t2d-standard-8 AMD",58.1473,57.8919,57.9263 "c2d-highcpu-8 AMD",52.4342,52.3356,52.4753 "Neural Magic DeepSparse 1.3.2 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR",59.9718,60.9256,60.2599 "c2-standard-8 CLX",68.4115,68.656,68.4554 "n2-standard-8 CLX",77.262,77.397,76.2393 "n2-highcpu-8 CLX",76.6799,78.7139,78.0359 "t2d-standard-8 AMD",77.8064,77.7841,77.7461 "c2d-highcpu-8 AMD",69.9899,70.1655,70.2313 "Neural Magic DeepSparse 1.3.2 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR",305.6511,305.4254,306.6208 "c2-standard-8 CLX",322.7785,323.0776,323.3922 "n2-standard-8 CLX",347.4549,346.6162,349.4186 "n2-highcpu-8 CLX",354.0418,354.4392,353.6651 "t2d-standard-8 AMD",495.2942,491.0203,480.913 "c2d-highcpu-8 AMD",436.407,436.0125,436.3328 "Neural Magic DeepSparse 1.3.2 - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR",124.5306,121.427,123.9216 "c2-standard-8 CLX",143.4097,142.4049,142.8531 "n2-standard-8 CLX",158.4149,155.3505,156.9424 "n2-highcpu-8 CLX",155.2988,155.1087,155.2759 "t2d-standard-8 AMD",153.0837,152.6101,153.7749 "c2d-highcpu-8 AMD",139.2674,139.0486,139.2906 "Neural Magic DeepSparse 1.3.2 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR",524.1603,532.3186,535.3511 "c2-standard-8 CLX",680.7529,683.0927,680.1892 "n2-standard-8 CLX",752.2976,750.5738,752.9436 "n2-highcpu-8 CLX",751.8185,751.0227,755.1877 "t2d-standard-8 AMD",642.2521,643.6139,643.0713 "c2d-highcpu-8 AMD",590.3661,584.5366,590.9368 "Xcompact3d Incompact3d 2021-03-11 - Input: input.i3d 129 Cells Per Direction", Lower Results Are Better "c3-highcpu-8 SPR",32.3710327,32.380722,32.4311943 "c2-standard-8 CLX",37.8030396,37.7471161,37.7225456 "n2-standard-8 CLX",40.776474,40.3633003,40.477253 "n2-highcpu-8 CLX",40.0648613,40.0728493,39.960762 "t2d-standard-8 AMD",20.9240894,21.5745411,22.0969238,21.4049168 "c2d-highcpu-8 AMD",26.5973759,26.531601,26.4354858 "OpenFOAM 10 - Input: drivaerFastback, Small Mesh Size - Mesh Time", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenFOAM 10 - Input: drivaerFastback, Small Mesh Size - Execution Time", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenRadioss 2022.10.13 - Model: Bumper Beam", Lower Results Are Better "c3-highcpu-8 SPR",303.9,303.89,302.36 "c2-standard-8 CLX",390.06,392.37,389.39 "n2-standard-8 CLX",438.53,432.2,438.09 "n2-highcpu-8 CLX",432.03,431.3,438.27 "t2d-standard-8 AMD",176.86,177.4,176.23 "c2d-highcpu-8 AMD",286.51,286.06,285.5 "OpenRadioss 2022.10.13 - Model: Cell Phone Drop Test", Lower Results Are Better "c3-highcpu-8 SPR",220.41,219.69,219.08 "c2-standard-8 CLX",290.79,291.56,292.12 "n2-standard-8 CLX",322.77,321.54,322.35 "n2-highcpu-8 CLX",321.72,319.68,319.68 "t2d-standard-8 AMD",136.46,135.42,136.09 "c2d-highcpu-8 AMD",210.23,221.48,210.55,213.26 "OpenRadioss 2022.10.13 - Model: Bird Strike on Windshield", Lower Results Are Better "c3-highcpu-8 SPR",594.67,595.69,595.05 "c2-standard-8 CLX",724.15,727.69,722.57 "n2-standard-8 CLX",821.29,810.03,803.97 "n2-highcpu-8 CLX",799.6,797.97,802.48 "t2d-standard-8 AMD",385.79,385.9,387.36 "c2d-highcpu-8 AMD",622.43,620.6,622.6 "OpenRadioss 2022.10.13 - Model: Rubber O-Ring Seal Installation", Lower Results Are Better "c3-highcpu-8 SPR",367.31,367.08,366.62 "c2-standard-8 CLX",522.65,523.51,524.2 "n2-standard-8 CLX",586.11,583.33,605.69 "n2-highcpu-8 CLX",581.18,585.53,585.56 "t2d-standard-8 AMD",208.25,209.81,208.36 "c2d-highcpu-8 AMD",362.65,365.87,364.47 "SPECFEM3D 4.0 - Model: Mount St. Helens", Lower Results Are Better "c3-highcpu-8 SPR",139.386798825,139.479269908,139.70734011 "c2-standard-8 CLX",145.075578016,146.460576912,144.60183063 "n2-standard-8 CLX",161.434957297,162.422645378,163.418394248 "n2-highcpu-8 CLX",160.654662875,159.810467059,160.423347305 "t2d-standard-8 AMD",80.642543828,80.822095145,82.092378082 "c2d-highcpu-8 AMD",126.041561266,126.904335223,123.925185872 "SPECFEM3D 4.0 - Model: Layered Halfspace", Lower Results Are Better "c3-highcpu-8 SPR",371.885371249,373.283088797,371.099982525 "c2-standard-8 CLX",379.481507671,370.913677284,373.875446657 "n2-standard-8 CLX",414.804415759,414.258592337,416.486218206 "n2-highcpu-8 CLX",417.284827339,417.510911283,414.443673393 "t2d-standard-8 AMD",217.859746784,222.606301607,228.863511893 "c2d-highcpu-8 AMD",324.042285372,327.627326014,322.888137017 "SPECFEM3D 4.0 - Model: Tomographic Model", Lower Results Are Better "c3-highcpu-8 SPR",142.240020359,147.227075116,142.34397315 "c2-standard-8 CLX",153.506961664,149.770206717,149.468709519 "n2-standard-8 CLX",166.415743239,165.207359155,167.509765722 "n2-highcpu-8 CLX",165.530767918,165.502030586,171.011357168 "t2d-standard-8 AMD",82.427631929,81.235241749,81.756522277 "c2d-highcpu-8 AMD",128.213054569,126.908824155,129.375336328 "SPECFEM3D 4.0 - Model: Homogeneous Halfspace", Lower Results Are Better "c3-highcpu-8 SPR",179.722228346,179.400771357,179.514705178 "c2-standard-8 CLX",192.918419677,187.062501134,192.401501618 "n2-standard-8 CLX",214.155696674,216.263207373,211.258246678 "n2-highcpu-8 CLX",216.487097462,210.277277426,219.059132038 "t2d-standard-8 AMD",102.154021264,101.943013521,102.91264017 "c2d-highcpu-8 AMD",164.35494657,165.01829324,162.623881197 "SPECFEM3D 4.0 - Model: Water-layered Halfspace", Lower Results Are Better "c3-highcpu-8 SPR",322.177254361,321.105269219,321.593231425 "c2-standard-8 CLX",348.370719597,348.923800897,346.143921716 "n2-standard-8 CLX",382.065243839,380.433593493,377.890450236 "n2-highcpu-8 CLX",370.337762398,379.787152399,372.4580242 "t2d-standard-8 AMD",216.059892122,195.385593027,196.450073224,194.738668337,197.142265842,195.551106212,192.914092447,200.876824274,199.64097586,192.186057713,191.832141524,197.468191019 "c2d-highcpu-8 AMD",287.022476017,286.948143906,288.300455495 "Timed FFmpeg Compilation 6.0 - Time To Compile", Lower Results Are Better "c3-highcpu-8 SPR",120.459,120.593,120.262 "c2-standard-8 CLX",138.984,139.056,139.077 "n2-standard-8 CLX",153.67,153.79,157.236 "n2-highcpu-8 CLX",154.801,154.853,155.054 "t2d-standard-8 AMD",80.794,80.303,80.851 "c2d-highcpu-8 AMD",119.645,119.645,119.63 "Timed Linux Kernel Compilation 6.1 - Build: defconfig", Lower Results Are Better "c3-highcpu-8 SPR",246.045,243.959,244.397 "c2-standard-8 CLX",291.361,288.901,288.723 "n2-standard-8 CLX",324.686,321.152,321.305 "n2-highcpu-8 CLX",329.056,327.81,326.398 "t2d-standard-8 AMD",184.218,184.452,185.379 "c2d-highcpu-8 AMD",260.479,258.773,258.752 "Blender 3.4 - Blend File: BMW27 - Compute: CPU-Only", Lower Results Are Better "c3-highcpu-8 SPR",314.2,314.02,317.5 "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Geometric Mean Of All Test Results - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Geometric Mean Of Timed Code Compilation Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of C/C++ Compiler Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Compression Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "c2d-highcpu-8 AMD",0 "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of CPU Massive Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Creator Workloads Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "n2-standard-8 CLX",0 "Geometric Mean Of Cryptography Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Database Test Suite - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Fortran Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c2d-highcpu-8 AMD",0 "c3-highcpu-8 SPR",0 "c2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "n2-standard-8 CLX",0 "Geometric Mean Of Game Development Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2-standard-8 CLX",0 "c2d-highcpu-8 AMD",0 "n2-highcpu-8 CLX",0 "n2-standard-8 CLX",0 "Geometric Mean Of HPC - High Performance Computing Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Common Kernel Benchmarks Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Machine Learning Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "c3-highcpu-8 SPR",0 "t2d-standard-8 AMD",0 "c2-standard-8 CLX",0 "c2d-highcpu-8 AMD",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Molecular Dynamics Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "n2-standard-8 CLX",0 "Geometric Mean Of MPI Benchmarks Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c2d-highcpu-8 AMD",0 "c3-highcpu-8 SPR",0 "c2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "n2-standard-8 CLX",0 "Geometric Mean Of Multi-Core Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of NVIDIA GPU Compute Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2-standard-8 CLX",0 "c2d-highcpu-8 AMD",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Intel oneAPI Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "c3-highcpu-8 SPR",0 "t2d-standard-8 AMD",0 "c2-standard-8 CLX",0 "c2d-highcpu-8 AMD",0 "n2-highcpu-8 CLX",0 "n2-standard-8 CLX",0 "Geometric Mean Of OpenMPI Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c2d-highcpu-8 AMD",0 "c3-highcpu-8 SPR",0 "c2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "n2-standard-8 CLX",0 "Geometric Mean Of Programmer / Developer System Benchmarks Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c2d-highcpu-8 AMD",0 "c3-highcpu-8 SPR",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Python Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "c3-highcpu-8 SPR",0 "t2d-standard-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "c2d-highcpu-8 AMD",0 "Geometric Mean Of Renderers Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "n2-standard-8 CLX",0 "Geometric Mean Of Scientific Computing Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "n2-standard-8 CLX",0 "Geometric Mean Of Server Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "Geometric Mean Of Server CPU Tests - Result Composite - Google Cloud c3 Sapphire Rapids vs. AMD Milan", Higher Results Are Better "t2d-standard-8 AMD",0 "c3-highcpu-8 SPR",0 "c2d-highcpu-8 AMD",0 "c2-standard-8 CLX",0 "n2-standard-8 CLX",0 "n2-highcpu-8 CLX",0 "miniBUDE 20210901 - Performance / Cost - Implementation: OpenMP - Input Deck: BM1", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenSSL 3.1 - Performance / Cost - Algorithm: SHA256", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenSSL 3.1 - Performance / Cost - Algorithm: SHA512", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenSSL 3.1 - Performance / Cost - Algorithm: ChaCha20", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenSSL 3.1 - Performance / Cost - Algorithm: AES-128-GCM", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenSSL 3.1 - Performance / Cost - Algorithm: AES-256-GCM", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenSSL 3.1 - Performance / Cost - Algorithm: ChaCha20-Poly1305", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "nekRS 22.0 - Performance / Cost - Input: TurboPipe Periodic", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Embree 4.0.1 - Performance / Cost - Binary: Pathtracer ISPC - Model: Crown", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Embree 4.0.1 - Performance / Cost - Binary: Pathtracer ISPC - Model: Asian Dragon", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "uvg266 0.4.1 - Performance / Cost - Video Input: Bosphorus 4K - Video Preset: Very Fast", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "uvg266 0.4.1 - Performance / Cost - Video Input: Bosphorus 4K - Video Preset: Super Fast", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "uvg266 0.4.1 - Performance / Cost - Video Input: Bosphorus 4K - Video Preset: Ultra Fast", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "uvg266 0.4.1 - Performance / Cost - Video Input: Bosphorus 1080p - Video Preset: Very Fast", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "uvg266 0.4.1 - Performance / Cost - Video Input: Bosphorus 1080p - Video Preset: Super Fast", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "uvg266 0.4.1 - Performance / Cost - Video Input: Bosphorus 1080p - Video Preset: Ultra Fast", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "miniBUDE 20210901 - Performance / Cost - Implementation: OpenMP - Input Deck: BM1", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Intel Open Image Denoise 1.4.0 - Performance / Cost - Run: RT.hdr_alb_nrm.3840x2160", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Intel Open Image Denoise 1.4.0 - Performance / Cost - Run: RTLightmap.hdr.4096x4096", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "TensorFlow 2.10 - Performance / Cost - Device: CPU - Batch Size: 16 - Model: ResNet-50", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "TensorFlow 2.10 - Performance / Cost - Device: CPU - Batch Size: 32 - Model: ResNet-50", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "TensorFlow 2.10 - Performance / Cost - Device: CPU - Batch Size: 64 - Model: ResNet-50", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenVKL 1.3.1 - Performance / Cost - Benchmark: vklBenchmark ISPC", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Zstd Compression 1.5.4 - Performance / Cost - Compression Level: 19 - Compression Speed", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Zstd Compression 1.5.4 - Performance / Cost - Compression Level: 19 - Decompression Speed", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Zstd Compression 1.5.4 - Performance / Cost - Compression Level: 19, Long Mode - Compression Speed", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Zstd Compression 1.5.4 - Performance / Cost - Compression Level: 19, Long Mode - Decompression Speed", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "7-Zip Compression 22.01 - Performance / Cost - Test: Compression Rating", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "LeelaChessZero 0.28 - Performance / Cost - Backend: BLAS", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "LeelaChessZero 0.28 - Performance / Cost - Backend: Eigen", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "GROMACS 2023 - Performance / Cost - Implementation: MPI CPU - Input: water_GMX50_bare", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "CockroachDB 22.2 - Performance / Cost - Workload: KV, 50% Reads - Concurrency: 128", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "CockroachDB 22.2 - Performance / Cost - Workload: KV, 95% Reads - Concurrency: 128", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Memcached 1.6.18 - Performance / Cost - Set To Get Ratio: 1:10", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Memcached 1.6.18 - Performance / Cost - Set To Get Ratio: 1:100", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "MariaDB 11.0.1 - Performance / Cost - Clients: 2048", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "MariaDB 11.0.1 - Performance / Cost - Clients: 4096", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "John The Ripper 2023.03.14 - Performance / Cost - Test: bcrypt", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "John The Ripper 2023.03.14 - Performance / Cost - Test: Blowfish", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "John The Ripper 2023.03.14 - Performance / Cost - Test: MD5", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "nginx 1.23.2 - Performance / Cost - Connections: 100", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "nginx 1.23.2 - Performance / Cost - Connections: 200", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "nginx 1.23.2 - Performance / Cost - Connections: 500", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "nginx 1.23.2 - Performance / Cost - Connections: 1000", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "nginx 1.23.2 - Performance / Cost - Connections: 4000", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenSSL 3.1 - Performance / Cost - Algorithm: RSA4096", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "PostgreSQL 15 - Performance / Cost - Scaling Factor: 100 - Clients: 800 - Mode: Read Only", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "PostgreSQL 15 - Performance / Cost - Scaling Factor: 100 - Clients: 1000 - Mode: Read Only", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "BRL-CAD 7.34 - Performance / Cost - VGR Performance Metric", Higher Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "NAMD 2.14 - Performance / Cost - ATPase Simulation - 327,506 Atoms", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "oneDNN 3.0 - Performance / Cost - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "oneDNN 3.0 - Performance / Cost - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "oneDNN 3.0 - Performance / Cost - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "oneDNN 3.0 - Performance / Cost - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "oneDNN 3.0 - Performance / Cost - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "oneDNN 3.0 - Performance / Cost - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "oneDNN 3.0 - Performance / Cost - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "OSPRay Studio 0.11 - Performance / Cost - Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OSPRay Studio 0.11 - Performance / Cost - Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "PostgreSQL 15 - Performance / Cost - Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latency", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "PostgreSQL 15 - Performance / Cost - Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Google Draco 1.5.6 - Performance / Cost - Model: Lion", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Google Draco 1.5.6 - Performance / Cost - Model: Church Facade", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenCV 4.7 - Performance / Cost - Test: Core", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenCV 4.7 - Performance / Cost - Test: Graph API", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenCV 4.7 - Performance / Cost - Test: Stitching", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenCV 4.7 - Performance / Cost - Test: Image Processing", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenCV 4.7 - Performance / Cost - Test: Object Detection", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Neural Magic DeepSparse 1.3.2 - Performance / Cost - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Xcompact3d Incompact3d 2021-03-11 - Performance / Cost - Input: input.i3d 129 Cells Per Direction", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenFOAM 10 - Performance / Cost - Input: drivaerFastback, Small Mesh Size - Mesh Time", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenFOAM 10 - Performance / Cost - Input: drivaerFastback, Small Mesh Size - Execution Time", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenRadioss 2022.10.13 - Performance / Cost - Model: Bumper Beam", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenRadioss 2022.10.13 - Performance / Cost - Model: Cell Phone Drop Test", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenRadioss 2022.10.13 - Performance / Cost - Model: Bird Strike on Windshield", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "OpenRadioss 2022.10.13 - Performance / Cost - Model: Rubber O-Ring Seal Installation", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "SPECFEM3D 4.0 - Performance / Cost - Model: Mount St. Helens", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "SPECFEM3D 4.0 - Performance / Cost - Model: Layered Halfspace", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "SPECFEM3D 4.0 - Performance / Cost - Model: Tomographic Model", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "SPECFEM3D 4.0 - Performance / Cost - Model: Homogeneous Halfspace", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "SPECFEM3D 4.0 - Performance / Cost - Model: Water-layered Halfspace", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Timed FFmpeg Compilation 6.0 - Performance / Cost - Time To Compile", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Timed Linux Kernel Compilation 6.1 - Performance / Cost - Build: defconfig", Lower Results Are Better "c3-highcpu-8 SPR", "c2-standard-8 CLX", "n2-standard-8 CLX", "n2-highcpu-8 CLX", "t2d-standard-8 AMD", "c2d-highcpu-8 AMD", "Blender 3.4 - Performance / Cost - Blend File: BMW27 - Compute: CPU-Only", Lower Results Are Better "c3-highcpu-8 SPR",