Amazon AWS Graviton3E vs. Graviton 2/3 benchmarks

Benchmarks by Michael Larabel for a future article on Phoronix.com.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2308110-NE-2307106NE96
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:

BLAS (Basic Linear Algebra Sub-Routine) Tests 4 Tests
C++ Boost Tests 3 Tests
Chess Test Suite 2 Tests
Timed Code Compilation 3 Tests
C/C++ Compiler Tests 6 Tests
CPU Massive 10 Tests
Creator Workloads 2 Tests
Fortran Tests 6 Tests
HPC - High Performance Computing 17 Tests
Common Kernel Benchmarks 2 Tests
LAPACK (Linear Algebra Pack) Tests 2 Tests
Linear Algebra 2 Tests
Molecular Dynamics 6 Tests
MPI Benchmarks 8 Tests
Multi-Core 12 Tests
NVIDIA GPU Compute 3 Tests
OpenMPI Tests 18 Tests
Programmer / Developer System Benchmarks 5 Tests
Python Tests 5 Tests
Scientific Computing 12 Tests
Software Defined Radio 2 Tests
Server 2 Tests
Server CPU Tests 6 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
m7g.16xlarge Graviton3
June 22 2023
  6 Hours, 40 Minutes
c6g.16xlarge Graviton2
June 23 2023
  8 Hours, 18 Minutes
c7g.16xlarge Graviton3
June 23 2023
  6 Hours, 40 Minutes
c7gn.16xlarge Graviton3E
July 10 2023
  6 Hours, 39 Minutes
c6a.16xlarge AMD Zen 3
August 11 2023
  8 Hours, 48 Minutes
Invert Hiding All Results Option
  7 Hours, 25 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):

Amazon AWS Graviton3E vs. Graviton 2/3 benchmarks, "NAS Parallel Benchmarks 3.4 - Test / Class: LU.C", Higher Results Are Better "m7g.16xlarge Graviton3",28406.34,28372.25,28246.46 "c6g.16xlarge Graviton2",18793.97,18712.21,18719.52 "c7g.16xlarge Graviton3",28416.4,28407,28303.73 "c7gn.16xlarge Graviton3E",28292.16,28443.6,28371.57 "c6a.16xlarge AMD Zen 3",95065.97,95378.48,95219.76 "Liquid-DSP 1.6 - Threads: 32 - Buffer Length: 256 - Filter Length: 512", Higher Results Are Better "m7g.16xlarge Graviton3",81393000,81399000,81398000 "c6g.16xlarge Graviton2",67486000,67487000,67486000 "c7g.16xlarge Graviton3",81411000,81414000,81411000 "c7gn.16xlarge Graviton3E",81393000,81394000,81395000 "c6a.16xlarge AMD Zen 3",274870000,275100000,274440000 "OpenSSL 3.1 - Algorithm: RSA4096", Higher Results Are Better "m7g.16xlarge Graviton3",10180.2,10184.4,10181.2 "c6g.16xlarge Graviton2",2626.9,2621.1,2625 "c7g.16xlarge Graviton3",10180.3,10179.4,10184.4 "c7gn.16xlarge Graviton3E",10181.9,10183.3,10184.8 "c6a.16xlarge AMD Zen 3",8395.8,8386.3,8395.1 "srsRAN Project 23.5 - Test: Downlink Processor Benchmark", Higher Results Are Better "m7g.16xlarge Graviton3",316.8,318.8,319.9 "c6g.16xlarge Graviton2",197,197.7,196.9 "c7g.16xlarge Graviton3",321.3,318,319.7 "c7gn.16xlarge Graviton3E",323.1,323.2,323.3 "c6a.16xlarge AMD Zen 3",693.2,688.9,691.7 "NAS Parallel Benchmarks 3.4 - Test / Class: SP.C", Higher Results Are Better "m7g.16xlarge Graviton3",17231.47,17238.21,17264.86 "c6g.16xlarge Graviton2",9711.39,9709.2,9714.52 "c7g.16xlarge Graviton3",17225.92,17228.32,17205.6 "c7gn.16xlarge Graviton3E",17103.98,17210.52,17174.82 "c6a.16xlarge AMD Zen 3",34009.57,33999.8,34066.67 "Liquid-DSP 1.6 - Threads: 64 - Buffer Length: 256 - Filter Length: 512", Higher Results Are Better "m7g.16xlarge Graviton3",162760000,162760000,162740000 "c6g.16xlarge Graviton2",134930000,134920000,134930000 "c7g.16xlarge Graviton3",162770000,162760000,162770000 "c7gn.16xlarge Graviton3E",162770000,162760000,162740000 "c6a.16xlarge AMD Zen 3",460680000,459340000,460210000 "srsRAN Project 23.5 - Test: PUSCH Processor Benchmark, Throughput Thread", Higher Results Are Better "m7g.16xlarge Graviton3",95.8,95.8,95.9 "c6g.16xlarge Graviton2",63.7,63.8,63.8 "c7g.16xlarge Graviton3",95.8,95.7,95.7 "c7gn.16xlarge Graviton3E",97.5,97.4,97.3 "c6a.16xlarge AMD Zen 3",216.4,214.8,216.5 "OpenSSL 3.1 - Algorithm: RSA4096", Higher Results Are Better "m7g.16xlarge Graviton3",713821.6,713897.2,713859.8 "c6g.16xlarge Graviton2",214094.4,213868.4,214159.9 "c7g.16xlarge Graviton3",713947.2,713924.5,713966.1 "c7gn.16xlarge Graviton3E",713358.7,713944.2,713961.4 "c6a.16xlarge AMD Zen 3",548423.1,548438.7,548327.6 "Liquid-DSP 1.6 - Threads: 32 - Buffer Length: 256 - Filter Length: 57", Higher Results Are Better "m7g.16xlarge Graviton3",721500000,721490000,721490000 "c6g.16xlarge Graviton2",489310000,489270000,489230000 "c7g.16xlarge Graviton3",721560000,721050000,721550000 "c7gn.16xlarge Graviton3E",721080000,721540000,721520000 "c6a.16xlarge AMD Zen 3",1425200000,1453800000,1453800000 "Graph500 3.0 - Scale: 26", Higher Results Are Better "m7g.16xlarge Graviton3", "c6g.16xlarge Graviton2", "c7g.16xlarge Graviton3", "c7gn.16xlarge Graviton3E", "c6a.16xlarge AMD Zen 3", "Graph500 3.0 - Scale: 26", Higher Results Are Better "m7g.16xlarge Graviton3", "c6g.16xlarge Graviton2", "c7g.16xlarge Graviton3", "c7gn.16xlarge Graviton3E", "c6a.16xlarge AMD Zen 3", "OpenSSL 3.1 - Algorithm: AES-256-GCM", Higher Results Are Better "m7g.16xlarge Graviton3",283326924660,283345934750,283326481480 "c6g.16xlarge Graviton2",129195105760,129200865010,129202808700 "c7g.16xlarge Graviton3",283307370910,283396068690,283417947610 "c7gn.16xlarge Graviton3E",351171034040,351104323860,351182038360 "c6a.16xlarge AMD Zen 3",138541055180,138417027480,138415585690 "OpenSSL 3.1 - Algorithm: AES-128-GCM", Higher Results Are Better "m7g.16xlarge Graviton3",332117483250,331870630670,332111401780 "c6g.16xlarge Graviton2",158452691490,158418667930,158437132150 "c7g.16xlarge Graviton3",332052297590,332088876780,332051875160 "c7gn.16xlarge Graviton3E",411151459670,411112846130,411127104030 "c6a.16xlarge AMD Zen 3",151453688630,151440817360,151453301960 "ACES DGEMM 1.0 - Sustained Floating-Point Rate", Higher Results Are Better "m7g.16xlarge Graviton3",26.359169,23.988112,24.311963,24.205719,23.994175,23.985587,24.164991,24.153162,24.362813,24.298996,24.32914,24.160416,24.396346 "c6g.16xlarge Graviton2",20.300569,20.724191,20.229097 "c7g.16xlarge Graviton3",24.995891,23.807982,23.879846,23.878702 "c7gn.16xlarge Graviton3E",24.969594,23.810828,23.800742,23.73295 "c6a.16xlarge AMD Zen 3",9.435473,9.312792,9.415884 "Stress-NG 0.15.10 - Test: Memory Copying", Higher Results Are Better "m7g.16xlarge Graviton3",20491.84,20480.38,20480.51 "c6g.16xlarge Graviton2",11325.13,11322.69,11326.54 "c7g.16xlarge Graviton3",20477.21,20471.45,20487.35 "c7gn.16xlarge Graviton3E",20478.46,20475.65,20473.78 "c6a.16xlarge AMD Zen 3",8079.57,8081.15,8080.58 "Stress-NG 0.15.10 - Test: Matrix Math", Higher Results Are Better "m7g.16xlarge Graviton3",368667.05,368850.12,368734.84 "c6g.16xlarge Graviton2",284708.66,284729.52,284702.7 "c7g.16xlarge Graviton3",368617.88,368746.71,368649.57 "c7gn.16xlarge Graviton3E",369236.67,369224.35,369315.65 "c6a.16xlarge AMD Zen 3",147908.27,147367.49,147453.48 "Stress-NG 0.15.10 - Test: Vector Shuffle", Higher Results Are Better "m7g.16xlarge Graviton3",54186.1,54118.6,54125.49 "c6g.16xlarge Graviton2",35665.94,35710.45,35467.14 "c7g.16xlarge Graviton3",54608.52,54194.03,54613.67 "c7gn.16xlarge Graviton3E",54837.78,55119.38,54127.96 "c6a.16xlarge AMD Zen 3",22255.21,22255.48,22256.84 "nekRS 23.0 - Input: Kershaw", Higher Results Are Better "m7g.16xlarge Graviton3",3149080000,3153830000,3149130000 "c6g.16xlarge Graviton2",1761800000,1759760000,1759450000 "c7g.16xlarge Graviton3",3257260000,3262480000,3265820000 "c7gn.16xlarge Graviton3E",3313160000,3294860000,3300450000 "c6a.16xlarge AMD Zen 3",4278470000,4295570000,4352390000 "Stress-NG 0.15.10 - Test: Matrix 3D Math", Higher Results Are Better "m7g.16xlarge Graviton3",10414.79,10392.7,10404.31 "c6g.16xlarge Graviton2",5751.4,5754.88,5750.23 "c7g.16xlarge Graviton3",10813.83,10829.66,10797.27 "c7gn.16xlarge Graviton3E",10916.37,10850.14,10879.56 "c6a.16xlarge AMD Zen 3",4571.02,4575.73,4569.12 "Monte Carlo Simulations of Ionised Nebulae 2.02.73.3 - Input: Dust 2D tau100.0", Lower Results Are Better "m7g.16xlarge Graviton3",82.654,82.697,82.655 "c6g.16xlarge Graviton2",144.49,147.089,144.542 "c7g.16xlarge Graviton3",82.83,82.819,82.816 "c7gn.16xlarge Graviton3E",82.867,83.116,82.939 "c6a.16xlarge AMD Zen 3",201.495,190.118,195.976,189.473,200.147,192.5,191.337 "Xcompact3d Incompact3d 2021-03-11 - Input: input.i3d 129 Cells Per Direction", Lower Results Are Better "m7g.16xlarge Graviton3",3.04834509,3.10688996,3.14089608 "c6g.16xlarge Graviton2",5.64157677,5.59083509,5.67921019 "c7g.16xlarge Graviton3",3.17316389,3.18032908,3.07994699 "c7gn.16xlarge Graviton3E",3.10512495,3.09088993,3.14867997 "c6a.16xlarge AMD Zen 3",6.75374794,7.42592907,6.74197483,7.49560404,7.45090818,6.71217489,7.53647089,7.46926212,6.79676294,6.8381362,6.80064201,6.77357912,6.81989098,6.85191011,6.82929993 "Stress-NG 0.15.10 - Test: Vector Floating Point", Higher Results Are Better "m7g.16xlarge Graviton3",76402.17,76155.68,75749.79 "c6g.16xlarge Graviton2",42902.3,42794.21,42855.94 "c7g.16xlarge Graviton3",76073.56,76145.54,76316.28 "c7gn.16xlarge Graviton3E",76910.69,76909.4,76915.13 "c6a.16xlarge AMD Zen 3",95824.57,106879.84,95625.1,95729.52,95881.64,95774.15,95897.14,95670.41,95216.34,95702.7,95586.45,95348.81,95746.92 "OpenSSL 3.1 - Algorithm: SHA512", Higher Results Are Better "m7g.16xlarge Graviton3",32141198980,32090090800,32145056830 "c6g.16xlarge Graviton2",14411537800,14380665470,14389573200 "c7g.16xlarge Graviton3",32153353020,32146805740,32137583680 "c7gn.16xlarge Graviton3E",32094161810,32146475560,32137539750 "c6a.16xlarge AMD Zen 3",15291297260,15290917500,15291635130 "Xcompact3d Incompact3d 2021-03-11 - Input: input.i3d 193 Cells Per Direction", Lower Results Are Better "m7g.16xlarge Graviton3",13.9768667,13.9034071,13.9559803 "c6g.16xlarge Graviton2",25.8232422,25.9205341,25.9039211 "c7g.16xlarge Graviton3",13.7439699,14.0185366,13.7355013 "c7gn.16xlarge Graviton3E",13.6651058,13.7798252,13.8370867 "c6a.16xlarge AMD Zen 3",30.2278252,30.8359165,29.8798447 "Rodinia 3.1 - Test: OpenMP CFD Solver", Lower Results Are Better "m7g.16xlarge Graviton3",4.392,4.378,4.354 "c6g.16xlarge Graviton2",6.053,6.079,6.022 "c7g.16xlarge Graviton3",4.41,4.434,4.481 "c7gn.16xlarge Graviton3E",4.387,4.48,4.419 "c6a.16xlarge AMD Zen 3",9.344,9.343,9.339 "Algebraic Multi-Grid Benchmark 1.2 - ", Higher Results Are Better "m7g.16xlarge Graviton3",1646949000,1646743000,1646593000 "c6g.16xlarge Graviton2",1035728000,1035725000,1035306000 "c7g.16xlarge Graviton3",1765633000,1765229000,1764971000 "c7gn.16xlarge Graviton3E",1766117000,1765055000,1766727000 "c6a.16xlarge AMD Zen 3",835028600,838640200,837329100 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: c2c - Backend: FFTW - Precision: float - X Y Z: 512", Higher Results Are Better "m7g.16xlarge Graviton3",88.0112,88.0938,88.0396 "c6g.16xlarge Graviton2",42.8384,42.813,42.8337 "c7g.16xlarge Graviton3",88.2401,88.2266,88.0859 "c7gn.16xlarge Graviton3E",88.4917,88.4637,88.41 "c6a.16xlarge AMD Zen 3",44.1735,44.5968,44.1826 "Stress-NG 0.15.10 - Test: Fused Multiply-Add", Higher Results Are Better "m7g.16xlarge Graviton3",63769373.53,63752936.76,63764447.99 "c6g.16xlarge Graviton2",37724883.03,37734980.03,37736708.57 "c7g.16xlarge Graviton3",63814815.37,63827277.54,63813282.92 "c7gn.16xlarge Graviton3E",63716659.55,63710406.98,63743228.12 "c6a.16xlarge AMD Zen 3",30941724.98,30964282.97,30856724.81 "OpenSSL 3.1 - Algorithm: ChaCha20", Higher Results Are Better "m7g.16xlarge Graviton3",103224603170,103226670010,103229080370 "c6g.16xlarge Graviton2",67221173320,67320622560,67335827730 "c7g.16xlarge Graviton3",103275951170,103278264050,103272335770 "c7gn.16xlarge Graviton3E",114119152710,114116610180,114118595380 "c6a.16xlarge AMD Zen 3",138456168310,138380965750,138331002200 "Graph500 3.0 - Scale: 26", Higher Results Are Better "m7g.16xlarge Graviton3", "c6g.16xlarge Graviton2", "c7g.16xlarge Graviton3", "c7gn.16xlarge Graviton3E", "c6a.16xlarge AMD Zen 3", "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: r2c - Backend: FFTW - Precision: double - X Y Z: 512", Higher Results Are Better "m7g.16xlarge Graviton3",84.4459,84.5072,84.4685 "c6g.16xlarge Graviton2",44.8843,44.9169,44.9878 "c7g.16xlarge Graviton3",84.7317,84.757,84.7466 "c7gn.16xlarge Graviton3E",85.0235,84.9644,85.0302 "c6a.16xlarge AMD Zen 3",42.3373,42.4937,42.4873 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: r2c - Backend: FFTW - Precision: float - X Y Z: 512", Higher Results Are Better "m7g.16xlarge Graviton3",162.851,162.8,163.216 "c6g.16xlarge Graviton2",81.9613,81.8899,81.9723 "c7g.16xlarge Graviton3",163.225,163.379,163.224 "c7gn.16xlarge Graviton3E",163.6,163.584,163.492 "c6a.16xlarge AMD Zen 3",82.8045,82.5942,82.8764 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: c2c - Backend: FFTW - Precision: double - X Y Z: 256", Higher Results Are Better "m7g.16xlarge Graviton3",40.9039,40.8717,40.9012 "c6g.16xlarge Graviton2",20.6087,20.6441,20.6309 "c7g.16xlarge Graviton3",40.8256,40.7837,40.8757 "c7gn.16xlarge Graviton3E",40.9354,40.9471,41.0298 "c6a.16xlarge AMD Zen 3",20.5249,21.0102,21.0805 "OpenSSL 3.1 - Algorithm: ChaCha20-Poly1305", Higher Results Are Better "m7g.16xlarge Graviton3",74286014740,74290139140,74286229090 "c6g.16xlarge Graviton2",46716200000,46719871110,46716839310 "c7g.16xlarge Graviton3",74317980310,74321247980,74317298350 "c7gn.16xlarge Graviton3E",79968232790,79972954880,79967208790 "c6a.16xlarge AMD Zen 3",92761134210,92058302050,92749561860 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: c2c - Backend: FFTW - Precision: double - X Y Z: 512", Higher Results Are Better "m7g.16xlarge Graviton3",46.2611,46.2369,46.2532 "c6g.16xlarge Graviton2",24.2616,24.2477,24.2881 "c7g.16xlarge Graviton3",46.3845,46.3799,46.3473 "c7gn.16xlarge Graviton3E",46.5171,46.5358,46.537 "c6a.16xlarge AMD Zen 3",23.5743,23.5581,23.4311 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: r2c - Backend: FFTW - Precision: double - X Y Z: 256", Higher Results Are Better "m7g.16xlarge Graviton3",78.5004,78.5397,78.4745 "c6g.16xlarge Graviton2",40.1011,40.1301,40.1001 "c7g.16xlarge Graviton3",77.948,78.1896,77.168 "c7gn.16xlarge Graviton3E",78.154,78.2168,78.1265 "c6a.16xlarge AMD Zen 3",41.2465,41.723,41.791 "nekRS 23.0 - Input: TurboPipe Periodic", Higher Results Are Better "m7g.16xlarge Graviton3",3978660000,3974750000,3975490000 "c6g.16xlarge Graviton2",2220110000,2219990000,2220470000 "c7g.16xlarge Graviton3",3979200000,3978650000,3979100000 "c7gn.16xlarge Graviton3E",4140340000,4139770000,4144210000 "c6a.16xlarge AMD Zen 3",4315700000,4360030000,4336880000 "NAS Parallel Benchmarks 3.4 - Test / Class: MG.C", Higher Results Are Better "m7g.16xlarge Graviton3",50119.12,50088.24,50171.5 "c6g.16xlarge Graviton2",25657.26,25677.93,25678.68 "c7g.16xlarge Graviton3",49700.22,49719.43,49807.24 "c7gn.16xlarge Graviton3E",49839.23,49854.14,49888.68 "c6a.16xlarge AMD Zen 3",46126.6,46101.33,45612.49 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: c2c - Backend: FFTW - Precision: float - X Y Z: 256", Higher Results Are Better "m7g.16xlarge Graviton3",81.4572,81.4237,81.4518 "c6g.16xlarge Graviton2",42.0584,41.9858,41.9007 "c7g.16xlarge Graviton3",80.9355,80.9538,81.1395 "c7gn.16xlarge Graviton3E",81.3449,81.0912,81.0653 "c6a.16xlarge AMD Zen 3",41.8778,44.5821,42.8573,43.9574,44.4164,43.8533 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128", Higher Results Are Better "m7g.16xlarge Graviton3",307.766,306.891,304.964 "c6g.16xlarge Graviton2",210.033,210.235,208.22 "c7g.16xlarge Graviton3",300.635,301.117,302.502 "c7gn.16xlarge Graviton3E",298.76,298.799,303.63 "c6a.16xlarge AMD Zen 3",154.984,160.667,160.923 "LAMMPS Molecular Dynamics Simulator 23Jun2022 - Model: Rhodopsin Protein", Higher Results Are Better "m7g.16xlarge Graviton3",37.599,37.445,37.629 "c6g.16xlarge Graviton2",26.05,25.785,26.015 "c7g.16xlarge Graviton3",37.353,37.468,37.415 "c7gn.16xlarge Graviton3E",37.451,37.533,37.462 "c6a.16xlarge AMD Zen 3",19.338,19.947,18.933,20.449,20.296,18.729,19.304,20.089,20.469,19.102,20.507,17.596 "Graph500 3.0 - Scale: 26", Higher Results Are Better "m7g.16xlarge Graviton3", "c6g.16xlarge Graviton2", "c7g.16xlarge Graviton3", "c7gn.16xlarge Graviton3E", "c6a.16xlarge AMD Zen 3", "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: c2c - Backend: FFTW - Precision: float - X Y Z: 128", Higher Results Are Better "m7g.16xlarge Graviton3",185.858,186.765,186.445 "c6g.16xlarge Graviton2",136.025,134.857,135.193 "c7g.16xlarge Graviton3",184.753,183.156,184.169 "c7gn.16xlarge Graviton3E",184.108,183.764,184.457 "c6a.16xlarge AMD Zen 3",101.612,100.656,95.8093,105.042,104.52,92.5493,97.2508,96.5669,107.708,98.5401,98.6242,96.3325,94.3451,92.28 "LAMMPS Molecular Dynamics Simulator 23Jun2022 - Model: 20k Atoms", Higher Results Are Better "m7g.16xlarge Graviton3",36.981,36.936,36.864 "c6g.16xlarge Graviton2",25.167,25.157,25.189 "c7g.16xlarge Graviton3",36.822,36.909,36.854 "c7gn.16xlarge Graviton3E",36.867,36.804,36.844 "c6a.16xlarge AMD Zen 3",20.305,20.251,20.47 "Pennant 1.0.1 - Test: leblancbig", Lower Results Are Better "m7g.16xlarge Graviton3",6.722107,6.719106,6.720398 "c6g.16xlarge Graviton2",12.19264,12.1987,12.13914 "c7g.16xlarge Graviton3",6.951176,6.969912,6.962947 "c7gn.16xlarge Graviton3E",6.840908,6.839726,6.83936 "c6a.16xlarge AMD Zen 3",9.891914,9.924368,9.936414 "NWChem 7.0.2 - Input: C240 Buckyball", Lower Results Are Better "m7g.16xlarge Graviton3", "c6g.16xlarge Graviton2", "c7g.16xlarge Graviton3", "c7gn.16xlarge Graviton3E", "c6a.16xlarge AMD Zen 3", "Pennant 1.0.1 - Test: sedovbig", Lower Results Are Better "m7g.16xlarge Graviton3",9.184135,9.214283,9.221052 "c6g.16xlarge Graviton2",16.45079,16.51362,16.47708 "c7g.16xlarge Graviton3",9.438394,9.40001,9.428406 "c7gn.16xlarge Graviton3E",9.347923,9.33521,9.339727 "c6a.16xlarge AMD Zen 3",16.49269,16.60386,16.49494 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: r2c - Backend: FFTW - Precision: float - X Y Z: 256", Higher Results Are Better "m7g.16xlarge Graviton3",164.602,164.6,165.418 "c6g.16xlarge Graviton2",92.6392,92.0272,92.5325 "c7g.16xlarge Graviton3",161.957,161.844,162.228 "c7gn.16xlarge Graviton3E",162.367,162.281,162.436 "c6a.16xlarge AMD Zen 3",103.343,100.164,104.448 "Liquid-DSP 1.6 - Threads: 64 - Buffer Length: 256 - Filter Length: 57", Higher Results Are Better "m7g.16xlarge Graviton3",1442100000,1442500000,1442600000 "c6g.16xlarge Graviton2",978180000,978200000,978220000 "c7g.16xlarge Graviton3",1441800000,1442600000,1442700000 "c7gn.16xlarge Graviton3E",1442800000,1442700000,1442500000 "c6a.16xlarge AMD Zen 3",1712800000,1709500000,1710100000 "GROMACS 2023 - Implementation: MPI CPU - Input: water_GMX50_bare", Higher Results Are Better "m7g.16xlarge Graviton3",4.218,4.226,4.226 "c6g.16xlarge Graviton2",2.771,2.765,2.764 "c7g.16xlarge Graviton3",4.2,4.207,4.194 "c7gn.16xlarge Graviton3E",4.814,4.82,4.826 "c6a.16xlarge AMD Zen 3",3.991,3.954,3.951 "LULESH 2.0.3 - ", Higher Results Are Better "m7g.16xlarge Graviton3",28256.539,28284.486,28348.108 "c6g.16xlarge Graviton2",17621.914,17488.589,17561.953 "c7g.16xlarge Graviton3",28689.522,28730.219,28706.227 "c7gn.16xlarge Graviton3E",28760.842,28718.318,28729.519 "c6a.16xlarge AMD Zen 3",16875.244,16566.054,16683.476 "nginx 1.23.2 - Connections: 500", Higher Results Are Better "m7g.16xlarge Graviton3",256392.48,255308.09,255604.74 "c6g.16xlarge Graviton2",149107.04,148795.66,148991.36 "c7g.16xlarge Graviton3",255380.92,255397.4,254658.23 "c7gn.16xlarge Graviton3E",254131.96,253350.82,253072.76 "c6a.16xlarge AMD Zen 3",165846.14,165743.98,165953.13 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128", Higher Results Are Better "m7g.16xlarge Graviton3",137.859,137.941,138.243 "c6g.16xlarge Graviton2",81.9281,80.2463,82.1749 "c7g.16xlarge Graviton3",133.746,132.606,134.191 "c7gn.16xlarge Graviton3E",133.448,133.483,133.336 "c6a.16xlarge AMD Zen 3",85.7513,91.6601,87.4248,77.3029,92.4783,87.0846,90.2829,84.0824,77.9971,92.2407,86.3793,83.7914 "NAS Parallel Benchmarks 3.4 - Test / Class: CG.C", Higher Results Are Better "m7g.16xlarge Graviton3",22246.66,21827.86,21892.46 "c6g.16xlarge Graviton2",13040.83,13140.56,13129.46 "c7g.16xlarge Graviton3",21351.64,22268.02,22113.41 "c7gn.16xlarge Graviton3E",21919.57,22346.29,22200.21 "c6a.16xlarge AMD Zen 3",20181.38,20217.55,20231.07 "NAS Parallel Benchmarks 3.4 - Test / Class: EP.D", Higher Results Are Better "m7g.16xlarge Graviton3",3742.33,3737.68,3736.94 "c6g.16xlarge Graviton2",2214.21,2213.86,2220.7 "c7g.16xlarge Graviton3",3425.02,3735.16,3738.37,3741.06,3740.69,3741.17,3733.91,3738.39,3569.58,3738.57,3740.38,3429.09,3741.98,3737.43,3417.24 "c7gn.16xlarge Graviton3E",3739.67,3737.67,3487.06,3412.31,3732.15,3740.45,3482.43,3734.63,3628.49,3739.72,3736.08,3736.77,3740.14,3736.73,3480.75 "c6a.16xlarge AMD Zen 3",3057.86,3070.86,3055.55 "QMCPACK 3.16 - Input: simple-H2O", Lower Results Are Better "m7g.16xlarge Graviton3",28.106,27.994,28.023 "c6g.16xlarge Graviton2",45.081,44.893,45.701 "c7g.16xlarge Graviton3",27.952,28.032,27.986 "c7gn.16xlarge Graviton3E",27.928,28.022,28.047 "c6a.16xlarge AMD Zen 3",27.025,26.772,26.803 "srsRAN Project 23.5 - Test: PUSCH Processor Benchmark, Throughput Total", Higher Results Are Better "m7g.16xlarge Graviton3",5412.7,5421.4,5407.4 "c6g.16xlarge Graviton2",3933.9,3939.7,3942.5 "c7g.16xlarge Graviton3",5357.1,5359.7,5353.5 "c7gn.16xlarge Graviton3E",5424.6,5434.4,5434.7 "c6a.16xlarge AMD Zen 3",6517.8,6442.5,6477 "GPAW 23.6 - Input: Carbon Nanotube", Lower Results Are Better "m7g.16xlarge Graviton3",61.806,61.791,61.896 "c6g.16xlarge Graviton2",92.735,92.793,92.753 "c7g.16xlarge Graviton3",62.021,62.15,62.078 "c7gn.16xlarge Graviton3E",56.405,56.403,56.511 "c6a.16xlarge AMD Zen 3",89.654,90.065,89.735 "QMCPACK 3.16 - Input: FeCO6_b3lyp_gms", Lower Results Are Better "m7g.16xlarge Graviton3",212.03,211.34,211.42 "c6g.16xlarge Graviton2",302.91,301.97,301.69 "c7g.16xlarge Graviton3",211.11,211.7,211.16 "c7gn.16xlarge Graviton3E",188.86,188.07,187.91 "c6a.16xlarge AMD Zen 3",182.44,185.99,183.87 "Monte Carlo Simulations of Ionised Nebulae 2.02.73.3 - Input: Gas HII40", Lower Results Are Better "m7g.16xlarge Graviton3",13.488,13.588,13.65 "c6g.16xlarge Graviton2",21.016,20.824,20.434 "c7g.16xlarge Graviton3",13.708,13.662,13.608 "c7gn.16xlarge Graviton3E",13.527,13.469,13.578 "c6a.16xlarge AMD Zen 3",12.629,12.677,12.7 "BRL-CAD 7.34 - VGR Performance Metric", Higher Results Are Better "m7g.16xlarge Graviton3", "c6g.16xlarge Graviton2", "c7g.16xlarge Graviton3", "c7gn.16xlarge Graviton3E", "c6a.16xlarge AMD Zen 3", "LeelaChessZero 0.28 - Backend: Eigen", Higher Results Are Better "m7g.16xlarge Graviton3",1403,1410,1381 "c6g.16xlarge Graviton2",900,884,889 "c7g.16xlarge Graviton3",1354,1385,1408 "c7gn.16xlarge Graviton3E",1448,1416,1467 "c6a.16xlarge AMD Zen 3",1163,1138,1155 "nginx 1.23.2 - Connections: 1000", Higher Results Are Better "m7g.16xlarge Graviton3",255673.36,255354.98,255819.78 "c6g.16xlarge Graviton2",159043.97,158445.53,158539.69 "c7g.16xlarge Graviton3",255653.24,255542.92,255459.99 "c7gn.16xlarge Graviton3E",257328.19,256482.76,255946.54 "c6a.16xlarge AMD Zen 3",162952.82,163425.41,163157.77 "Kripke 1.2.6 - ", Higher Results Are Better "m7g.16xlarge Graviton3",339163300,337855400,339982500 "c6g.16xlarge Graviton2",220015800,220019100,220325800 "c7g.16xlarge Graviton3",353547200,354414400,355366600 "c7gn.16xlarge Graviton3E",354409300,353390400,354902500 "c6a.16xlarge AMD Zen 3",244591300,234451400,230904400,238403500 "QMCPACK 3.16 - Input: FeCO6_b3lyp_gms", Lower Results Are Better "m7g.16xlarge Graviton3",205.68,206.51,204.96 "c6g.16xlarge Graviton2",300.04,299.31,294.46 "c7g.16xlarge Graviton3",206.14,204.87,203.29 "c7gn.16xlarge Graviton3E",204.66,204,204.1 "c6a.16xlarge AMD Zen 3",183.16,187.68,191.12 "Remhos 1.0 - Test: Sample Remap Example", Lower Results Are Better "m7g.16xlarge Graviton3",13.979,14.028,14.114 "c6g.16xlarge Graviton2",20.904,20.629,20.687 "c7g.16xlarge Graviton3",14.113,14.188,14.059 "c7gn.16xlarge Graviton3E",14.128,14.066,14.053 "c6a.16xlarge AMD Zen 3",21.924,22.294,22.095 "Liquid-DSP 1.6 - Threads: 32 - Buffer Length: 256 - Filter Length: 32", Higher Results Are Better "m7g.16xlarge Graviton3",1136300000,1136300000,1135600000 "c6g.16xlarge Graviton2",765130000,764900000,766370000 "c7g.16xlarge Graviton3",1136100000,1136100000,1136200000 "c7gn.16xlarge Graviton3E",1136100000,1136000000,1135900000 "c6a.16xlarge AMD Zen 3",1193200000,1195100000,1193600000 "Stress-NG 0.15.10 - Test: Wide Vector Math", Higher Results Are Better "m7g.16xlarge Graviton3",1470754.87,1589761.09,1594752.35,1589674.23,1589814.9,1460576.11,1589770.99,1464021.3,1594783.4,1472843.78,1473617.63,1594786.42,1594695.64,1589782.56,1472888.8 "c6g.16xlarge Graviton2",997833.68,996263.05,997721.22 "c7g.16xlarge Graviton3",1596411.4,1460472.9,1591140.9,1596461.44,1470846.28,1585045.28,1596432.77,1591144.18,1475720.77,1466977.29,1467857.7,1473361.25,1470603.1,1591102.39,1596470.87 "c7gn.16xlarge Graviton3E",1599160.15,1477686.68,1470642.47,1463498.57,1594292.33,1594304.21,1476838.57,1472803.16,1594333.94,1468492.66,1477192.45,1473559.64,1594356.78,1594291.21,1599200.01 "c6a.16xlarge AMD Zen 3",1375675.93,1380415.4,1384348.57 "Laghos 3.1 - Test: Sedov Blast Wave, ube_922_hex.mesh", Higher Results Are Better "m7g.16xlarge Graviton3",411.2472171934,409.7870709832,410.6239584126 "c6g.16xlarge Graviton2",321.2803321251,321.7064307843,324.1331802357 "c7g.16xlarge Graviton3",406.7931930374,409.74192091,407.5026052718 "c7gn.16xlarge Graviton3E",423.552179013,421.5682768546,424.1967768128 "c6a.16xlarge AMD Zen 3",276.7508584359,275.9449860937,275.0715210425 "Stress-NG 0.15.10 - Test: Vector Math", Higher Results Are Better "m7g.16xlarge Graviton3",217321.92,217228.54,217156.3 "c6g.16xlarge Graviton2",147923.61,147810.22,147924.59 "c7g.16xlarge Graviton3",217481.58,217409.05,217447.73 "c7gn.16xlarge Graviton3E",217513.09,217594.06,217594.14 "c6a.16xlarge AMD Zen 3",221970.29,221726.02,221632.14 "Liquid-DSP 1.6 - Threads: 64 - Buffer Length: 256 - Filter Length: 32", Higher Results Are Better "m7g.16xlarge Graviton3",2269800000,2271300000,2270400000 "c6g.16xlarge Graviton2",1530900000,1531700000,1531600000 "c7g.16xlarge Graviton3",2272300000,2271400000,2272200000 "c7gn.16xlarge Graviton3E",2266800000,2261800000,2271900000 "c6a.16xlarge AMD Zen 3",2184600000,2185300000,2184700000 "Timed Godot Game Engine Compilation 4.0 - Time To Compile", Lower Results Are Better "m7g.16xlarge Graviton3",154.838,154.536,153.761 "c6g.16xlarge Graviton2",218.866,217.89,218.071 "c7g.16xlarge Graviton3",157.926,156.272,155.862 "c7gn.16xlarge Graviton3E",155.797,156.801,155.255 "c6a.16xlarge AMD Zen 3",147.873,147.499,147.84 "LeelaChessZero 0.28 - Backend: BLAS", Higher Results Are Better "m7g.16xlarge Graviton3",1308,1302,1292 "c6g.16xlarge Graviton2",970,931,940 "c7g.16xlarge Graviton3",1326,1334,1338 "c7gn.16xlarge Graviton3E",1383,1406,1386 "c6a.16xlarge AMD Zen 3",1338,1321,1264,1327,1330 "QMCPACK 3.16 - Input: Li2_STO_ae", Lower Results Are Better "m7g.16xlarge Graviton3",112.51,112.77,112.54 "c6g.16xlarge Graviton2",163.21,167.13,165.02 "c7g.16xlarge Graviton3",112.64,112.44,112.85 "c7gn.16xlarge Graviton3E",112.91,112.87,113.81 "c6a.16xlarge AMD Zen 3",123.88,123.77,124.2 "Rodinia 3.1 - Test: OpenMP LavaMD", Lower Results Are Better "m7g.16xlarge Graviton3",44.083,43.699,43.583 "c6g.16xlarge Graviton2",62.175,62.298,62.2 "c7g.16xlarge Graviton3",44.09,44.063,43.735 "c7gn.16xlarge Graviton3E",44.156,43.739,44.238 "c6a.16xlarge AMD Zen 3",63.243,64.232,65.061 "7-Zip Compression 22.01 - Test: Compression Rating", Higher Results Are Better "m7g.16xlarge Graviton3",316757,316597,317120 "c6g.16xlarge Graviton2",240686,240347,241072 "c7g.16xlarge Graviton3",311168,310919,311080 "c7gn.16xlarge Graviton3E",311393,312301,312333 "c6a.16xlarge AMD Zen 3",231289,229683,231939 "Laghos 3.1 - Test: Triple Point Problem", Higher Results Are Better "m7g.16xlarge Graviton3",231.8847454562,232.5445664364,231.5861677246 "c6g.16xlarge Graviton2",179.9285071694,180.8780592768,181.5869906302 "c7g.16xlarge Graviton3",230.5558294183,230.4909930046,230.9945449947 "c7gn.16xlarge Graviton3E",235.8116629005,236.7251972473,236.1179341663 "c6a.16xlarge AMD Zen 3",225.2955609149,228.3009203543,228.6109025279 "Coremark 1.0 - CoreMark Size 666 - Iterations Per Second", Higher Results Are Better "m7g.16xlarge Graviton3",1635678.231423,1545987.076514,1635782.747604,1633278.040066,1536337.994359,1549261.679981,1636514.735025,1635364.763,1624674.747731,1545800.374374,1611583.254643,1632028.5605,1635678.231423,1533301.389554,1636933.307756 "c6g.16xlarge Graviton2",1260338.71603,1260835.303388,1260752.511655 "c7g.16xlarge Graviton3",1635051.414703,1495501.810959,1575869.498307,1635678.231423,1636828.644501,1618614.06171,1636305.528923,1634112.089876,1632965.490846,1629742.806213,1492276.304284,1557367.076287,1636933.307756,1635573.728597,1636410.125288 "c7gn.16xlarge Graviton3E",1548793.030431,1560309.623941,1636723.994629,1632965.490846,1629742.806213,1637037.984397,1637037.984397 "c6a.16xlarge AMD Zen 3",1463916.739735,1479312.735958,1456531.634046 "OpenSSL 3.1 - Algorithm: SHA256", Higher Results Are Better "m7g.16xlarge Graviton3",54235081860,54226866930,54175597950 "c6g.16xlarge Graviton2",42723186190,42713258660,41981951690 "c7g.16xlarge Graviton3",54192930870,54248302980,54208449940 "c7gn.16xlarge Graviton3E",54164888370,54181446940,54116320470 "c6a.16xlarge AMD Zen 3",45814248990,45906468010,45851887330 "Timed Gem5 Compilation 21.2 - Time To Compile", Lower Results Are Better "m7g.16xlarge Graviton3",180.108,180.13,180.502 "c6g.16xlarge Graviton2",225.854,225.399,224.662 "c7g.16xlarge Graviton3",182.197,181.834,181.305 "c7gn.16xlarge Graviton3E",183.217,182.224,181.973 "c6a.16xlarge AMD Zen 3",192.172,192.548,191.635 "Timed Node.js Compilation 19.8.1 - Time To Compile", Lower Results Are Better "m7g.16xlarge Graviton3",237.842,238.326,237.182 "c6g.16xlarge Graviton2",288.122,287.615,287.704 "c7g.16xlarge Graviton3",238.556,238.883,238.19 "c7gn.16xlarge Graviton3E",239.263,238.271,238.373 "c6a.16xlarge AMD Zen 3",229.631,230.864,230.775 "7-Zip Compression 22.01 - Test: Decompression Rating", Higher Results Are Better "m7g.16xlarge Graviton3",285449,285727,285444 "c6g.16xlarge Graviton2",234220,234214,234171 "c7g.16xlarge Graviton3",285882,285375,285642 "c7gn.16xlarge Graviton3E",285584,285672,285774 "c6a.16xlarge AMD Zen 3",236144,237648,233570 "Stress-NG 0.15.10 - Test: CPU Cache", Higher Results Are Better "m7g.16xlarge Graviton3",3355632.88,4037596.07,4060936.91,4077127.2,4123087.89,3767041.64,4106379.86,4012458.57,3917544.69,3676649.71,3889438.43,3881044.56,3743134.71,3628154.61,4109717.41 "c6g.16xlarge Graviton2",1976267.22,1951070.44,2134539.42,1840595.5,1984370.5,1870194.92,1899718.08,2021620.03,1862335.35,1914339.52,1906700.77,1806225.16,1903672.43,1819919.79,1935208.82 "c7g.16xlarge Graviton3",3632437,4018555.55,3886340.23,3821416.14,3504224.45,3746036.61,3593964.42,3554605.54,4241661.25,3958486.15,3591826.94,4106555.7,3940806.5,3971192.17,4093421.09 "c7gn.16xlarge Graviton3E",3754672.68,3994647.6,3994684.28,3538542.83,3814492.08,3825968.17,3979052.2,3545284.44,4025184.61,3820836.7,3831054.1,3872864.46,3917295.05,3921017.87,4069433.59 "c6a.16xlarge AMD Zen 3",1367697.58,1490420.32,1419340.62,1531530.41,1539783.45,1325093,1693572.08,1374608.57,1456455.84,1444545.28,1412009.55,1312127.47 "Stress-NG 0.15.10 - Test: NUMA", Higher Results Are Better "m7g.16xlarge Graviton3",3762.45,3748.95,3765.9 "c6g.16xlarge Graviton2",2111.43,2110.85,2115.71 "c7g.16xlarge Graviton3",3517.82,3529.57,3523.35 "c7gn.16xlarge Graviton3E",3528.14,3536.08,3511.28 "c6a.16xlarge AMD Zen 3",508.12,516.48,593.22,535.67,542,575.69,641.68,562.72,558.75,546.08,594.85,533.61,497.54,558.75,524.99 "Stockfish 15 - Total Time", Higher Results Are Better "m7g.16xlarge Graviton3",99696135,124269486,94808830,111278930,124273503,101653494,119368423,98107814,109030084,131088373,108938527,117615885,105432738,124273250,111960193 "c6g.16xlarge Graviton2",87315632,82492809,72817003,88625238,86252658,98643756,83039034,82727325,74592319,80008507,109883614,96059801,97389773,79347560,79944233 "c7g.16xlarge Graviton3",114989787,114707499,107475454,124199784,136870937,114357228,122985373,119373200,126151937,121223075,96255646,109207795 "c7gn.16xlarge Graviton3E",107268236,106260684,120983065,126414496,123061315,115136550,116458699,114074195,114742517,116920187,122860933,114602467,124267059,112337641,120018768 "c6a.16xlarge AMD Zen 3",93583736,101129571,104612276,92482730,90555926,95404780,91882547,91541063,105699782,93409418,107501507,94651323,100520743,95665725,94943008 "HeFFTe - Highly Efficient FFT for Exascale 2.3 - Test: c2c - Backend: FFTW - Precision: double - X Y Z: 128", Higher Results Are Better "m7g.16xlarge Graviton3",57.3824,56.5873,57.4812 "c6g.16xlarge Graviton2",32.7006,32.6333,32.9066 "c7g.16xlarge Graviton3",55.2629,55.2457,54.808 "c7gn.16xlarge Graviton3E",55.4516,54.4605,55.3994 "c6a.16xlarge AMD Zen 3",42.7635,49.1546,46.8618,51.2808,51.5664,46.8349,47.9484,48.4237,51.9229,53.2691,51.6927,46.4424,51.1666,43.0256,51.7946 "Rodinia 3.1 - Test: OpenMP Streamcluster", Lower Results Are Better "m7g.16xlarge Graviton3",11.411,11.691,11.886 "c6g.16xlarge Graviton2",14.255,12.837,12.394,14.242,12.796,14.265,13.928,12.415,14.571,14.488,14.254,12.784,14.248,14.36,14.187 "c7g.16xlarge Graviton3",11.218,11.809,11.906,11.793,11.253,11.709,11.879,11.433 "c7gn.16xlarge Graviton3E",11.264,11.403,11.847,9.909,10.032,9.963,11.359,10.235,10.297,10.248,9.777,11.942 "c6a.16xlarge AMD Zen 3",7.542,7.881,8.628,7.779,8.575,8.54,8.642,8.633,8.534,8.737,8.549,8.608,8.776,8.519,7.99