m6g.metal Graviton2 vs. Ampere Altra

Ampere Altra ARMv8 Neoverse-N1 tests against Amazon Graviton2 m6g.metal for possible future article.

HTML result view exported from: https://openbenchmarking.org/result/2012190-HA-ALTRAEC2377&rdt&grs.

m6g.metal Graviton2 vs. Ampere AltraProcessorMotherboardMemoryDiskNetworkChipsetGraphicsMonitorOSKernelCompilerFile-SystemScreen Resolutionm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64cARMv8 Neoverse-N1 (64 Cores)Amazon EC2 m6g.metal v1.0252GB94GB Amazon Elastic Block StoreAmazon ElasticUbuntu 20.045.4.0-1029-aws (aarch64)GCC 9.3.0ext4Ampere Altra ARMv8 Neoverse-N1 @ 3.30GHz (160 Cores)WIWYNN Mt.Jade (1.1.20201019 BIOS)Ampere Computing LLC Device e10016 x 32 GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE3841GB Micron_9300_MTFDHAL3T8TDP + 960GB SAMSUNG MZ1LB960HAJQ-00007ASPEEDVE228Mellanox MT28908 + Intel I2105.4.0-58-generic (aarch64)1920x1080Ampere Altra ARMv8 Neoverse-N1 @ 3.30GHz (80 Cores)Ampere Altra ARMv8 Neoverse-N1 @ 3.30GHz (64 Cores)1024x768OpenBenchmarking.orgCompiler Details- --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v Python Details- Python 3.8.5Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected Processor Details- Ampere Altra Q80-33 2P 160c, Ampere Altra Q80-33 1P 80c, Ampere Altra Q80-33 1P 64c: Scaling Governor: cppc_cpufreq performance

m6g.metal Graviton2 vs. Ampere Altrastress-ng: CPU Stressstress-ng: Vector Mathstress-ng: Cryptostress-ng: Matrix Mathc-ray: Total Time - 4K, 16 Rays Per Pixelm-queens: Time To Solveastcenc: Exhaustivestress-ng: Context Switchinghpcg: tnn: CPU - SqueezeNet v1.1byte: Dhrystone 2compress-lz4: 3 - Compression Speedcompress-lz4: 9 - Compression Speedtnn: CPU - MobileNet v2gromacs: Water Benchmarkcoremark: CoreMark Size 666 - Iterations Per Secondjohn-the-ripper: Blowfishstream: Addstream: Triadstream: Copym6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c7228.57353821.3411355.88256330.0615.60419.43970.7319337654.5621.4364332.79325752636.437.3435.72355.2562.7611205893.12310844218170481.7170932.8165514.723501.471143937.0736316.96819104.514.9076.55128.6745404883.1044.9108267.86433963046.248.1746.01311.9256.6113256887.00196190773266737.9272185.3239685.811784.05577961.0718691.07420159.199.45412.03549.1222953240.3822.7101251.55433953700.047.0743.84291.3223.8711854977.71050548711166228.6165070.5162465.99415.04465202.1215037.10311734.2812.04714.85760.8218513502.9722.4646255.59933950617.148.1644.37300.4192.8351551293.00223350803166546.2167747.4162886.4OpenBenchmarking.org

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: CPU Stressm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c5K10K15K20K25KSE +/- 0.93, N = 3SE +/- 120.41, N = 3SE +/- 9.44, N = 3SE +/- 29.91, N = 37228.5723501.4711784.059415.041. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Vector Mathm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c200K400K600K800K1000KSE +/- 2.19, N = 3SE +/- 1813.61, N = 3SE +/- 2494.00, N = 3SE +/- 419.80, N = 3353821.341143937.07577961.07465202.121. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Cryptom6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c8K16K24K32K40KSE +/- 22.19, N = 3SE +/- 360.65, N = 3SE +/- 75.96, N = 3SE +/- 32.09, N = 311355.8836316.9618691.0715037.101. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

Stress-NG

Test: Matrix Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Matrix Mathm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c200K400K600K800K1000KSE +/- 9.77, N = 3SE +/- 6853.85, N = 3SE +/- 335.41, N = 3SE +/- 1405.87, N = 3256330.06819104.51420159.19311734.281. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixelm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c48121620SE +/- 0.020, N = 3SE +/- 0.018, N = 3SE +/- 0.021, N = 3SE +/- 0.033, N = 315.6044.9079.45412.0471. (CC) gcc options: -lm -lpthread -O3

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solvem6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c510152025SE +/- 0.008, N = 3SE +/- 0.070, N = 5SE +/- 0.132, N = 3SE +/- 0.034, N = 319.4396.55112.03514.8571. (CXX) g++ options: -fopenmp -O2 -march=native

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: Exhaustivem6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c1632486480SE +/- 0.01, N = 3SE +/- 0.45, N = 13SE +/- 0.21, N = 3SE +/- 0.17, N = 370.7328.6749.1260.821. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -lpthread

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.11.07Test: Context Switchingm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c10M20M30M40M50MSE +/- 252656.21, N = 3SE +/- 353501.41, N = 3SE +/- 217249.98, N = 6SE +/- 176208.12, N = 1519337654.5645404883.1022953240.3818513502.971. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1m6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c1020304050SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 321.4444.9122.7122.461. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1m6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c70140210280350SE +/- 0.27, N = 3SE +/- 3.88, N = 15SE +/- 0.46, N = 3SE +/- 1.68, N = 3332.79267.86251.55255.60MIN: 332.17 / MAX: 333.54MIN: 249.7 / MAX: 411.03MIN: 249.95 / MAX: 252.68MIN: 251.62 / MAX: 265.031. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

BYTE Unix Benchmark

Computational Test: Dhrystone 2

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2m6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c7M14M21M28M35MSE +/- 3044.65, N = 3SE +/- 8257.21, N = 3SE +/- 7604.20, N = 3SE +/- 34772.76, N = 325752636.433963046.233953700.033950617.1

LZ4 Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression Speedm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c1122334455SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.68, N = 3SE +/- 0.11, N = 337.3448.1747.0748.161. (CC) gcc options: -O3

LZ4 Compression

Compression Level: 9 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression Speedm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c1020304050SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.44, N = 1535.7246.0143.8444.371. (CC) gcc options: -O3

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2m6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c80160240320400SE +/- 0.14, N = 3SE +/- 1.51, N = 3SE +/- 2.60, N = 3SE +/- 3.40, N = 15355.26311.93291.32300.42MIN: 354.82 / MAX: 355.87MIN: 293.86 / MAX: 414.93MIN: 285.33 / MAX: 397.43MIN: 285.58 / MAX: 343.171. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water Benchmarkm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c246810SE +/- 0.001, N = 3SE +/- 0.014, N = 3SE +/- 0.016, N = 3SE +/- 0.058, N = 152.7616.6113.8712.8351. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Secondm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c700K1400K2100K2800K3500KSE +/- 20239.38, N = 15SE +/- 54021.40, N = 15SE +/- 13320.07, N = 3SE +/- 12939.15, N = 31205893.123256887.001854977.711551293.001. (CC) gcc options: -O2 -lrt" -lrt

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: Blowfishm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c20K40K60K80K100KSE +/- 9.00, N = 3SE +/- 4405.69, N = 15SE +/- 1790.62, N = 15SE +/- 1823.77, N = 15442189077348711508031. (CC) gcc options: -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt

Stream

Type: Add

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Addm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c60K120K180K240K300KSE +/- 33.82, N = 5SE +/- 15401.72, N = 5SE +/- 2620.82, N = 5SE +/- 329.58, N = 5170481.7266737.9166228.6166546.21. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Triad

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triadm6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c60K120K180K240K300KSE +/- 69.34, N = 5SE +/- 15170.38, N = 5SE +/- 3156.35, N = 5SE +/- 292.37, N = 5170932.8272185.3165070.5167747.41. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Copy

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copym6g.metal Graviton2 64cAmpere Altra Q80-33 2P 160cAmpere Altra Q80-33 1P 80cAmpere Altra Q80-33 1P 64c50K100K150K200K250KSE +/- 83.68, N = 5SE +/- 4388.23, N = 25SE +/- 1282.06, N = 25SE +/- 1497.95, N = 5165514.7239685.8162465.9162886.41. (CC) gcc options: -O3 -march=native -fopenmp


Phoronix Test Suite v10.8.4