Graviton3 Neoverse-V1 Compiler Tests

Benchmarks by Michael Larabel for a future article. amazon testing on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2206081-NE-ARMSVE03321&rdt&grs.

Graviton3 Neoverse-V1 Compiler TestsProcessorMotherboardChipsetMemoryDiskNetworkOSKernelCompilerFile-SystemSystem Layer-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1ARMv8 Neoverse-V1 (32 Cores)Amazon EC2 c7g.8xlarge (1.0 BIOS)Amazon Device 020062GB301GB Amazon Elastic Block StoreAmazon ElasticUbuntu 22.045.15.0-1004-aws (aarch64)GCC 12.0.0 20220117ext4amazonOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseEnvironment Details- -march=armv8.4-a+sve: CXXFLAGS="-O3 -march=armv8.4-a+sve" CFLAGS="-O3 -march=armv8.4-a+sve"- -march=armv8.4-a: CXXFLAGS="-O3 -march=armv8.4-a" CFLAGS="-O3 -march=armv8.4-a"- -march=armv8.4-a+sve -mcpu=neoverse-v1: CXXFLAGS="-O3 -march=armv8.4-a+sve -mcpu=neoverse-v1" CFLAGS="-O3 -march=armv8.4-a+sve -mcpu=neoverse-v1"Compiler Details- --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-nls --disable-werror --enable-checking=yes,extra,rtl --enable-clocale=gnu --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-objc-gc=auto --enable-plugin --enable-shared --host=aarch64-linux-gnu --program-prefix= --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v Python Details- Python 3.10.4Security 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: Mitigation of CSV2 BHB + srbds: Not affected + tsx_async_abort: Not affected

Graviton3 Neoverse-V1 Compiler Testscryptopp: Unkeyed Algorithmsencode-opus: WAV To Opus Encodetnn: CPU - SqueezeNet v1.1espeak: Text-To-Speech Synthesisliquid-dsp: 32 - 256 - 57liquid-dsp: 8 - 256 - 57liquid-dsp: 16 - 256 - 57tnn: CPU - DenseNetgraphics-magick: HWB Color Spacejpegxl: JPEG - 7luajit: Fast Fourier Transformbotan: KASUMI - Decryptencode-mp3: WAV To MP3tnn: CPU - MobileNet v2stockfish: Total Timengspice: C7552tnn: CPU - SqueezeNet v2nettle: poly1305-aesaom-av1: Speed 10 Realtime - Bosphorus 4Kkripke: graphics-magick: Rotateluajit: Dense LU Matrix Factorizationbotan: KASUMImt-dgemm: Sustained Floating-Point Ratebotan: Twofish - Decryptcoremark: CoreMark Size 666 - Iterations Per Secondnettle: sha512graphics-magick: Noise-Gaussianngspice: C2670jpegxl: JPEG - 8caffe: AlexNet - CPU - 200caffe: GoogleNet - CPU - 200graphics-magick: Swirlbotan: Twofishopenjpeg: NASA Curiosity Panorama M34jpegxl: PNG - 7aom-av1: Speed 8 Realtime - Bosphorus 1080pcompress-zstd: 19, Long Mode - Compression Speedpovray: Trace Timeastcenc: Mediumgraphics-magick: Resizinggraphics-magick: Enhancedmrbayes: Primate Phylogeny Analysisstargate: 44100 - 1024aom-av1: Speed 9 Realtime - Bosphorus 1080pcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19 - Decompression Speedstargate: 480000 - 1024stargate: 480000 - 512stargate: 44100 - 512astcenc: Thoroughluajit: Compositeastcenc: Exhaustivebotan: Blowfish - Decryptlczero: Eigenrnnoise: webp: Quality 100, Losslessaom-av1: Speed 10 Realtime - Bosphorus 1080pdraco: Church Facadestargate: 96000 - 1024compress-zstd: 3, Long Mode - Decompression Speedcompress-zstd: 19 - Compression Speedlammps: Rhodopsin Proteinbotan: AES-256stargate: 96000 - 512encode-wavpack: WAV To WavPackc-ray: Total Time - 4K, 16 Rays Per Pixellczero: BLASredis: GETbotan: ChaCha20Poly1305 - Decryptcompress-zstd: 3 - Compression Speedbotan: ChaCha20Poly1305nettle: chachabotan: AES-256 - Decryptprimesieve: 1e12 Prime Number Generationonnx: GPT-2 - CPU - Standardluajit: Sparse Matrix Multiplydraco: Lionaom-av1: Speed 8 Realtime - Bosphorus 4Kredis: SEThimeno: Poisson Pressure Solveropenssl: SHA256botan: Blowfishencode-flac: WAV To FLACxmrig: Wownero - 1Mopenssl: RSA4096botan: CAST-256botan: CAST-256 - Decryptwebp: Quality 100, Highest Compressionxmrig: Monero - 1Mx264: Bosphorus 1080ponnx: ArcFace ResNet-100 - CPU - Standardx264: Bosphorus 4Konnx: bertsquad-12 - CPU - Standardnettle: aes256aobench: 2048 x 2048 - Total Timecompress-zstd: 3, Long Mode - Compression Speedluajit: Monte Carlogromacs: MPI CPU - water_GMX50_bareluajit: Jacobi Successive Over-Relaxationopenssl: RSA4096smallpt: Global Illumination Renderer; 128 Samplesonnx: super-resolution-10 - CPU - Standardgmpbench: Total Timesysbench: CPUonnx: fcn-resnet101-11 - CPU - Standardjpegxl: PNG - 8-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1449.02420814.402205.79929.9826686366671677333333354233332346.322106779.58615.7162.2617.440280.24355823340111.64476.301820.5165.621927092336113521.1362.0013.442233258.148762066.501163504.33515106.91027.34439311251251272248.887551968.36123.9540.320.2634.80922414718234.2556.538163156.713263.73094.86.4501826.1244556.2135009.01311309.0335.1926289.032133317.38523.403193.6878434.8077973824.874.021.1495442.6494.47484820.51519.29912972513289.2383.9457027.2390.311733.595474.3218.533123171162.33530962.191861924.135508.28243527428176880280.57038.51511877.85088.1108.754108.6238.6408669.8169.5893548.517724447.0433.4941242.7343.852.275902.16356407.83.89654114155.696666.76730.67459.87016318.320257.70436.5877052333331763633333527000002730.4097873.21661.5562.2778.054260.77857485680103.93371.130871.9061.882041431675773355.5362.01712.813927246.155789646.924800498.83494102.55826.30436341238071225239.703572058.32120.1340.019.8474.88332339732237.5426.370035152.463250.93083.46.3226846.0053866.0729169.14351282.5935.3647288.505131117.62223.852190.2779354.7298483820.872.921.3305494.3134.41405520.48819.29612812523377.92382.5146937.8389.375740.255477.5718.438123641151.57535462.131865840.135561.55928727603943570278.87438.31111811.25090.5108.786108.5998.6308645.4168.9293848.437734435.9133.4811241.3343.272.277901.02356359.63.89554134152.396726.40730.67270.93160914.380205.28029.9856024433331506733333013300002390.259101678.80668.4067.5117.446273.39559966785106.76776.214859.9363.251947763675913547.9065.29213.348870246.611798137.708406481.90509104.09527.09422621204281257244.209554158.07124.2239.019.6114.72902402741241.5396.360138156.633339.73167.56.2880065.9816626.0686508.94271303.8934.6761283.410133717.29023.845193.5577974.7297563882.373.021.0185415.1944.41248720.76319.55512802546595.58378.9766938.3385.377731.075409.8158.435124601164.28529761.5618799625538.73991227681290600280.98938.60111842.05114.1109.290109.1088.6028681.4169.3093848.567744438.2733.5531243.8343.902.279902.14355966.73.89254164152.796702.81730.67OpenBenchmarking.org

Crypto++

Test: Unkeyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed Algorithms-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1100200300400500SE +/- 0.25, N = 3SE +/- 0.25, N = 3SE +/- 1.67, N = 3449.02459.87270.93-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -fPIC -pthread -pipe

Opus Codec Encoding

WAV To Opus Encode

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.3.1WAV To Opus Encode-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1510152025SE +/- 0.02, N = 5SE +/- 0.00, N = 5SE +/- 0.01, N = 514.4018.3214.38-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm

TNN

Target: CPU - Model: SqueezeNet v1.1

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v1.1-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v160120180240300SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.25, N = 3205.80257.70205.28-march=armv8.4-a+sve - MIN: 205.46 / MAX: 206.28-march=armv8.4-a - MIN: 256.95 / MAX: 258.39-march=armv8.4-a+sve -mcpu=neoverse-v1 - MIN: 204.74 / MAX: 206.11. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

eSpeak-NG Speech Engine

Text-To-Speech Synthesis

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech Synthesis-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1816243240SE +/- 0.30, N = 20SE +/- 0.31, N = 16SE +/- 0.28, N = 2029.9836.5929.99-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -std=c99

Liquid-DSP

Threads: 32 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 32 - Buffer Length: 256 - Filter Length: 57-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1150M300M450M600M750MSE +/- 1978807.16, N = 3SE +/- 125476.87, N = 3SE +/- 16666.67, N = 3668636667705233333602443333-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 8 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v140M80M120M160M200MSE +/- 26666.67, N = 3SE +/- 12018.50, N = 3SE +/- 12018.50, N = 3167733333176363333150673333-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 16 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 16 - Buffer Length: 256 - Filter Length: 57-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v180M160M240M320M400MSE +/- 20275.88, N = 3SE +/- 30550.50, N = 3SE +/- 64291.01, N = 3335423333352700000301330000-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

TNN

Target: CPU - Model: DenseNet

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: DenseNet-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v16001200180024003000SE +/- 22.16, N = 3SE +/- 12.63, N = 3SE +/- 24.72, N = 32346.322730.402390.26-march=armv8.4-a+sve - MIN: 2268.4 / MAX: 2446.6-march=armv8.4-a - MIN: 2665.42 / MAX: 2834.73-march=armv8.4-a+sve -mcpu=neoverse-v1 - MIN: 2289.32 / MAX: 2501.921. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color Space-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v12004006008001000SE +/- 0.33, N = 3SE +/- 1.00, N = 3SE +/- 1.00, N = 310679781016-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -fopenmp -O3 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread

JPEG XL libjxl

Input: JPEG - Encode Speed: 7

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: JPEG - Encode Speed: 7-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v120406080100SE +/- 0.12, N = 3SE +/- 0.13, N = 3SE +/- 0.22, N = 379.5873.2178.80-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -funwind-tables -O2 -fPIE -pie

LuaJIT

Test: Fast Fourier Transform

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Fast Fourier Transform-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1140280420560700SE +/- 10.69, N = 3SE +/- 0.39, N = 3SE +/- 0.07, N = 3615.71661.55668.40-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

Botan

Test: KASUMI - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - Decrypt-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11530456075SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 362.2662.2867.511. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1246810SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.001, N = 37.4408.0547.446-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm

TNN

Target: CPU - Model: MobileNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: MobileNet v2-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v160120180240300SE +/- 0.69, N = 3SE +/- 0.10, N = 3SE +/- 0.24, N = 3280.24260.78273.40-march=armv8.4-a+sve - MIN: 277.9 / MAX: 282.31-march=armv8.4-a - MIN: 259.13 / MAX: 262.38-march=armv8.4-a+sve -mcpu=neoverse-v1 - MIN: 272.22 / MAX: 274.951. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 13Total Time-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v113M26M39M52M65MSE +/- 645132.01, N = 3SE +/- 721518.45, N = 14SE +/- 655325.68, N = 15558233405748568059966785-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -lgcov -lpthread -O3 -fno-exceptions -std=c++17 -pedantic -flto -fprofile-use -fno-peel-loops -fno-tracer -flto=jobserver

Ngspice

Circuit: C7552

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C7552-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v120406080100SE +/- 1.04, N = 3SE +/- 0.51, N = 3SE +/- 1.20, N = 3111.64103.93106.77-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

TNN

Target: CPU - Model: SqueezeNet v2

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.3Target: CPU - Model: SqueezeNet v2-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v120406080100SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 376.3071.1376.21-march=armv8.4-a+sve - MIN: 76.07 / MAX: 76.53-march=armv8.4-a - MIN: 70.76 / MAX: 71.58-march=armv8.4-a+sve -mcpu=neoverse-v1 - MIN: 75.89 / MAX: 76.521. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

Nettle

Test: poly1305-aes

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: poly1305-aes-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v12004006008001000SE +/- 5.37, N = 3SE +/- 1.52, N = 3SE +/- 0.05, N = 3820.51871.90859.93-march=armv8.4-a+sve -lgmp-march=armv8.4-a -lgmp-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -ggdb3 -lnettle -lm -lcrypto

AOM AV1

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11530456075SE +/- 0.22, N = 3SE +/- 0.47, N = 3SE +/- 0.29, N = 365.6261.8863.25-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Kripke

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v140M80M120M160M200MSE +/- 298633.53, N = 3SE +/- 226703.11, N = 3SE +/- 200700.56, N = 3192709233204143167194776367-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -fopenmp

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Rotate-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1130260390520650SE +/- 1.20, N = 3SE +/- 0.00, N = 3SE +/- 0.67, N = 3611577591-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -fopenmp -O3 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread

LuaJIT

Test: Dense LU Matrix Factorization

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Dense LU Matrix Factorization-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v18001600240032004000SE +/- 86.66, N = 3SE +/- 6.02, N = 3SE +/- 93.82, N = 33521.133355.533547.90-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

Botan

Test: KASUMI

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11530456075SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 362.0062.0265.291. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Rate-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v13691215SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 313.4412.8113.35-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -march=native -fopenmp

Botan

Test: Twofish - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - Decrypt-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v160120180240300SE +/- 0.11, N = 3SE +/- 0.20, N = 3SE +/- 0.06, N = 3258.15246.16246.611. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1200K400K600K800K1000KSE +/- 416.47, N = 3SE +/- 169.09, N = 3SE +/- 108.80, N = 3762066.50789646.92798137.71-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O2 -O3 -lrt" -lrt

Nettle

Test: sha512

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: sha512-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1110220330440550SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3504.33498.83481.90-march=armv8.4-a+sve -lgmp-march=armv8.4-a -lgmp-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -ggdb3 -lnettle -lm -lcrypto

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-Gaussian-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1110220330440550SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3515494509-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -fopenmp -O3 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread

Ngspice

Circuit: C2670

OpenBenchmarking.orgSeconds, Fewer Is BetterNgspice 34Circuit: C2670-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v120406080100SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3106.91102.56104.10-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lXft -lfontconfig -lXrender -lfreetype -lSM -lICE

JPEG XL libjxl

Input: JPEG - Encode Speed: 8

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: JPEG - Encode Speed: 8-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1612182430SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 327.3426.3027.09-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -funwind-tables -O2 -fPIE -pie

Caffe

Model: AlexNet - Acceleration: CPU - Iterations: 200

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: AlexNet - Acceleration: CPU - Iterations: 200-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v19K18K27K36K45KSE +/- 12.55, N = 3SE +/- 31.22, N = 3SE +/- 6.51, N = 3439314363442262-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -fPIC -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

Caffe

Model: GoogleNet - Acceleration: CPU - Iterations: 200

OpenBenchmarking.orgMilli-Seconds, Fewer Is BetterCaffe 2020-02-13Model: GoogleNet - Acceleration: CPU - Iterations: 200-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v130K60K90K120K150KSE +/- 105.70, N = 3SE +/- 49.72, N = 3SE +/- 69.18, N = 3125125123807120428-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -fPIC -rdynamic -lglog -lgflags -lprotobuf -lcrypto -lcurl -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Swirl-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v130060090012001500SE +/- 1.33, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3127212251257-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -fopenmp -O3 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread

Botan

Test: Twofish

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v150100150200250SE +/- 0.26, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 3248.89239.70244.211. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

OpenJPEG

Encode: NASA Curiosity Panorama M34

OpenBenchmarking.orgms, Fewer Is BetterOpenJPEG 2.4Encode: NASA Curiosity Panorama M34-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v112K24K36K48K60KSE +/- 89.48, N = 3SE +/- 19.06, N = 3SE +/- 7.80, N = 3551965720555415-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -rdynamic

JPEG XL libjxl

Input: PNG - Encode Speed: 7

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: PNG - Encode Speed: 7-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1246810SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 38.368.328.07-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -funwind-tables -O2 -fPIE -pie

AOM AV1

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1306090120150SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3123.95120.13124.22-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression Speed-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1918273645SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 340.340.039.0-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lz -llzma

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1510152025SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 320.2619.8519.61-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -pipe -O3 -ffast-math -R/usr/lib -lXpm -lSM -lICE -lX11 -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -lIlmThread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

ASTC Encoder

Preset: Medium

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: Medium-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11.09872.19743.29614.39485.4935SE +/- 0.0080, N = 3SE +/- 0.0125, N = 3SE +/- 0.0099, N = 34.80924.88334.7290-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -flto -pthread

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Resizing-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v15001000150020002500SE +/- 1.86, N = 3SE +/- 22.36, N = 3SE +/- 0.33, N = 3241423392402-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -fopenmp -O3 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Enhanced-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1160320480640800SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3718732741-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -fopenmp -O3 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny Analysis-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v150100150200250SE +/- 0.18, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3234.26237.54241.54-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -std=c99 -pedantic -lm

Stargate Digital Audio Workstation

Sample Rate: 44100 - Buffer Size: 1024

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 44100 - Buffer Size: 1024-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1246810SE +/- 0.002411, N = 3SE +/- 0.002515, N = 3SE +/- 0.002583, N = 36.5381636.3700356.3601381. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

AOM AV1

Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1306090120150SE +/- 0.20, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3156.71152.46156.63-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression Speed-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v17001400210028003500SE +/- 0.59, N = 3SE +/- 7.62, N = 3SE +/- 5.09, N = 33263.73250.93339.7-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lz -llzma

Zstd Compression

Compression Level: 19 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression Speed-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v17001400210028003500SE +/- 6.60, N = 3SE +/- 8.46, N = 3SE +/- 8.27, N = 33094.83083.43167.5-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lz -llzma

Stargate Digital Audio Workstation

Sample Rate: 480000 - Buffer Size: 1024

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 480000 - Buffer Size: 1024-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1246810SE +/- 0.002250, N = 3SE +/- 0.002118, N = 3SE +/- 0.001046, N = 36.4501826.3226846.2880061. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

Stargate Digital Audio Workstation

Sample Rate: 480000 - Buffer Size: 512

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 480000 - Buffer Size: 512-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1246810SE +/- 0.002030, N = 3SE +/- 0.001956, N = 3SE +/- 0.002132, N = 36.1244556.0053865.9816621. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

Stargate Digital Audio Workstation

Sample Rate: 44100 - Buffer Size: 512

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 44100 - Buffer Size: 512-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1246810SE +/- 0.003428, N = 3SE +/- 0.002564, N = 3SE +/- 0.002556, N = 36.2135006.0729166.0686501. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: Thorough-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v13691215SE +/- 0.0027, N = 3SE +/- 0.0046, N = 3SE +/- 0.0034, N = 39.01319.14358.9427-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -flto -pthread

LuaJIT

Test: Composite

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Composite-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v130060090012001500SE +/- 18.19, N = 3SE +/- 0.41, N = 3SE +/- 13.31, N = 61309.031282.591303.89-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: Exhaustive-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1816243240SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 335.1935.3634.68-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -flto -pthread

Botan

Test: Blowfish - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - Decrypt-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v160120180240300SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3289.03288.51283.411. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

LeelaChessZero

Backend: Eigen

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: Eigen-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v130060090012001500SE +/- 14.64, N = 5SE +/- 13.65, N = 3SE +/- 3.18, N = 3133313111337-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -flto -O3 -pthread

RNNoise

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v148121620SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 317.3917.6217.29-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pedantic -fvisibility=hidden

WebP Image Encode

Encode Settings: Quality 100, Lossless

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1612182430SE +/- 0.18, N = 3SE +/- 0.01, N = 3SE +/- 0.23, N = 323.4023.8523.85-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -fvisibility=hidden -O3 -lm -ljpeg -lpng16 -ltiff

AOM AV1

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v14080120160200SE +/- 0.20, N = 3SE +/- 0.28, N = 3SE +/- 0.17, N = 3193.68190.27193.55-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Google Draco

Model: Church Facade

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church Facade-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v12K4K6K8K10KSE +/- 7.00, N = 3SE +/- 6.64, N = 3SE +/- 26.24, N = 3784379357797-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 1024

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 96000 - Buffer Size: 1024-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11.08182.16363.24544.32725.409SE +/- 0.002826, N = 3SE +/- 0.000903, N = 3SE +/- 0.000548, N = 34.8077974.7298484.7297561. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

Zstd Compression

Compression Level: 3, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Decompression Speed-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v18001600240032004000SE +/- 1.28, N = 3SE +/- 3.95, N = 3SE +/- 40.64, N = 33824.83820.83882.3-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lz -llzma

Zstd Compression

Compression Level: 19 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression Speed-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11632486480SE +/- 0.03, N = 3SE +/- 0.23, N = 3SE +/- 0.09, N = 374.072.973.0-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lz -llzma

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin Protein-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1510152025SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 321.1521.3321.02-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -lm

Botan

Test: AES-256

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v112002400360048006000SE +/- 9.30, N = 3SE +/- 14.75, N = 3SE +/- 3.07, N = 35442.655494.315415.191. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 512

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 21.10.9Sample Rate: 96000 - Buffer Size: 512-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11.00682.01363.02044.02725.034SE +/- 0.002191, N = 3SE +/- 0.003502, N = 3SE +/- 0.001339, N = 34.4748484.4140554.4124871. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

WavPack Audio Encoding

WAV To WavPack

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPack-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1510152025SE +/- 0.03, N = 5SE +/- 0.00, N = 5SE +/- 0.03, N = 520.5220.4920.76-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -rdynamic

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1510152025SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 319.3019.3019.56-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -lm -lpthread -O3

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLAS-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v130060090012001500SE +/- 6.96, N = 3SE +/- 13.99, N = 5SE +/- 16.50, N = 3129712811280-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -flto -O3 -pthread

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GET-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1500K1000K1500K2000K2500KSE +/- 9056.40, N = 3SE +/- 1605.36, N = 3SE +/- 8325.87, N = 32513289.202523377.922546595.58-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Botan

Test: ChaCha20Poly1305 - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - Decrypt-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v180160240320400SE +/- 0.13, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3383.95382.51378.981. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

Zstd Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression Speed-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v115003000450060007500SE +/- 15.42, N = 3SE +/- 14.45, N = 3SE +/- 9.61, N = 37027.26937.86938.3-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lz -llzma

Botan

Test: ChaCha20Poly1305

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v180160240320400SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3390.31389.38385.381. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

Nettle

Test: chacha

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: chacha-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1160320480640800SE +/- 0.55, N = 3SE +/- 0.61, N = 3SE +/- 0.15, N = 3733.59740.25731.07-march=armv8.4-a+sve -lgmp - MIN: 442.26 / MAX: 956.22-march=armv8.4-a -lgmp - MIN: 454.21 / MAX: 956.53-march=armv8.4-a+sve -mcpu=neoverse-v1 - MIN: 446.51 / MAX: 951.281. (CC) gcc options: -O3 -ggdb3 -lnettle -lm -lcrypto

Botan

Test: AES-256 - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - Decrypt-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v112002400360048006000SE +/- 8.64, N = 3SE +/- 5.58, N = 3SE +/- 1.75, N = 35474.325477.575409.821. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.71e12 Prime Number Generation-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1246810SE +/- 0.043, N = 3SE +/- 0.022, N = 3SE +/- 0.022, N = 38.5338.4388.435-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3

ONNX Runtime

Model: GPT-2 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: Standard-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v13K6K9K12K15KSE +/- 12.91, N = 3SE +/- 63.90, N = 3SE +/- 10.09, N = 3123171236412460-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -flto -fno-fat-lto-objects -ldl -lrt

LuaJIT

Test: Sparse Matrix Multiply

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Sparse Matrix Multiply-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v130060090012001500SE +/- 7.20, N = 3SE +/- 3.14, N = 3SE +/- 7.84, N = 31162.331151.571164.28-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

Google Draco

Model: Lion

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Lion-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v111002200330044005500SE +/- 2.40, N = 3SE +/- 2.65, N = 3SE +/- 7.84, N = 3530953545297-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3

AOM AV1

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.3Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11428425670SE +/- 0.61, N = 3SE +/- 0.43, N = 3SE +/- 0.62, N = 662.1962.1361.56-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SET-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1400K800K1200K1600K2000KSE +/- 7427.93, N = 3SE +/- 794.78, N = 3SE +/- 1178.58, N = 31861924.131865840.131879962.00-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v112002400360048006000SE +/- 5.76, N = 3SE +/- 2.66, N = 3SE +/- 13.44, N = 35508.285561.565538.74-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3

OpenSSL

Algorithm: SHA256

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v16000M12000M18000M24000M30000MSE +/- 32102278.66, N = 3SE +/- 25639974.71, N = 3SE +/- 24491056.96, N = 3274281768802760394357027681290600-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

Botan

Test: Blowfish

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v160120180240300SE +/- 0.10, N = 3SE +/- 0.29, N = 3SE +/- 0.03, N = 3280.57278.87280.991. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.3WAV To FLAC-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1918273645SE +/- 0.01, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 538.5238.3138.60-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm

Xmrig

Variant: Wownero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1M-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v13K6K9K12K15KSE +/- 26.88, N = 3SE +/- 27.59, N = 3SE +/- 0.35, N = 311877.811811.211842.0-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -fexceptions -fno-rtti -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v111002200330044005500SE +/- 0.53, N = 3SE +/- 0.78, N = 3SE +/- 4.19, N = 35088.15090.55114.1-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

Botan

Test: CAST-256

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v120406080100SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3108.75108.79109.291. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

Botan

Test: CAST-256 - Decrypt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - Decrypt-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v120406080100SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3108.62108.60109.111. (CXX) g++ options: -fstack-protector -pthread -lbotan-2 -ldl -lrt

WebP Image Encode

Encode Settings: Quality 100, Highest Compression

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest Compression-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1246810SE +/- 0.017, N = 3SE +/- 0.006, N = 3SE +/- 0.006, N = 38.6408.6308.602-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -fvisibility=hidden -O3 -lm -ljpeg -lpng16 -ltiff

Xmrig

Variant: Monero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1M-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v12K4K6K8K10KSE +/- 6.18, N = 3SE +/- 9.56, N = 3SE +/- 3.15, N = 38669.88645.48681.4-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -fexceptions -fno-rtti -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

x264

Video Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2022-02-22Video Input: Bosphorus 1080p-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v14080120160200SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3169.58168.92169.301. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -lm -lpthread -O3 -flto

ONNX Runtime

Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v12004006008001000SE +/- 0.17, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3935938938-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -flto -fno-fat-lto-objects -ldl -lrt

x264

Video Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2022-02-22Video Input: Bosphorus 4K-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11122334455SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 348.5148.4348.561. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -lm -lpthread -O3 -flto

ONNX Runtime

Model: bertsquad-12 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: Standard-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1170340510680850SE +/- 0.50, N = 3SE +/- 0.44, N = 3SE +/- 0.44, N = 3772773774-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -flto -fno-fat-lto-objects -ldl -lrt

Nettle

Test: aes256

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.8Test: aes256-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v110002000300040005000SE +/- 0.39, N = 3SE +/- 3.11, N = 3SE +/- 0.72, N = 34447.044435.914438.27-march=armv8.4-a+sve -lgmp - MIN: 3925.11 / MAX: 5627.84-march=armv8.4-a -lgmp - MIN: 3927.32 / MAX: 5628.86-march=armv8.4-a+sve -mcpu=neoverse-v1 - MIN: 3923.68 / MAX: 5627.251. (CC) gcc options: -O3 -ggdb3 -lnettle -lm -lcrypto

AOBench

Size: 2048 x 2048 - Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total Time-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v1816243240SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 333.4933.4833.55-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -lm -O3

Zstd Compression

Compression Level: 3, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Compression Speed-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v130060090012001500SE +/- 4.88, N = 3SE +/- 5.37, N = 3SE +/- 4.22, N = 31242.71241.31243.8-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -pthread -lz -llzma

LuaJIT

Test: Monte Carlo

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Monte Carlo-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v170140210280350SE +/- 0.54, N = 3SE +/- 0.35, N = 3SE +/- 0.56, N = 3343.85343.27343.90-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2022.1Implementation: MPI CPU - Input: water_GMX50_bare-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v10.51281.02561.53842.05122.564SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 32.2752.2772.279-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3

LuaJIT

Test: Jacobi Successive Over-Relaxation

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Jacobi Successive Over-Relaxation-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v12004006008001000SE +/- 1.00, N = 3SE +/- 0.68, N = 3SE +/- 1.01, N = 3902.16901.02902.14-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v180K160K240K320K400KSE +/- 10.52, N = 3SE +/- 8.85, N = 3SE +/- 38.59, N = 3356407.8356359.6355966.7-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl

Smallpt

Global Illumination Renderer; 128 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 Samples-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v10.87661.75322.62983.50644.383SE +/- 0.003, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 33.8963.8953.892-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -fopenmp -O3

ONNX Runtime

Model: super-resolution-10 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: Standard-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v112002400360048006000SE +/- 2.17, N = 3SE +/- 0.93, N = 3SE +/- 0.67, N = 3541154135416-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -flto -fno-fat-lto-objects -ldl -lrt

GNU GMP GMPbench

Total Time

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.2.1Total Time-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v190018002700360045004155.64152.34152.7-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O3 -lm

Sysbench

Test: CPU

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPU-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v120K40K60K80K100KSE +/- 2.72, N = 3SE +/- 8.50, N = 3SE +/- 7.82, N = 396666.7696726.4096702.81-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CC) gcc options: -O2 -funroll-loops -O3 -rdynamic -ldl -laio -lm

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: Standard-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11632486480SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3737373-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -ffunction-sections -fdata-sections -march=native -mtune=native -flto -fno-fat-lto-objects -ldl -lrt

JPEG XL libjxl

Input: PNG - Encode Speed: 8

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.6.1Input: PNG - Encode Speed: 8-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v10.15080.30160.45240.60320.754SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.670.670.67-march=armv8.4-a+sve-march=armv8.4-a-march=armv8.4-a+sve -mcpu=neoverse-v11. (CXX) g++ options: -O3 -funwind-tables -O2 -fPIE -pie

Phoronix Test Suite v10.8.5