Xavier Carmel CPU Core Compiler Tests

NVIDIA Jetson Xavier ARMv8 compiler benchmarks on GCC and LLVM Clang for a future article on Phoronix.

HTML result view exported from: https://openbenchmarking.org/result/1901055-SP-XAVIERCAR07&grs&rdt.

Xavier Carmel CPU Core Compiler TestsProcessorMotherboardMemoryDiskGraphicsOSKernelDesktopDisplay ServerDisplay DriverVulkanCompilerFile-SystemScreen ResolutionGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.1ARMv8 rev 0 @ 2.27GHz (8 Cores)jetson-xavier16384MB31GB HBG4a2NVIDIA TEGRAUbuntu 18.044.9.108-tegra (aarch64)Unity 7.5.0X Server 1.19.6NVIDIA 1.0.01.1.76GCC 7.3.0 + CUDA 10.0ext41920x2160Clang 6.0.0-1ubuntu2 + CUDA 10.0GCC 8.2.0 + clang (GCC) 8.2.0 + CUDA 10.0GCC 9.0.0 20181230 + clang (GCC) 9.0.0 20181230 (experimental) + CUDA 10.0Clang 8.0.0 (SVN 350356) + LLVM 8.0.0svn + CUDA 10.0Clang 7.0.1 + LLVM 7.0.1 + CUDA 10.0OpenBenchmarking.orgCompiler Details- GCC 7.3.0: --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++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --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 -v - GCC 8.2.0: --enable-checking=release- GCC 9.0.0: --enable-checking=release- Clang 8.0 SVN: Optimized build; Default target: aarch64-unknown-linux-gnu; Host CPU: (unknown)- Clang 7.0.1: Optimized build; Default target: aarch64-unknown-linux-gnu; Host CPU: (unknown)Processor Details- Scaling Governor: tegra_cpufreq schedutil

Xavier Carmel CPU Core Compiler Testsencode-mp3: WAV To MP3scimark2: Sparse Matrix Multiplyscimark2: Dense LU Matrix Factorizationscimark2: Monte Carloscimark2: Jacobi Successive Over-Relaxationscimark2: Compositescimark2: Fast Fourier Transformredis: LPOPredis: LPUSHredis: GETredis: SETc-ray: Total Time - 4K, 16 Rays Per Pixelredis: SADDencode-flac: WAV To FLACbullet: 1000 Convexbullet: Raytestsbullet: Convex Trimeshbullet: 1000 Stackbullet: Prim Trimeshapache: Static Web Page Servingasmfish: 1024 Hash Memory, 26 Depthbuild-linux-kernel: Time To Compilehimeno: Poisson Pressure Solverbuild-php: Time To Compilebullet: 136 Ragdollsbullet: 3000 Fallprimesieve: 1e12 Prime Number Generationcompress-7zip: Compress Speed Testttsiod-renderer: Phong Rendering With Soft-Shadow MappingGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.131.83620962217879572183110527070523297350075655025889906657.279.955.532.3212.862.121078282950448312692767.3012.681061813914618.865468402149355401631254672744500113849381637740892393054.61107418305398265319106137160.36565966197879554164417642254896391000274012469310886152.9026.9613.925.5225.013.8562187195166131224840912.9319.2313420239127139.8611815147.4524512669.79377319239389363700274302451303100140.1225.5013.025.0422.163.356009499190096336811.4717.13865153.2678.1819834.3014810252.86372959237439366870262650796299731166.906061504698027035513749.8678.1119734.3314810252.89377274234910366301268782796302329166.5260405083834281337144OpenBenchmarking.org

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3GCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.14080120160200SE +/- 0.22, N = 3SE +/- 0.06, N = 3SE +/- 0.81, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 331.8318.86160.36139.8653.2649.86-O3 -pipe-O3 -pipe-O3 -pipe1. (CC) gcc options: -lm

SciMark

Computational Test: Sparse Matrix Multiply

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix MultiplyGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.1130260390520650SE +/- 10.12, N = 3SE +/- 0.18, N = 3SE +/- 1.06, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3620.00546.00565.00118.0078.1878.111. (CC) gcc options: -lm

SciMark

Computational Test: Dense LU Matrix Factorization

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix FactorizationGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.12004006008001000SE +/- 2.27, N = 3SE +/- 1.97, N = 3SE +/- 4.72, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 39628409661511981971. (CC) gcc options: -lm

SciMark

Computational Test: Monte Carlo

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte CarloGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.150100150200250SE +/- 5.39, N = 3SE +/- 0.65, N = 3SE +/- 0.68, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3217.00214.00197.0047.4534.3034.331. (CC) gcc options: -lm

SciMark

Computational Test: Jacobi Successive Over-Relaxation

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-RelaxationGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.12004006008001000SE +/- 1.25, N = 3SE +/- 1.40, N = 3SE +/- 1.42, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 38799358792451481481. (CC) gcc options: -lm

SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.1120240360480600SE +/- 3.05, N = 3SE +/- 1.05, N = 3SE +/- 0.74, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 35725405541261021021. (CC) gcc options: -lm

SciMark

Computational Test: Fast Fourier Transform

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier TransformGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.14080120160200SE +/- 1.66, N = 3SE +/- 1.69, N = 3SE +/- 1.17, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.17, N = 3183.00163.00164.0069.7952.8652.891. (CC) gcc options: -lm

Redis

Test: LPOP

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPOPGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.1300K600K900K1200K1500KSE +/- 19718.57, N = 3SE +/- 25123.07, N = 3SE +/- 3139.15, N = 3SE +/- 1253.32, N = 3SE +/- 4358.43, N = 3SE +/- 4473.18, N = 3110527012546724176423773193729593772741. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: LPUSH

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPUSHGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.1160K320K480K640K800KSE +/- 7980.16, N = 3SE +/- 10043.38, N = 3SE +/- 1181.72, N = 3SE +/- 514.78, N = 3SE +/- 622.41, N = 3SE +/- 1581.62, N = 37052327445002548962393892374392349101. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: GETGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.1200K400K600K800K1000KSE +/- 14230.07, N = 3SE +/- 21615.34, N = 3SE +/- 1882.65, N = 3SE +/- 4402.98, N = 3SE +/- 2409.99, N = 3SE +/- 5813.65, N = 497350011384933910003637003668703663011. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SETGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.1200K400K600K800K1000KSE +/- 13045.74, N = 4SE +/- 14106.11, N = 3SE +/- 3860.69, N = 6SE +/- 749.65, N = 3SE +/- 1710.87, N = 3SE +/- 1314.35, N = 37565508163772740122743022626502687821. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.12004006008001000SE +/- 15.86, N = 9SE +/- 9.68, N = 9SE +/- 0.29, N = 3SE +/- 0.12, N = 3SE +/- 0.21, N = 3SE +/- 0.24, N = 32584084694517967961. (CC) gcc options: -lm -lpthread -O3

Redis

Test: SADD

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SADDGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.1200K400K600K800K1000KSE +/- 12029.26, N = 3SE +/- 12868.83, N = 5SE +/- 2388.40, N = 3SE +/- 2439.85, N = 3SE +/- 333.80, N = 3SE +/- 410.29, N = 38990669239303108863031002997313023291. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.14080120160200SE +/- 0.26, N = 5SE +/- 0.39, N = 5SE +/- 0.12, N = 5SE +/- 0.30, N = 5SE +/- 0.29, N = 5SE +/- 0.28, N = 557.2754.61152.90140.12166.90166.52-fvisibility=hidden-fvisibility=hidden-fvisibility=hidden1. (CXX) g++ options: -O2 -logg -lm

Bullet Physics Engine

Test: 1000 Convex

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 ConvexGCC 7.3.0GCC 8.2.0GCC 9.0.0612182430SE +/- 0.13, N = 3SE +/- 0.31, N = 3SE +/- 0.01, N = 39.9526.9625.50-lglut -lGL -lGLU-lglut -lGL -lGLU1. (CXX) g++ options: -O3 -rdynamic

Bullet Physics Engine

Test: Raytests

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: RaytestsGCC 7.3.0GCC 8.2.0GCC 9.0.048121620SE +/- 0.07, N = 8SE +/- 0.07, N = 3SE +/- 0.00, N = 35.5313.9213.02-lglut -lGL -lGLU-lglut -lGL -lGLU1. (CXX) g++ options: -O3 -rdynamic

Bullet Physics Engine

Test: Convex Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex TrimeshGCC 7.3.0GCC 8.2.0GCC 9.0.01.2422.4843.7264.9686.21SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 32.325.525.04-lglut -lGL -lGLU-lglut -lGL -lGLU1. (CXX) g++ options: -O3 -rdynamic

Bullet Physics Engine

Test: 1000 Stack

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 StackGCC 7.3.0GCC 8.2.0GCC 9.0.0612182430SE +/- 0.39, N = 3SE +/- 0.31, N = 3SE +/- 0.03, N = 312.8625.0122.16-lglut -lGL -lGLU-lglut -lGL -lGLU1. (CXX) g++ options: -O3 -rdynamic

Bullet Physics Engine

Test: Prim Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim TrimeshGCC 7.3.0GCC 8.2.0GCC 9.0.00.86631.73262.59893.46524.3315SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 32.123.853.35-lglut -lGL -lGLU-lglut -lGL -lGLU1. (CXX) g++ options: -O3 -rdynamic

Apache Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page ServingGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.12K4K6K8K10KSE +/- 46.91, N = 3SE +/- 79.09, N = 3SE +/- 18.16, N = 3SE +/- 26.79, N = 3SE +/- 13.10, N = 3SE +/- 12.48, N = 3107821074162186009606160401. (CC) gcc options: -shared -fPIC -O2 -pthread

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.12M4M6M8M10MSE +/- 52344.77, N = 3SE +/- 140386.45, N = 3SE +/- 146948.80, N = 9SE +/- 36548.95, N = 3SE +/- 37685.79, N = 3SE +/- 36318.07, N = 3829504483053987195166499190050469805083834

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To CompileGCC 7.3.0GCC 8.2.0GCC 9.0.030060090012001500SE +/- 4.78, N = 3SE +/- 10.52, N = 3SE +/- 4.39, N = 38311312963

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverGCC 7.3.0Clang 6.0GCC 8.2.0GCC 9.0.0Clang 8.0 SVNClang 7.0.180160240320400SE +/- 4.23, N = 3SE +/- 0.99, N = 3SE +/- 3.17, N = 7SE +/- 0.28, N = 3SE +/- 0.20, N = 3SE +/- 1.87, N = 32692652483682702811. (CC) gcc options: -O3

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To CompileGCC 7.3.0Clang 6.0GCC 8.2.0Clang 8.0 SVNClang 7.0.190180270360450SE +/- 0.49, N = 3SE +/- 4.66, N = 3SE +/- 0.74, N = 3SE +/- 0.95, N = 3SE +/- 0.35, N = 3276319409355337

Bullet Physics Engine

Test: 136 Ragdolls

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 RagdollsGCC 7.3.0GCC 8.2.0GCC 9.0.03691215SE +/- 0.33, N = 3SE +/- 0.19, N = 3SE +/- 0.02, N = 37.3012.9311.47-lglut -lGL -lGLU-lglut -lGL -lGLU1. (CXX) g++ options: -O3 -rdynamic

Bullet Physics Engine

Test: 3000 Fall

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 FallGCC 7.3.0GCC 8.2.0GCC 9.0.0510152025SE +/- 1.11, N = 3SE +/- 0.17, N = 3SE +/- 0.05, N = 312.6819.2317.13-lglut -lGL -lGLU-lglut -lGL -lGLU1. (CXX) g++ options: -O3 -rdynamic

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.21e12 Prime Number GenerationGCC 7.3.0Clang 6.0GCC 8.2.0Clang 8.0 SVNClang 7.0.1306090120150SE +/- 2.56, N = 12SE +/- 1.17, N = 12SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 31061061341371441. (CXX) g++ options: -O3 -lpthread

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestGCC 7.3.0GCC 8.2.0GCC 9.0.04K8K12K16K20KSE +/- 479.86, N = 12SE +/- 203.21, N = 12SE +/- 10.27, N = 3181392023986511. (CXX) g++ options: -pipe -lpthread

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingGCC 7.3.0Clang 6.0GCC 8.2.0306090120150SE +/- 2.80, N = 3SE +/- 1.58, N = 3SE +/- 2.94, N = 12146137127-mtune=native-ltbb-mtune=native1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -flto -lSDL -fopenmp -fwhole-program -lstdc++

Phoronix Test Suite v10.8.4