NVIDIA AMD OpenCL Linux GPGPU Tests

Benchmarks by Michael Larabel for a future article on Phoronix. Just looking at a range of OpenBenchmarking.org OpenCL benchmarks on a range of AMD Radeon and NVIDIA GeForce graphics cards with the proprietary drivers under Ubuntu Linux.

HTML result view exported from: https://openbenchmarking.org/result/1401213-PL-1311092SO60&grw&rdt&rro.

NVIDIA AMD OpenCL Linux GPGPU TestsProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionGeForce GTX 680GeForce GTX 550 TiGeForce GTX 650GeForce GTX 460GeForce GT 610GeForce GT 240Radeon HD 6870Radeon HD 7850Radeon HD 7950Radeon R9 270XGeForce GTX 470AMD FX-8350 Eight-Core @ 4.00GHz (8 Cores)ASUS Crosshair V FormulaAMD RD890 bridge8192MB64GB OCZ AGILITYNVIDIA GeForce GTX 680 2048MB (705/3004MHz)Realtek ALC889Intel 82583V Gigabit ConnectionUbuntu 13.103.11.0-12-generic (x86_64)Unity 7.1.2X Server 1.14.3NVIDIA 331.204.3.0GCC 4.8ext42560x1600eVGA NVIDIA GeForce GTX 550 Ti 1024MB (951/2178MHz)MSI NVIDIA GeForce GTX 650 1024MB (1084/2500MHz)ASUS NVIDIA GeForce GTX 460 768MB (675/1800MHz)NVIDIA GeForce GT 610 1024MB (810/533MHz)ECS NVIDIA GeForce GT 240 512MB (550/1700MHz)3.3.0Sapphire AMD Radeon HD 6800 1024MB (900/1050MHz)SyncMaster + SyncMasterfglrx 13.25.54.3.12614ASUS AMD Radeon HD 7800 1024MB (860/1200MHz)XFX AMD Radeon HD 7900 3072MB (900/1375MHz)Gigabyte AMD Radeon R9 200 2048MB (1100/1400MHz)AMD Phenom II X4 955 @ 3.20GHz (4 Cores)Gigabyte GA-MA790X-UD3P12288MB2 x 1000GB SAMSUNG HD103UJ + 2000GB Hitachi HDS5C302 + 500GB SAMSUNG HD501LJ + 2000GB HDS5C3020ALA632NVIDIA GeForce GTX 470 /3DNOW! 1280MB (656/1701MHz)Philips 230WGentoo Base 2.23.7.6-gentoo-k8-31 (i686)KDE 4.10.5NVIDIA 331.204.4.0 NVIDIA 331.20GCC 4.6.3 + LLVM 3.11920x1200OpenBenchmarking.orgCompiler Details- GeForce GTX 680, GeForce GTX 550 Ti, GeForce GTX 650, GeForce GTX 460, GeForce GT 610, GeForce GT 240, Radeon HD 6870, Radeon HD 7850, Radeon HD 7950, Radeon R9 270X: --build=x86_64-linux-gnu --disable-browser-plugin --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-4.8-amd64/jre --with-jvm-jar-dir=/usr/lib/jvm-exports/java-1.5.0-gcj-4.8-amd64 --with-jvm-root-dir=/usr/lib/jvm/java-1.5.0-gcj-4.8-amd64 --with-multilib-list=m32,m64,mx32 --with-tune=generic -vProcessor Details- Scaling Governor: acpi-cpufreq ondemandOpenCL Details- GeForce GTX 680: GPU Compute Cores: 1536- GeForce GTX 550 Ti: GPU Compute Cores: 192- GeForce GTX 650: GPU Compute Cores: 384- GeForce GTX 460: GPU Compute Cores: 336- GeForce GT 610: GPU Compute Cores: 48- GeForce GT 240: GPU Compute Cores: 96- GeForce GTX 470: GPU Compute Cores: 448System Details- GeForce GTX 680: GPU Compute Cores: 1536.- GeForce GTX 550 Ti: GPU Compute Cores: 192.- GeForce GTX 650: GPU Compute Cores: 384.- GeForce GTX 460: GPU Compute Cores: 336.- GeForce GT 610: GPU Compute Cores: 48.- GeForce GT 240: GPU Compute Cores: 96.- GeForce GTX 470: GPU Compute Cores: 448.Environment Details- Radeon HD 6870, Radeon HD 7850, Radeon HD 7950, Radeon R9 270X: LIBGL_DRIVERS_PATH=/usr/lib/i386-linux-gnu/dri:/usr/lib/x86_64-linux-gnu/dri

NVIDIA AMD OpenCL Linux GPGPU Testsrodinia: OpenCL LavaMDrodinia: OpenCL Myocyterodinia: OpenCL Heartwallrodinia: OpenCL Leukocyterodinia: OpenCL Particle Filtermandelgpu: GPUjuliagpu: GPUluxmark: GPU - Roomluxmark: GPU - Salaluxmark: GPU - Luxball HDRmandelbulbgpu: GPUopendwarfs: LU Decompositionopendwarfs: Compressed Sparse RowGeForce GTX 680GeForce GTX 550 TiGeForce GTX 650GeForce GTX 460GeForce GT 610GeForce GT 240Radeon HD 6870Radeon HD 7850Radeon HD 7950Radeon R9 270XGeForce GTX 4709.2660.785.4214.0218.1947966936.6736123507.37296651421617083392.3358.946.105.4927.7044.3517362190.0717540483.9715031921627729296.07110.816.5520.1430.3966.4812405397.7010841150.338217711834992671.83152.706.7662.814.8024.6635.9621375259.4021199859.5038225919382926.1797.696.4095.8822.72100.3115.283715320.134060660.0727423151776400.70458.269.00137.9036.9940.495291547.0013543191.9010517095143.77220.276.88493.5119.6789.871076316149161.4224.507.66508.496.7989.1518.1162411348361135.7918.095.79481.625.8883.8310.781002189613087123.9617.836.17485.325.4084.6613.01867158811031126.6016.2580.583.7517.4628658784.4029347833.2014828161.27OpenBenchmarking.org

Rodinia

Test: OpenCL LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL LavaMDRadeon R9 270XRadeon HD 7950Radeon HD 7850GeForce GTX 6803691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 66.175.797.669.261. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenCL Myocyte

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL MyocyteGeForce GTX 470Radeon R9 270XRadeon HD 7950Radeon HD 7850Radeon HD 6870GeForce GT 240GeForce GT 610GeForce GTX 460GeForce GTX 680110220330440550SE +/- 1.37, N = 6SE +/- 0.67, N = 3SE +/- 0.84, N = 3SE +/- 0.96, N = 3SE +/- 1.88, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 1.14, N = 380.58485.32481.62508.49493.51137.9095.8862.8160.781. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenCL Heartwall

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL HeartwallGeForce GTX 470Radeon R9 270XRadeon HD 7950Radeon HD 7850Radeon HD 6870GeForce GT 240GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 680918273645SE +/- 0.26, N = 6SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 3SE +/- 0.28, N = 3SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 6SE +/- 0.09, N = 63.755.405.886.7919.6736.9922.724.8020.145.495.421. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenCL Leukocyte

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL LeukocyteRadeon R9 270XRadeon HD 7950Radeon HD 7850Radeon HD 6870GeForce GT 240GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 68020406080100SE +/- 6.06, N = 6SE +/- 4.92, N = 6SE +/- 5.05, N = 6SE +/- 3.37, N = 6SE +/- 0.75, N = 3SE +/- 1.23, N = 3SE +/- 0.30, N = 3SE +/- 0.26, N = 3SE +/- 0.48, N = 4SE +/- 0.24, N = 484.6683.8389.1589.8740.49100.3124.6630.3927.7014.021. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenCL Particle Filter

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL Particle FilterGeForce GTX 470Radeon R9 270XRadeon HD 7950Radeon HD 7850GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 6801530456075SE +/- 0.23, N = 6SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.57, N = 6SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.24, N = 3SE +/- 0.17, N = 317.4613.0110.7818.1115.2835.9666.4844.3518.191. (CXX) g++ options: -O2 -lOpenCL

MandelGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPUGeForce GTX 470GeForce GT 240GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 68010M20M30M40M50MSE +/- 4541.93, N = 3SE +/- 217.94, N = 3SE +/- 230.98, N = 3SE +/- 2448.11, N = 3SE +/- 857.65, N = 3SE +/- 6289.55, N = 3SE +/- 5781.86, N = 328658784.405291547.003715320.1321375259.4012405397.7017362190.0747966936.671. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

JuliaGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterJuliaGPU 1.2pts1OpenCL Device: GPUGeForce GTX 470GeForce GT 240GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 6808M16M24M32M40MSE +/- 120737.03, N = 3SE +/- 17817.43, N = 3SE +/- 2505.78, N = 3SE +/- 4955.24, N = 3SE +/- 2871.63, N = 3SE +/- 13067.53, N = 3SE +/- 72150.98, N = 329347833.2013543191.904060660.0721199859.5010841150.3317540483.9736123507.371. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

LuxMark

OpenCL Device: GPU - Scene: Room

OpenBenchmarking.orgScore, More Is BetterLuxMark 2.1beta1OpenCL Device: GPU - Scene: RoomRadeon R9 270XRadeon HD 7950Radeon HD 7850Radeon HD 6870GeForce GT 610GeForce GTX 650GeForce GTX 550 TiGeForce GTX 6802004006008001000SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 386710026241072782150296

LuxMark

OpenCL Device: GPU - Scene: Sala

OpenBenchmarking.orgScore, More Is BetterLuxMark 2.1beta1OpenCL Device: GPU - Scene: SalaRadeon R9 270XRadeon HD 7950Radeon HD 7850Radeon HD 6870GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 680400800120016002000SE +/- 0.00, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 315881896113463142382177319651

LuxMark

OpenCL Device: GPU - Scene: Luxball HDR

OpenBenchmarking.orgScore, More Is BetterLuxMark 2.1beta1OpenCL Device: GPU - Scene: Luxball HDRRadeon R9 270XRadeon HD 7950Radeon HD 7850Radeon HD 6870GeForce GT 240GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 6803K6K9K12K15KSE +/- 3.61, N = 3SE +/- 4.84, N = 3SE +/- 1.45, N = 3SE +/- 0.88, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.67, N = 311031130878361614910513152591118321624216

MandelbulbGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterMandelbulbGPU 1.0pts1OpenCL Device: GPUGeForce GTX 470GeForce GT 240GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 6804M8M12M16M20MSE +/- 58117.66, N = 3SE +/- 3953.96, N = 3SE +/- 614.61, N = 3SE +/- 10640.98, N = 3SE +/- 4281.68, N = 3SE +/- 4259.44, N = 3SE +/- 72849.89, N = 314828161.277095143.771776400.709382926.174992671.837729296.0717083392.331. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

OpenDwarfs

Test: LU Decomposition

OpenBenchmarking.orgms, Fewer Is BetterOpenDwarfs 2013-11-06Test: LU DecompositionRadeon R9 270XRadeon HD 7950Radeon HD 7850Radeon HD 6870GeForce GT 240GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 680100200300400500SE +/- 4.83, N = 6SE +/- 4.65, N = 6SE +/- 5.24, N = 6SE +/- 4.12, N = 6SE +/- 1.06, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.21, N = 3SE +/- 0.14, N = 3SE +/- 0.88, N = 5126.60123.96135.79161.42220.27458.2697.69152.70110.8158.941. (CC) gcc options: -lm -lOpenCL

OpenDwarfs

Test: Compressed Sparse Row

OpenBenchmarking.orgms, Fewer Is BetterOpenDwarfs 2013-11-06Test: Compressed Sparse RowRadeon R9 270XRadeon HD 7950Radeon HD 7850Radeon HD 6870GeForce GT 240GeForce GT 610GeForce GTX 460GeForce GTX 650GeForce GTX 550 TiGeForce GTX 680612182430SE +/- 0.89, N = 6SE +/- 0.86, N = 6SE +/- 0.50, N = 6SE +/- 0.81, N = 6SE +/- 0.11, N = 3SE +/- 0.56, N = 6SE +/- 0.76, N = 6SE +/- 0.57, N = 6SE +/- 0.80, N = 6SE +/- 0.58, N = 616.2517.8318.0924.506.889.006.406.766.556.101. (CC) gcc options: -lm -lOpenCL


Phoronix Test Suite v10.8.5