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&grs&sor.

NVIDIA AMD OpenCL Linux GPGPU TestsProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionGeForce GT 240GeForce GTX 460GeForce GTX 550 TiGeForce GT 610GeForce GTX 650GeForce GTX 680Radeon 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 AGILITYECS NVIDIA GeForce GT 240 512MB (550/1700MHz)Realtek ALC889Intel 82583V Gigabit ConnectionUbuntu 13.103.11.0-12-generic (x86_64)Unity 7.1.2X Server 1.14.3NVIDIA 331.203.3.0GCC 4.8ext42560x1600ASUS NVIDIA GeForce GTX 460 768MB (675/1800MHz)4.3.0eVGA NVIDIA GeForce GTX 550 Ti 1024MB (951/2178MHz)NVIDIA GeForce GT 610 1024MB (810/533MHz)MSI NVIDIA GeForce GTX 650 1024MB (1084/2500MHz)NVIDIA GeForce GTX 680 2048MB (705/3004MHz)Sapphire 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 GT 240, GeForce GTX 460, GeForce GTX 550 Ti, GeForce GT 610, GeForce GTX 650, GeForce GTX 680, 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 GT 240: GPU Compute Cores: 96- GeForce GTX 460: GPU Compute Cores: 336- GeForce GTX 550 Ti: GPU Compute Cores: 192- GeForce GT 610: GPU Compute Cores: 48- GeForce GTX 650: GPU Compute Cores: 384- GeForce GTX 680: GPU Compute Cores: 1536- GeForce GTX 470: GPU Compute Cores: 448System Details- GeForce GT 240: GPU Compute Cores: 96.- GeForce GTX 460: GPU Compute Cores: 336.- GeForce GTX 550 Ti: GPU Compute Cores: 192.- GeForce GT 610: GPU Compute Cores: 48.- GeForce GTX 650: GPU Compute Cores: 384.- GeForce GTX 680: GPU Compute Cores: 1536.- 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 Heartwallmandelbulbgpu: GPUjuliagpu: GPUrodinia: OpenCL Myocyterodinia: OpenCL Particle Filterluxmark: GPU - Salaluxmark: GPU - Luxball HDRluxmark: GPU - Roommandelgpu: GPUrodinia: OpenCL LavaMDopendwarfs: Compressed Sparse Rowopendwarfs: LU Decompositionrodinia: OpenCL LeukocyteGeForce GT 240GeForce GTX 460GeForce GTX 550 TiGeForce GT 610GeForce GTX 650GeForce GTX 680Radeon HD 6870Radeon HD 7850Radeon HD 7950Radeon R9 270XGeForce GTX 47036.997095143.7713543191.90137.9010515291547.006.88220.2740.494.809382926.1721199859.5062.8135.96382259121375259.406.4097.6924.665.497729296.0717540483.9744.35319216215017362190.076.55110.8127.7022.721776400.704060660.0795.8815.2842315273715320.139.00458.26100.3120.144992671.8310841150.3366.4817711838212405397.706.76152.7030.395.4217083392.3336123507.3760.7818.19651421629647966936.679.266.1058.9414.0219.67493.51631614910724.50161.4289.876.79508.4918.11113483616247.6618.09135.7989.155.88481.6210.7818961308710025.7917.83123.9683.835.40485.3213.011588110318676.1716.25126.6084.663.7514828161.2729347833.2080.5817.4628658784.40OpenBenchmarking.org

Rodinia

Test: OpenCL Heartwall

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL HeartwallGeForce GTX 470GeForce GTX 460Radeon R9 270XGeForce GTX 680GeForce GTX 550 TiRadeon HD 7950Radeon HD 7850Radeon HD 6870GeForce GTX 650GeForce GT 610GeForce GT 240918273645SE +/- 0.26, N = 6SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 6SE +/- 0.13, N = 6SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.28, N = 33.754.805.405.425.495.886.7919.6720.1422.7236.991. (CXX) g++ options: -O2 -lOpenCL

MandelbulbGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterMandelbulbGPU 1.0pts1OpenCL Device: GPUGeForce GTX 680GeForce GTX 470GeForce GTX 460GeForce GTX 550 TiGeForce GT 240GeForce GTX 650GeForce GT 6104M8M12M16M20MSE +/- 72849.89, N = 3SE +/- 58117.66, N = 3SE +/- 10640.98, N = 3SE +/- 4259.44, N = 3SE +/- 3953.96, N = 3SE +/- 4281.68, N = 3SE +/- 614.61, N = 317083392.3314828161.279382926.177729296.077095143.774992671.831776400.701. (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 680GeForce GTX 470GeForce GTX 460GeForce GTX 550 TiGeForce GT 240GeForce GTX 650GeForce GT 6108M16M24M32M40MSE +/- 72150.98, N = 3SE +/- 120737.03, N = 3SE +/- 4955.24, N = 3SE +/- 13067.53, N = 3SE +/- 17817.43, N = 3SE +/- 2871.63, N = 3SE +/- 2505.78, N = 336123507.3729347833.2021199859.5017540483.9713543191.9010841150.334060660.071. (CC) gcc options: -O3 -march=native -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL -lm

Rodinia

Test: OpenCL Myocyte

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL MyocyteGeForce GTX 680GeForce GTX 460GeForce GTX 470GeForce GT 610GeForce GT 240Radeon HD 7950Radeon R9 270XRadeon HD 6870Radeon HD 7850110220330440550SE +/- 1.14, N = 3SE +/- 0.07, N = 3SE +/- 1.37, N = 6SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.84, N = 3SE +/- 0.67, N = 3SE +/- 1.88, N = 3SE +/- 0.96, N = 360.7862.8180.5895.88137.90481.62485.32493.51508.491. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenCL Particle Filter

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL Particle FilterRadeon HD 7950Radeon R9 270XGeForce GT 610GeForce GTX 470Radeon HD 7850GeForce GTX 680GeForce GTX 460GeForce GTX 550 TiGeForce GTX 6501530456075SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.57, N = 6SE +/- 0.23, N = 6SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 0.24, N = 3SE +/- 0.07, N = 310.7813.0115.2817.4618.1118.1935.9644.3566.481. (CXX) g++ options: -O2 -lOpenCL

LuxMark

OpenCL Device: GPU - Scene: Sala

OpenBenchmarking.orgScore, More Is BetterLuxMark 2.1beta1OpenCL Device: GPU - Scene: SalaRadeon HD 7950Radeon R9 270XRadeon HD 7850GeForce GTX 680Radeon HD 6870GeForce GTX 460GeForce GTX 550 TiGeForce GTX 650GeForce GT 610400800120016002000SE +/- 0.67, N = 3SE +/- 0.00, 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 = 318961588113465163138231917742

LuxMark

OpenCL Device: GPU - Scene: Luxball HDR

OpenBenchmarking.orgScore, More Is BetterLuxMark 2.1beta1OpenCL Device: GPU - Scene: Luxball HDRRadeon HD 7950Radeon R9 270XRadeon HD 7850Radeon HD 6870GeForce GTX 680GeForce GTX 460GeForce GTX 550 TiGeForce GTX 650GeForce GT 240GeForce GT 6103K6K9K12K15KSE +/- 4.84, N = 3SE +/- 3.61, N = 3SE +/- 1.45, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 313087110318361614942162591216211831051315

LuxMark

OpenCL Device: GPU - Scene: Room

OpenBenchmarking.orgScore, More Is BetterLuxMark 2.1beta1OpenCL Device: GPU - Scene: RoomRadeon HD 7950Radeon R9 270XRadeon HD 7850GeForce GTX 680GeForce GTX 550 TiRadeon HD 6870GeForce GTX 650GeForce GT 6102004006008001000SE +/- 0.58, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 310028676242961501078227

MandelGPU

OpenCL Device: GPU

OpenBenchmarking.orgSamples/sec, More Is BetterMandelGPU 1.3pts1OpenCL Device: GPUGeForce GTX 680GeForce GTX 470GeForce GTX 460GeForce GTX 550 TiGeForce GTX 650GeForce GT 240GeForce GT 61010M20M30M40M50MSE +/- 5781.86, N = 3SE +/- 4541.93, N = 3SE +/- 2448.11, N = 3SE +/- 6289.55, N = 3SE +/- 857.65, N = 3SE +/- 217.94, N = 3SE +/- 230.98, N = 347966936.6728658784.4021375259.4017362190.0712405397.705291547.003715320.131. (CC) gcc options: -O3 -lm -ftree-vectorize -funroll-loops -lglut -lOpenCL -lGL

Rodinia

Test: OpenCL LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL LavaMDRadeon HD 7950Radeon R9 270XRadeon HD 7850GeForce GTX 6803691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 65.796.177.669.261. (CXX) g++ options: -O2 -lOpenCL

OpenDwarfs

Test: Compressed Sparse Row

OpenBenchmarking.orgms, Fewer Is BetterOpenDwarfs 2013-11-06Test: Compressed Sparse RowGeForce GTX 680GeForce GTX 460GeForce GTX 550 TiGeForce GTX 650GeForce GT 240GeForce GT 610Radeon R9 270XRadeon HD 7950Radeon HD 7850Radeon HD 6870612182430SE +/- 0.58, N = 6SE +/- 0.76, N = 6SE +/- 0.80, N = 6SE +/- 0.57, N = 6SE +/- 0.11, N = 3SE +/- 0.56, N = 6SE +/- 0.89, N = 6SE +/- 0.86, N = 6SE +/- 0.50, N = 6SE +/- 0.81, N = 66.106.406.556.766.889.0016.2517.8318.0924.501. (CC) gcc options: -lm -lOpenCL

OpenDwarfs

Test: LU Decomposition

OpenBenchmarking.orgms, Fewer Is BetterOpenDwarfs 2013-11-06Test: LU DecompositionGeForce GTX 680GeForce GTX 460GeForce GTX 550 TiRadeon HD 7950Radeon R9 270XRadeon HD 7850GeForce GTX 650Radeon HD 6870GeForce GT 240GeForce GT 610100200300400500SE +/- 0.88, N = 5SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 4.65, N = 6SE +/- 4.83, N = 6SE +/- 5.24, N = 6SE +/- 0.21, N = 3SE +/- 4.12, N = 6SE +/- 1.06, N = 3SE +/- 0.06, N = 358.9497.69110.81123.96126.60135.79152.70161.42220.27458.261. (CC) gcc options: -lm -lOpenCL

Rodinia

Test: OpenCL Leukocyte

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL LeukocyteGeForce GTX 680GeForce GTX 460GeForce GTX 550 TiGeForce GTX 650GeForce GT 240Radeon HD 7950Radeon R9 270XRadeon HD 7850Radeon HD 6870GeForce GT 61020406080100SE +/- 0.24, N = 4SE +/- 0.30, N = 3SE +/- 0.48, N = 4SE +/- 0.26, N = 3SE +/- 0.75, N = 3SE +/- 4.92, N = 6SE +/- 6.06, N = 6SE +/- 5.05, N = 6SE +/- 3.37, N = 6SE +/- 1.23, N = 314.0224.6627.7030.3940.4983.8384.6689.1589.87100.311. (CXX) g++ options: -O2 -lOpenCL


Phoronix Test Suite v10.8.4