--- Program Information ---: Skybuck's CUDA Memory Bandwidth Performance Test Version 0.06 created on 7 february 2015 by Skybuck Flying Author e-mail address: skybuck2000@hotmail.com Program website: http://www.skybuck.org/CUDA/BandwidthTest/ --- Cuda Information ---: mCudaLibrary.Initialized. mCudaVersionManagement.Version: 6050 mCudaDeviceManagement.DeviceCount: 1 mCudaContext.APIVersion: 3020 mCudaContext.Handle: 38298304 mCudaContext.IsOpen: True mCudaContext.IsCurrent: True mCudaContext.IsSameDevice: True mCudaContext.CachePreference: 0 mCudaContext.ResourceLimit[CudaDriverContextResourceLimitStackSize]: 1024 mCudaContext.ResourceLimit[CudaDriverContextResourceLimitPrintfFifoSize]: 1048576 mCudaContext.ResourceLimit[CudaDriverContextResourceLimitMallocHeapSize]: 8388608 mCudaDevice.Number: 0 mCudaDevice.Handle: 0 mCudaDevice.Name: GeForce GT 520 mCudaDevice.ComputeCapability.Major: 2 mCudaDevice.ComputeCapability.Minor: 1 mCudaDevice.MemorySize: 1073741824 mCudaDevice.Properties.MaxThreadsPerBlock: 1024 mCudaDevice.Properties.MaxBlockDimension[0]: 1024 mCudaDevice.Properties.MaxBlockDimension[1]: 1024 mCudaDevice.Properties.MaxBlockDimension[2]: 64 mCudaDevice.Properties.MaxGridDimension[0]: 65535 mCudaDevice.Properties.MaxGridDimension[1]: 65535 mCudaDevice.Properties.MaxGridDimension[2]: 65535 mCudaDevice.Properties.MaxSharedMemoryPerBlock: 49152 mCudaDevice.Properties.MaxConstantMemory: 65536 mCudaDevice.Properties.WarpSize: 32 mCudaDevice.Properties.MaxMemoryPitch: 2147483647 mCudaDevice.Properties.MaxRegistersPerBlock: 32768 mCudaDevice.Properties.ClockFrequency: 1620000000 mCudaDevice.Properties.TextureAlignment: 512 mCudaDevice.Attributes.MaxThreadsPerBlock: 1024 mCudaDevice.Attributes.MaxBlockDimensionX: 1024 mCudaDevice.Attributes.MaxBlockDimensionY: 1024 mCudaDevice.Attributes.MaxBlockDimensionZ: 64 mCudaDevice.Attributes.MaxGridDimensionX: 65535 mCudaDevice.Attributes.MaxGridDimensionY: 65535 mCudaDevice.Attributes.MaxGridDimensionZ: 65535 mCudaDevice.Attributes.MaxSharedMemoryForBlocksPerMultiProcessor: 49152 mCudaDevice.Attributes.MaxConstantMemory: 65536 mCudaDevice.Attributes.MaxWarpSize: 32 mCudaDevice.Attributes.MaxMemoryPitch: 2147483647 mCudaDevice.Attributes.MaxRegistersForBlocksPerMultiProcessor: 32768 mCudaDevice.Attributes.ClockFrequency: 1620000000 mCudaDevice.Attributes.TextureAlignment: 512 mCudaDevice.Attributes.MemoryCopyAndKernelExecutionOverlap: True mCudaDevice.Attributes.MultiProcessorCount: 1 mCudaDevice.Attributes.RunTimeLimitForKernels: False mCudaDevice.Attributes.IntegratedWithHostMemory: False mCudaDevice.Attributes.CanMapHostMemoryIntoCudaAddressSpace: True mCudaDevice.Attributes.ComputeMode: 0 (DEFAULT/UNRESTRICTED) mCudaDevice.Attributes.MaxTexture1DWidth: 65536 mCudaDevice.Attributes.MaxTexture2DWidth: 65536 mCudaDevice.Attributes.MaxTexture2DHeight: 65535 mCudaDevice.Attributes.MaxTexture3DWidth: 2048 mCudaDevice.Attributes.MaxTexture3DHeight: 2048 mCudaDevice.Attributes.MaxTexture3DDepth: 2048 mCudaDevice.Attributes.MaxTexture2DLayeredWidth: 16384 mCudaDevice.Attributes.MaxTexture2DLayeredHeight: 16384 mCudaDevice.Attributes.MaxTexture2DLayeredLayers: 2048 mCudaDevice.Attributes.MaxTexture2DArrayWidth: 16384 mCudaDevice.Attributes.MaxTexture2DArrayHeight: 16384 mCudaDevice.Attributes.MaxTexture2DArraySlices: 2048 mCudaDevice.Attributes.SurfaceAlignment: 512 mCudaDevice.Attributes.ConcurrentKernels: True mCudaDevice.Attributes.ErrorCorrectingCodesEnabled: False mCudaDevice.Attributes.PCIBusID: 5 mCudaDevice.Attributes.PCIDeviceID: 0 mCudaDevice.Attributes.UsingTCCDriver: False mCudaDevice.Attributes.MemoryClockFrequency: 600000000 mCudaDevice.Attributes.GlobalMemoryBusWidthInBits: 64 mCudaDevice.Attributes.Level2CacheSize: 65536 mCudaDevice.Attributes.MaxResidentThreadsPerMultiProcessor: 1536 mCudaDevice.Attributes.AsynchronousEngineCount: 1 mCudaDevice.Attributes.UnifiedAddressing: False mCudaDevice.Attributes.MaxTexture1DLayeredWidth: 16384 mCudaDevice.Attributes.MaxTexture1DLayeredLayers: 2048 mCudaDevice.Attributes.PCIDomainID: 0 --- Cuda Device (Most Interesting) Information ---: mCudaDevice.Name: GeForce GT 520 mCudaDevice.MemorySize: 1073741824 mCudaDevice.MemoryClockFrequency: 600000000 mCudaDevice.GlobalMemoryBusWidthInBits: 64 mCudaDevice.Level2CacheSize: 65536 mCudaDevice.SharedMemoryPerMultiProcessor: 49152 mCudaDevice.RegistersPerMultiProcessor: 32768 mCudaDevice.ConstantMemory: 65536 mCudaDevice.MultiProcessorCount: 1 mCudaDevice.ClockFrequency: 1620000000 mCudaDevice.MaxWarpSize: 32 --- Cuda Kernel Information ---: mCudaKernelBandwidth.Attributes.MaxThreadsPerBlock: 1024 mCudaKernelBandwidth.Attributes.SharedMemoryPerBlock: 0 mCudaKernelBandwidth.Attributes.ConstantMemoryPerBlock: 0 mCudaKernelBandwidth.Attributes.LocalMemoryPerThread: 4 mCudaKernelBandwidth.Attributes.RegistersPerThread: 2 mCudaKernelBandwidth.Attributes.PTXversion.Value: 20 mCudaKernelBandwidth.Attributes.PTXversion.Major: 2 mCudaKernelBandwidth.Attributes.PTXversion.Minor: 0 mCudaKernelBandwidth.Attributes.BinaryVersion.Value: 21 mCudaKernelBandwidth.Attributes.BinaryVersion.Major: 2 mCudaKernelBandwidth.Attributes.BinaryVersion.Minor: 1 --- Run Settings ---: MemoryBlockSize: 134217728 Rounds: 2 Estimated Bandwidth: 9600000000 Memory Total: 1073741824 Memory Free: 1005076480 Memory Blocks:7 Memory Block Number: 1 NewMemoryFree: 870858752 FreeMemory: 1005076480 Overhead: 0 ParaCudaKernel.Parameters.ProblemSize: 600000000 ParaCudaKernel.Parameters.CalculateOptimalDimensions successfull. ParaCudaKernel.Parameters.ComputeCapability: 2.1 ParaCudaKernel.Parameters.MaxResidentThreadsPerMultiProcessor: 1536 ParaCudaKernel.Parameters.MaxResidentWarpsPerMultiProcessor: 48 ParaCudaKernel.Parameters.MaxResidentBlocksPerMultiProcessor: 8 ParaCudaKernel.Parameters.OptimalThreadsPerBlock: 256 ParaCudaKernel.Parameters.OptimalWarpsPerBlock: 6 ParaCudaKernel.Parameters.ThreadWidth: 256 ParaCudaKernel.Parameters.ThreadHeight: 1 ParaCudaKernel.Parameters.ThreadDepth: 1 ParaCudaKernel.Parameters.BlockWidth: 65535 ParaCudaKernel.Parameters.BlockHeight: 36 ParaCudaKernel.Parameters.BlockDepth: 1 ParaCudaKernel.Parameters.RemainingProblemSize: 0 mCudaKernelExecutionTimeInMilliseconds: 3620 mCudaKernelExecutionTimeInMilliseconds: 3540 Memory Block Number: 2 NewMemoryFree: 736641024 FreeMemory: 870858752 Overhead: 0 ParaCudaKernel.Parameters.ProblemSize: 600000000 ParaCudaKernel.Parameters.CalculateOptimalDimensions successfull. ParaCudaKernel.Parameters.ComputeCapability: 2.1 ParaCudaKernel.Parameters.MaxResidentThreadsPerMultiProcessor: 1536 ParaCudaKernel.Parameters.MaxResidentWarpsPerMultiProcessor: 48 ParaCudaKernel.Parameters.MaxResidentBlocksPerMultiProcessor: 8 ParaCudaKernel.Parameters.OptimalThreadsPerBlock: 256 ParaCudaKernel.Parameters.OptimalWarpsPerBlock: 6 ParaCudaKernel.Parameters.ThreadWidth: 256 ParaCudaKernel.Parameters.ThreadHeight: 1 ParaCudaKernel.Parameters.ThreadDepth: 1 ParaCudaKernel.Parameters.BlockWidth: 65535 ParaCudaKernel.Parameters.BlockHeight: 36 ParaCudaKernel.Parameters.BlockDepth: 1 ParaCudaKernel.Parameters.RemainingProblemSize: 0 mCudaKernelExecutionTimeInMilliseconds: 3692 mCudaKernelExecutionTimeInMilliseconds: 3541 Memory Block Number: 3 NewMemoryFree: 602423296 FreeMemory: 736641024 Overhead: 0 ParaCudaKernel.Parameters.ProblemSize: 600000000 ParaCudaKernel.Parameters.CalculateOptimalDimensions successfull. ParaCudaKernel.Parameters.ComputeCapability: 2.1 ParaCudaKernel.Parameters.MaxResidentThreadsPerMultiProcessor: 1536 ParaCudaKernel.Parameters.MaxResidentWarpsPerMultiProcessor: 48 ParaCudaKernel.Parameters.MaxResidentBlocksPerMultiProcessor: 8 ParaCudaKernel.Parameters.OptimalThreadsPerBlock: 256 ParaCudaKernel.Parameters.OptimalWarpsPerBlock: 6 ParaCudaKernel.Parameters.ThreadWidth: 256 ParaCudaKernel.Parameters.ThreadHeight: 1 ParaCudaKernel.Parameters.ThreadDepth: 1 ParaCudaKernel.Parameters.BlockWidth: 65535 ParaCudaKernel.Parameters.BlockHeight: 36 ParaCudaKernel.Parameters.BlockDepth: 1 ParaCudaKernel.Parameters.RemainingProblemSize: 0 mCudaKernelExecutionTimeInMilliseconds: 3717 mCudaKernelExecutionTimeInMilliseconds: 3541 Memory Block Number: 4 NewMemoryFree: 468205568 FreeMemory: 602423296 Overhead: 0 ParaCudaKernel.Parameters.ProblemSize: 600000000 ParaCudaKernel.Parameters.CalculateOptimalDimensions successfull. ParaCudaKernel.Parameters.ComputeCapability: 2.1 ParaCudaKernel.Parameters.MaxResidentThreadsPerMultiProcessor: 1536 ParaCudaKernel.Parameters.MaxResidentWarpsPerMultiProcessor: 48 ParaCudaKernel.Parameters.MaxResidentBlocksPerMultiProcessor: 8 ParaCudaKernel.Parameters.OptimalThreadsPerBlock: 256 ParaCudaKernel.Parameters.OptimalWarpsPerBlock: 6 ParaCudaKernel.Parameters.ThreadWidth: 256 ParaCudaKernel.Parameters.ThreadHeight: 1 ParaCudaKernel.Parameters.ThreadDepth: 1 ParaCudaKernel.Parameters.BlockWidth: 65535 ParaCudaKernel.Parameters.BlockHeight: 36 ParaCudaKernel.Parameters.BlockDepth: 1 ParaCudaKernel.Parameters.RemainingProblemSize: 0 mCudaKernelExecutionTimeInMilliseconds: 3731 mCudaKernelExecutionTimeInMilliseconds: 3540 Memory Block Number: 5 NewMemoryFree: 333987840 FreeMemory: 468205568 Overhead: 0 ParaCudaKernel.Parameters.ProblemSize: 600000000 ParaCudaKernel.Parameters.CalculateOptimalDimensions successfull. ParaCudaKernel.Parameters.ComputeCapability: 2.1 ParaCudaKernel.Parameters.MaxResidentThreadsPerMultiProcessor: 1536 ParaCudaKernel.Parameters.MaxResidentWarpsPerMultiProcessor: 48 ParaCudaKernel.Parameters.MaxResidentBlocksPerMultiProcessor: 8 ParaCudaKernel.Parameters.OptimalThreadsPerBlock: 256 ParaCudaKernel.Parameters.OptimalWarpsPerBlock: 6 ParaCudaKernel.Parameters.ThreadWidth: 256 ParaCudaKernel.Parameters.ThreadHeight: 1 ParaCudaKernel.Parameters.ThreadDepth: 1 ParaCudaKernel.Parameters.BlockWidth: 65535 ParaCudaKernel.Parameters.BlockHeight: 36 ParaCudaKernel.Parameters.BlockDepth: 1 ParaCudaKernel.Parameters.RemainingProblemSize: 0 mCudaKernelExecutionTimeInMilliseconds: 3754 mCudaKernelExecutionTimeInMilliseconds: 3541 Memory Block Number: 6 NewMemoryFree: 199770112 FreeMemory: 333987840 Overhead: 0 ParaCudaKernel.Parameters.ProblemSize: 600000000 ParaCudaKernel.Parameters.CalculateOptimalDimensions successfull. ParaCudaKernel.Parameters.ComputeCapability: 2.1 ParaCudaKernel.Parameters.MaxResidentThreadsPerMultiProcessor: 1536 ParaCudaKernel.Parameters.MaxResidentWarpsPerMultiProcessor: 48 ParaCudaKernel.Parameters.MaxResidentBlocksPerMultiProcessor: 8 ParaCudaKernel.Parameters.OptimalThreadsPerBlock: 256 ParaCudaKernel.Parameters.OptimalWarpsPerBlock: 6 ParaCudaKernel.Parameters.ThreadWidth: 256 ParaCudaKernel.Parameters.ThreadHeight: 1 ParaCudaKernel.Parameters.ThreadDepth: 1 ParaCudaKernel.Parameters.BlockWidth: 65535 ParaCudaKernel.Parameters.BlockHeight: 36 ParaCudaKernel.Parameters.BlockDepth: 1 ParaCudaKernel.Parameters.RemainingProblemSize: 0 mCudaKernelExecutionTimeInMilliseconds: 3748 mCudaKernelExecutionTimeInMilliseconds: 3541 Memory Block Number: 7 NewMemoryFree: 65552384 FreeMemory: 199770112 Overhead: 0 ParaCudaKernel.Parameters.ProblemSize: 600000000 ParaCudaKernel.Parameters.CalculateOptimalDimensions successfull. ParaCudaKernel.Parameters.ComputeCapability: 2.1 ParaCudaKernel.Parameters.MaxResidentThreadsPerMultiProcessor: 1536 ParaCudaKernel.Parameters.MaxResidentWarpsPerMultiProcessor: 48 ParaCudaKernel.Parameters.MaxResidentBlocksPerMultiProcessor: 8 ParaCudaKernel.Parameters.OptimalThreadsPerBlock: 256 ParaCudaKernel.Parameters.OptimalWarpsPerBlock: 6 ParaCudaKernel.Parameters.ThreadWidth: 256 ParaCudaKernel.Parameters.ThreadHeight: 1 ParaCudaKernel.Parameters.ThreadDepth: 1 ParaCudaKernel.Parameters.BlockWidth: 65535 ParaCudaKernel.Parameters.BlockHeight: 36 ParaCudaKernel.Parameters.BlockDepth: 1 ParaCudaKernel.Parameters.RemainingProblemSize: 0 mCudaKernelExecutionTimeInMilliseconds: 3778 mCudaKernelExecutionTimeInMilliseconds: 3542