Class DriverAPINativeMethods.Occupancy

This section describes the occupancy calculation functions of the low-level CUDA driver application programming interface.

Inheritance

System.Object

DriverAPINativeMethods.Occupancy

Inherited Members

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: ManagedCuda

Assembly: ManagedCuda.dll

Syntax

public static class Occupancy

Methods

cuOccupancyMaxActiveBlocksPerMultiprocessor(ref Int32, CUfunction, Int32, SizeT)

Returns in numBlocks the number of the maximum active blocks per streaming multiprocessor.

Declaration

public static CUResult cuOccupancyMaxActiveBlocksPerMultiprocessor(ref int numBlocks, CUfunction func, int blockSize, SizeT dynamicSMemSize)

Parameters

Type	Name	Description
System.Int32	numBlocks	Returned occupancy
CUfunction	func	Kernel for which occupancy is calulated
System.Int32	blockSize	Block size the kernel is intended to be launched with
SizeT	dynamicSMemSize	Per-block dynamic shared memory usage intended, in bytes

Returns

Type	Description
CUResult	CUDA Error Codes: Success, ErrorDeinitialized, ErrorNotInitialized, ErrorInvalidContext, ErrorInvalidValue, ErrorUnknown.

cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(ref Int32, CUfunction, Int32, SizeT, CUoccupancy_flags)

Returns occupancy of a function

Returns in \p *numBlocks the number of the maximum active blocks per streaming multiprocessor.

The \p Flags parameter controls how special cases are handled. The valid flags are:

• ::CU_OCCUPANCY_DEFAULT, which maintains the default behavior as ::cuOccupancyMaxActiveBlocksPerMultiprocessor;
• ::CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, if caching is enabled, but per-block SM resource usage would result in zero occupancy, the occupancy calculator will calculate the occupancy as if caching is disabled. Setting ::CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE makes the occupancy calculator to return 0 in such cases. More information can be found about this feature in the "Unified L1/Texture Cache" section of the Maxwell tuning guide.

Declaration

public static CUResult cuOccupancyMaxActiveBlocksPerMultiprocessorWithFlags(ref int numBlocks, CUfunction func, int blockSize, SizeT dynamicSMemSize, CUoccupancy_flags flags)

Parameters

Type	Name	Description
System.Int32	numBlocks	Returned occupancy
CUfunction	func	Kernel for which occupancy is calculated
System.Int32	blockSize	Block size the kernel is intended to be launched with
SizeT	dynamicSMemSize	Per-block dynamic shared memory usage intended, in bytes
CUoccupancy_flags	flags	Requested behavior for the occupancy calculator

Returns

Type	Description
CUResult

cuOccupancyMaxPotentialBlockSize(ref Int32, ref Int32, CUfunction, del_CUoccupancyB2DSize, SizeT, Int32)

Returns in blockSize a reasonable block size that can achieve the maximum occupancy (or, the maximum number of active warps with the fewest blocks per multiprocessor), and in minGridSize the minimum grid size to achieve the maximum occupancy.

If blockSizeLimit is 0, the configurator will use the maximum block size permitted by the device / function instead.

If per-block dynamic shared memory allocation is not needed, the user should leave both blockSizeToDynamicSMemSize and dynamicSMemSize as 0.

If per-block dynamic shared memory allocation is needed, then if the dynamic shared memory size is constant regardless of block size, the size should be passed through dynamicSMemSize, and blockSizeToDynamicSMemSize should be NULL.

Otherwise, if the per-block dynamic shared memory size varies with different block sizes, the user needs to provide a unary function through blockSizeToDynamicSMemSize that computes the dynamic shared memory needed by func for any given block size. dynamicSMemSize is ignored.

Declaration

public static CUResult cuOccupancyMaxPotentialBlockSize(ref int minGridSize, ref int blockSize, CUfunction func, del_CUoccupancyB2DSize blockSizeToDynamicSMemSize, SizeT dynamicSMemSize, int blockSizeLimit)

Parameters

Type	Name	Description
System.Int32	minGridSize	Returned minimum grid size needed to achieve the maximum occupancy
System.Int32	blockSize	Returned maximum block size that can achieve the maximum occupancy
CUfunction	func	Kernel for which launch configuration is calulated
del_CUoccupancyB2DSize	blockSizeToDynamicSMemSize	A function that calculates how much per-block dynamic shared memory \p func uses based on the block size
SizeT	dynamicSMemSize	Dynamic shared memory usage intended, in bytes
System.Int32	blockSizeLimit	The maximum block size \p func is designed to handle

Returns

Type	Description
CUResult	CUDA Error Codes: Success, ErrorDeinitialized, ErrorNotInitialized, ErrorInvalidContext, ErrorInvalidValue, ErrorUnknown.

cuOccupancyMaxPotentialBlockSizeWithFlags(ref Int32, ref Int32, CUfunction, del_CUoccupancyB2DSize, SizeT, Int32, CUoccupancy_flags)

Suggest a launch configuration with reasonable occupancy

An extended version of ::cuOccupancyMaxPotentialBlockSize. In addition to arguments passed to ::cuOccupancyMaxPotentialBlockSize, ::cuOccupancyMaxPotentialBlockSizeWithFlags also takes a \p Flags parameter.

The \p Flags parameter controls how special cases are handled. The valid flags are:

• ::CU_OCCUPANCY_DEFAULT, which maintains the default behavior as ::cuOccupancyMaxPotentialBlockSize;
• ::CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE, which suppresses the default behavior on platform where global caching affects occupancy. On such platforms, the launch configurations that produces maximal occupancy might not support global caching. Setting ::CU_OCCUPANCY_DISABLE_CACHING_OVERRIDE guarantees that the the produced launch configuration is global caching compatible at a potential cost of occupancy. More information can be found about this feature in the "Unified L1/Texture Cache" section of the Maxwell tuning guide.

Declaration

public static CUResult cuOccupancyMaxPotentialBlockSizeWithFlags(ref int minGridSize, ref int blockSize, CUfunction func, del_CUoccupancyB2DSize blockSizeToDynamicSMemSize, SizeT dynamicSMemSize, int blockSizeLimit, CUoccupancy_flags flags)

Parameters

Type	Name	Description
System.Int32	minGridSize	Returned minimum grid size needed to achieve the maximum occupancy
System.Int32	blockSize	Returned maximum block size that can achieve the maximum occupancy
CUfunction	func	Kernel for which launch configuration is calculated
del_CUoccupancyB2DSize	blockSizeToDynamicSMemSize	A function that calculates how much per-block dynamic shared memory \p func uses based on the block size
SizeT	dynamicSMemSize	Dynamic shared memory usage intended, in bytes
System.Int32	blockSizeLimit	The maximum block size \p func is designed to handle
CUoccupancy_flags	flags	Options

Returns

Type	Description
CUResult