cuda.bindings._v2.driver.dev_sm_resource_split_by_count#

cuda.bindings._v2.driver.dev_sm_resource_split_by_count( input, unsigned int flags, unsigned int min_count, ) → tuple#

Splits CU_DEV_RESOURCE_TYPE_SM resources.

Splits CU_DEV_RESOURCE_TYPE_SM resources into nb_groups, adhering to the minimum SM count specified in min_count and the usage flags in flags. If result is NULL, the API simulates a split and provides the amount of groups that would be created in nb_groups. Otherwise, nb_groups must point to the amount of elements in result and on return, the API will overwrite nb_groups with the amount actually created. The groups are written to the array in result. nb_groups can be less than the total amount if a smaller number of groups is needed. This API is used to spatially partition the input resource. The input resource needs to come from one of cuDeviceGetDevResource, cuCtxGetDevResource, or cuGreenCtxGetDevResource. A limitation of the API is that the output results cannot be split again without first creating a descriptor and a green context with that descriptor. When creating the groups, the API will take into account the performance and functional characteristics of the input resource, and guarantee a split that will create a disjoint set of symmetrical partitions. This may lead to fewer groups created than purely dividing the total SM count by the min_count due to cluster requirements or alignment and granularity requirements for the min_count. These requirements can be queried with cuDeviceGetDevResource, cuCtxGetDevResource, and cuGreenCtxGetDevResource for CU_DEV_RESOURCE_TYPE_SM, using the minSmPartitionSize and smCoscheduledAlignment fields to determine minimum partition size and alignment granularity, respectively. The remainder set does not have the same functional or performance guarantees as the groups in result. Its use should be carefully planned and future partitions of the remainder set are discouraged. The following flags are supported:.

CU_DEV_SM_RESOURCE_SPLIT_IGNORE_SM_COSCHEDULING : Lower the minimum SM count and alignment, and treat each SM independent of its hierarchy. This allows more fine grained partitions but at the cost of advanced features (such as large clusters on compute capability 9.0+).
CU_DEV_SM_RESOURCE_SPLIT_MAX_POTENTIAL_CLUSTER_SIZE : Compute Capability 9.0+ only. Attempt to create groups that may allow for maximally sized thread clusters. This can be queried post green context creation using cuOccupancyMaxPotentialClusterSize.

A successful API call must either have:.

A valid array of result pointers of size passed in nb_groups, with input of type CU_DEV_RESOURCE_TYPE_SM. Value of min_count must be between 0 and the SM count specified in input. remainder may be NULL.
NULL passed in for result, with a valid integer pointer in nb_groups and input of type CU_DEV_RESOURCE_TYPE_SM. Value of min_count must be between 0 and the SM count specified in input. remainder may be NULL. This queries the number of groups that would be created by the API.

Note: The API is not supported on 32-bit platforms.

Parameters:

input (intptr_t) – Input SM resource to be split. Must be a valid CU_DEV_RESOURCE_TYPE_SM resource.
flags (unsigned int) – Flags specifying how these partitions are used or which constraints to abide by when splitting the input. Zero is valid for default behavior.
min_count (unsigned int) – Minimum number of SMs required.

Returns:

CUdevResource_v1: Output array of CUdevResource resources. Can
be NULL to query the number of groups.
CUdevResource_v1: If the input resource cannot be cleanly split
among nb_groups, the remainder is placed in here. Can be ommitted (NULL) if the user does not need the remaining set.

Return type:

A 2-tuple containing