cuda.bindings._v2.driver.Limit

class cuda.bindings._v2.driver.Limit(value: int)

Limits

See CUlimit.

STACK_SIZE: 0

GPU thread stack size

PRINTF_FIFO_SIZE: 1

GPU printf FIFO size

MALLOC_HEAP_SIZE: 2

GPU malloc heap size

DEV_RUNTIME_SYNC_DEPTH: 3

GPU device runtime launch synchronize depth

DEV_RUNTIME_PENDING_LAUNCH_COUNT: 4

GPU device runtime pending launch count

MAX_L2_FETCH_GRANULARITY: 5

A value between 0 and 128 that indicates the maximum fetch granularity of L2 (in Bytes). This is a hint

PERSISTING_L2_CACHE_SIZE: 6

A size in bytes for L2 persisting lines cache size

SHMEM_SIZE: 7

A maximum size in bytes of shared memory available to CUDA kernels on a CIG context. Can only be queried, cannot be set

CIG_ENABLED: 8

A non-zero value indicates this CUDA context is a CIG-enabled context. Can only be queried, cannot be set

CIG_SHMEM_FALLBACK_ENABLED: 9

When set to zero, CUDA will fail to launch a kernel on a CIG context, instead of using the fallback path, if the kernel uses more shared memory than available

PER_BLOCK_MEMORY_SIZE: 10

Per-block memory size

MAX: 11