cuda.bindings._v2.driver.FuncCache

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

Function cache configurations

See CUfunc_cache.

NONE: 0

no preference for shared memory or L1 (default)

SHARED: 1

prefer larger shared memory and smaller L1 cache

L1: 2

prefer larger L1 cache and smaller shared memory

EQUAL: 3

prefer equal sized L1 cache and shared memory