Function: cmo_async

Product	Supported
Atlas 350 Accelerator Card	√
Atlas A3 training product/Atlas A3 inference product	√
Atlas A2 training product/Atlas A2 inference product	√
Atlas training product	x
Atlas inference product	x
Atlas 200I/500 A2 inference product	x

Implements cache memory operations on the device.

C Prototype

aclError aclrtCmoAsync(void *src, size_t size, aclrtCmoType cmoType, aclrtStream stream)

Python Function

ret = acl.rt.cmo_async(src, size, cmo_type, stream)

Parameter	Description
src	Int, address of the device memory to be operated.
size	Int, size of the device memory to be operated, in bytes.
cmoType	Int, cache memory operation type. For details, see aclrtCmoType. Currently, only ACL_RT_CMO_TYPE_PREFETCH (memory prefetch) is supported.
stream	Int, stream.

Return Value	Description
ret	Int, error code. 0 on success; else, failure.

The Atlas training product does not support this API.

The Atlas inference product does not support this API.

The Atlas 200I/500 A2 inference product does not support this API.

Parent topic: Memory Management