Function: init_dump

aclError aclmdlInitDump()

ret = acl.mdl.init_dump()

Initializes the dump.

None

ret: int, error code.

• 0 indicates success.
• Other values indicate failure.

• acl.mdl.init_dump needs to be called in conjunction with acl.mdl.set_dump and acl.mdl.finalize_dump to dump data to files. These APIs can be called for multiple times in a single process to obtain dump data of different Dump configurations.
• Example scenario:
  • To execute two models, you need to set dump information differently. The API call sequence is as follows: acl.init --> acl.mdl.init_dump --> acl.mdl.set_dump --> model loading --> model execution --> acl.mdl.finalize_dump --> model unloading --> acl.mdl.init_dump --> acl.mdl.set_dump --> model loading --> model execution --> acl.mdl.finalize_dump --> model unloading --> execution of other tasks --> acl.finalize.
  • To execute the same model twice, you only need to perform the dump operation for the first execution. The API call sequence is as follows: acl.init --> acl.mdl.init_dump --> acl.mdl.set_dump --> model loading --> model execution --> acl.mdl.finalize_dump --> model unloading --> model loading --> model execution --> execution of other tasks --> acl.finalize
• For the model dump configuration, single-operator dump configuration, and overflow operator dump configuration, if the dump information has been configured by calling acl.init, a failure message is returned when acl.mdl.init_dump is called.

• acl.mdl.init_dump must be called after calling acl.init and before calling the model loading API.

pyACL also provides the acl.init API. During pyACL initialization, the dump configuration is passed as a JSON configuration file to dump the app data at run time. In this mode, the acl.init API can be invoked only once in a process. To modify the dump configuration, you need to modify the configuration in the JSON file.