aclrtSetOpExecuteTimeOutV2
Applicable Products
Product |
Supported |
|---|---|
√ |
|
√ |
|
√ |
|
√ |
|
√ |
|
√ |
Function
Sets the timeout interval (in microseconds) for operator execution. If a timeout interval is carried during operator delivery, the timeout interval takes precedence over the timeout interval set by this API.
Prototype
1 | aclError aclrtSetOpExecuteTimeOutV2(uint64_t timeout, uint64_t *actualTimeout) |
Parameters
Parameter |
Input/Output |
Description |
|---|---|---|
timeout |
Input |
Timeout interval, in microseconds. 0 means to use the maximum timeout interval. |
actualTimeout |
Output |
Actual timeout, in microseconds. |
Returns
0 on success; otherwise, failure. For details, see aclError.
Restrictions
- For the product models below, if the interval obtained by calling the aclrtGetOpTimeoutInterval API is less than 100,000 microseconds and the timeout parameter is set to 0, AI Core operators will never time out. In this case, the value of the actualTimeout parameter is the maximum value of uint64_t.
Ascend 950PR /Ascend 950DT Atlas A3 training products /Atlas A3 inference products Atlas A2 training products /Atlas A2 inference products - For the following product models, only the timeout interval for AI Core operator execution can be set by calling this API:
Atlas 200I/500 A2 inference products Atlas inference products Atlas training products