aclrtLaunchKernelWithConfig
Applicability
Product |
Supported |
|---|---|
Atlas 350 Accelerator Card |
√ |
√ |
|
√ |
|
√ |
|
√ |
|
√ |
Description
Specifies the configuration delivered by a task and starts the compute task of the corresponding operator. This API is asynchronous.
When calling this API to deliver the compute task of an AI Core operator, call aclrtBinaryLoadFromFile to load and parse the operator binary file.
Prototype
1 | aclError aclrtLaunchKernelWithConfig(aclrtFuncHandle funcHandle, uint32_t numBlocks, aclrtStream stream, aclrtLaunchKernelCfg *cfg, aclrtArgsHandle argsHandle, void *reserve) |
Parameters
Parameter |
Input/Output |
Description |
|---|---|---|
funcHandle |
Input |
Kernel function handle. For details about the type definition, see aclrtFuncHandle. |
numBlocks |
Input |
Number of cores on which a kernel function will be executed. |
stream |
Input |
Stream for executing a task. For details about the type definition, see aclrtStream. |
cfg |
Input |
Configuration delivered by the task. For details about the type definition, see aclrtLaunchKernelCfg. If no configuration is specified, NULL can be passed. |
argsHandle |
Input |
Handle to the parameter list. For details about the type definition, see aclrtArgsHandle. |
reserve |
Input |
Reserved parameter. Currently, the value is fixed to NULL. |
Returns
0 on success; otherwise, failure. For details, see aclError.
Reference
All the APIs listed in the following table enable the compute tasks of the corresponding operators. However, their functions and usage modes are different.
API |
How Kernel Function Parameter Values Are Passed |
Where Kernel Function Parameter Values Are Stored |
Configuration Customizable to Deliver |
|---|---|---|---|
Specify the device memory address pointer for storing all input arguments of the kernel function. |
Device memory |
No |
|
Specify the device memory address pointer for storing all input arguments of the kernel function. |
Device memory |
Yes |
|
Specify the parameter list handle aclrtArgsHandle. |
Host memory |
Yes |
|
Specify the host memory address pointer for storing all input arguments of the kernel function. |
Host memory |
Yes |