RunGraphWithStreamAsync
Applicability
|
Product |
Supported |
|---|---|
|
Atlas 350 Accelerator Card |
√ |
|
|
√ |
|
|
√ |
|
|
x |
|
|
√ |
|
|
√ |
Header File/Library File
- Header file: #include <ge/ge_api.h>
- Library file: libge_runner.so
Function Usage
Asynchronously runs the graph of a specified ID and returns the execution result. This API is used to compile, load, and run graphs.
Both this API and RunGraph are used to run the graph of a specified ID and output the result. Specifically:
- This API is asynchronous.
- inputs and outputs are memory on the device and are allocated by the user before graph execution.
You do not need to allocate the output memory in either of the following cases:
- If an external allocator is set by calling RegisterExternalAllocator and no output memory is allocated, the GE calls the external allocator API to allocate memory. You need to free the memory before the external allocator is destructed.
- If no external allocator is set and no output memory is allocated in the dynamic graph scenario, the GE uses the built-in allocator to allocate memory. The lifetime of the memory is the same as that of the graph. You need to free the memory before unloading the graph (before session destructor and GEFinalize).
Prototype
1
|
Status RunGraphWithStreamAsync(uint32_t graph_id, void *stream, const std::vector<Tensor> &inputs,std::vector<Tensor> &outputs) |
Parameters
|
Parameter |
Input/Output |
Description |
|---|---|---|
|
graph_id |
Input |
Subgraph ID. |
|
stream |
Input |
Stream on which the graph is run. |
|
inputs |
Input |
Input data of the current subgraph, which is the memory on the device. If the value of the ge.exec.hostInputIndexes parameter is specified using options, Tensor of the corresponding index specifies the memory space on the host. |
|
outputs |
Output |
Output data of the current subgraph, which is the memory on the device. |
Returns
|
Parameter |
Type |
Description |
|---|---|---|
|
- |
Status |
SUCCESS: The graph is successfully run by using the asynchronous API. FAILED: The graph fails to be run by using the asynchronous API. |
Restrictions
- The memory required by Tensor must be allocated before this API call.
- The storage address of the tensor on the device must be 32-byte aligned. Otherwise, an undefined error may occur.
- Before calling this API, you need to use aclrtCreateStream provided by acl to create a stream. The stream can be created only when the default context is used.
- Before the graph execution result is obtained, the tasks on the stream must be completed by using aclrtSynchronizeStream.