aclopCompileAndExecute

Description

Compiles and executes an operator. This API is asynchronous. Currently, only static-shape operators are supported. The compilation options are set by using the aclSetCompileopt call.

Restrictions

• This API is asynchronous. The API call delivers a task rather than executes a task. After this API is called, you need to call a synchronization API (for example, aclrtSynchronizeStream) to ensure that the task is complete. Otherwise, service exceptions (such as training or inference exception) or unknown situations (such as device link or card disconnection) may occur.
• In multi-thread scenarios, you cannot specify the same stream or use the default stream when calling this API. Otherwise, the task execution may be abnormal.
• As the inputs, outputs, and attributes of each operator are different, the app needs to organize operators in strict accordance with their inputs, outputs, and attributes. When aclopCompileAndExecute is called, AscendCL searches for the corresponding task based on the optype, input tensor description, output tensor description, and attributes before compiling and running the operator.
• If an operator with an unused optional input is compiled and executed:
  • Create data of the aclTensorDesc type by using the aclCreateTensorDesc(ACL_DT_UNDEFINED, 0, nullptr, ACL_FORMAT_UNDEFINED) call, indicating that the data type is ACL_DT_UNDEFINED, the format is ACL_FORMAT_UNDEFINED, and the shape is nullptr.
  • Create data of the aclDataBuffer type by using the aclCreateDataBuffer(nullptr, 0) call, where aclDataBuffer does not need to be freed since it is a null pointer.
• Before compiling and executing an operator with constant input, call aclSetTensorConst to set the constant input.

  If an operator has a constant input but aclSetTensorConst has not been called to set the constant input, call aclSetTensorPlaceMent to set the placement attribute of TensorDesc and set memType to the host memory.

• Typically, it is a best practice to store the input/output tensor data to feed for running a single-operator (for example, the add operator) in the device memory. Some operators, however, take not only tensor data in the device memory (such as the feature map and weights) but also tensor data in the host memory (such as tensor shape and learning rate). In this case, you do not need to manually transfer such tensor data from the host to the device. You only need to call aclSetTensorPlaceMent to set the placement attribute of the corresponding TensorDesc to the host memory to instruct AscendCL to transfer the tensor data from the host to the device at operator runtime.

Prototype

aclError aclopCompileAndExecute(const char *opType,

int numInputs,

const aclTensorDesc *const inputDesc[],

const aclDataBuffer *const inputs[],

int numOutputs,

const aclTensorDesc *const outputDesc[],

aclDataBuffer *const outputs[],

const aclopAttr *attr,

aclopEngineType engineType,

aclopCompileType compileFlag,

const char *opPath,

aclrtStream stream)

Parameters

Returns

The value 0 indicates success, and other values indicate failure. For details, see aclError.