aclopCompile

Applicability

Product	Supported
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	√
Atlas inference products	√
Atlas training products	√

Description

Builds an operator. The build options are set by using the aclSetCompileopt call.

As the inputs and outputs of operators are organized differently from each other, the API organizes operators in strict accordance with their input and output parameters. When aclopCompile is called, the API searches for the corresponding task based on the optype, input tensor description, output tensor description, and attributes before building the operator.

Prototype

aclError aclopCompile(const char *opType,
int numInputs,
const aclTensorDesc *const inputDesc[],
int numOutputs,
const aclTensorDesc *const outputDesc[],
const aclopAttr *attr,
aclopEngineType engineType,
aclopCompileType compileFlag,
const char *opPath)

Parameters

Parameter	Input/Output	Description
opType	Input	Pointer to the operator type name.
numInputs	Input	Number of input tensors.
inputDesc	Input	Pointer array of the input tensor description. Call aclCreateTensorDesc to create data of the aclTensorDesc type in advance. The array length is consistent with numInputs.
numOutputs	Input	Number of output tensors.
outputDesc	Input	Pointer array of the output tensor description. Call aclCreateTensorDesc to create data of the aclTensorDesc type in advance. The array length is consistent with numOutputs.
attr	Input	Pointer to the operator attributes. Call aclopCreateAttr to create data of the aclopAttr type in advance.
engineType	Input	Operator execution engine.
compileFlag	Input	Operator built flag.
opPath	Input	Pointer to the path of the operator implementation file (.py), excluding the file name. This parameter is reserved. Currently, this parameter can only be set to nullptr.

Returns

0 on success; else, failure. For details, see aclError.

Restrictions

To build a dynamic-shape operator with known shape range, set the element value in the dims array that indicates a dynamic dimension to –1 when creating data of the aclTensorDesc type by using the aclCreateTensorDesc call, and then call aclSetTensorShapeRange to set the size range of each dimension for a tensor. To build a dynamic-shape operator with an unknown shape range (which is reserved in the current version), set the dims array to –2 when creating data of the aclTensorDesc type by using the aclCreateTensorDesc call, for example, int64_t dims[] = {-2}.
To build an operator with an unused optional input, 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.
Before building an operator with constant input, call aclSetTensorConst to set the constant input. The constant input passed to the aclopCompile and aclopExecuteV2 calls must be consistent.

Parent topic: Single-Operator Model Execution