Detailed Description

TVM Network Kernels.

Defines
#define	TIVX_KERNEL_TVM_NAME "com.ti.tvm"
	tvm kernel name

Functions
void	tivxTVMLoadKernels (vx_context context)
	Used for the Application to load the tvm kernels into the context.

void	tivxTVMUnLoadKernels (vx_context context)
	Used for the Application to unload the tvm kernels from the context.

void	tivxRegisterTVMTargetKernels (void)
	Function to register TVM Kernels on the TVM Target.

void	tivxUnRegisterTVMTargetKernels (void)
	Function to un-register TVM Kernels on the TVM Target.

VX_API_ENTRY vx_node VX_API_CALL	tivxTVMNode (vx_graph graph, vx_kernel kernel, vx_reference appParams[], vx_tensor input_tensors[], vx_tensor output_tensors[])
	[Graph] Creates a TVM Node. More...

vx_kernel	tivxAddKernelTVM (vx_context context, uint32_t num_input_tensors, uint32_t num_output_tensors)
	Used for the Application to create the tvm kernel from the context. More...

Function Documentation

VX_API_ENTRY vx_node VX_API_CALL tivxTVMNode	(	vx_graph	graph,
		vx_kernel	kernel,
		vx_reference	appParams[],
		vx_tensor	input_tensors[],
		vx_tensor	output_tensors[]
	)

[Graph] Creates a TVM Node.

Parameters

[in]	graph	Reference to vx_graph.
[in]	kernel	Reference to vx_kernel.
[in,out]	appParams	is an array of 2 parameters: config vx_user_data_object type corresponding to the configuration (named string: tivxTVMJ7Params) deploy_mod vx_user_data_object type corresponding to the TVM deployable module (named string: tivxTVMJ7DeployMod)
[in]	input_tensors	Array of input tensors This parameter is ignored when the first layer of the network is a data layer, which is most of the time. Only networks that are dependent on the output of a previous networks have first layer that are not data layer.
[out]	output_tensors	Array of output tensors

Return values

vx_node A node reference. Any possible errors preventing a successful creation should be checked using vxGetStatus

Used for the Application to create the tvm kernel from the context.

Parameters

[in]	context	OpenVX context which must be created using vxCreateContext
[in]	num_input_tensors	Number of input vx_tensor objects to be created
[in]	num_output_tensors	Number of output vx_tensor objects to be created

Note: The caller of this function should check status of the return vx_kernel handle and if found to be NULL must handle or propagate error appropriately.