Snapdragon Neural Processing Engine SDK
Reference Guide
IBufferAttributes Class Referenceabstract

#include <IBufferAttributes.hpp>

Public Member Functions

virtual size_t getElementSize () const noexcept=0
virtual zdl::DlSystem::UserBufferEncoding::ElementType_t getEncodingType () const noexcept=0
virtual const TensorShape getDims () const noexcept=0
virtual const TensorShape getAlignments () const noexcept=0
virtual zdl::DlSystem::UserBufferEncodinggetEncoding () const noexcept=0

Member Function Documentation

◆ getAlignments()

virtual const TensorShape getAlignments ( ) const
pure virtualnoexcept

Gets the alignment requirement of each dimension.

Alignment per each dimension is expressed as an multiple, for example, if one particular dimension can accept multiples of 8, the alignment will be 8.

Alignment in each dimension, in terms of multiple of number of elements

◆ getDims()

virtual const TensorShape getDims ( ) const
pure virtualnoexcept

Gets the number of elements in each dimension.

Dimension size, in terms of number of elements

◆ getElementSize()

virtual size_t getElementSize ( ) const
pure virtualnoexcept

Gets the buffer's element size, in bytes.

This can be used to compute the memory size required to back this buffer.

Element size, in bytes

◆ getEncoding()

virtual zdl::DlSystem::UserBufferEncoding* getEncoding ( ) const
pure virtualnoexcept

Gets the buffer encoding returned from the network responsible for generating this buffer. Depending on the encoding type, this will be an instance of an encoding type specific derived class.

Derived user buffer encoding object.

◆ getEncodingType()

virtual zdl::DlSystem::UserBufferEncoding::ElementType_t getEncodingType ( ) const
pure virtualnoexcept

Gets the element's encoding type.

encoding type

The documentation for this class was generated from the following file: