loco::PaddingND Class Reference

#include <PaddingND.h>

Public Member Functions
const uint32_t &	front (uint32_t dim) const
uint32_t &	front (uint32_t dim)
const uint32_t &	back (uint32_t dim) const
uint32_t &	back (uint32_t dim)
uint32_t	rank (void) const
void	rank (uint32_t s)

Detailed Description

This class indicates how many pads to add before(front) and after(back) the contents of tensor in that dimension.

Definition at line 30 of file PaddingND.h.

Member Function Documentation

back() [1/2]

uint32_t & loco::PaddingND::back ( uint32_t  dim )

inline

Definition at line 39 of file PaddingND.h.

{ return _back.at(dim); }

back() [2/2]

const uint32_t & loco::PaddingND::back ( uint32_t  dim ) const

inline

Definition at line 38 of file PaddingND.h.

{ return _back.at(dim); }

front() [1/2]

uint32_t & loco::PaddingND::front ( uint32_t  dim )

inline

Definition at line 35 of file PaddingND.h.

{ return _front.at(dim); }

front() [2/2]

const uint32_t & loco::PaddingND::front ( uint32_t  dim ) const

inline

Definition at line 34 of file PaddingND.h.

{ return _front.at(dim); }

rank() [1/2]

void loco::PaddingND::rank ( uint32_t  s )

inline

Definition at line 43 of file PaddingND.h.

  {
    _front.resize(s);
    _back.resize(s);
  }

rank() [2/2]

uint32_t loco::PaddingND::rank ( void  ) const

inline

Definition at line 42 of file PaddingND.h.

{ return _front.size(); }

---

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

• compiler/loco/include/loco/IR/PaddingND.h