#include <TTL_simplex_scheme.h>

Collaboration diagram for TTL_simplex_buffering< TENSORTYPE >:

Public Member Functions
	TTL_simplex_buffering (TENSORTYPE const int_base1, TENSORTYPE const int_base2, TENSORTYPE const int_base3, const TTL_tensor< TENSORTYPE > &ext_tensor_in, const TTL_tensor< TENSORTYPE > &ext_tensor_out, TTL_event input_event_in, TTL_event *input_event_out, const TTL_tile first_tile)
	Create a TTL_simplex_buffering and begin the buffering process.

TTL_io_tensors< TENSORTYPE >	step_buffering (const TTL_tile &tile_next_import, const TTL_tile &tile_current_export)

void	finish_buffering ()
	Complete any transfers required to finish the buffering process.

Data Fields
TTL_common_buffering< TENSORTYPE, 3 >	m_common
	The information that is m_common to all pipeline schemes.

TTL_event *	m_event_in

TTL_event *	m_event_out

TTL_tile	m_next_exported_tile

TTL_sub_tensor< TENSORTYPE >	m_int_prev_imported

Detailed Description

template<typename TENSORTYPE>
struct TTL_simplex_buffering< TENSORTYPE >

Definition at line 61 of file p/pipelines/TTL_simplex_scheme.h.

Constructor & Destructor Documentation

◆ TTL_simplex_buffering()

template<typename TENSORTYPE>

TTL_simplex_buffering< TENSORTYPE >::TTL_simplex_buffering	(	TENSORTYPE *const	int_base1,
		TENSORTYPE *const	int_base2,
		TENSORTYPE *const	int_base3,
		const TTL_tensor< TENSORTYPE > &	ext_tensor_in,
		const TTL_tensor< TENSORTYPE > &	ext_tensor_out,
		TTL_event *	input_event_in,
		TTL_event *	input_event_out,
		const TTL_tile	first_tile )

inline

Create a TTL_simplex_buffering and begin the buffering process.

Parameters

int_base1	The address of the first buffer to be used in local memory
int_base2	The address of the second buffer to be used in local memory
int_base3	The address of the third buffer to be used in local memory
ext_tensor_in	The external tensor to import the input data from
ext_tensor_out	The external tensor to export the output data to
m_event_in	A pointer to the event to use for the inward (external to internal) transfer completion
m_event_out	A pointer to the event to use for the inward (internal to external) transfer completion
first_tile	The first tile to fetch for the scheme

Solid description of TTL_simplex_buffering buffering here

Returns: The TTL_simplex_buffering created from the input parameters

Example:

TTL_event tb_e_in = TTL_get_event();
TTL_event tb_e_out = TTL_get_event();
TTL_simplex_buffering tb_scheme(
      ext_base_in, ext_base_out, l_buff1, l_buff2, l_buff3, ext_layout_in,
      ext_layout_out, &tb_e_in, &tb_e_out);

This can be optimized and standardized using the TTL_step_buffering call.

Definition at line 103 of file p/pipelines/TTL_simplex_scheme.h.

Member Function Documentation

◆ finish_buffering()

template<typename TENSORTYPE>

void TTL_simplex_buffering< TENSORTYPE >::finish_buffering ( )

inline

Complete any transfers required to finish the buffering process.

Any transfers that are still in progress will be completed and any transfers that need to be started and completed before finish_buffering returns

Definition at line 187 of file p/pipelines/TTL_simplex_scheme.h.

◆ step_buffering()

template<typename TENSORTYPE>

TTL_io_tensors< TENSORTYPE > TTL_simplex_buffering< TENSORTYPE >::step_buffering	(	const TTL_tile &	tile_next_import,
		const TTL_tile &	tile_current_export )