#ifndef MOC_DATA_TRANSFER_SPU_H_
#define MOC_DATA_TRANSFER_SPU_H_

#include <stdint.h>
#include "moc_datatype_spu.h"
#include "../moc.h"

/**
 * \addtogroup dma_access
 **/
//@{
/**
 * @name SPU-only
 **/
//@{


/**
 * Wrapper-function for a blocking DMA-get operation.
 * Data can be of any size, constraints of low-level DMA-functions
 * are dealt by this function.
 * However data-addresses have to be at least 16-byte aligned.
 *
 * @param target \b out pointer to buffer
 * @param source \b in ea-address of data
 * @param count \b in size of data in byte
 * @param datatype \b in Type of Elements
 * @retval MOC_SUCCESS No error; MPI routine completed successfully.
 * @retval ... error-code
 **/
int MOC_Get_data(void* target, uint64_t source, int count,
	MOC_Datatype datatype);

/**
 * Wrapper-function for a blocking DMA-put operation.
 * Data-size should be a multiple of 16 because of low-level constraints, but
 * there is no upper limit of transfer-size.
 * Data-addresses have to be at least 16-byte aligned.
 *
 * @param source \b in pointer to data
 * @param target \b in ea-address of buffer
 * @param count \b in size of data in byte
 * @param datatype \b in Type of Elements
 * @retval MOC_SUCCESS No error; MPI routine completed successfully.
 * @retval ... error-code
 **/
int MOC_Put_data(void* source, uint64_t target, int count,
	MOC_Datatype datatype);

/**
 * Wrapper-function for a non-blocking DMA-get operation.
 * Data can be of any size, constraints of low-level DMA-functions
 * are dealt by this function.
 * However data-addresses have to be at least 16-byte aligned.
 * Operation-completion can be derived with MOC_Test and MOC_Wait.
 *
 * @param target \b out pointer to buffer
 * @param source \b in ea-address of data
 * @param count \b in size of data in byte
 * @param datatype \b in Type of Elements
 * @param request \b out communication request (handle)
 * @retval MOC_SUCCESS No error; MPI routine completed successfully.
 * @retval ... error-code
 **/
int MOC_IGet_data(void* target, uint64_t source, int count,
	MOC_Datatype datatype, MOC_Request *request);

/**
 * Wrapper-function for a non-blocking DMA-put operation.
 * Data-size should be a multiple of 16 because of low-level constraints, but
 * there is no upper limit of transfer-size.
 * Data-addresses have to be at least 16-byte aligned.
 * Operation-completion can be derived with MOC_Test and MOC_Wait.
 *
 * @param source \b in pointer to data
 * @param target \b in ea-address of buffer
 * @param count \b in size of data in byte
 * @param datatype \b in Type of Elements
 * @param request \b out communication request (handle)
 * @retval MOC_SUCCESS No error; MPI routine completed successfully.
 * @retval ... error-code
 **/
int MOC_IPut_data(void* source, uint64_t target, int count,
	MOC_Datatype datatype, MOC_Request *request);

/**
 * Translates a local-store address of the calling SPU into the corresponding
 * effective-address.
 *
 * @param ls \b in local-store address
 * @param ea \b out effective-address
 **/
int MOC_Translate_LS_to_EA(void* ls, uint64_t* ea);

//@}


/**
 * Tests if a MOC_IGet_data or IMOC_IPut_data is completed.
 *
 * @param request \b in request-handle
 * @param flag \b out true if operation is completed
 * @return 0 when success otherwise error-code
 **/
int MOC_Test_data(MOC_Request* request, int *flag);

/**
 * Waits till a MOC_IGet_data or IMOC_IPut_data is completed.
 *
 * @param request \b in request-handle
 * @return 0 when success otherwise error-code
 **/
int MOC_Wait_data(MOC_Request* request);

//@}
#endif /*MOC_DATA_TRANSFER_SPU_H_*/