APULPF3.h

Go to the documentation of this file.

/*
 * Copyright (c) 2024-2025, Texas Instruments Incorporated
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * *  Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * *  Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * *  Neither the name of Texas Instruments Incorporated nor the names of
 *    its contributors may be used to endorse or promote products derived
 *    from this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
 * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
 * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
 * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
 * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
 * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
/*!*****************************************************************************
 *  @file       APULPF3.h
 *  @brief      <b>PRELIMINARY</b> APU driver interface
 *
 *  <b>WARNING</b> These APIs are <b>PRELIMINARY</b>, and subject to
 *  change in the next few months.
 *
 *  @anchor ti_drivers_APU_Overview
 *  # Overview
 *  The APU driver allows you to interact with the Algorithm Processing Unit
 *  (APU), a linear algebra accelerator peripheral using 64-bit complex numbers.
 *  Complex numbers are represented by the _float complex_ type from
 *  _complex.h_, where each number is made up of two 32-bit floats. The APU
 *  works with complex numbers in either Cartesian or Polar formats. In the
 *  Cartesian representation, the lower 32 bits are the real part and the upper
 *  32 bits are the imaginary part. In Polar format, the lower 32 bits are the
 *  absolute part and the upper 32 bits are the angle, represented as pi
 *  radians.
 *  As long as arguments to the APU functions use the same format, the result
 *  will also be in that format. Mixing formats produces wrong results. The
 *  driver provides basic data types for vectors and matrices constructed from
 *  _float complex_, as well as many common linear algebra operations on these
 *  data types.
 *
 *  @anchor ti_drivers_APU_DataManagement
 *  ## Data management
 *  All the vector/matrix operations can accept input and output pointers that
 *  are inside or outside APU RAM. If all pointers provided to an operation are
 *  inside APU RAM, the APU will operate in <b>scratchpad mode</b>.
 *  This means the driver will assume that, given the current pointers, the
 *  input is already in APU memory and that input and result will not overlap
 *  each other. Therefore, no data will be copied, and the function output will
 *  be placed inside APU memory. This is the most efficient way to utilize the
 *  APU and is ideal for algorithms with multiple operations that feed into each
 *  other, such as MUSIC (https://en.wikipedia.org/wiki/MUSIC_(algorithm)). When
 *  chaining together operations, make sure as many as possible use vectors and
 *  matrices that are already in APU memory, to prevent unnecessary copying and
 *  overhead.
 *
 *  If any of the pointers are outside APU memory, the driver will copy input
 *  data to the start of its memory, place the result immediately following, and
 *  then copy the output back to the provided pointer. This may overwrite data
 *  that was already in this location.
 *
 *  The APU driver uses uDMA for data transfers involving the APU data memory.
 *  More specifically, channel 8 is used.
 *
 *  @warning Due to errata SYS_211, the APU memory has strict access rules. Use
 *  the provided APU functions to move data safely.
 *  To load data into APU memory: #APULPF3_loadArgMirrored() or
 *  #APULPF3_loadTriangular().
 *  To directly perform a memory access: #APULPF3_dataMemTransfer().
 *  Copying data back from APU memory is automatically handled by the
 *  driver, and happens in an interrupt when the result pointer is
 *  outside APU memory.
 *
 *  @warning Due to errata SYS_211, no other SW DMA transactions can occur
 *  while the APU is being used.
 *
 *  @warning Due to errata SYS_211, the APU cannot be used at the same time as
 *  I2S.
 *
 *  The primary purpose of this driver is executing the MUSIC algorithm for
 *  distance estimation in Bluetooth Channel Sounding. An implementation of
 *  MUSIC using the APU can be found in the apu_music example.
 *
 *  @anchor ti_drivers_APU_Usage
 *  # Usage
 *  This section will cover driver usage.
 *
 *  @anchor ti_drivers_APU_Synopsis
 *  ## Synopsis
 *  @anchor ti_drivers_APU_Synopsis_Code
 *  @code
 *
 *  APULPF3_init();
 *
 *  float complex *apuMem = (float complex *)APULPF3_MEM_BASE;
 *  float complex argA[10];
 *  float complex argB[10];
 *
 *  APULPF3_ComplexVector vecA = {.data = bufA, .size = 10};
 *  APULPF3_ComplexVector vecB = {.data = bufB, .size = 10};
 *  APULPF3_ComplexVector resultVec = {.data = apuMem, .size = 10};
 *
 *  // Get control of APU
 *  APULPF3_startOperationSequence();
 *
 *  // Perform element-wise product without conjugation,
 *  // placing the result in resultVec, which is inside APU memory
 *  APULPF3_vectorMult(&argA, &argB, false, resultVec);
 *
 *  // Perform non-conjugated dot product inside of APU memory, which
 *  // reduces overhead.
 *  APULPF3_dotProduct(&resultVec, &resultVec, false, apuMem)
 *
 *  // Give up control of APU
 *  APULPF3_stopOperationSequence();
 *
 *  @endcode
 ***************************************************************************
 */
#ifndef ti_drivers_APULPF3__include
#define ti_drivers_APULPF3__include

#include <stddef.h>
#include <stdint.h>
#include <stdbool.h>
#include <complex.h>

#include <ti/drivers/dpl/HwiP.h>
#include <ti/drivers/dpl/SemaphoreP.h>

#include <ti/devices/DeviceFamily.h>
#include DeviceFamily_constructPath(inc/hw_memmap.h)
#include DeviceFamily_constructPath(driverlib/apu.h)
#include DeviceFamily_constructPath(driverlib/udma.h)
#ifdef __cplusplus
extern "C" {
#endif

/*
 * ========= APU datatype structs =========
 * These structs define the core data types used by APU functions,
 * which are vectors, full matrices and upper triangle matrices of
 * complex numbers. Matrices are column-major.
 */

typedef struct
{
    complex float *data;
    uint16_t size;
} APULPF3_ComplexVector;

typedef struct
{
    complex float *data;
    uint16_t rows;
    uint16_t cols;
} APULPF3_ComplexMatrix;

typedef struct
{
    complex float *data;
    uint16_t size;

} APULPF3_ComplexTriangleMatrix;

typedef enum
{
    APULPF3_R2COp_R2C   = APU_OP_R2C,   
    APULPF3_R2COp_R2CC  = APU_OP_R2CC,  
    APULPF3_R2COp_R2CA  = APU_OP_R2CA,  
    APULPF3_R2COp_R2CAA = APU_OP_R2CCA, 
    APULPF3_R2COp_RA    = APU_OP_RA,    
    APULPF3_R2COp_IMA   = APU_OP_IMA,   
    APULPF3_R2COp_ABS   = APU_OP_ABS,   
} APULPF3_R2COp;

typedef enum
{
    APULPF3_OperationMode_MIRRORED
} APULPF3_OperationMode;

typedef enum
{
    APULPF3_SchedulingMode_PIPELINED

} APULPF3_SchedulingMode;

typedef struct
{
    void *object;
    void const *hwAttrs;
} APULPF3_Config;

typedef struct
{
    unsigned int intPriority;

    APULPF3_OperationMode operationMode;

    APULPF3_SchedulingMode schedulingMode;

    volatile uDMAControlTableEntry *dmaTableEntry;

    uint32_t dmaChannelMask;

} APULPF3_HWAttrs;

#define APULPF3_STATUS_SUCCESS 0

#define APULPF3_STATUS_ERROR 1

#define APULPF3_STATUS_RESOURCE_UNAVAILABLE 2

#define APULPF3_RESULT_INPLACE 0

#define APULPF3_MEM_BASE APURAM_DATA0_BASE

#define APULPF3_MEM_SIZE_MIRRORED APURAM_DATA0_SIZE

void APULPF3_init(void);

void APULPF3_startOperationSequence();

void APULPF3_stopOperationSequence();

/* Vector functions */
int_fast16_t APULPF3_dotProduct(APULPF3_ComplexVector *vecA,
                                APULPF3_ComplexVector *vecB,
                                bool conjugate,
                                float complex *result);

int_fast16_t APULPF3_vectorMult(APULPF3_ComplexVector *vecA,
                                APULPF3_ComplexVector *vecB,
                                bool conjugate,
                                APULPF3_ComplexVector *result);

int_fast16_t APULPF3_vectorScalarMult(APULPF3_ComplexVector *vecA,
                                      float complex *scalar,
                                      APULPF3_ComplexVector *result);

int_fast16_t APULPF3_vectorScalarSum(APULPF3_ComplexVector *vecA,
                                     float complex *scalar,
                                     bool subtraction,
                                     APULPF3_ComplexVector *result);

int_fast16_t APULPF3_vectorSum(APULPF3_ComplexVector *vecA,
                               APULPF3_ComplexVector *vecB,
                               bool subtraction,
                               APULPF3_ComplexVector *result);

int_fast16_t APULPF3_vectorR2C(APULPF3_ComplexVector *vecA,
                               APULPF3_ComplexVector *vecB,
                               APULPF3_R2COp
                               operator,
                               APULPF3_ComplexVector * result);
int_fast16_t APULPF3_cartesianToPolarVector(APULPF3_ComplexVector *vec, APULPF3_ComplexVector *result);

int_fast16_t APULPF3_polarToCartesianVector(APULPF3_ComplexVector *vec,
                                            float complex *temp,
                                            APULPF3_ComplexVector *result);

int_fast16_t APULPF3_sortVector(APULPF3_ComplexVector *vec, APULPF3_ComplexVector *result);

int_fast16_t APULPF3_covMatrixSpatialSmoothing(APULPF3_ComplexVector *vec,
                                               uint16_t covMatrixSize,
                                               bool fbAveraging,
                                               APULPF3_ComplexTriangleMatrix *result);

int_fast16_t APULPF3_computeFFT(APULPF3_ComplexVector *vec, bool inverse, APULPF3_ComplexVector *result);

int_fast16_t APULPF3_vectorMaxMin(APULPF3_ComplexVector *vec,
                                  float scalarThreshold,
                                  bool min,
                                  APULPF3_ComplexVector *result);

/* Matrix functions */
int_fast16_t APULPF3_matrixMult(APULPF3_ComplexMatrix *matA,
                                APULPF3_ComplexMatrix *matB,
                                APULPF3_ComplexMatrix *result);

int_fast16_t APULPF3_matrixSum(APULPF3_ComplexMatrix *matA, APULPF3_ComplexMatrix *matB, APULPF3_ComplexMatrix *result);

int_fast16_t APULPF3_matrixScalarSum(APULPF3_ComplexMatrix *mat, float complex *scalar, APULPF3_ComplexMatrix *result);

int_fast16_t APULPF3_matrixScalarMult(APULPF3_ComplexMatrix *mat, float complex *scalar, APULPF3_ComplexMatrix *result);

int_fast16_t APULPF3_matrixNorm(APULPF3_ComplexMatrix *mat, float complex *result);
/* Matrix algorithms */
int_fast16_t APULPF3_jacobiEVD(APULPF3_ComplexTriangleMatrix *mat,
                               uint16_t maxIter,
                               float stopThreshold,
                               float epsTol,
                               APULPF3_ComplexVector *result);

int_fast16_t APULPF3_gaussJordanElim(APULPF3_ComplexMatrix *mat, float zeroThreshold, APULPF3_ComplexMatrix *result);

/* Utility functions */

int_fast16_t APULPF3_unitCircle(uint16_t numPoints,
                                uint16_t constant,
                                uint16_t phase,
                                bool conjugate,
                                APULPF3_ComplexVector *result);

int_fast16_t APULPF3_HermLo(APULPF3_ComplexTriangleMatrix *mat, APULPF3_ComplexTriangleMatrix *result);

void APULPF3_prepareResult(uint16_t resultSize, uint16_t inputSize, complex float *resultBuffer);

uint16_t APULPF3_prepareVectors(APULPF3_ComplexVector *vecA, APULPF3_ComplexVector *vecB);

uint16_t APULPF3_prepareMatrices(APULPF3_ComplexMatrix *matA, APULPF3_ComplexMatrix *matB);

void *APULPF3_loadTriangular(APULPF3_ComplexMatrix *mat, uint16_t offset);

void *APULPF3_loadArgMirrored(uint16_t argSize, uint16_t offset, float complex *src);

void APULPF3_dataMemTransfer(const float *src, float *dst, size_t length);

#ifdef __cplusplus
}
#endif

#endif /* ti_drivers_APU__include */