VCELPF3.h

Go to the documentation of this file.

/*
 * Copyright (c) 2024, 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       VCELPF3.h
 *  @brief      <b>PRELIMINARY</b> VCE driver interface
 *
 *  <b>WARNING</b> These APIs are <b>PRELIMINARY</b>, and subject to
 *  change in the next few months.
 *
 *  @anchor ti_drivers_VCE_Overview
 *  # Overview
 *  The VCE driver allows you to interact with the Vector Compute Engine
 *  (VCE), a linear algebra accellerator 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 VCE 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 VCE
 *  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_VCE_DataManagement
 *  ## Data management
 *  All the vector/matrix operations can accept input and output pointers that
 *  are inside or outside VCE RAM. If all pointers provided to an operation are
 *  inside VCE RAM, the VCE will operate in <b> scratchpad mode </b>.
 *  This means the driver will assume that, given the current pointers,
 *  the input is already in VCE memory and that input and result will not
 *  overlap eachother. Therefore, no data will be copied, and the function
 *  output will be placed inside VCE memory. This is the most efficient way to
 *  utilize the VCE 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 VCE memory, to prevent unnecessary copying and overhead.
 *
 *  If any of the pointers are outside VCE 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 primary purpose of this driver is executing the MUSIC algorithm for
 *  distance estimation in Bluetooth Channel Sounding. An implementation of
 *  MUSIC using the VCE can be found in the vce_music example.
 *
 *  @anchor ti_drivers_VCE_Usage
 *  # Usage
 *  This section will cover driver usage.
 *
 *  @anchor ti_drivers_VCE_Synopsis
 *  ## Synopsis
 *  @anchor ti_drivers_VCE_Synopsis_Code
 *  @code
 *
 *  VCELPF3_init();
 *
 *  float complex *vceMem = (float complex *)VCELPF3_MEM_BASE;
 *  float complex argA[10];
 *  float complex argB[10];
 *
 *  VCELPF3_ComplexVector vecA = {.data = bufA, .size = 10};
 *  VCELPF3_ComplexVector vecB = {.data = bufB, .size = 10};
 *  VCELPF3_ComplexVector resultVec = {.data = vceMem, .size = 10};
 *
 *  // Get control of VCE
 *  VCELPF3_startOperationSequence();
 *
 *  // Perform element-wise product, placing the result in resultVec,
 *  // which is inside VCE memory
 *  VCELPF3_elemProduct(&argA, &argB, resultVec);
 *
 *  // Perform non-conjugated dot product inside of VCE memory, which
 *  // reduces overhead.
 *  VCELPF3_dotProduct(&resultVec, &resultVec, false, vceMem)
 *
 *  // Give up control of VCE
 *  VCELPF3_finishOperationSequence();
 *
 *  @endcode
 ***************************************************************************
 */
#ifndef ti_drivers_VCELPF3__include
#define ti_drivers_VCELPF3__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)

#ifdef __cplusplus
extern "C" {
#endif

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

typedef struct
{
    complex float *data;
    uint16_t size;
} VCELPF3_ComplexVector;

typedef struct
{
    complex float *data;
    uint16_t rows;
    uint16_t cols;
} VCELPF3_ComplexMatrix;

typedef struct
{
    complex float *data;
    uint16_t size;

} VCELPF3_ComplexTriangleMatrix;

typedef enum
{
    VCELPF3_OperationMode_MIRRORED
} VCELPF3_OperationMode;

typedef enum
{
    VCELPF3_SchedulingMode_PIPELINED

} VCELPF3_SchedulingMode;

typedef struct
{
    void *object;
    void const *hwAttrs;
} VCELPF3_Config;

typedef struct
{
    unsigned int intPriority;

    VCELPF3_OperationMode operationMode;

    VCELPF3_SchedulingMode schedulingMode;
} VCELPF3_HWAttrs;

#define VCELPF3_STATUS_SUCCESS 0

#define VCELPF3_STATUS_ERROR 1

#define VCELPF3_STATUS_RESOURCE_UNAVAILABLE 2

#define VCELPF3_RESULT_INPLACE 0

#define VCELPF3_MEM_BASE VCERAM_DATA0_BASE

#define VCELPF3_MEM_SIZE_MIRRORED VCERAM_DATA0_SIZE

void VCELPF3_init(void);

void VCELPF3_startOperationSequence();

void VCELPF3_stopOperationSequence();

/* Vector functions */
int_fast16_t VCELPF3_dotProduct(VCELPF3_ComplexVector *vecA,
                                VCELPF3_ComplexVector *vecB,
                                bool conjugate,
                                float complex *result);

int_fast16_t VCELPF3_vectorMult(VCELPF3_ComplexVector *vecA,
                                VCELPF3_ComplexVector *vecB,
                                bool conjugate,
                                VCELPF3_ComplexVector *result);

int_fast16_t VCELPF3_vectorSum(VCELPF3_ComplexVector *vecA, VCELPF3_ComplexVector *vecB, VCELPF3_ComplexVector *result);
int_fast16_t VCELPF3_cartesianToPolarVector(VCELPF3_ComplexVector *vec, VCELPF3_ComplexVector *result);

int_fast16_t VCELPF3_polarToCartesianVector(VCELPF3_ComplexVector *vec,
                                            float complex *temp,
                                            VCELPF3_ComplexVector *result);

int_fast16_t VCELPF3_sortVector(VCELPF3_ComplexVector *vec, VCELPF3_ComplexVector *result);

int_fast16_t VCELPF3_covMatrixSpatialSmoothing(VCELPF3_ComplexVector *vec,
                                               uint16_t covMatrixSize,
                                               bool fbAveraging,
                                               VCELPF3_ComplexTriangleMatrix *result);

int_fast16_t VCELPF3_computeFFT(VCELPF3_ComplexVector *vec, bool inverse, VCELPF3_ComplexVector *result);
/* Matrix functions */
int_fast16_t VCELPF3_matrixMult(VCELPF3_ComplexMatrix *matA,
                                VCELPF3_ComplexMatrix *matB,
                                VCELPF3_ComplexMatrix *result);

int_fast16_t VCELPF3_matrixSum(VCELPF3_ComplexMatrix *matA, VCELPF3_ComplexMatrix *matB, VCELPF3_ComplexMatrix *result);

int_fast16_t VCELPF3_matrixScalarSum(VCELPF3_ComplexMatrix *mat, float complex *scalar, VCELPF3_ComplexMatrix *result);

int_fast16_t VCELPF3_matrixScalarMult(VCELPF3_ComplexMatrix *mat, float complex *scalar, VCELPF3_ComplexMatrix *result);

int_fast16_t VCELPF3_matrixNorm(VCELPF3_ComplexMatrix *mat, float complex *result);
/* Matrix algorithms */
int_fast16_t VCELPF3_jacobiEVD(VCELPF3_ComplexTriangleMatrix *mat,
                               uint16_t maxIter,
                               float stopThreshold,
                               VCELPF3_ComplexVector *result);

int_fast16_t VCELPF3_gaussJordanElim(VCELPF3_ComplexMatrix *mat, float zeroThreshold, VCELPF3_ComplexMatrix *result);

/* Utility functions */

int_fast16_t VCELPF3_unitCircle(uint16_t numPoints,
                                uint16_t constant,
                                uint16_t phase,
                                bool conjugate,
                                VCELPF3_ComplexVector *result);

void VCELPF3_prepareResult(uint16_t resultSize, uint16_t inputSize, complex float *resultBuffer);

uint16_t VCELPF3_prepareVectors(VCELPF3_ComplexVector *vecA, VCELPF3_ComplexVector *vecB);

uint16_t VCELPF3_prepareMatrices(VCELPF3_ComplexMatrix *matA, VCELPF3_ComplexMatrix *matB);

void *VCELPF3_loadTriangular(VCELPF3_ComplexMatrix *mat, uint16_t offset);

void *VCELPF3_loadArgMirrored(uint16_t argSize, uint16_t offset, float complex *src);

#ifdef __cplusplus
}
#endif

#endif /* ti_drivers_VCE__include */