distance

Functions

	Name
void	plp_euclidean_distance_f32p_xpulpv2(void * S) 32-bit floating-point parallel Euclidean distance between two vectors
void	plp_euclidean_distance_f32s_rv32im(const float32_t restrict pSrcA, const float32_t restrict pSrcB, uint32_t blockSize, float32_t *restrict pRes) 32-bit floating point Euclidean distance between two vectors
void	plp_euclidean_distance_f32s_xpulpv2(const float32_t restrict pSrcA, const float32_t restrict pSrcB, uint32_t blockSize, float32_t *restrict pRes) 32-bit floating point Euclidean distance between two vectors
void	plp_euclidean_distance_q16s_rv32im(const int16_t restrict pSrcA, const int16_t restrict pSrcB, uint32_t blockSize, uint32_t fracBits, int32_t *restrict pRes) Euclidean distance of 16-bit fixed point vectors kernel for RV32IM extension.
void	plp_euclidean_distance_q16s_xpulpv2(const int16_t restrict pSrcA, const int16_t restrict pSrcB, uint32_t blockSize, uint32_t fracBits, int32_t *restrict pRes) Euclidean distance of 16-bit fixed point vectors kernel for XPULPV2.
void	plp_euclidean_distance_q32p_xpulpv2(void * S) Parallel euclidean distance with interleaved access 32-bit fixed point vectors. vectors kernel for XPULPV2 extension.
void	plp_euclidean_distance_q32s_rv32im(const int32_t restrict pSrcA, const int32_t restrict pSrcB, uint32_t blockSize, uint32_t fracBits, int32_t *restrict pRes) Euclidean distance of 32-bit fixed point vectors.
void	plp_euclidean_distance_q32s_xpulpv2(const int32_t restrict pSrcA, const int32_t restrict pSrcB, uint32_t blockSize, uint32_t fracBits, int32_t *restrict pRes) Euclidean distance of 32-bit fixed point vectors kernel for XPULPV2 extension.
void	plp_euclidean_distance_f32(const float32_t restrict pSrcA, const float32_t restrict pSrcB, uint32_t blockSize, float32_t *restrict pRes) Glue code for Euclidean distance between 32-bit float vectors.
void	plp_euclidean_distance_f32_parallel(const float32_t restrict pSrcA, const float32_t restrict pSrcB, uint32_t blockSize, uint32_t nPE, float32_t *restrict pRes) Glue code for parallel Euclidean distance between 32-bit float vectors.
void	plp_euclidean_distance_q16(const int16_t restrict pSrcA, const int16_t restrict pSrcB, uint16_t blockSize, uint16_t fracBits, int32_t *restrict pRes) Glue code for euclidean distance of 16-bit fixed point vectors.
void	plp_euclidean_distance_q32(const int32_t restrict pSrcA, const int32_t restrict pSrcB, uint32_t blockSize, uint32_t fracBits, int32_t *restrict pRes) Glue code for euclidean distance of 32-bit fixed point vectors.
void	plp_euclidean_distance_q32_parallel(const int32_t restrict pSrcA, const int32_t restrict pSrcB, uint32_t blockSize, uint32_t fracBits, uint32_t nPE, uint32_t *restrict pRes) Glue code for parallel Euclidean distance of 32-bit fixed point vectors.

Detailed Description

Euclidean distance

Functions Documentation

function plp_euclidean_distance_f32p_xpulpv2

void plp_euclidean_distance_f32p_xpulpv2(
    void * S
)

32-bit floating-point parallel Euclidean distance between two vectors

Parameters:

S points to the instance structure for float euclidean distance

Return: none

function plp_euclidean_distance_f32s_rv32im

void plp_euclidean_distance_f32s_rv32im(
    const float32_t *__restrict__ pSrcA,
    const float32_t *__restrict__ pSrcB,
    uint32_t blockSize,
    float32_t *__restrict__ pRes
)

32-bit floating point Euclidean distance between two vectors

Parameters:

pA First vector
pB Second vector
blockSize vector length
pRes output result returned here

Return: none

function plp_euclidean_distance_f32s_xpulpv2

void plp_euclidean_distance_f32s_xpulpv2(
    const float32_t *__restrict__ pSrcA,
    const float32_t *__restrict__ pSrcB,
    uint32_t blockSize,
    float32_t *__restrict__ pRes
)

32-bit floating point Euclidean distance between two vectors

Parameters:

pA First vector
pB Second vector
blockSize vector length
pRes output result returned here

Return: none

function plp_euclidean_distance_q16s_rv32im

void plp_euclidean_distance_q16s_rv32im(
    const int16_t *__restrict__ pSrcA,
    const int16_t *__restrict__ pSrcB,
    uint32_t blockSize,
    uint32_t fracBits,
    int32_t *__restrict__ pRes
)

Euclidean distance of 16-bit fixed point vectors kernel for RV32IM extension.

Parameters:

pSrcA points to the first input vector [16 bit]
pSrcB points to the second input vector [16 bit]
blockSize number of samples in each vector
fracBits decimal point for right shift
pRes output result returned here [32 bit]

Return: none

Par: Exploiting SIMD instructions

When the ISA supports, the 16 bit values are packed two by two into 32 bit vectors and then the two dot products are performed simultaneously on 32 bit vectors, with 32 bit accumulator. RV32IM doesn't support SIMD. For SIMD, check out other ISA extensions (e.g. XPULPV2).

function plp_euclidean_distance_q16s_xpulpv2

void plp_euclidean_distance_q16s_xpulpv2(
    const int16_t *__restrict__ pSrcA,
    const int16_t *__restrict__ pSrcB,
    uint32_t blockSize,
    uint32_t fracBits,
    int32_t *__restrict__ pRes
)

Euclidean distance of 16-bit fixed point vectors kernel for XPULPV2.

Parameters:

pSrcA points to the first input vector [16 bit]
pSrcB points to the second input vector [16 bit]
blockSize number of samples in each vector
fracBits decimal point for right shift
pRes output result returned here [32 bit]

Return: none

Par: Exploiting SIMD instructions

The 16 bit values are packed two by two into 32 bit vectors and then the sums and prducts are performed simultaneously on 32 bit vectors, with 32 bit accumulator.

function plp_euclidean_distance_q32p_xpulpv2

void plp_euclidean_distance_q32p_xpulpv2(
    void * S
)

Parallel euclidean distance with interleaved access 32-bit fixed point vectors. vectors kernel for XPULPV2 extension.

Parameters:

S points to the instance structure for integer parallel Euclidean distance

Return: none

function plp_euclidean_distance_q32s_rv32im

void plp_euclidean_distance_q32s_rv32im(
    const int32_t *__restrict__ pSrcA,
    const int32_t *__restrict__ pSrcB,
    uint32_t blockSize,
    uint32_t fracBits,
    int32_t *__restrict__ pRes
)

Euclidean distance of 32-bit fixed point vectors.

Parameters:

pSrcA points to the first input vector
pSrcB points to the second input vector
blockSize number of samples in each vector
fracBits number of fixed point fractional bits
pRes output result returned here

Return: none

function plp_euclidean_distance_q32s_xpulpv2

void plp_euclidean_distance_q32s_xpulpv2(
    const int32_t *__restrict__ pSrcA,
    const int32_t *__restrict__ pSrcB,
    uint32_t blockSize,
    uint32_t fracBits,
    int32_t *__restrict__ pRes
)

Euclidean distance of 32-bit fixed point vectors kernel for XPULPV2 extension.

Parameters:

pSrcA points to the first input vector
pSrcB points to the second input vector
blockSize number of samples in each vector
fracBits number of fixed point fractional bits
pRes output result returned here

Return: none

function plp_euclidean_distance_f32

void plp_euclidean_distance_f32(
    const float32_t *__restrict__ pSrcA,
    const float32_t *__restrict__ pSrcB,
    uint32_t blockSize,
    float32_t *__restrict__ pRes
)

Glue code for Euclidean distance between 32-bit float vectors.

Parameters:

pSrcA First vector
pSrcB Second vector
blockSize vector length

Return: none

function plp_euclidean_distance_f32_parallel

void plp_euclidean_distance_f32_parallel(
    const float32_t *__restrict__ pSrcA,
    const float32_t *__restrict__ pSrcB,
    uint32_t blockSize,
    uint32_t nPE,
    float32_t *__restrict__ pRes
)

Glue code for parallel Euclidean distance between 32-bit float vectors.

Parameters:

pSrcA points to the first input vector
pSrcB points to the second input vector
blockSize number of samples in each vector
nPE number of parallel processing units
pRes output result returned here

Return: none

function plp_euclidean_distance_q16

void plp_euclidean_distance_q16(
    const int16_t *__restrict__ pSrcA,
    const int16_t *__restrict__ pSrcB,
    uint16_t blockSize,
    uint16_t fracBits,
    int32_t *__restrict__ pRes
)

Glue code for euclidean distance of 16-bit fixed point vectors.

Parameters:

pSrcA points to the first input vector
pSrcB points to the second input vector
blockSize number of samples in each vector
fracBits number of fixed point fractional bits
pRes output result returned here

Return: none

function plp_euclidean_distance_q32

void plp_euclidean_distance_q32(
    const int32_t *__restrict__ pSrcA,
    const int32_t *__restrict__ pSrcB,
    uint32_t blockSize,
    uint32_t fracBits,
    int32_t *__restrict__ pRes
)

Glue code for euclidean distance of 32-bit fixed point vectors.

Parameters:

pSrcA points to the first input vector
pSrcB points to the second input vector
blockSize number of samples in each vector
fracBits number of fixed point fractional bits
pRes output result returned here

Return: none

function plp_euclidean_distance_q32_parallel

void plp_euclidean_distance_q32_parallel(
    const int32_t *__restrict__ pSrcA,
    const int32_t *__restrict__ pSrcB,
    uint32_t blockSize,
    uint32_t fracBits,
    uint32_t nPE,
    uint32_t *__restrict__ pRes
)

Glue code for parallel Euclidean distance of 32-bit fixed point vectors.

Parameters:

pSrcA points to the first input vector
pSrcB points to the second input vector
blockSize number of samples in each vector
fracBits number of fixed point fractional bits
nPE number of parallel processing units
pRes output result returned here

Return: none

Updated on 2023-03-01 at 16:16:32 +0000