Jensen-Shannon distance. More...

Functions
__STATIC_INLINE float16_t	rel_entr (float16_t x, float16_t y)

RISCV_DSP_ATTRIBUTE float16_t	riscv_jensenshannon_distance_f16 (const float16_t pA, const float16_t pB, uint32_t blockSize)
	Jensen-Shannon distance between two vectors. More...

__STATIC_INLINE float32_t	rel_entr (float32_t x, float32_t y)

RISCV_DSP_ATTRIBUTE float32_t	riscv_jensenshannon_distance_f32 (const float32_t pA, const float32_t pB, uint32_t blockSize)
	Jensen-Shannon distance between two vectors. More...

Detailed Description

Jensen-Shannon distance.

Function Documentation

◆ rel_entr() [1/2]

__STATIC_INLINE float16_t rel_entr	(	float16_t	x,
		float16_t	y
	)

private

◆ rel_entr() [2/2]

__STATIC_INLINE float32_t rel_entr	(	float32_t	x,
		float32_t	y
	)

private

◆ riscv_jensenshannon_distance_f16()

RISCV_DSP_ATTRIBUTE float16_t riscv_jensenshannon_distance_f16	(	const float16_t *	pA,
		const float16_t *	pB,
		uint32_t	blockSize
	)

Jensen-Shannon distance between two vectors.

This function is assuming that elements of second vector are > 0 and 0 only when the corresponding element of first vector is 0. Otherwise the result of the computation does not make sense and for speed reasons, the cases returning NaN or Infinity are not managed.

When the function is computing x log (x / y) with x == 0 and y == 0, it will compute the right result (0) but a division by zero will occur and should be ignored in client code.

Parameters

[in]	pA	First vector
[in]	pB	Second vector
[in]	blockSize	vector length

Returns: distance

◆ riscv_jensenshannon_distance_f32()

RISCV_DSP_ATTRIBUTE float32_t riscv_jensenshannon_distance_f32	(	const float32_t *	pA,
		const float32_t *	pB,
		uint32_t	blockSize
	)