这个函数用于求16位定点数的减法，源代码分析如下：
复制代码
/**
* @brief Q15 vector subtraction.
* @param[in] *pSrcA points to the first input vector
* @param[in] *pSrcB points to the second input vector
* @param[out] *pDst points to the output vector
* @param[in] blockSize number of samples in each vector
* @return none.
*
* Scaling and Overflow Behavior:
* par
* The function uses saturating arithmetic.
* Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
*/
void arm_sub_q15(
q15_t * pSrcA,
q15_t * pSrcB,
q15_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t inA1, inA2;
q31_t inB1, inB2;
/*loop Unrolling */
blkCnt = blockSize >> 2u;
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while(blkCnt > 0u)
{
/* C = A - B */
/* Subtract and then store the results in the destination buffer two samples at a time. */
inA1 = *__SIMD32(pSrcA)++; (1)
inA2 = *__SIMD32(pSrcA)++;
inB1 = *__SIMD32(pSrcB)++;
inB2 = *__SIMD32(pSrcB)++;
*__SIMD32(pDst)++ = __QSUB16(inA1, inB1); (2)
*__SIMD32(pDst)++ = __QSUB16(inA2, inB2);
/* Decrement the loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4u;
while(blkCnt > 0u)
{
/* C = A - B */
/* Subtract and then store the result in the destination buffer. */
*pDst++ = (q15_t) __QSUB16(*pSrcA++, *pSrcB++);
/* Decrement the loop counter */
blkCnt--;
}
#else
/* Run the below code for Cortex-M0 */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
while(blkCnt > 0u)
{
/* C = A - B */
/* Subtract and then store the result in the destination buffer. */
*pDst++ = (q15_t) __SSAT(((q31_t) * pSrcA++ - *pSrcB++), 16);
/* Decrement the loop counter */
blkCnt--;
}
#endif /* #ifndef ARM_MATH_CM0_FAMILY */
}
这个函数用于求8位定点数的减法，源代码分析如下：
复制代码
/**
* @brief Q7 vector subtraction.
* @param[in] *pSrcA points to the first input vector
* @param[in] *pSrcB points to the second input vector
* @param[out] *pDst points to the output vector
* @param[in] blockSize number of samples in each vector
* @return none.
*
* Scaling and Overflow Behavior:
* par
* The function uses saturating arithmetic.
* Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.
*/
void arm_sub_q7(
q7_t * pSrcA,
q7_t * pSrcB,
q7_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
/*loop Unrolling */
blkCnt = blockSize >> 2u;
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while(blkCnt > 0u)
{
/* C = A - B */
/* Subtract and then store the results in the destination buffer 4 samples at a time. */
*__SIMD32(pDst)++ = __QSUB8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++); (1)
/* Decrement the loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4u;
while(blkCnt > 0u)
{
/* C = A - B */
/* Subtract and then store the result in the destination buffer. */
*pDst++ = __SSAT(*pSrcA++ - *pSrcB++, 8);
/* Decrement the loop counter */
blkCnt--;
}
#else
/* Run the below code for Cortex-M0 */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
while(blkCnt > 0u)
{
/* C = A - B */
/* Subtract and then store the result in the destination buffer. */
*pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ - *pSrcB++, 8);
/* Decrement the loop counter */
blkCnt--;
}
#endif /* #ifndef ARM_MATH_CM0_FAMILY */
}
这个函数用于求32位浮点数的比例放缩，源代码分析如下：
复制代码
/**
* @brief Multiplies a floating-point vector by a scalar.
* @param[in] *pSrc points to the input vector
* @param[in] scale scale factor to be applied
* @param[out] *pDst points to the output vector
* @param[in] blockSize number of samples in the vector
* @return none.
*/
void arm_scale_f32(
float32_t * pSrc,
float32_t scale,
float32_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
float32_t in1, in2, in3, in4; /* temporary variabels */
/*loop Unrolling */
blkCnt = blockSize >> 2u;
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while(blkCnt > 0u)
{
/* C = A * scale */
/* Scale the input and then store the results in the destination buffer. */
/* read input samples from source */
in1 = *pSrc;
in2 = *(pSrc + 1);
/* multiply with scaling factor */ (1)
in1 = in1 * scale;
/* read input sample from source */
in3 = *(pSrc + 2);
/* multiply with scaling factor */
in2 = in2 * scale;
/* read input sample from source */
in4 = *(pSrc + 3);
/* multiply with scaling factor */
in3 = in3 * scale;
in4 = in4 * scale;
/* store the result to destination */
*pDst = in1;
*(pDst + 1) = in2;
*(pDst + 2) = in3;
*(pDst + 3) = in4;
/* update pointers to process next samples */
pSrc += 4u;
pDst += 4u;
/* Decrement the loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4u;
#else
/* Run the below code for Cortex-M0 */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
#endif /* #ifndef ARM_MATH_CM0_FAMILY */
while(blkCnt > 0u)
{
/* C = A * scale */
/* Scale the input and then store the result in the destination buffer. */
*pDst++ = (*pSrc++) * scale;
/* Decrement the loop counter */
blkCnt--;
}
}
这个函数用于求16位定点数的比例放缩，源代码分析如下：
复制代码
/**
* @brief Multiplies a Q15 vector by a scalar.
* @param[in] *pSrc points to the input vector
* @param[in] scaleFract fractional portion of the scale value
* @param[in] shift number of bits to shift the result by
* @param[out] *pDst points to the output vector
* @param[in] blockSize number of samples in the vector
* @return none.
*
* Scaling and Overflow Behavior: (1)
* par
* The input data *pSrc and scaleFract are in 1.15 format.
* These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format.
*/
void arm_scale_q15(
q15_t * pSrc,
q15_t scaleFract,
int8_t shift,
q15_t * pDst,
uint32_t blockSize)
{
int8_t kShift = 15 - shift; /* shift to apply after scaling */ (2)
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
q15_t in1, in2, in3, in4;
q31_t inA1, inA2; /* Temporary variables */
q31_t out1, out2, out3, out4;
/*loop Unrolling */
blkCnt = blockSize >> 2u;
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while(blkCnt > 0u)
{
/* Reading 2 inputs from memory */
inA1 = *__SIMD32(pSrc)++; (3)
inA2 = *__SIMD32(pSrc)++;
/* C = A * scale */
/* Scale the inputs and then store the 2 results in the destination buffer
* in single cycle by packing the outputs */
out1 = (q31_t) ((q15_t) (inA1 >> 16) * scaleFract); (4)
out2 = (q31_t) ((q15_t) inA1 * scaleFract);
out3 = (q31_t) ((q15_t) (inA2 >> 16) * scaleFract);
out4 = (q31_t) ((q15_t) inA2 * scaleFract);
/* apply shifting */
out1 = out1 >> kShift;
out2 = out2 >> kShift;
out3 = out3 >> kShift;
out4 = out4 >> kShift;
/* saturate the output */
in1 = (q15_t) (__SSAT(out1, 16)); (5)
in2 = (q15_t) (__SSAT(out2, 16));
in3 = (q15_t) (__SSAT(out3, 16));
in4 = (q15_t) (__SSAT(out4, 16));
/* store the result to destination */ (6)
*__SIMD32(pDst)++ = __PKHBT(in2, in1, 16);
*__SIMD32(pDst)++ = __PKHBT(in4, in3, 16);
/* Decrement the loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4u;
while(blkCnt > 0u)
{
/* C = A * scale */
/* Scale the input and then store the result in the destination buffer. */
*pDst++ = (q15_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 16));
/* Decrement the loop counter */
blkCnt--;
}
#else
/* Run the below code for Cortex-M0 */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
while(blkCnt > 0u)
{
/* C = A * scale */
/* Scale the input and then store the result in the destination buffer. */
*pDst++ = (q15_t) (__SSAT(((q31_t) * pSrc++ * scaleFract) >> kShift, 16));
/* Decrement the loop counter */
blkCnt--;
}
#endif /* #ifndef ARM_MATH_CM0_FAMILY */
}
这个函数用于求8位定点数的比例放缩，源代码分析如下：
复制代码
/**
* @brief Multiplies a Q7 vector by a scalar.
* @param[in] *pSrc points to the input vector
* @param[in] scaleFract fractional portion of the scale value
* @param[in] shift number of bits to shift the result by
* @param[out] *pDst points to the output vector
* @param[in] blockSize number of samples in the vector
* @return none.
*
* Scaling and Overflow Behavior: (1)
* par
* The input data *pSrc and scaleFract are in 1.7 format.
* These are multiplied to yield a 2.14 intermediate result and this is shifted with saturation to 1.7 format.
*/
void arm_scale_q7(
q7_t * pSrc,
q7_t scaleFract,
int8_t shift,
q7_t * pDst,
uint32_t blockSize)
{
int8_t kShift = 7 - shift; /* shift to apply after scaling */ (2)
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
q7_t in1, in2, in3, in4, out1, out2, out3, out4; /* Temporary variables to store input & output */
/*loop Unrolling */
blkCnt = blockSize >> 2u;
/* First part of the processing with loop unrolling. Compute 4 outputs at a time.
** a second loop below computes the remaining 1 to 3 samples. */
while(blkCnt > 0u)
{
/* Reading 4 inputs from memory */
in1 = *pSrc++;
in2 = *pSrc++;
in3 = *pSrc++;
in4 = *pSrc++;
/* C = A * scale */
/* Scale the inputs and then store the results in the temporary variables. */
out1 = (q7_t) (__SSAT(((in1) * scaleFract) >> kShift, 8)); (3)
out2 = (q7_t) (__SSAT(((in2) * scaleFract) >> kShift, 8));
out3 = (q7_t) (__SSAT(((in3) * scaleFract) >> kShift, 8));
out4 = (q7_t) (__SSAT(((in4) * scaleFract) >> kShift, 8));
/* Packing the individual outputs into 32bit and storing in
* destination buffer in single write */
*__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4); (4)
/* Decrement the loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 4, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4u;
while(blkCnt > 0u)
{
/* C = A * scale */
/* Scale the input and then store the result in the destination buffer. */
*pDst++ = (q7_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 8));
/* Decrement the loop counter */
blkCnt--;
}
#else
/* Run the below code for Cortex-M0 */
/* Initialize blkCnt with number of samples */
blkCnt = blockSize;
while(blkCnt > 0u)
{
/* C = A * scale */
/* Scale the input and then store the result in the destination buffer. */
*pDst++ = (q7_t) (__SSAT((((q15_t) * pSrc++ * scaleFract) >> kShift), 8));
/* Decrement the loop counter */
blkCnt--;
}
#endif /* #ifndef ARM_MATH_CM0_FAMILY */
}
0
/6 
工商网监
湘ICP备2023018690号
5475
淘帖
1221
发表评论
赞
回复
