void arm_negate_q7(
q7_t * pSrc,
q7_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
q7_t in1; /* Input value1 */
q7_t in2; /* Input value2 */
q7_t in3; /* Input value3 */
q7_t in4; /* Input value4 */
/*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 */
/* Read four inputs */
in1 = *pSrc++;
in2 = *pSrc++;
in3 = *pSrc++;
in4 = *pSrc++;
/* Store the Negated results in the destination buffer in a single cycle by packing the results */
*__SIMD32(pDst)++ =
__PACKq7(__SSAT(-in1, 8), __SSAT(-in2, 8), __SSAT(-in3, 8),
__SSAT(-in4, 8));
/* 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 */
while(blkCnt > 0u) {
/* C = -A */
/* Negate and then store the results in the destination buffer. */
*pDst++ = __SSAT(-*pSrc++, 8);
/* Decrement the loop counter */
blkCnt--;
}
}
void arm_fill_q7(
q7_t value,
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 */
q31_t packedValue; /* value packed to 32 bits */
/*loop Unrolling */
blkCnt = blockSize >> 2u;
/* Packing four 8 bit values to 32 bit value in order to use SIMD */
packedValue = __PACKq7(value, value, value, value);
/* 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 = value */
/* Fill the value in the destination buffer */
*__SIMD32(pDst)++ = packedValue;
/* 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 */
/* Loop over blockSize number of values */
blkCnt = blockSize;
#endif /* #ifndef ARM_MATH_CM0_FAMILY */
while(blkCnt > 0u)
{
/* C = value */
/* Fill the value in the destination buffer */
*pDst++ = value;
/* Decrement the loop counter */
blkCnt--;
}
}
void arm_abs_q7(
q7_t * pSrc,
q7_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
q7_t in1; /* Input value1 */
q7_t in2; /* Input value2 */
q7_t in3; /* Input value3 */
q7_t in4; /* Input value4 */
/*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| */
/* Read 4 inputs */
in1 = *pSrc++;
in2 = *pSrc++;
in3 = *pSrc++;
in4 = *pSrc++;
/* Store the Absolute result in the destination buffer by packing the 4 values in single cycle */
*__SIMD32(pDst)++ =
__PACKq7(((in1 > 0) ? in1 : __SSAT(-in1, 8)),
((in2 > 0) ? in2 : __SSAT(-in2, 8)),
((in3 > 0) ? in3 : __SSAT(-in3, 8)),
((in4 > 0) ? in4 : __SSAT(-in4, 8)));
/* 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| */
/* Read the input */
in1 = *pSrc++;
/* Store the Absolute result in the destination buffer */
*pDst++ = (in1 > 0) ? in1 : __SSAT(-in1, 8);
/* Decrement the loop counter */
blkCnt--;
}
}
void arm_offset_q7(
q7_t * pSrc,
q7_t offset,
q7_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t offset_packed; /* Offset packed to 32 bit */
/*loop Unrolling */
blkCnt = blockSize >> 2u;
/* Offset is packed to 32 bit in order to use SIMD32 for addition */
offset_packed = __PACKq7(offset, offset, offset, offset);
/* 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 + offset */
/* Add offset and then store the results in the destination bufferfor 4 samples at a time. */
*__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrc)++, offset_packed);
/* 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 + offset */
/* Add offset and then store the result in the destination buffer. */
*pDst++ = (q7_t) __SSAT(*pSrc++ + offset, 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 + offset */
/* Add offset and then store the result in the destination buffer. */
*pDst++ = (q7_t) __SSAT((q15_t) * pSrc++ + offset, 8);
/* Decrement the loop counter */
blkCnt--;
}
#endif /* #ifndef ARM_MATH_CM0 */
}