void AMDemod::update(void)
{
if (!pass) return;
audio_block_t *blocki, *blockq;
int16_t *pi, *pq, *end;
int32_t sum;
blocki = receiveWritable(0); // receives I, end result is written in channel 0
blockq = receiveReadOnly(1); // receives Q
if (!blocki) {
if (blockq) release(blockq);
return;
}
if (!blockq) {
release(blocki);
return;
}
pi = (int16_t *)(blocki->data);
pq = (int16_t *)(blockq->data);
end = pi + AUDIO_BLOCK_SAMPLES;
while (pi < end) {
// square and sum I and Q
sum = *pi * *pi;
sum += *pq * *pq;
// The result of squaring a 1.15 is 2.30.
// Shift the sum up one bit to make it 1.31 (Q31)
// and then that becomes the input to the arm sqrt function
sum <<= 1;
arm_sqrt_q31((q31_t)sum,(q31_t *) &sum);
// The result is in the high order 16 bits of sum
*pi++ = sum >> 16;
pq++;
}
transmit(blocki);
release(blocki);
release(blockq);
}
void arm_rms_q31(
q31_t * pSrc,
uint32_t blockSize,
q31_t * pResult)
{
q63_t sum = 0; /* accumulator */
q31_t in; /* Temporary variable to store the input */
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t in1, in2, in3, in4; /* Temporary input variables */
/*loop Unrolling */
blkCnt = blockSize >> 2u;
/* First part of the processing with loop unrolling. Compute 8 outputs at a time.
** a second loop below computes the remaining 1 to 7 samples. */
while(blkCnt > 0u)
{
/* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
/* Compute sum of the squares and then store the result in a temporary variable, sum */
/* read two samples from source buffer */
in1 = pSrc[0];
in2 = pSrc[1];
/* calculate power and accumulate to accumulator */
sum += (q63_t) in1 *in1;
sum += (q63_t) in2 *in2;
/* read two samples from source buffer */
in3 = pSrc[2];
in4 = pSrc[3];
/* calculate power and accumulate to accumulator */
sum += (q63_t) in3 *in3;
sum += (q63_t) in4 *in4;
/* update source buffer to process next samples */
pSrc += 4u;
/* Decrement the loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 8, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x4u;
#else
/* Run the below code for Cortex-M0 */
blkCnt = blockSize;
#endif /* #ifndef ARM_MATH_CM0 */
while(blkCnt > 0u)
{
/* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
/* Compute sum of the squares and then store the results in a temporary variable, sum */
in = *pSrc++;
sum += (q63_t) in *in;
/* Decrement the loop counter */
blkCnt--;
}
/* Convert data in 2.62 to 1.31 by 31 right shifts and saturate */
sum = __SSAT(sum >> 31, 31);
/* Compute Rms and store the result in the destination vector */
arm_sqrt_q31((q31_t) ((q31_t) sum / (int32_t) blockSize), pResult);
}
