void arm_q7_to_q31(
q7_t * pSrc,
q31_t * pDst,
uint32_t blockSize)
{
q7_t *pIn = pSrc; /* Src pointer */
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0_FAMILY
q31_t in;
/* 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 = (q31_t) A << 24 */
/* convert from q7 to q31 and then store the results in the destination buffer */
in = *__SIMD32(pIn)++;
#ifndef ARM_MATH_BIG_ENDIAN
*pDst++ = (__ROR(in, 8)) & 0xFF000000;
*pDst++ = (__ROR(in, 16)) & 0xFF000000;
*pDst++ = (__ROR(in, 24)) & 0xFF000000;
*pDst++ = (in & 0xFF000000);
#else
*pDst++ = (in & 0xFF000000);
*pDst++ = (__ROR(in, 24)) & 0xFF000000;
*pDst++ = (__ROR(in, 16)) & 0xFF000000;
*pDst++ = (__ROR(in, 8)) & 0xFF000000;
#endif // #ifndef ARM_MATH_BIG_ENDIAN
/* 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 = (q31_t) A << 24 */
/* convert from q7 to q31 and then store the results in the destination buffer */
*pDst++ = (q31_t) * pIn++ << 24;
/* Decrement the loop counter */
blkCnt--;
}
}
void arm_q7_to_q15(
q7_t * pSrc,
q15_t * pDst,
uint32_t blockSize)
{
q7_t *pIn = pSrc; /* Src pointer */
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0_FAMILY
q31_t in;
q31_t in1, in2;
q31_t out1, out2;
/* 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 = (q15_t) A << 8 */
/* convert from q7 to q15 and then store the results in the destination buffer */
in = *__SIMD32(pIn)++;
/* rotatate in by 8 and extend two q7_t values to q15_t values */
in1 = __SXTB16(__ROR(in, 8));
/* extend remainig two q7_t values to q15_t values */
in2 = __SXTB16(in);
in1 = in1 << 8u;
in2 = in2 << 8u;
in1 = in1 & 0xFF00FF00;
in2 = in2 & 0xFF00FF00;
#ifndef ARM_MATH_BIG_ENDIAN
out2 = __PKHTB(in1, in2, 16);
out1 = __PKHBT(in2, in1, 16);
#else
out1 = __PKHTB(in1, in2, 16);
out2 = __PKHBT(in2, in1, 16);
#endif
*__SIMD32(pDst)++ = out1;
*__SIMD32(pDst)++ = out2;
/* 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 = (q15_t) A << 8 */
/* convert from q7 to q15 and then store the results in the destination buffer */
*pDst++ = (q15_t) * pIn++ << 8;
/* Decrement the loop counter */
blkCnt--;
}
}
void arm_dot_prod_q7(
q7_t * pSrcA,
q7_t * pSrcB,
uint32_t blockSize,
q31_t * result)
{
uint32_t blkCnt; /* loop counter */
q31_t sum = 0; /* Temporary variables to store output */
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t input1, input2; /* Temporary variables to store input */
q31_t inA1, inA2, inB1, inB2; /* Temporary variables to store input */
/*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)
{
/* read 4 samples at a time from sourceA */
input1 = *__SIMD32(pSrcA)++;
/* read 4 samples at a time from sourceB */
input2 = *__SIMD32(pSrcB)++;
/* extract two q7_t samples to q15_t samples */
inA1 = __SXTB16(__ROR(input1, 8));
/* extract reminaing two samples */
inA2 = __SXTB16(input1);
/* extract two q7_t samples to q15_t samples */
inB1 = __SXTB16(__ROR(input2, 8));
/* extract reminaing two samples */
inB2 = __SXTB16(input2);
/* multiply and accumulate two samples at a time */
sum = __SMLAD(inA1, inB1, sum);
sum = __SMLAD(inA2, inB2, sum);
/* 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[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
/* Dot product and then store the results in a temporary buffer. */
sum = __SMLAD(*pSrcA++, *pSrcB++, sum);
/* 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[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
/* Dot product and then store the results in a temporary buffer. */
sum += (q31_t) ((q15_t) * pSrcA++ * *pSrcB++);
/* Decrement the loop counter */
blkCnt--;
}
#endif /* #ifndef ARM_MATH_CM0_FAMILY */
/* Store the result in the destination buffer in 18.14 format */
*result = sum;
}
void arm_power_q7(
q7_t * pSrc,
uint32_t blockSize,
q31_t * pResult)
{
q31_t sum = 0; /* Temporary result storage */
q7_t in; /* Temporary variable to store input */
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t input1; /* Temporary variable to store packed input */
q31_t in1, in2; /* Temporary variables to store input */
/*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 two inputs of pSrc vector and packing */
input1 = *__SIMD32(pSrc)++;
in1 = __SXTB16(__ROR(input1, 8));
in2 = __SXTB16(input1);
/* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
/* calculate power and accumulate to accumulator */
sum = __SMLAD(in1, in1, sum);
sum = __SMLAD(in2, in2, sum);
/* 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 */
while(blkCnt > 0u)
{
/* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
/* Compute Power and then store the result in a temporary variable, sum. */
in = *pSrc++;
sum += ((q15_t) in * in);
/* Decrement the loop counter */
blkCnt--;
}
/* Store the result in 18.14 format */
*pResult = sum;
}
/**
* @brief AES CCM Authentication TAG generation.
* @param hcryp: pointer to a CRYP_HandleTypeDef structure that contains
* the configuration information for CRYP module
* @param AuthTag: Pointer to the authentication buffer
* @param Timeout: Timeout duration
* @retval HAL status
*/
HAL_StatusTypeDef HAL_CRYPEx_AESCCM_GenerateAuthTAG(CRYP_HandleTypeDef *hcryp, uint32_t *AuthTag, uint32_t Timeout)
{
uint32_t tagaddr = (uint32_t)AuthTag;
uint32_t ctr0 [4]={0};
uint32_t ctr0addr = (uint32_t)ctr0;
uint32_t tickstart = 0U;
if(hcryp->State == HAL_CRYP_STATE_READY)
{
/* Process locked */
__HAL_LOCK(hcryp);
/* Change the CRYP peripheral state */
hcryp->State = HAL_CRYP_STATE_BUSY;
/* Check if initialization phase has already been performed */
if(hcryp->Phase == CRYPEx_PHASE_PROCESS)
{
/* Change the CRYP phase */
hcryp->Phase = CRYPEx_PHASE_FINAL;
}
else /* Initialization phase has not been performed*/
{
/* Disable the peripheral */
__HAL_CRYP_DISABLE(hcryp);
/* Sequence error code field */
hcryp->ErrorCode |= HAL_CRYP_ERROR_AUTH_TAG_SEQUENCE;
/* Change the CRYP peripheral state */
hcryp->State = HAL_CRYP_STATE_READY;
/* Process unlocked */
__HAL_UNLOCK(hcryp);
return HAL_ERROR;
}
/* Disable CRYP to start the final phase */
__HAL_CRYP_DISABLE(hcryp);
/* Select final phase & ALGODIR bit must be set to ‘0’. */
MODIFY_REG(hcryp->Instance->CR, CRYP_CR_GCM_CCMPH|CRYP_CR_ALGODIR, CRYP_PHASE_FINAL|CRYP_OPERATINGMODE_ENCRYPT);
/* Enable the CRYP peripheral */
__HAL_CRYP_ENABLE(hcryp);
/* Write the counter block in the IN FIFO, CTR0 information from B0
data has to be swapped according to the DATATYPE*/
ctr0[0]=(hcryp->Init.B0[0]) & CRYP_CCM_CTR0_0;
ctr0[1]=hcryp->Init.B0[1];
ctr0[2]=hcryp->Init.B0[2];
ctr0[3]=hcryp->Init.B0[3] & CRYP_CCM_CTR0_3;
if(hcryp->Init.DataType == CRYP_DATATYPE_8B)
{
hcryp->Instance->DIN = __REV(*(uint32_t*)(ctr0addr));
ctr0addr+=4;
hcryp->Instance->DIN = __REV(*(uint32_t*)(ctr0addr));
ctr0addr+=4;
hcryp->Instance->DIN = __REV(*(uint32_t*)(ctr0addr));
ctr0addr+=4;
hcryp->Instance->DIN = __REV(*(uint32_t*)(ctr0addr));
}
else if(hcryp->Init.DataType == CRYP_DATATYPE_16B)
{
hcryp->Instance->DIN = __ROR(*(uint32_t*)(ctr0addr), 16U);
ctr0addr+=4;
hcryp->Instance->DIN = __ROR(*(uint32_t*)(ctr0addr), 16U);
ctr0addr+=4;
hcryp->Instance->DIN = __ROR(*(uint32_t*)(ctr0addr), 16U);
ctr0addr+=4;
hcryp->Instance->DIN = __ROR(*(uint32_t*)(ctr0addr), 16U);
}
else if(hcryp->Init.DataType == CRYP_DATATYPE_1B)
{
hcryp->Instance->DIN = __RBIT(*(uint32_t*)(ctr0addr));
ctr0addr+=4;
hcryp->Instance->DIN = __RBIT(*(uint32_t*)(ctr0addr));
ctr0addr+=4;
hcryp->Instance->DIN = __RBIT(*(uint32_t*)(ctr0addr));
ctr0addr+=4;
hcryp->Instance->DIN = __RBIT(*(uint32_t*)(ctr0addr));
}
else
{
hcryp->Instance->DIN = *(uint32_t*)(ctr0addr);
ctr0addr+=4;
hcryp->Instance->DIN = *(uint32_t*)(ctr0addr);
ctr0addr+=4;
hcryp->Instance->DIN = *(uint32_t*)(ctr0addr);
ctr0addr+=4;
hcryp->Instance->DIN = *(uint32_t*)(ctr0addr);;
}
/* Wait for OFNE flag to be raised */
tickstart = HAL_GetTick();
while(HAL_IS_BIT_CLR(hcryp->Instance->SR, CRYP_FLAG_OFNE))
{
/* Check for the Timeout */
if(Timeout != HAL_MAX_DELAY)
{
if((Timeout == 0U)||((HAL_GetTick() - tickstart ) > Timeout))
{
/* Disable the CRYP peripheral Clock */
__HAL_CRYP_DISABLE(hcryp);
/* Change state */
hcryp->ErrorCode |= HAL_CRYP_ERROR_TIMEOUT;
hcryp->State = HAL_CRYP_STATE_READY;
/* Process unlocked */
__HAL_UNLOCK(hcryp);
return HAL_ERROR;
}
}
}
/* Read the Auth TAG in the IN FIFO */
*(uint32_t*)(tagaddr) = hcryp->Instance->DOUT;
tagaddr+=4U;
*(uint32_t*)(tagaddr) = hcryp->Instance->DOUT;
tagaddr+=4U;
*(uint32_t*)(tagaddr) = hcryp->Instance->DOUT;
tagaddr+=4U;
*(uint32_t*)(tagaddr) = hcryp->Instance->DOUT;
/* Change the CRYP peripheral state */
hcryp->State = HAL_CRYP_STATE_READY;
/* Process unlocked */
__HAL_UNLOCK(hcryp);
/* Disable CRYP */
__HAL_CRYP_DISABLE(hcryp);
}
else
{
/* Busy error code field */
hcryp->ErrorCode = HAL_CRYP_ERROR_BUSY;
return HAL_ERROR;
}
/* Return function status */
return HAL_OK;
}
/**
* @brief generate the GCM authentication TAG.
* @param hcryp: pointer to a CRYP_HandleTypeDef structure that contains
* the configuration information for CRYP module
* @param AuthTag: Pointer to the authentication buffer
* @param Timeout: Timeout duration
* @retval HAL status
*/
HAL_StatusTypeDef HAL_CRYPEx_AESGCM_GenerateAuthTAG(CRYP_HandleTypeDef *hcryp, uint32_t *AuthTag, uint32_t Timeout)
{
uint32_t tickstart = 0U;
uint64_t headerlength = hcryp->Init.HeaderSize * 32U; /* Header length in bits */
uint64_t inputlength = (hcryp->Size) * 32U; /* input length in bits */
uint32_t tagaddr = (uint32_t)AuthTag;
if(hcryp->State == HAL_CRYP_STATE_READY)
{
/* Process locked */
__HAL_LOCK(hcryp);
/* Change the CRYP peripheral state */
hcryp->State = HAL_CRYP_STATE_BUSY;
/* Check if initialization phase has already been performed */
if(hcryp->Phase == CRYPEx_PHASE_PROCESS)
{
/* Change the CRYP phase */
hcryp->Phase = CRYPEx_PHASE_FINAL;
}
else /* Initialization phase has not been performed*/
{
/* Disable the Peripheral */
__HAL_CRYP_DISABLE(hcryp);
/* Sequence error code field */
hcryp->ErrorCode |= HAL_CRYP_ERROR_AUTH_TAG_SEQUENCE;
/* Change the CRYP peripheral state */
hcryp->State = HAL_CRYP_STATE_READY;
/* Process unlocked */
__HAL_UNLOCK(hcryp);
return HAL_ERROR;
}
/* Disable CRYP to start the final phase */
__HAL_CRYP_DISABLE(hcryp);
/* Select final phase */
MODIFY_REG(hcryp->Instance->CR, CRYP_CR_GCM_CCMPH, CRYP_PHASE_FINAL);
/*ALGODIR bit must be set to ‘0’.*/
hcryp->Instance->CR &= ~CRYP_CR_ALGODIR;
/* Enable the CRYP peripheral */
__HAL_CRYP_ENABLE(hcryp);
/* Write the number of bits in header (64 bits) followed by the number of bits
in the payload */
if(hcryp->Init.DataType == CRYP_DATATYPE_1B)
{
hcryp->Instance->DIN = 0U;
hcryp->Instance->DIN = __RBIT((uint32_t)(headerlength));
hcryp->Instance->DIN = 0U;
hcryp->Instance->DIN = __RBIT((uint32_t)(inputlength));
}
else if(hcryp->Init.DataType == CRYP_DATATYPE_8B)
{
hcryp->Instance->DIN = 0U;
hcryp->Instance->DIN = __REV((uint32_t)(headerlength));
hcryp->Instance->DIN = 0U;
hcryp->Instance->DIN = __REV((uint32_t)(inputlength));
}
else if(hcryp->Init.DataType == CRYP_DATATYPE_16B)
{
hcryp->Instance->DIN = 0U;
hcryp->Instance->DIN = __ROR((uint32_t)headerlength, 16U);
hcryp->Instance->DIN = 0U;
hcryp->Instance->DIN = __ROR((uint32_t)inputlength, 16U);
}
else if(hcryp->Init.DataType == CRYP_DATATYPE_32B)
{
hcryp->Instance->DIN = 0U;
hcryp->Instance->DIN = (uint32_t)(headerlength);
hcryp->Instance->DIN = 0U;
hcryp->Instance->DIN = (uint32_t)(inputlength);
}
/* Wait for OFNE flag to be raised */
tickstart = HAL_GetTick();
while(HAL_IS_BIT_CLR(hcryp->Instance->SR, CRYP_FLAG_OFNE))
{
/* Check for the Timeout */
if(Timeout != HAL_MAX_DELAY)
{
if((Timeout == 0U)||((HAL_GetTick() - tickstart ) > Timeout))
{
/* Disable the CRYP Peripheral Clock */
__HAL_CRYP_DISABLE(hcryp);
/* Change state */
hcryp->ErrorCode |= HAL_CRYP_ERROR_TIMEOUT;
hcryp->State = HAL_CRYP_STATE_READY;
/* Process unlocked */
__HAL_UNLOCK(hcryp);
return HAL_ERROR;
}
}
}
/* Read the authentication TAG in the output FIFO */
*(uint32_t*)(tagaddr) = hcryp->Instance->DOUT;
tagaddr+=4U;
*(uint32_t*)(tagaddr) = hcryp->Instance->DOUT;
tagaddr+=4U;
*(uint32_t*)(tagaddr) = hcryp->Instance->DOUT;
tagaddr+=4U;
*(uint32_t*)(tagaddr) = hcryp->Instance->DOUT;
/* Disable the peripheral */
__HAL_CRYP_DISABLE(hcryp);
/* Change the CRYP peripheral state */
hcryp->State = HAL_CRYP_STATE_READY;
/* Process unlocked */
__HAL_UNLOCK(hcryp);
}
else
{
/* Busy error code field */
hcryp->ErrorCode |= HAL_CRYP_ERROR_BUSY;
return HAL_ERROR;
}
/* Return function status */
return HAL_OK;
}
void arm_q7_to_q15(
q7_t * pSrc,
q15_t * pDst,
uint32_t blockSize)
{
q7_t *pIn = pSrc; /* Src pointer */
uint32_t blkCnt; /* loop counter */
q31_t in;
q31_t in1, in2;
q31_t out1, out2;
q31_t and = 0xFF00FF00;
/*loop Unrolling */
blkCnt = blockSize >> 3u;
/* 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 = (q15_t) A << 8 */
/* convert from q7 to q15 and then store the results in the destination buffer */
/* read 4 samples at a time */
in = *__SIMD32(pIn)++;
#ifdef CCS
/* rotatate in by 8 and extend two q7_t values to q15_t values */
in1 = __SXTB16(in, 8);
/* extend remainig two q7_t values to q15_t values */
in2 = __SXTB16(in, 0);
#else
/* rotatate in by 8 and extend two q7_t values to q15_t values */
in1 = __SXTB16(__ROR(in, 8));
/* extend remainig two q7_t values to q15_t values */
in2 = __SXTB16(in);
#endif /* shift in1 by 8 to convert q7_t value to q15_t value (ex: 0x00ff00ff ==> 0xff00ff00*/
in1 = in1 << 8u;
in2 = in2 << 8u;
/* read next 4 sampels */
in = *__SIMD32(pIn)++;
/* anding with 0xff00ff00 */
in1 = in1 & and;
out2 = in2 & and;
/* pack two 16 bit values */
out1 = __PKHTB(in1, out2, 16);
out2 = __PKHBT(out2, in1, 16);
#ifndef ARM_MATH_BIG_ENDIAN
/* store two q15_t samples at a time to destination */
_SIMD32_OFFSET(pDst + 2) = out1;
#ifdef CCS
/* rotatate in by 8 and extend two q7_t values to q15_t values */
in1 = __SXTB16(in, 8);
#else
/* rotatate in by 8 and extend two q7_t values to q15_t values */
in1 = __SXTB16(__ROR(in, 8));
#endif
/* store two q15_t samples at a time to destination */
_SIMD32_OFFSET(pDst) = out2;
#else
/* store two q15_t samples at a time to destination */
_SIMD32_OFFSET(pDst) = out1;
#ifdef CCS
/* rotatate in by 8 and extend two q7_t values to q15_t values */
in1 = __SXTB16(in, 8);
#else
/* rotatate in by 8 and extend two q7_t values to q15_t values */
in1 = __SXTB16(__ROR(in, 8));
#endif
/* store two q15_t samples at a time to destination */
_SIMD32_OFFSET(pDst + 2) = out2;
#endif // #ifndef ARM_MATH_BIG_ENDIAN
#ifdef CCS
/* rotatate in by 8 and extend two q7_t values to q15_t values */
in2 = __SXTB16(in, 0);
#else
/* rotatate in by 8 and extend two q7_t values to q15_t values */
in2 = __SXTB16(in);
#endif
/* shift in1 by 8 to convert q7_t value to q15_t value (ex: 0x00ff00ff ==> 0xff00ff00*/
in1 = in1 << 8u;
in2 = in2 << 8u;
/* anding with 0xff00ff00 */
out1 = in1 & and;
out2 = in2 & and;
/* pack two 16 bit values */
out1 = __PKHTB(in1, out2, 16);
out2 = __PKHBT(out2, in1, 16);
/* store two q15_t samples at a time to destination */
#ifndef ARM_MATH_BIG_ENDIAN
_SIMD32_OFFSET(pDst + 6) = out1;
_SIMD32_OFFSET(pDst + 4) = out2;
#else
_SIMD32_OFFSET(pDst + 4) = out1;
_SIMD32_OFFSET(pDst + 6) = out2;
#endif // #ifndef ARM_MATH_BIG_ENDIAN
/* incremnet destination pointer */
pDst += 8u;
/* 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 % 0x8u;
while(blkCnt > 0u)
{
/* C = (q15_t) A << 8 */
/* convert from q7 to q15 and then store the results in the destination buffer */
*pDst++ = (q15_t) * pIn++ << 8;
/* Decrement the loop counter */
blkCnt--;
}
}
void arm_power_q7(
q7_t * pSrc,
uint32_t blockSize,
q31_t * pResult)
{
q31_t acc = 0; /* Temporary result storage */
q31_t input1; /* Temporary variable to store packed input */
q7_t in; /* Temporary variable to store input */
uint32_t blkCnt; /* loop counter */
q31_t inA1, inA2; /* Temporary variables to hold intermiediate data */
q31_t acc1 = 0;
/*loop Unrolling */
blkCnt = blockSize >> 3u;
/* 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)
{
/* read four samples at a time from soruce buffer */
input1 = _SIMD32_OFFSET(pSrc);
/* extend two q7_t values to q15_t values */
#ifdef CCS
inA1 = __SXTB16(input1, 8);
inA2 = __SXTB16(input1, 0);
#else
inA1 = __SXTB16(__ROR(input1, 8));
inA2 = __SXTB16(input1);
#endif // #ifdef CCS
/* calculate power and accumulate to accumulator */
acc = __SMLAD(inA1, inA1, acc);
/* read four samples at a time from soruce buffer */
input1 = _SIMD32_OFFSET(pSrc + 4);
#ifdef CCS
/* extend two q7_t values to q15_t values */
inA1 = __SXTB16(input1, 8);
/* calculate power and accumulate to accumulator */
acc1 = __SMLAD(inA2, inA2, acc1);
/* extend two q7_t values to q15_t values */
inA2 = __SXTB16(input1, 0);
#else
/* extend two q7_t values to q15_t values */
inA1 = __SXTB16(__ROR(input1, 8));
/* calculate power and accumulate to accumulator */
acc1 = __SMLAD(inA2, inA2, acc1);
/* extend two q7_t values to q15_t values */
inA2 = __SXTB16(input1);
#endif // #ifdef CCS
/* calculate power and accumulate to accumulator */
acc = __SMLAD(inA1, inA1, acc);
acc1 = __SMLAD(inA2, inA2, acc1);
/* update source buffer to process next samples */
pSrc += 8u;
/* Decrement the loop counter */
blkCnt--;
}
/* add accumulators */
acc = acc + acc1;
/* If the blockSize is not a multiple of 8, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x8u;
while(blkCnt > 0u)
{
/* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
/* Compute Power and then store the result in a temporary variable, acc. */
in = *pSrc++;
acc += ((q15_t) in * in);
/* Decrement the loop counter */
blkCnt--;
}
/* Store the result in 18.14 format */
*pResult = acc;
}
