void arm_negate_q7(
q7_t * pSrc,
q7_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
q7_t in;
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t input; /* Input values1-4 */
q31_t zero = 0x00000000;
/*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 */
input = *__SIMD32(pSrc)++;
/* Store the Negated results in the destination buffer in a single cycle by packing the results */
*__SIMD32(pDst)++ = __QSUB8(zero, input);
/* 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 */
/* Negate and then store the results in the destination buffer. */ \
in = *pSrc++;
*pDst++ = (in == (q7_t) 0x80) ? 0x7f : -in;
/* 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 in; /* Input value1 */
#ifndef ARM_MATH_CM0_FAMILY
/* Run the below code for Cortex-M4 and Cortex-M3 */
q31_t in1, in2, in3, in4; /* temporary input variables */
q31_t out1, out2, out3, out4; /* temporary output variables */
/*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 inputs */
in1 = (q31_t) * pSrc;
in2 = (q31_t) * (pSrc + 1);
in3 = (q31_t) * (pSrc + 2);
/* find absolute value */
out1 = (in1 > 0) ? in1 : (q31_t)__QSUB8(0, in1);
/* read input */
in4 = (q31_t) * (pSrc + 3);
/* find absolute value */
out2 = (in2 > 0) ? in2 : (q31_t)__QSUB8(0, in2);
/* store result to destination */
*pDst = (q7_t) out1;
/* find absolute value */
out3 = (in3 > 0) ? in3 : (q31_t)__QSUB8(0, in3);
/* find absolute value */
out4 = (in4 > 0) ? in4 : (q31_t)__QSUB8(0, in4);
/* store result to destination */
*(pDst + 1) = (q7_t) out2;
/* store result to destination */
*(pDst + 2) = (q7_t) out3;
/* store result to destination */
*(pDst + 3) = (q7_t) out4;
/* 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 */
blkCnt = blockSize;
#endif // #define ARM_MATH_CM0_FAMILY
while(blkCnt > 0u)
{
/* C = |A| */
/* Read the input */
in = *pSrc++;
/* Store the Absolute result in the destination buffer */
*pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? 0x7f : -in);
/* Decrement the loop counter */
blkCnt--;
}
}
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)++);
/* 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 */
}
void arm_sub_q7(
q7_t * pSrcA,
q7_t * pSrcB,
q7_t * pDst,
uint32_t blockSize)
{
uint32_t blkCnt; /* loop counter */
q31_t inA1, inB1, inA2, inB2; /* temporary input variabels */
q7_t inA, inB; /* temporary variables */
q31_t out1, out2, out3, out4; /* temporary output variables */
/*loop Unrolling */
blkCnt = blockSize >> 4u;
/* First part of the processing with loop unrolling. Compute 16 outputs at a time.
** a second loop below computes the remaining 1 to 15 samples. */
while(blkCnt > 0u)
{
/* C = A - B */
/* Subtract and then store the results in the destination buffer 4 samples at a time. */
/* read 4 samples at a time from sourceA */
inA1 = _SIMD32_OFFSET(pSrcA);
/* read 4 samples at a time from sourceB */
inB1 = _SIMD32_OFFSET(pSrcB);
/* read 4 samples at a time from sourceA */
inA2 = _SIMD32_OFFSET(pSrcA + 4);
/* out = saturate(sourceA - sourceB) four samples at a time */
out1 = __QSUB8(inA1, inB1);
/* read 4 samples at a time from sourceB */
inB2 = _SIMD32_OFFSET(pSrcB + 4);
/* store result to destination four samples at a time */
_SIMD32_OFFSET(pDst) = out1;
/* out = saturate(sourceA - sourceB) four samples at a time */
out2 = __QSUB8(inA2, inB2);
/* read 4 samples at a time from sourceA */
inA1 = _SIMD32_OFFSET(pSrcA + 8);
/* read 4 samples at a time from sourceB */
inB1 = _SIMD32_OFFSET(pSrcB + 8);
/* read 4 samples at a time from sourceA */
inA2 = _SIMD32_OFFSET(pSrcA + 12);
/* out = saturate(sourceA - sourceB) four samples at a time */
out3 = __QSUB8(inA1, inB1);
/* read 4 samples at a time from sourceB */
inB2 = _SIMD32_OFFSET(pSrcB + 12);
/* increment sourceA pointer by 16 to process next samples */
pSrcA += 16u;
/* store result to destination four samples at a time */
_SIMD32_OFFSET(pDst + 4) = out2;
/* out = saturate(sourceA - sourceB) four samples at a time */
out4 = __QSUB8(inA2, inB2);
/* store result to destination four samples at a time */
_SIMD32_OFFSET(pDst + 8) = out3;
/* Update source pointer to process next sampels */
pSrcB += 16u;
/* store result to destination four samples at a time */
_SIMD32_OFFSET(pDst + 12) = out4;
/* Update destination pointer to process next sampels */
pDst += 16u;
/* Decrement the loop counter */
blkCnt--;
}
/* If the blockSize is not a multiple of 16, compute any remaining output samples here.
** No loop unrolling is used. */
blkCnt = blockSize % 0x10u;
while(blkCnt > 0u)
{
/* C = A - B */
/* Subtract and then store the result in the destination buffer. */
inA = *pSrcA++;
inB = *pSrcB++;
#ifdef CCS
*pDst++ = __SSATA(inA - inB, 0, 8);
#else
*pDst++ = __SSAT(inA - inB, 8);
#endif //#ifdef CCS
/* Decrement the loop counter */
blkCnt--;
}
}
/**
\brief Test case: TC_CoreSimd_ParAddSub8
\details
- Check Parallel 8-bit addition and subtraction:
__SADD8 S Signed
__SSUB8 Q Signed Saturating
__SHADD8 SH Signed Halving
__SHSUB8 U Unsigned
__QADD8 UQ Unsigned Saturating
__QSUB8 UH Unsigned Halving
__UADD8
__USUB8
__UHADD8
__UHSUB8
__UQADD8
__UQSUB8
*/
void TC_CoreSimd_ParAddSub8 (void) {
#if ((defined (__ARM_ARCH_7EM__ ) && (__ARM_ARCH_7EM__ == 1)) || \
(defined (__ARM_FEATURE_DSP) && (__ARM_FEATURE_DSP == 1)) )
volatile uint32_t op1_u32, op2_u32;
volatile uint32_t res_u32;
volatile int32_t op1_s32, op2_s32;
volatile int32_t res_s32;
/* --- __SADD8 Test ---------------------------------------------- */
op1_s32 = (int32_t)0x87858381;
op2_s32 = (int32_t)0x08060402;
res_s32 = __SADD8(op1_s32, op2_s32);
ASSERT_TRUE(res_s32 == (int32_t)0x8F8B8783);
/* --- __SSUB8 Test ---------------------------------------------- */
op1_s32 = (int32_t)0x8F8B8783;
op2_s32 = (int32_t)0x08060402;
res_s32 = __SSUB8(op1_s32, op2_s32);
ASSERT_TRUE(res_s32 == (int32_t)0x87858381);
/* --- __SHADD8 Test ---------------------------------------------- */
op1_s32 = 0x07050302;
op2_s32 = 0x08060402;
res_s32 = __SHADD8(op1_s32, op2_s32);
ASSERT_TRUE(res_s32 == 0x07050302);
/* --- __SHSUB8 Test ---------------------------------------------- */
op1_s32 = (int32_t)0x8F8B8783;
op2_s32 = 0x08060402;
res_s32 = __SHSUB8(op1_s32, op2_s32);
ASSERT_TRUE(res_s32 == (int32_t)0xC3C2C1C0);
/* --- __QADD8 Test ---------------------------------------------- */
op1_s32 = (int32_t)0x8085837F;
op2_s32 = (int32_t)0xFF060402;
res_s32 = __QADD8(op1_s32, op2_s32);
ASSERT_TRUE(res_s32 == (int32_t)0x808B877F);
/* --- __QSUB8 Test ---------------------------------------------- */
op1_s32 = (int32_t)0x808B8783;
op2_s32 = (int32_t)0x08060402;
res_s32 = __QSUB8(op1_s32, op2_s32);
ASSERT_TRUE(res_s32 == (int32_t)0x80858381);
/* --- __UADD8 Test ---------------------------------------------- */
op1_u32 = 0x07050301;
op2_u32 = 0x08060402;
res_u32 = __UADD8(op1_u32, op2_u32);
ASSERT_TRUE(res_u32 == 0x0F0B0703);
/* --- __USUB8 Test ---------------------------------------------- */
op1_u32 = 0x0F0B0703;
op2_u32 = 0x08060402;
res_u32 = __USUB8(op1_u32, op2_u32);
ASSERT_TRUE(res_u32 == 0x07050301);
/* --- __UHADD8 Test ---------------------------------------------- */
op1_u32 = 0x07050302;
op2_u32 = 0x08060402;
res_u32 = __UHADD8(op1_u32, op2_u32);
ASSERT_TRUE(res_u32 == 0x07050302);
/* --- __UHSUB8 Test ---------------------------------------------- */
op1_u32 = 0x0F0B0703;
op2_u32 = 0x08060402;
res_u32 = __UHSUB8(op1_u32, op2_u32);
ASSERT_TRUE(res_u32 == 0x03020100);
/* --- __UQADD8 Test ---------------------------------------------- */
op1_u32 = 0xFF050301;
op2_u32 = 0x08060402;
res_u32 = __UQADD8(op1_u32, op2_u32);
ASSERT_TRUE(res_u32 == 0xFF0B0703);
/* --- __UQSUB8 Test ---------------------------------------------- */
op1_u32 = 0x080B0702;
op2_u32 = 0x0F060408;
res_u32 = __UQSUB8(op1_u32, op2_u32);
ASSERT_TRUE(res_u32 == 0x00050300);
#endif
}