1 /* ----------------------------------------------------------------------
2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
4 * $Date: 17. January 2013
7 * Project: CMSIS DSP Library
10 * Description: Q15 vector addition
12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
14 * Redistribution and use in source and binary forms, with or without
15 * modification, are permitted provided that the following conditions
17 * - Redistributions of source code must retain the above copyright
18 * notice, this list of conditions and the following disclaimer.
19 * - Redistributions in binary form must reproduce the above copyright
20 * notice, this list of conditions and the following disclaimer in
21 * the documentation and/or other materials provided with the
23 * - Neither the name of ARM LIMITED nor the names of its contributors
24 * may be used to endorse or promote products derived from this
25 * software without specific prior written permission.
27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
30 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
31 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
32 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
33 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
34 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
35 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
37 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
38 * POSSIBILITY OF SUCH DAMAGE.
39 * -------------------------------------------------------------------- */
48 * @addtogroup BasicAdd
53 * @brief Q15 vector addition.
54 * @param[in] *pSrcA points to the first input vector
55 * @param[in] *pSrcB points to the second input vector
56 * @param[out] *pDst points to the output vector
57 * @param[in] blockSize number of samples in each vector
60 * <b>Scaling and Overflow Behavior:</b>
62 * The function uses saturating arithmetic.
63 * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
72 uint32_t blkCnt; /* loop counter */
74 #ifndef ARM_MATH_CM0_FAMILY
76 /* Run the below code for Cortex-M4 and Cortex-M3 */
77 q31_t inA1, inA2, inB1, inB2;
80 blkCnt = blockSize >> 2u;
82 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
83 ** a second loop below computes the remaining 1 to 3 samples. */
87 /* Add and then store the results in the destination buffer. */
88 inA1 = *__SIMD32(pSrcA)++;
89 inA2 = *__SIMD32(pSrcA)++;
90 inB1 = *__SIMD32(pSrcB)++;
91 inB2 = *__SIMD32(pSrcB)++;
93 *__SIMD32(pDst)++ = __QADD16(inA1, inB1);
94 *__SIMD32(pDst)++ = __QADD16(inA2, inB2);
96 /* Decrement the loop counter */
100 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
101 ** No loop unrolling is used. */
102 blkCnt = blockSize % 0x4u;
107 /* Add and then store the results in the destination buffer. */
108 *pDst++ = (q15_t) __QADD16(*pSrcA++, *pSrcB++);
110 /* Decrement the loop counter */
116 /* Run the below code for Cortex-M0 */
120 /* Initialize blkCnt with number of samples */
126 /* Add and then store the results in the destination buffer. */
127 *pDst++ = (q15_t) __SSAT(((q31_t) * pSrcA++ + *pSrcB++), 16);
129 /* Decrement the loop counter */
133 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
139 * @} end of BasicAdd group