1 /* ----------------------------------------------------------------------
2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
4 * $Date: 17. January 2013
7 * Project: CMSIS DSP Library
10 * Description: Root Mean Square of the elements of a Q31 vector.
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 * ---------------------------------------------------------------------------- */
50 * @brief Root Mean Square of the elements of a Q31 vector.
51 * @param[in] *pSrc points to the input vector
52 * @param[in] blockSize length of the input vector
53 * @param[out] *pResult rms value returned here
57 * <b>Scaling and Overflow Behavior:</b>
60 * The function is implemented using an internal 64-bit accumulator.
61 * The input is represented in 1.31 format, and intermediate multiplication
62 * yields a 2.62 format.
63 * The accumulator maintains full precision of the intermediate multiplication results,
64 * but provides only a single guard bit.
65 * There is no saturation on intermediate additions.
66 * If the accumulator overflows, it wraps around and distorts the result.
67 * In order to avoid overflows completely, the input signal must be scaled down by
68 * log2(blockSize) bits, as a total of blockSize additions are performed internally.
69 * Finally, the 2.62 accumulator is right shifted by 31 bits to yield a 1.31 format value.
78 q63_t sum = 0; /* accumulator */
79 q31_t in; /* Temporary variable to store the input */
80 uint32_t blkCnt; /* loop counter */
82 #ifndef ARM_MATH_CM0_FAMILY
84 /* Run the below code for Cortex-M4 and Cortex-M3 */
86 q31_t in1, in2, in3, in4; /* Temporary input variables */
89 blkCnt = blockSize >> 2u;
91 /* First part of the processing with loop unrolling. Compute 8 outputs at a time.
92 ** a second loop below computes the remaining 1 to 7 samples. */
95 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
96 /* Compute sum of the squares and then store the result in a temporary variable, sum */
97 /* read two samples from source buffer */
101 /* calculate power and accumulate to accumulator */
102 sum += (q63_t) in1 *in1;
103 sum += (q63_t) in2 *in2;
105 /* read two samples from source buffer */
109 /* calculate power and accumulate to accumulator */
110 sum += (q63_t) in3 *in3;
111 sum += (q63_t) in4 *in4;
114 /* update source buffer to process next samples */
117 /* Decrement the loop counter */
121 /* If the blockSize is not a multiple of 8, compute any remaining output samples here.
122 ** No loop unrolling is used. */
123 blkCnt = blockSize % 0x4u;
127 /* Run the below code for Cortex-M0 */
130 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
134 /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
135 /* Compute sum of the squares and then store the results in a temporary variable, sum */
137 sum += (q63_t) in *in;
139 /* Decrement the loop counter */
143 /* Convert data in 2.62 to 1.31 by 31 right shifts and saturate */
145 sum = __SSAT(sum >> 31, 31);
148 /* Compute Rms and store the result in the destination vector */
149 arm_sqrt_q31((q31_t) ((q31_t) sum / (int32_t) blockSize), pResult);
153 * @} end of RMS group