Lines Matching +full:- +full:a

1 /* ----------------------------------------------------------------------
4 * Description: Sum of the squares of the elements of a Q31 vector
9 * Target Processor: Cortex-M and Cortex-A cores
10 * -------------------------------------------------------------------- */
12 * Copyright (C) 2010-2021 ARM Limited or its affiliates. All rights reserved.
14 * SPDX-License-Identifier: Apache-2.0
18 * You may obtain a copy of the License at
20 * www.apache.org/licenses/LICENSE-2.0
41 @brief Sum of the squares of the elements of a Q31 vector.
47 The function is implemented using a 64-bit internal accumulator.
49 Intermediate multiplication yields a 2.62 format, and this
51 … The 2.48 result is then added without saturation to a 64-bit accumulator in 16.48 format.
67 /* Compute 4 outputs at a time */ in arm_power_q31()
77 blkCnt --; in arm_power_q31()
87 /* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */ in arm_power_q31()
89 /* Compute Power and store result in a temporary variable, sum. */ in arm_power_q31()
94 blkCnt--; in arm_power_q31()
111 /* Loop unrolling: Compute 4 outputs at a time */ in arm_power_q31()
116 /* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */ in arm_power_q31()
118 …ntermediate results by 14 bits to maintain 16.48 format and store result in a temporary variable s… in arm_power_q31()
132 blkCnt--; in arm_power_q31()
147 /* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */ in arm_power_q31()
149 /* Compute Power and store result in a temporary variable, sum. */ in arm_power_q31()
154 blkCnt--; in arm_power_q31()