diff options
| author | joshua <joshua@joshuayun.com> | 2023-12-30 23:54:31 -0500 |
|---|---|---|
| committer | joshua <joshua@joshuayun.com> | 2023-12-30 23:54:31 -0500 |
| commit | 86608c6770cf08c138a2bdab5855072f64be09ef (patch) | |
| tree | 494a61b3ef37e76f9235a0d10f5c93d97290a35f /Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_power_f32.c | |
| download | sdr-software-master.tar.gz | |
Diffstat (limited to 'Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_power_f32.c')
| -rw-r--r-- | Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_power_f32.c | 175 |
1 files changed, 175 insertions, 0 deletions
diff --git a/Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_power_f32.c b/Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_power_f32.c new file mode 100644 index 0000000..abf444b --- /dev/null +++ b/Drivers/CMSIS/DSP/Source/StatisticsFunctions/arm_power_f32.c @@ -0,0 +1,175 @@ +/* ----------------------------------------------------------------------
+ * Project: CMSIS DSP Library
+ * Title: arm_power_f32.c
+ * Description: Sum of the squares of the elements of a floating-point vector
+ *
+ * $Date: 18. March 2019
+ * $Revision: V1.6.0
+ *
+ * Target Processor: Cortex-M cores
+ * -------------------------------------------------------------------- */
+/*
+ * Copyright (C) 2010-2019 ARM Limited or its affiliates. All rights reserved.
+ *
+ * SPDX-License-Identifier: Apache-2.0
+ *
+ * Licensed under the Apache License, Version 2.0 (the License); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an AS IS BASIS, WITHOUT
+ * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include "arm_math.h"
+
+/**
+ @ingroup groupStats
+ */
+
+/**
+ @defgroup power Power
+
+ Calculates the sum of the squares of the elements in the input vector.
+ The underlying algorithm is used:
+
+ <pre>
+ Result = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + pSrc[2] * pSrc[2] + ... + pSrc[blockSize-1] * pSrc[blockSize-1];
+ </pre>
+
+ There are separate functions for floating point, Q31, Q15, and Q7 data types.
+ */
+
+/**
+ @addtogroup power
+ @{
+ */
+
+/**
+ @brief Sum of the squares of the elements of a floating-point vector.
+ @param[in] pSrc points to the input vector
+ @param[in] blockSize number of samples in input vector
+ @param[out] pResult sum of the squares value returned here
+ @return none
+ */
+#if defined(ARM_MATH_NEON)
+void arm_power_f32(
+ const float32_t * pSrc,
+ uint32_t blockSize,
+ float32_t * pResult)
+{
+ float32_t sum = 0.0f; /* accumulator */
+ float32_t in; /* Temporary variable to store input value */
+ uint32_t blkCnt; /* loop counter */
+
+ float32x4_t sumV = vdupq_n_f32(0.0f); /* Temporary result storage */
+ float32x2_t sumV2;
+ float32x4_t inV;
+
+ blkCnt = blockSize >> 2U;
+
+ /* Compute 4 outputs at a time.
+ ** a second loop below computes the remaining 1 to 3 samples. */
+ 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. */
+ inV = vld1q_f32(pSrc);
+ sumV = vmlaq_f32(sumV, inV, inV);
+ pSrc += 4;
+
+ /* Decrement the loop counter */
+ blkCnt--;
+ }
+ sumV2 = vpadd_f32(vget_low_f32(sumV),vget_high_f32(sumV));
+ sum = sumV2[0] + sumV2[1];
+
+ /* 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] * 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 += in * in;
+
+ /* Decrement the loop counter */
+ blkCnt--;
+ }
+
+ /* Store the result to the destination */
+ *pResult = sum;
+}
+#else
+void arm_power_f32(
+ const float32_t * pSrc,
+ uint32_t blockSize,
+ float32_t * pResult)
+{
+ uint32_t blkCnt; /* Loop counter */
+ float32_t sum = 0.0f; /* Temporary result storage */
+ float32_t in; /* Temporary variable to store input value */
+
+#if defined (ARM_MATH_LOOPUNROLL)
+
+ /* Loop unrolling: Compute 4 outputs at a time */
+ blkCnt = blockSize >> 2U;
+
+ while (blkCnt > 0U)
+ {
+ /* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */
+
+ /* Compute Power and store result in a temporary variable, sum. */
+ in = *pSrc++;
+ sum += in * in;
+
+ in = *pSrc++;
+ sum += in * in;
+
+ in = *pSrc++;
+ sum += in * in;
+
+ in = *pSrc++;
+ sum += in * in;
+
+ /* Decrement loop counter */
+ blkCnt--;
+ }
+
+ /* Loop unrolling: Compute remaining outputs */
+ blkCnt = blockSize % 0x4U;
+
+#else
+
+ /* Initialize blkCnt with number of samples */
+ blkCnt = blockSize;
+
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
+ while (blkCnt > 0U)
+ {
+ /* C = A[0] * A[0] + A[1] * A[1] + ... + A[blockSize-1] * A[blockSize-1] */
+
+ /* Compute Power and store result in a temporary variable, sum. */
+ in = *pSrc++;
+ sum += in * in;
+
+ /* Decrement loop counter */
+ blkCnt--;
+ }
+
+ /* Store result to destination */
+ *pResult = sum;
+}
+#endif /* #if defined(ARM_MATH_NEON) */
+
+/**
+ @} end of power group
+ */
|