pigweed / third_party / github / STMicroelectronics / cmsis_core / refs/heads/cm4 / . / DSP / Source / SupportFunctions / arm_copy_f32.c

/* ---------------------------------------------------------------------- | |

* Project: CMSIS DSP Library | |

* Title: arm_copy_f32.c | |

* Description: Copies 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 groupSupport | |

*/ | |

/** | |

@defgroup copy Vector Copy | |

Copies sample by sample from source vector to destination vector. | |

<pre> | |

pDst[n] = pSrc[n]; 0 <= n < blockSize. | |

</pre> | |

There are separate functions for floating point, Q31, Q15, and Q7 data types. | |

*/ | |

/** | |

@addtogroup copy | |

@{ | |

*/ | |

/** | |

@brief Copies the elements of a floating-point vector. | |

@param[in] pSrc points to input vector | |

@param[out] pDst points to output vector | |

@param[in] blockSize number of samples in each vector | |

@return none | |

*/ | |

#if defined(ARM_MATH_NEON_EXPERIMENTAL) | |

void arm_copy_f32( | |

const float32_t * pSrc, | |

float32_t * pDst, | |

uint32_t blockSize) | |

{ | |

uint32_t blkCnt; /* loop counter */ | |

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 */ | |

/* Copy and then store the results in the destination buffer */ | |

inV = vld1q_f32(pSrc); | |

vst1q_f32(pDst, inV); | |

pSrc += 4; | |

pDst += 4; | |

/* 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 & 3; | |

while (blkCnt > 0U) | |

{ | |

/* C = A */ | |

/* Copy and then store the results in the destination buffer */ | |

*pDst++ = *pSrc++; | |

/* Decrement the loop counter */ | |

blkCnt--; | |

} | |

} | |

#else | |

void arm_copy_f32( | |

const float32_t * pSrc, | |

float32_t * pDst, | |

uint32_t blockSize) | |

{ | |

uint32_t blkCnt; /* Loop counter */ | |

#if defined (ARM_MATH_LOOPUNROLL) | |

/* Loop unrolling: Compute 4 outputs at a time */ | |

blkCnt = blockSize >> 2U; | |

while (blkCnt > 0U) | |

{ | |

/* C = A */ | |

/* Copy and store result in destination buffer */ | |

*pDst++ = *pSrc++; | |

*pDst++ = *pSrc++; | |

*pDst++ = *pSrc++; | |

*pDst++ = *pSrc++; | |

/* 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 */ | |

/* Copy and store result in destination buffer */ | |

*pDst++ = *pSrc++; | |

/* Decrement loop counter */ | |

blkCnt--; | |

} | |

} | |

#endif /* #if defined(ARM_MATH_NEON) */ | |

/** | |

@} end of BasicCopy group | |

*/ |