1  /* ----------------------------------------------------------------------
 2   * Project:      CMSIS DSP Library
 3   * Title:        arm_vlog_f32.c
 4   * Description:  Fast vectorized log
 5   *
 6   * $Date:        23 April 2021
 7   * $Revision:    V1.9.0
 8   *
 9   * Target Processor: Cortex-M and Cortex-A cores
10   * -------------------------------------------------------------------- */
11  /*
12   * Copyright (C) 2010-2021 ARM Limited or its affiliates. All rights reserved.
13   *
14   * SPDX-License-Identifier: Apache-2.0
15   *
16   * Licensed under the Apache License, Version 2.0 (the License); you may
17   * not use this file except in compliance with the License.
18   * You may obtain a copy of the License at
19   *
20   * www.apache.org/licenses/LICENSE-2.0
21   *
22   * Unless required by applicable law or agreed to in writing, software
23   * distributed under the License is distributed on an AS IS BASIS, WITHOUT
24   * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
25   * See the License for the specific language governing permissions and
26   * limitations under the License.
27   */
28  
29  #include "dsp/fast_math_functions.h"
30  #include "arm_common_tables.h"
31  
32  #if (defined(ARM_MATH_MVEF) || defined(ARM_MATH_HELIUM) || defined(ARM_MATH_NEON) || defined(ARM_MATH_NEON_EXPERIMENTAL)) && !defined(ARM_MATH_AUTOVECTORIZE)
33  #include "arm_vec_math.h"
34  #endif
35  
36  void arm_vexp_f32(
37    const float32_t * pSrc,
38          float32_t * pDst,
39          uint32_t blockSize)
40  {
41     uint32_t blkCnt; 
42  
43  #if (defined(ARM_MATH_MVEF) || defined(ARM_MATH_HELIUM)) && !defined(ARM_MATH_AUTOVECTORIZE)
44     f32x4_t src;
45     f32x4_t dst;
46  
47     blkCnt = blockSize >> 2;
48  
49     while (blkCnt > 0U)
50     {
51        src = vld1q(pSrc);
52        dst = vexpq_f32(src);
53        vst1q(pDst, dst);
54  
55        pSrc += 4;
56        pDst += 4;
57        /* Decrement loop counter */
58        blkCnt--;
59     }
60  
61     blkCnt = blockSize & 3;
62  #else
63  #if (defined(ARM_MATH_NEON) || defined(ARM_MATH_NEON_EXPERIMENTAL)) && !defined(ARM_MATH_AUTOVECTORIZE)
64     f32x4_t src;
65     f32x4_t dst;
66  
67     blkCnt = blockSize >> 2;
68  
69     while (blkCnt > 0U)
70     {
71        src = vld1q_f32(pSrc);
72        dst = vexpq_f32(src);
73        vst1q_f32(pDst, dst);
74  
75        pSrc += 4;
76        pDst += 4;
77        /* Decrement loop counter */
78        blkCnt--;
79     }
80  
81     blkCnt = blockSize & 3;
82  #else
83     blkCnt = blockSize;
84  #endif
85  #endif
86  
87     while (blkCnt > 0U)
88     {
89        /* C = log(A) */
90    
91        /* Calculate log and store result in destination buffer. */
92        *pDst++ = expf(*pSrc++);
93    
94        /* Decrement loop counter */
95        blkCnt--;
96     }
97  }