Renesas / mbed-dsp-neon

Fork of mbed-dsp. CMSIS-DSP library of supporting NEON

Dependents:   mbed-os-example-cmsis_dsp_neon

Fork of mbed-dsp by mbed official

Information

Japanese version is available in lower part of this page.
このページの後半に日本語版が用意されています．

CMSIS-DSP of supporting NEON

What is this ?

A library for CMSIS-DSP of supporting NEON.
We supported the NEON to CMSIS-DSP Ver1.4.3(CMSIS V4.1) that ARM supplied, has achieved the processing speed improvement.
If you use the mbed-dsp library, you can use to replace this library.
CMSIS-DSP of supporting NEON is provied as a library.

Library Creation environment

CMSIS-DSP library of supporting NEON was created by the following environment.

  • Compiler
    ARMCC Version 5.03
  • Compile option switch[C Compiler]
   -DARM_MATH_MATRIX_CHECK -DARM_MATH_ROUNDING -O3 -Otime --cpu=Cortex-A9 --littleend --arm 
   --apcs=/interwork --no_unaligned_access --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp 
   --vectorize --asm
  • Compile option switch[Assembler]
   --cpreproc --cpu=Cortex-A9 --littleend --arm --apcs=/interwork --no_unaligned_access 
   --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp


Effects of NEON support

In the data which passes to each function, large size will be expected more effective than small size.
Also if the data is a multiple of 16, effect will be expected in every function in the CMSIS-DSP.


NEON対応CMSIS-DSP

概要

NEON対応したCMSIS-DSPのライブラリです。
ARM社提供のCMSIS-DSP Ver1.4.3(CMSIS V4.1)をターゲットにNEON対応を行ない、処理速度向上を実現しております。
mbed-dspライブラリを使用している場合は、本ライブラリに置き換えて使用することができます。
NEON対応したCMSIS-DSPはライブラリで提供します。

ライブラリ作成環境

NEON対応CMSIS-DSPライブラリは、以下の環境で作成しています。

  • コンパイラ
    ARMCC Version 5.03
  • コンパイルオプションスイッチ[C Compiler]
   -DARM_MATH_MATRIX_CHECK -DARM_MATH_ROUNDING -O3 -Otime --cpu=Cortex-A9 --littleend --arm 
   --apcs=/interwork --no_unaligned_access --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp 
   --vectorize --asm
  • コンパイルオプションスイッチ[Assembler]
   --cpreproc --cpu=Cortex-A9 --littleend --arm --apcs=/interwork --no_unaligned_access 
   --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp


NEON対応による効果について

CMSIS-DSP内の各関数へ渡すデータは、小さいサイズよりも大きいサイズの方が効果が見込めます。
また、16の倍数のデータであれば、CMSIS-DSP内のどの関数でも効果が見込めます。


cmsis_dsp/FastMathFunctions/arm_sqrt_q15.c@3:7a284390b0ce, 2013-11-08 (annotated)

Committer:
mbed_official
Date:
Fri Nov 08 13:45:10 2013 +0000
Revision:
3:7a284390b0ce
Parent:
2:da51fb522205 
Synchronized with git revision e69956aba2f68a2a26ac26b051f8d349deaa1ce8

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
mbed_official 3:7a284390b0ce 2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
mbed_official 3:7a284390b0ce 4 * $Date: 17. January 2013
mbed_official 3:7a284390b0ce 5 * $Revision: V1.4.1
emilmont 1:fdd22bb7aa52 6 *
emilmont 1:fdd22bb7aa52 7 * Project: CMSIS DSP Library
emilmont 2:da51fb522205 8 * Title: arm_sqrt_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q15 square root function.
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 13 *
mbed_official 3:7a284390b0ce 14 * Redistribution and use in source and binary forms, with or without
mbed_official 3:7a284390b0ce 15 * modification, are permitted provided that the following conditions
mbed_official 3:7a284390b0ce 16 * are met:
mbed_official 3:7a284390b0ce 17 * - Redistributions of source code must retain the above copyright
mbed_official 3:7a284390b0ce 18 * notice, this list of conditions and the following disclaimer.
mbed_official 3:7a284390b0ce 19 * - Redistributions in binary form must reproduce the above copyright
mbed_official 3:7a284390b0ce 20 * notice, this list of conditions and the following disclaimer in
mbed_official 3:7a284390b0ce 21 * the documentation and/or other materials provided with the
mbed_official 3:7a284390b0ce 22 * distribution.
mbed_official 3:7a284390b0ce 23 * - Neither the name of ARM LIMITED nor the names of its contributors
mbed_official 3:7a284390b0ce 24 * may be used to endorse or promote products derived from this
mbed_official 3:7a284390b0ce 25 * software without specific prior written permission.
mbed_official 3:7a284390b0ce 26 *
mbed_official 3:7a284390b0ce 27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
mbed_official 3:7a284390b0ce 28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
mbed_official 3:7a284390b0ce 29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
mbed_official 3:7a284390b0ce 30 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
mbed_official 3:7a284390b0ce 31 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
mbed_official 3:7a284390b0ce 32 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
mbed_official 3:7a284390b0ce 33 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
mbed_official 3:7a284390b0ce 34 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
mbed_official 3:7a284390b0ce 35 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
mbed_official 3:7a284390b0ce 36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
mbed_official 3:7a284390b0ce 37 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
mbed_official 3:7a284390b0ce 38 * POSSIBILITY OF SUCH DAMAGE.
emilmont 1:fdd22bb7aa52 39 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 40 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 41 #include "arm_common_tables.h"
emilmont 1:fdd22bb7aa52 42
emilmont 1:fdd22bb7aa52 43
emilmont 1:fdd22bb7aa52 44 /**
emilmont 1:fdd22bb7aa52 45 * @ingroup groupFastMath
emilmont 1:fdd22bb7aa52 46 */
emilmont 1:fdd22bb7aa52 47
emilmont 1:fdd22bb7aa52 48 /**
emilmont 1:fdd22bb7aa52 49 * @addtogroup SQRT
emilmont 1:fdd22bb7aa52 50 * @{
emilmont 1:fdd22bb7aa52 51 */
emilmont 1:fdd22bb7aa52 52
emilmont 1:fdd22bb7aa52 53 /**
emilmont 1:fdd22bb7aa52 54 * @brief Q15 square root function.
emilmont 1:fdd22bb7aa52 55 * @param[in] in input value. The range of the input value is [0 +1) or 0x0000 to 0x7FFF.
emilmont 1:fdd22bb7aa52 56 * @param[out] *pOut square root of input value.
mbed_official 3:7a284390b0ce 57 * @return The function returns ARM_MATH_SUCCESS if the input value is positive
mbed_official 3:7a284390b0ce 58 * and ARM_MATH_ARGUMENT_ERROR if the input is negative. For
mbed_official 3:7a284390b0ce 59 * negative inputs, the function returns *pOut = 0.
emilmont 1:fdd22bb7aa52 60 */
emilmont 1:fdd22bb7aa52 61
emilmont 1:fdd22bb7aa52 62 arm_status arm_sqrt_q15(
emilmont 1:fdd22bb7aa52 63 q15_t in,
emilmont 1:fdd22bb7aa52 64 q15_t * pOut)
emilmont 1:fdd22bb7aa52 65 {
emilmont 1:fdd22bb7aa52 66 q15_t number, temp1, var1, signBits1, half;
emilmont 1:fdd22bb7aa52 67 q31_t bits_val1;
emilmont 1:fdd22bb7aa52 68 float32_t temp_float1;
mbed_official 3:7a284390b0ce 69 union
mbed_official 3:7a284390b0ce 70 {
mbed_official 3:7a284390b0ce 71 q31_t fracval;
mbed_official 3:7a284390b0ce 72 float32_t floatval;
mbed_official 3:7a284390b0ce 73 } tempconv;
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75 number = in;
emilmont 1:fdd22bb7aa52 76
emilmont 1:fdd22bb7aa52 77 /* If the input is a positive number then compute the signBits. */
emilmont 1:fdd22bb7aa52 78 if(number > 0)
emilmont 1:fdd22bb7aa52 79 {
emilmont 1:fdd22bb7aa52 80 signBits1 = __CLZ(number) - 17;
emilmont 1:fdd22bb7aa52 81
emilmont 1:fdd22bb7aa52 82 /* Shift by the number of signBits1 */
emilmont 1:fdd22bb7aa52 83 if((signBits1 % 2) == 0)
emilmont 1:fdd22bb7aa52 84 {
emilmont 1:fdd22bb7aa52 85 number = number << signBits1;
emilmont 1:fdd22bb7aa52 86 }
emilmont 1:fdd22bb7aa52 87 else
emilmont 1:fdd22bb7aa52 88 {
emilmont 1:fdd22bb7aa52 89 number = number << (signBits1 - 1);
emilmont 1:fdd22bb7aa52 90 }
emilmont 1:fdd22bb7aa52 91
emilmont 1:fdd22bb7aa52 92 /* Calculate half value of the number */
emilmont 1:fdd22bb7aa52 93 half = number >> 1;
emilmont 1:fdd22bb7aa52 94 /* Store the number for later use */
emilmont 1:fdd22bb7aa52 95 temp1 = number;
emilmont 1:fdd22bb7aa52 96
emilmont 1:fdd22bb7aa52 97 /*Convert to float */
emilmont 1:fdd22bb7aa52 98 temp_float1 = number * 3.051757812500000e-005f;
emilmont 1:fdd22bb7aa52 99 /*Store as integer */
mbed_official 3:7a284390b0ce 100 tempconv.floatval = temp_float1;
mbed_official 3:7a284390b0ce 101 bits_val1 = tempconv.fracval;
emilmont 1:fdd22bb7aa52 102 /* Subtract the shifted value from the magic number to give intial guess */
emilmont 1:fdd22bb7aa52 103 bits_val1 = 0x5f3759df - (bits_val1 >> 1); // gives initial guess
emilmont 1:fdd22bb7aa52 104 /* Store as float */
mbed_official 3:7a284390b0ce 105 tempconv.fracval = bits_val1;
mbed_official 3:7a284390b0ce 106 temp_float1 = tempconv.floatval;
emilmont 1:fdd22bb7aa52 107 /* Convert to integer format */
emilmont 1:fdd22bb7aa52 108 var1 = (q31_t) (temp_float1 * 16384);
emilmont 1:fdd22bb7aa52 109
emilmont 1:fdd22bb7aa52 110 /* 1st iteration */
emilmont 1:fdd22bb7aa52 111 var1 = ((q15_t) ((q31_t) var1 * (0x3000 -
emilmont 1:fdd22bb7aa52 112 ((q15_t)
emilmont 1:fdd22bb7aa52 113 ((((q15_t)
emilmont 1:fdd22bb7aa52 114 (((q31_t) var1 * var1) >> 15)) *
emilmont 1:fdd22bb7aa52 115 (q31_t) half) >> 15))) >> 15)) << 2;
emilmont 1:fdd22bb7aa52 116 /* 2nd iteration */
emilmont 1:fdd22bb7aa52 117 var1 = ((q15_t) ((q31_t) var1 * (0x3000 -
emilmont 1:fdd22bb7aa52 118 ((q15_t)
emilmont 1:fdd22bb7aa52 119 ((((q15_t)
emilmont 1:fdd22bb7aa52 120 (((q31_t) var1 * var1) >> 15)) *
emilmont 1:fdd22bb7aa52 121 (q31_t) half) >> 15))) >> 15)) << 2;
emilmont 1:fdd22bb7aa52 122 /* 3rd iteration */
emilmont 1:fdd22bb7aa52 123 var1 = ((q15_t) ((q31_t) var1 * (0x3000 -
emilmont 1:fdd22bb7aa52 124 ((q15_t)
emilmont 1:fdd22bb7aa52 125 ((((q15_t)
emilmont 1:fdd22bb7aa52 126 (((q31_t) var1 * var1) >> 15)) *
emilmont 1:fdd22bb7aa52 127 (q31_t) half) >> 15))) >> 15)) << 2;
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 /* Multiply the inverse square root with the original value */
emilmont 1:fdd22bb7aa52 130 var1 = ((q15_t) (((q31_t) temp1 * var1) >> 15)) << 1;
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132 /* Shift the output down accordingly */
emilmont 1:fdd22bb7aa52 133 if((signBits1 % 2) == 0)
emilmont 1:fdd22bb7aa52 134 {
emilmont 1:fdd22bb7aa52 135 var1 = var1 >> (signBits1 / 2);
emilmont 1:fdd22bb7aa52 136 }
emilmont 1:fdd22bb7aa52 137 else
emilmont 1:fdd22bb7aa52 138 {
emilmont 1:fdd22bb7aa52 139 var1 = var1 >> ((signBits1 - 1) / 2);
emilmont 1:fdd22bb7aa52 140 }
emilmont 1:fdd22bb7aa52 141 *pOut = var1;
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 return (ARM_MATH_SUCCESS);
emilmont 1:fdd22bb7aa52 144 }
emilmont 1:fdd22bb7aa52 145 /* If the number is a negative number then store zero as its square root value */
emilmont 1:fdd22bb7aa52 146 else
emilmont 1:fdd22bb7aa52 147 {
emilmont 1:fdd22bb7aa52 148 *pOut = 0;
emilmont 1:fdd22bb7aa52 149 return (ARM_MATH_ARGUMENT_ERROR);
emilmont 1:fdd22bb7aa52 150 }
emilmont 1:fdd22bb7aa52 151 }
emilmont 1:fdd22bb7aa52 152
emilmont 1:fdd22bb7aa52 153 /**
emilmont 1:fdd22bb7aa52 154 * @} end of SQRT group
emilmont 1:fdd22bb7aa52 155 */