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。


Committer:
emilmont
Date:
Thu May 30 17:10:11 2013 +0100
Revision:
2:da51fb522205
Parent:
1:fdd22bb7aa52
Child:
3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
emilmont 1:fdd22bb7aa52 2 * Copyright (C) 2010 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
emilmont 1:fdd22bb7aa52 4 * $Date: 29. November 2010
emilmont 2:da51fb522205 5 * $Revision: V1.0.3
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 1:fdd22bb7aa52 8 *
emilmont 2:da51fb522205 9 * Title: math_helper.h
emilmont 1:fdd22bb7aa52 10 *
emilmont 1:fdd22bb7aa52 11 *
emilmont 2:da51fb522205 12 * Description: Prototypes of all helper functions required.
emilmont 1:fdd22bb7aa52 13 *
emilmont 1:fdd22bb7aa52 14 * Target Processor: Cortex-M4/Cortex-M3
emilmont 1:fdd22bb7aa52 15 *
emilmont 1:fdd22bb7aa52 16 * Version 1.0.3 2010/11/29
emilmont 1:fdd22bb7aa52 17 * Re-organized the CMSIS folders and updated documentation.
emilmont 1:fdd22bb7aa52 18 *
emilmont 1:fdd22bb7aa52 19 * Version 1.0.2 2010/11/11
emilmont 1:fdd22bb7aa52 20 * Documentation updated.
emilmont 1:fdd22bb7aa52 21 *
emilmont 1:fdd22bb7aa52 22 * Version 1.0.1 2010/10/05
emilmont 1:fdd22bb7aa52 23 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 24 *
emilmont 1:fdd22bb7aa52 25 * Version 1.0.0 2010/09/20
emilmont 1:fdd22bb7aa52 26 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 27 *
emilmont 1:fdd22bb7aa52 28 * Version 0.0.7 2010/06/10
emilmont 1:fdd22bb7aa52 29 * Misra-C changes done
emilmont 1:fdd22bb7aa52 30 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 31
emilmont 1:fdd22bb7aa52 32
emilmont 1:fdd22bb7aa52 33 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 34
emilmont 1:fdd22bb7aa52 35 #ifndef MATH_HELPER_H
emilmont 1:fdd22bb7aa52 36 #define MATH_HELPER_H
emilmont 1:fdd22bb7aa52 37
emilmont 1:fdd22bb7aa52 38 #ifdef __cplusplus
emilmont 1:fdd22bb7aa52 39 extern "C"
emilmont 1:fdd22bb7aa52 40 {
emilmont 1:fdd22bb7aa52 41 #endif
emilmont 1:fdd22bb7aa52 42
emilmont 1:fdd22bb7aa52 43 float arm_snr_f32(float *pRef, float *pTest, uint32_t buffSize);
emilmont 1:fdd22bb7aa52 44 void arm_float_to_q12_20(float *pIn, q31_t * pOut, uint32_t numSamples);
emilmont 1:fdd22bb7aa52 45 void arm_provide_guard_bits_q15(q15_t *input_buf, uint32_t blockSize, uint32_t guard_bits);
emilmont 1:fdd22bb7aa52 46 void arm_provide_guard_bits_q31(q31_t *input_buf, uint32_t blockSize, uint32_t guard_bits);
emilmont 1:fdd22bb7aa52 47 void arm_float_to_q14(float *pIn, q15_t *pOut, uint32_t numSamples);
emilmont 1:fdd22bb7aa52 48 void arm_float_to_q29(float *pIn, q31_t *pOut, uint32_t numSamples);
emilmont 1:fdd22bb7aa52 49 void arm_float_to_q28(float *pIn, q31_t *pOut, uint32_t numSamples);
emilmont 1:fdd22bb7aa52 50 void arm_float_to_q30(float *pIn, q31_t *pOut, uint32_t numSamples);
emilmont 1:fdd22bb7aa52 51 void arm_clip_f32(float *pIn, uint32_t numSamples);
emilmont 1:fdd22bb7aa52 52 uint32_t arm_calc_guard_bits(uint32_t num_adds);
emilmont 1:fdd22bb7aa52 53 void arm_apply_guard_bits (float32_t * pIn, uint32_t numSamples, uint32_t guard_bits);
emilmont 1:fdd22bb7aa52 54 uint32_t arm_compare_fixed_q15(q15_t *pIn, q15_t * pOut, uint32_t numSamples);
emilmont 1:fdd22bb7aa52 55 uint32_t arm_compare_fixed_q31(q31_t *pIn, q31_t *pOut, uint32_t numSamples);
emilmont 1:fdd22bb7aa52 56 uint32_t arm_calc_2pow(uint32_t guard_bits);
emilmont 1:fdd22bb7aa52 57
emilmont 1:fdd22bb7aa52 58 #ifdef __cplusplus
emilmont 1:fdd22bb7aa52 59 }
emilmont 1:fdd22bb7aa52 60 #endif
emilmont 1:fdd22bb7aa52 61
emilmont 1:fdd22bb7aa52 62 #endif
emilmont 1:fdd22bb7aa52 63