9、Android Studio的ARM Neon学习环境搭建

基本思想：最近在阅读NCNN源码，学完OpenMP之后，在学习一下Neon，因为手中的FPGA开发板还在做焊接，所以还是委屈一下手机，进行ARM的neon部分学习和验证吧~

首先先下载一下AIDA64.APK确认一下手机是否支持neon指令

(1) 构建一下Android工程和选择支持JNI编程 ，顺手也把opencv SDK包裹进去了,以防学习中用到 （不用的可以不包裹）

之间遇到一个之前没有遇到一个错误

More than one file was found with OS independent path 'lib/arm64-v8a/libcoreMesh.so'

 在build.gradle添加（ F:\neon\app\build.gradle）

packagingOptions {
        pickFirst "lib/arm64-v8a/libopencv_java4.so"
        pickFirst "lib/armeabi-v7a/libopencv_java4.so"
        pickFirst "lib/x86/libopencv_java4.so"
        pickFirst "lib/x86_64/libopencv_java4.so"
    }

(2)、因为要neon在android studio的真机内中支持测试，需要写入 

arguments '-DANDROID=c++_shared',"-DANDROID_ARM_NEON=TRUE", "-DANDROID_TOOLCHAIN=clang -mfloat-abi=softfp -mfpu=neon"//"-mfloat-abi=hard"

 截图修改如下（真心不会Android studio 只会JNI）

plugins {
    id 'com.android.application'
}

android {
    compileSdkVersion 30
    //buildToolsVersion "30.0.3"

    defaultConfig {
        applicationId "com.example.neon"
        minSdkVersion 21
        targetSdkVersion 30
        versionCode 1
        versionName "1.0"

        testInstrumentationRunner "androidx.test.runner.AndroidJUnitRunner"
        externalNativeBuild {
            cmake {
                cppFlags "-std=c++11"
                arguments '-DANDROID=c++_shared',"-DANDROID_ARM_NEON=TRUE", "-DANDROID_TOOLCHAIN=clang -mfloat-abi=softfp -mfpu=neon"//"-mfloat-abi=hard"
                abiFilters 'armeabi-v7a','arm64-v8a'//,'x86','x86_64'

            }
        }
    }
    packagingOptions {
        pickFirst "lib/arm64-v8a/libopencv_java4.so"
        pickFirst "lib/armeabi-v7a/libopencv_java4.so"
        pickFirst "lib/x86/libopencv_java4.so"
        pickFirst "lib/x86_64/libopencv_java4.so"
    }
    sourceSets{
        main{
            jniLibs.srcDirs=["src/main/jniLibs/libs"]
        }
    }


    buildTypes {
        release {
            minifyEnabled false
            proguardFiles getDefaultProguardFile('proguard-android-optimize.txt'), 'proguard-rules.pro'
        }
    }
    externalNativeBuild {
        cmake {
            path "src/main/cpp/CMakeLists.txt"
            version "3.10.2"
        }
    }
    compileOptions {
        sourceCompatibility JavaVersion.VERSION_1_8
        targetCompatibility JavaVersion.VERSION_1_8
    }
}

dependencies {

    implementation 'androidx.appcompat:appcompat:1.1.0'
    implementation 'com.google.android.material:material:1.1.0'
    implementation 'androidx.constraintlayout:constraintlayout:1.1.3'
    implementation project(path: ':sdk')
    testImplementation 'junit:junit:4.+'
    androidTestImplementation 'androidx.test.ext:junit:1.1.1'
    androidTestImplementation 'androidx.test.espresso:espresso-core:3.2.0'
}

（3）、修改一下主程序，测带打印一下手机的ARM架构

package com.example.neon;

import androidx.appcompat.app.AppCompatActivity;

import android.os.Bundle;
import android.util.Log;
import android.widget.TextView;

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class MainActivity extends AppCompatActivity {

    // Used to load the 'native-lib' library on application startup.
    static {
        System.loadLibrary("native-lib");
    }
    public static String getFieldFromCpuinfo(String field) throws IOException {
        BufferedReader br = new BufferedReader(new FileReader("/proc/cpuinfo"));
        Pattern p = Pattern.compile(field + "\\s*:\\s*(.*)");

        try {
            String line;
            while ((line = br.readLine()) != null) {
                Matcher m = p.matcher(line);
                if (m.matches()) {
                    return m.group(1);
                }
            }
        } finally {
            br.close();
        }

        return null;
    }
    public static boolean isCPU64(){
        boolean result = false;
        String mProcessor = null;
        List<String > list = null;
        try {
            mProcessor = getFieldFromCpuinfo("Processor");
        } catch (IOException e) {
            e.printStackTrace();
        }

        if (mProcessor != null) {
            // D/CpuUtils: isCPU64 mProcessor = AArch64 Processor rev 4 (aarch64)
            Log.d("TAG", "isCPU64 mProcessor = " + mProcessor);
            //list =  Arrays.asList(mProcessor.split("\\s"));
            if (mProcessor.contains("aarch64")) {
                result = true;
            }
        }

        return result;
    }

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_main);
        boolean aarch64=isCPU64();
        if(aarch64)
        {
            Log.d("TAG", "YES " );
        }else {
            Log.d("TAG", "NO ");
        }
        // Example of a call to a native method
        TextView tv = findViewById(R.id.sample_text);
        tv.setText(stringFromJNI());
    }

    /**
     * A native method that is implemented by the 'native-lib' native library,
     * which is packaged with this application.
     */
    public native String stringFromJNI();
}

(4)、在JNI对应cpp文件中开始测试 demo

#include <jni.h>
#include <string>
#include <arm_neon.h>
#include <android/log.h>

#define LOG_TAG "TEST_NEON"
#define LOGD(...) __android_log_print(ANDROID_LOG_DEBUG, LOG_TAG, __VA_ARGS__)
#define LOGI(...) __android_log_print(ANDROID_LOG_INFO, LOG_TAG, __VA_ARGS__)
extern "C"
{
void test() {
    int16_t result[8];
    int8x8_t a = vdup_n_s8(121);
    int8x8_t b = vdup_n_s8(2);
    int16x8_t c;
    c = vmull_s8(a,b);
    vst1q_s16(result,c);
    for(int i=0;i<8;i++){
        LOGD("data[%d] is %d ",i,result[i]);
    }

}
}

extern "C" JNIEXPORT jstring JNICALL
Java_com_example_neon_MainActivity_stringFromJNI(
        JNIEnv* env,
        jobject /* this */) {
    std::string hello = "Hello from C++";
    test();
    return env->NewStringUTF(hello.c_str());
}

测试结果

2021-07-14 15:51:29.484 31154-31154/com.example.neon D/TAG: isCPU64 mProcessor = AArch64 Processor rev 4 (aarch64)
2021-07-14 15:51:29.484 31154-31154/com.example.neon D/TAG: YES 
2021-07-14 15:51:52.171 31154-31154/com.example.neon D/TEST_NEON: data[0] is 242 
2021-07-14 15:51:52.171 31154-31154/com.example.neon D/TEST_NEON: data[1] is 242 
2021-07-14 15:51:52.171 31154-31154/com.example.neon D/TEST_NEON: data[2] is 242 
2021-07-14 15:51:52.171 31154-31154/com.example.neon D/TEST_NEON: data[3] is 242 
2021-07-14 15:51:52.171 31154-31154/com.example.neon D/TEST_NEON: data[4] is 242 
2021-07-14 15:51:52.171 31154-31154/com.example.neon D/TEST_NEON: data[5] is 242 
2021-07-14 15:51:52.171 31154-31154/com.example.neon D/TEST_NEON: data[6] is 242 
2021-07-14 15:51:52.172 31154-31154/com.example.neon D/TEST_NEON: data[7] is 242 
2021-07-14 15:51:52.223 31154-31154/com.example.neon E/ANR_LOG: >>> msg's executing time is too long
2021-07-14 15:51:52.224 31154-31154/com.example.neon E/ANR_LOG: Blocked msg = { when=-34s273ms what=100 target=android.app.ActivityThread$H obj=ActivityRecord{8f43ed token=android.os.BinderProxy@a005222 {com.example.neon/com.example.neon.MainActivity}} } , cost  = 23399 ms
2021-07-14 15:51:52.224 31154-31154/com.example.neon E/ANR_LOG: >>>Current msg List is:
2021-07-14 15:51:52.224 31154-31154/com.example.neon E/ANR_LOG: Current msg <1>  = { when=-33s541ms what=149 target=android.app.ActivityThread$H obj=android.os.BinderProxy@a005222 }
2021-07-14 15:51:52.224 31154-31154/com.example.neon E/ANR_LOG: Current msg <2>  = { when=-22s768ms what=0 target=android.os.Handler callback=androidx.core.content.res.ResourcesCompat$FontCallback$2 }
2021-07-14 15:51:52.224 31154-31154/com.example.neon E/ANR_LOG: Current msg <3>  = { when=-22s745ms what=0 target=android.os.Handler callback=androidx.core.content.res.ResourcesCompat$FontCallback$2 }
2021-07-14 15:51:52.224 31154-31154/com.example.neon E/ANR_LOG: Current msg <4>  = { when=-20ms what=0 target=android.view.ViewRootImpl$ViewRootHandler callback=android.view.ViewRootImpl$4 }
2021-07-14 15:51:52.225 31154-31154/com.example.neon E/ANR_LOG: Current msg <5>  = { when=-4ms barrier=0 }
2021-07-14 15:51:52.225 31154-31154/com.example.neon E/ANR_LOG: >>>CURRENT MSG DUMP OVER<<<
2021-07-14 15:51:52.309 31154-31154/com.example.neon I/ViewConfigCompat: Could not find method getScaledScrollFactor() on ViewConfiguration
2021-07-14 15:51:52.313 31154-31255/com.example.neon I/Adreno: QUALCOMM build                   : e0ff253, I1b6e53de78
    Build Date                       : 02/16/18
    OpenGL ES Shader Compiler Version: XE031.09.00.04
    Local Branch                     : 
    Remote Branch                    : quic/gfx-adreno.lnx.1.0.c15-rel
    Remote Branch                    : NONE
    Reconstruct Branch               : NOTHING
2021-07-14 15:51:52.334 31154-31255/com.example.neon I/OpenGLRenderer: Initialized EGL, version 1.4
2021-07-14 15:51:52.334 31154-31255/com.example.neon D/OpenGLRenderer: Swap behavior 1
2021-07-14 15:53:51.635 31154-31255/com.example.neon E/OpenGLRenderer: hwui_debug::CanvasContext createSurface sur=0x0, isValid =0
2021-07-14 15:53:51.733 31154-31255/com.example.neon E/OpenGLRenderer: hwui_debug::CanvasContext createSurface sur=0x0, isValid =0

环境算搭建起来了~。代码很简单，参考手册：​​https://developer.arm.com/architectures/instruction-sets/intrinsics/​​ 就可以知道，从内存中取数据到寄存器，然后在寄存器完成运算，然后进行再从寄存器把数据返回给内存，类似汇编语言一样；

(突然想起了我的恩师-雷老师的课了  ​​《汇编语言程序设计教程 雷印胜,贾萍,胡晓鹏等编著​​》《IBM-PC汇编语言程序设计》~)

先研究几个小demo，然后开始研究nihui大佬的代码，边学习边验证吧~ up yyds

参考：

https://developer.arm.com/solutions/os/android/developer-guides/neon-intrinsics-getting-started-on-android

https://developer.android.com/ndk/guides/cpu-arm-neon#cmake

https://developer.arm.com/architectures/instruction-sets/intrinsics/