转换为C / NDK / JNI的代码效率不如Java原始代码

如何解决转换为C / NDK / JNI的代码效率不如Java原始代码

这是我第一次不那么沉迷于NDK。

出于性能目的，我想将this code重写为NDK。我的c文件如下所示：

#include <jni.h>
#include <stdbool.h>
#include <stdio.h>
#include <time.h>
#include <android/log.h>

JNIEXPORT jbyteArray JNICALL
Java_com_company_app_tools_NV21FrameRotator_rotateNV21(JNIEnv *env,jclass thiz,jbyteArray data,jbyteArray output,jint width,jint height,jint rotation) {
    clock_t start,end;
    double cpu_time_used;
    start = clock();

    jbyte *dataPtr = (*env)->GetByteArrayElements(env,data,NULL);
    jbyte *outputPtr = (*env)->GetByteArrayElements(env,output,NULL);

    unsigned int frameSize = width * height;
    bool swap = rotation % 180 != 0;
    bool xflip = rotation % 270 != 0;
    bool yflip = rotation >= 180;

    for (unsigned int j = 0; j < height; j++) {
        for (unsigned int i = 0; i < width; i++) {
            unsigned int yIn = j * width + i;
            unsigned int uIn = frameSize + (j >> 1u) * width + (i & ~1u);
            unsigned int vIn = uIn + 1;

            unsigned int wOut = swap ? height : width;
            unsigned int hOut = swap ? width : height;
            unsigned int iSwapped = swap ? j : i;
            unsigned int jSwapped = swap ? i : j;
            unsigned int iOut = xflip ? wOut - iSwapped - 1 : iSwapped;
            unsigned int jOut = yflip ? hOut - jSwapped - 1 : jSwapped;

            unsigned int yOut = jOut * wOut + iOut;
            unsigned int uOut = frameSize + (jOut >> 1u) * wOut + (iOut & ~1u);
            unsigned int vOut = uOut + 1;

            outputPtr[yOut] = (jbyte) (0xff & dataPtr[yIn]);
            outputPtr[uOut] = (jbyte) (0xff & dataPtr[uIn]);
            outputPtr[vOut] = (jbyte) (0xff & dataPtr[vIn]);
        }
    }

    (*env)->ReleaseByteArrayElements(env,dataPtr,0);
    (*env)->ReleaseByteArrayElements(env,outputPtr,0);

    end = clock();
    cpu_time_used = ((double) (end - start)) / CLOCKS_PER_SEC;

    char str[10];
    sprintf(str,"%f",cpu_time_used * 1000);
    __android_log_write(ANDROID_LOG_ERROR,"NV21FrameRotator",str);

    return output;
}

这两个代码片段（链接到Java和更高版本）都可以很好地工作，但是当我测量处理持续时间时，看起来在同一设备上，Java版本大约需要7毫秒（Log.i( Java侧日志）和C 12-13毫秒。。不应该更快，为什么不呢？渔获物在哪里？

long micros = System.nanoTime() / 1000;
// ~7ms,Java
//data = rotateNV21(inputData,width,height,rotateCameraDegrees);
// ~12-13ms,C
NV21FrameRotator.rotateNV21(inputData,rotateCameraDegrees);
Log.d(TAG,"Last frame processing duration: " + (System.nanoTime() / 1000 - micros) + "µs");

PS。 Java日志有时显示的持续时间比clock()文件中的本机c测量的时间短……示例日志：

NV21FrameRotator: 7.942000
NV21RotatorJava: Last frame processing duration: 7403µs
NV21FrameRotator: 7.229000
NV21RotatorJava: Last frame processing duration: 7166µs
NV21FrameRotator: 16.918000
NV21RotatorJava: Last frame processing duration: 20644µs
NV21FrameRotator: 19.594000
NV21RotatorJava: Last frame processing duration: 20479µs
NV21FrameRotator: 9.484000
NV21RotatorJava: Last frame processing duration: 7274µs

编辑：compile_commands.json用于armeabi-v7a（旧设备，我只在建造这一个）

[
{
  "directory": "...app/.cxx/cmake/basicRelease/armeabi-v7a","command": "...sdk\\ndk\\21.0.6113669\\toolchains\\llvm\\prebuilt\\windows-x86_64\\bin\\clang.exe --target=armv7-none-linux-androideabi21 --gcc-toolchain=...sdk/ndk/21.0.6113669/toolchains/llvm/prebuilt/windows-x86_64 --sysroot=...sdk/ndk/21.0.6113669/toolchains/llvm/prebuilt/windows-x86_64/sysroot -DNV21FrameRotator_EXPORTS  -g -DANDROID -fdata-sections -ffunction-sections -funwind-tables -fstack-protector-strong -no-canonical-prefixes -D_FORTIFY_SOURCE=2 -march=armv7-a -mthumb -Wformat -Werror=format-security  -Oz -DNDEBUG  -fPIC   -o CMakeFiles\\NV21FrameRotator.dir\\NV21FrameRotator.c.o   -c ...app\\src\\main\\cpp\\NV21FrameRotator.c","file": "...app\\src\\main\\cpp\\NV21FrameRotator.c"
}
]

CMakeFile：

cmake_minimum_required(VERSION 3.4.1)
add_library(NV21FrameRotator SHARED
    NV21FrameRotator.c)
find_library(log-lib
    log )
target_link_libraries(NV21FrameRotator
    ${log-lib} )

解决方法

JNI具有非常高的开销，尤其是在传递非POD类型或缓冲区时。因此，调用JNI函数通常可能比Java版本慢得多。

请考虑传递java.nio.ByteBuffer，以避免可能的字节数组副本。

将Java的性能与真实设备上的C进行比较，仿真器不会产生可靠的结果。
在发行版本中比较Java与C的性能，在C中进行调试的速度很慢，而Java仍然获得了完整的JIT（和AOT）优化。
您可能会为您的方案寻找最佳的优化选择。默认情况下，版本将使用-Oz构建。要优先选择速度而不是大小，可以将其添加到 build.gradle ：
```
android {
  buildTypes {
    release {
      externalNativeBuild.cmake.cFlags "-O3"
    }
  }
}
```
您的C代码（实际上是原始Java代码）进行了一些优化。（据我所知）主要的效率低下是您重新计算了每个U和V值四次。简单的解决方法是split the loops。
进一步的优化可以避免内循环中的乘法（在外循环中也可以消除，但是效果可以忽略不计）：

#include <jni.h>
#include <stdbool.h>
#include <stdio.h>
#include <time.h>
#include <android/log.h>

JNIEXPORT jbyteArray JNICALL
Java_com_company_app_tools_NV21FrameRotator_rotateNV21(JNIEnv *env,jclass thiz,jbyteArray data,jbyteArray output,jint width,jint height,jint rotation) {
    clock_t start,end;
    double cpu_time_used;
    start = clock();

    jbyte *dataPtr = (*env)->GetByteArrayElements(env,data,NULL);
    jbyte *outputPtr = (*env)->GetByteArrayElements(env,output,NULL);

    unsigned int frameSize = width * height;
    bool swap = rotation % 180 != 0;
    bool xflip = rotation % 270 != 0;
    bool yflip = rotation >= 180;

    unsigned int wOut = swap ? height : width;
    unsigned int hOut = swap ? width : height;
    unsigned int yIn = 0;

    for (unsigned int j = 0; j < height; j++) {

        unsigned int iSwapped = swap ? j : 0;
        unsigned int jSwapped = swap ? 0 : j;
        unsigned int iOut = xflip ? wOut - iSwapped - 1 : iSwapped;
        unsigned int jOut = yflip ? hOut - jSwapped - 1 : jSwapped;
        unsigned int yOut = jOut * wOut + iOut;

        for (unsigned int i = 0; i < width; i++) {
            outputPtr[yOut] = dataPtr[yIn];
            if (swap) {
                yOut += yflip ? -wOut : wOut;
            } else {
                yOut += xflip ? -1 : 1;
            }
            yIn++;
        }
    }

    unsigned int uIn = frameSize;

    for (unsigned int j = 0; j < height; j+=2) {

        unsigned int iSwapped = swap ? j : 0;
        unsigned int jSwapped = swap ? 0 : j;
        unsigned int iOut = xflip ? wOut - iSwapped - 1 : iSwapped;
        unsigned int jOut = yflip ? hOut - jSwapped - 1 : jSwapped;
        unsigned int uOut = frameSize + (jOut / 2) * wOut + (iOut & ~1u);

        for (unsigned int i = 0; i < width; i+=2) {
            unsigned int vIn = uIn + 1;
            unsigned int vOut = uOut + 1;

            outputPtr[uOut] = dataPtr[uIn];
            outputPtr[vOut] = dataPtr[vIn];

            if (swap) {
                uOut += yflip ? -wOut : wOut;
            } else {
                uOut += xflip ? -2 : 2;
            }
            uIn += 2;
        }
    }

    (*env)->ReleaseByteArrayElements(env,dataPtr,JNI_ABORT);
    (*env)->ReleaseByteArrayElements(env,outputPtr,0);

    end = clock();
    cpu_time_used = ((double) (end - start)) / CLOCKS_PER_SEC;

    __android_log_print(ANDROID_LOG_ERROR,"NV21FrameRotator","%.1f ms",cpu_time_used * 1000);

    return output;
}

转换为C / NDK / JNI的代码效率不如Java原始代码

如何解决转换为C / NDK / JNI的代码效率不如Java原始代码

解决方法

相关推荐