https://stackoverflow.com/questions/63995298/code-translated-to-c-ndk-jni-less-efficient-than-java-original

NV21FrameRotator.c

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 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;

            outputPtr[yOut] = (jbyte) (0xff & dataPtr[yIn]);
        }
    }

    for (unsigned int j = 0; j < height; j+=2) {
        for (unsigned int i = 0; i < width; i+=2) {
            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 uOut = frameSize + (jOut >> 1u) * wOut + (iOut & ~1u);
            unsigned int vOut = uOut + 1;

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

    (*env)->ReleaseByteArrayElements(env, data, dataPtr, JNI_ABORT);
    (*env)->ReleaseByteArrayElements(env, output, 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;
}