我在BeagleBone X-15（ARM Cortex-A15）板上运行Linux 4.4。我的应用程序mmap SGX GPU的输出，需要复制DRM后备存储。
memcpy和我的自定义NEON复制代码都可以工作...但是NEON代码要快得多（~ 11 ms vs. ~ 35 ms）。
我注意到，在12500秒之后，当我使用NEON版本的副本时，Linux会因为内存不足（OOM）而终止应用程序。当我运行应用程序并将一行从NEON副本更改为标准memcpy时，它会无限期地运行（到目前为止运行了12个小时......）。但复制速度较慢。
我已经粘贴了mmap、copy和NEON copy的代码。我的NEON copy真的有什么问题吗？
NEON文案：

/**
* CompOpenGL neonCopyRGBAtoRGBA()
* Purpose: neonCopyRGBAtoRGBA - Software NEON copy
*
* @param src - Source buffer
* @param dst - Destination buffer
* @param numpix - Number of pixels to convert
*/
__attribute__((noinline)) void CompOpenGL::neonCopyRGBAtoRGBA(unsigned char* src, unsigned char* dst, int numPix)
{

    (void)src;
    (void)dst;
    (void)numPix;

    // This case takes RGBA -> BGRA
    __asm__ volatile(
                "mov r3, r3, lsr #3\n"           /* Divide number of pixels by 8 because we process them 8 at a time */
                "loopRGBACopy:\n"
                "vld4.8 {d0-d3}, [r1]!\n"        /* Load 8 pixels into d0 through d2. d0 = R[0-7], d1 = G[0-7], d2 = B[0-7], d3 = A[0-7] */
                "subs r3, r3, #1\n"              /* Decrement the loop counter */
                "vst4.8 {d0-d3}, [r2]!\n"        /* Store the RGBA into destination 8 pixels at a time */
                "bgt loopRGBACopy\n"
                "bx lr\n"
                );

}

Mmap并将代码复制到此处：

union gbm_bo_handle handleUnion = gbm_bo_get_handle(m_Fb->bo);
struct drm_omap_gem_info gemInfo;
char *gpuMmapFrame = NULL;
gemInfo.handle = handleUnion.s32;
int ret = drmCommandWriteRead(m_DRMController->m_Fd, DRM_OMAP_GEM_INFO,&gemInfo, sizeof(gemInfo));
if (ret) {
    qDebug() << "Cannot set write/read";
}
else {
    // Mmap the frame
    gpuMmapFrame = (char *)mmap(0, gemInfo.size, PROT_READ | PROT_WRITE, MAP_SHARED,m_DRMController->m_Fd, gemInfo.offset);

    if ( gpuMmapFrame != MAP_FAILED ) {

        QElapsedTimer timer;
        timer.restart();
        
        //m_OGLController->neonCopyRGBAtoRGBA((uchar*)gpuMmapFrame,  (uchar*)m_cpyFrame,dmaBuf.width * dmaBuf.height);
        memcpy(m_cpyFrame,gpuMmapFrame,dmaBuf.height * dmaBuf.width * 4);
        
        qDebug() << "Copy Performance: " << timer.elapsed();