c++ - parallel_for_each 上下文中的数组复制

Question

我非常是 AMP C++ 的新手。如果我在“parallel_for_each”函数中使用“memcpy”，一切正常，但我知道这不是最佳做法。我尝试使用“copy_to”，但它引发了异常。下面是一个简化的代码，重点是我遇到麻烦的问题。提前致谢。

typedef std::vector<DWORD> CArrDwData;

class CdataMatrix
{
public:
    CdataMatrix(int nChCount) : m_ChCount(nChCount)
    {
    }

    void SetSize(UINT uSize)
    {
        // MUST be multiple of m_ChCount*DWORD
        ASSERT(uSize%sizeof(DWORD) == 0);
        m_PackedLength = uSize/sizeof(DWORD);
        m_arrChannels.resize(m_ChCount*m_PackedLength);
    }

    UINT GetChannelPackedLen() const
    {
        return m_PackedLength;
    }
    const LPBYTE GetChannelBuffer(UINT uChannel) const
    {
        CArrDwData::const_pointer cPtr = m_arrChannels.data() + m_PackedLength*uChannel;

        return (const LPBYTE)cPtr;
    }

public:
    CArrDwData m_arrChannels;

protected:
    UINT m_ChCount;
    UINT m_PackedLength;
};

void CtypDiskHeader::ParalelProcess()
{
    const int nJobs = 6;
    const int nChannelCount = 3;
    UINT uAmount = 250000;
    int vch;

    CArrDwData arrCompData;

    // Check buffers sizes
    ASSERT((~uAmount & 0x00000003) == 3);   // DWORD aligned
    const UINT uInDWSize = uAmount/sizeof(DWORD);   // in size give in DWORDs

    CdataMatrix arrChData(nJobs);

    arrCompData.resize(nJobs*uInDWSize);
    vector<int> a(nJobs);
    for(vch = 0; vch < nJobs; vch++)
        a[vch] = vch;

    arrChData.SetSize(uAmount+16); // note: 16 bytes or 4 DWORDs larger than uInDWSize

    accelerator_view acc_view = accelerator().default_view;

    Concurrency::extent<2> eIn(nJobs, uInDWSize);
    Concurrency::extent<2> eOut(nJobs, arrChData.GetChannelPackedLen());

    array_view<DWORD, 2> viewOut(eOut, arrChData.m_arrChannels);

    array_view<DWORD, 2> viewIn(eIn, arrCompData);

    concurrency::parallel_for_each(begin(a), end(a), [&](int vch)
    {
        vector<DWORD>::pointer ptr = (LPDWORD)viewIn(vch).data();
        LPDWORD bufCompIn = (LPDWORD)ptr;
        ptr = viewOut(vch).data();
        LPDWORD bufExpandedIn = (LPDWORD)ptr;

        if(ConditionNotOk())
        {
            // Copy raw data bufCompIn to bufExpandedIn

            // Works fine, but not the best way, I suppose:
            memcpy(bufExpandedIn, bufCompIn, uAmount);

            // Raises exception:
            //viewIn(vch).copy_to(viewOut(vch));
        }
        else
        {
            // Some data processing here
        }
    });
}

Answer 1

是我的错。在原始代码中，viewOut(vch) 的范围比 viewIn(vch) 的范围大一点。使用这种方式，它会引发异常“runtime_exception”。捕获它时，它会提供以下消息 xcp.what() = "Failed to copy because extents do not match"。

我修复了替换原始代码的代码:viewIn(vch).copy_to(viewOut(vch).section(viewIn(vch).extent));它只复制源范围，这就是我所需要的。但只编译没有受限制的 AMP。