c++ - 下面的c++程序有没有代码优化方法

Question

        BYTE * srcData;
        BYTE * pData;

        int i,j;
        int srcPadding;

                    //some variable initialization

        for (int r = 0;r < h;r++,srcData+= srcPadding)
        {
            for (int col = 0;col < w;col++,pData += 4,srcData += 3)
            {
                memcpy(pData,srcData,3);        
            }
        }

我试过展开循环，但效果甚微。

        int segs = w / 4;
        int remain = w - segs * 4; 

        for (int r = 0;r < h;r++,srcData+= srcPadding)
        {
            int idx = 0;
            for (idx = 0;idx < segs;idx++,pData += 16,srcData += 12)
            {
                memcpy(pData,srcData,3);
                *(pData + 3) = 0xFF;
                memcpy(pData + 4,srcData + 3,3);
                *(pData + 7) = 0xFF;
                memcpy(pData + 8,srcData + 6,3);
                *(pData + 11) = 0xFF;
                memcpy(pData + 12,srcData + 9,3);
                *(pData + 15) = 0xFF;
            }
            for (idx = 0;idx < remain;idx++,pData += 4,srcData += 3)
            {
                memcpy(pData,srcData,3);
                *(pData + 3) = 0xFF;
            }
        }

Answer 1

根据您的编译器，对于这么小的拷贝，您可能根本不需要 memcpy。这是展开循环主体的变体版本；看看它是否更快:

uint32_t in0 = *(uint32_t*)(srcData);
uint32_t in1 = *(uint32_t*)(srcData + 4);
uint32_t in2 = *(uint32_t*)(srcData + 8);
uint32_t out0 = UINT32_C(0xFF000000) | (in0 & UINT32_C(0x00FFFFFF));
uint32_t out1 = UINT32_C(0xFF000000) | (in0 >> 24) | ((in1 & 0xFFFF) << 8);
uint32_t out2 = UINT32_C(0xFF000000) | (in1 >> 16) | ((in2 & 0xFF) << 16);
uint32_t out3 = UINT32_C(0xFF000000) | (in2 >> 8);
*(uint32_t*)(pData) = out0;
*(uint32_t*)(pData + 4) = out1;
*(uint32_t*)(pData + 8) = out2;
*(uint32_t*)(pData + 12) = out3;

您还应该将 srcData 和 pData 声明为 BYTE * restrict 指针，以便编译器知道它们没有别名。