Cuda中的纹理坐标

我正在研究使用cuda实现DCT： 有关部分如下：

__shared__ float CurBlockLocal1[BLOCK_SIZE2];

__global__ void CUDAkernel1DCT(float *Dst, int ImgWidth, int OffsetXBlocks, int OffsetYBlocks)
{
    // Block index
    const int bx = blockIdx.x + OffsetXBlocks;
    const int by = blockIdx.y + OffsetYBlocks;

    // Thread index (current coefficient)
    const int tx = threadIdx.x;
    const int ty = threadIdx.y;

    // Texture coordinates
    const float tex_x = (float)( (bx << BLOCK_SIZE_LOG2) + tx ) + 0.5f;
    const float tex_y = (float)( (by << BLOCK_SIZE_LOG2) + ty ) + 0.5f;

    //copy current image pixel to the first block
    CurBlockLocal1[ (ty << BLOCK_SIZE_LOG2) + tx ] = tex2D(TexSrc, tex_x, tex_y);

    //synchronize threads to make sure the block is copied
    __syncthreads();

\uuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuu；
__全局无效CUDAkernel1DCT（浮点*Dst、整数ImgWidth、整数offsetXblock、整数offsetBlocks）
{
//块索引
const int bx=blockIdx.x+offsetxblock；
const int by=blockIdx.y+OffsetYBlocks；
//螺纹指数（电流系数）
const int tx=threadIdx.x；
const int ty=threadIdx.y；
//纹理坐标
const float tex_x=（float）（（bx按相反顺序回答您的问题：

如标准C或C++，
以相反的顺序回答你的问题：
如标准C或C++中的
__shared__ float CurBlockLocal1[BLOCK_SIZE2];

__global__ void CUDAkernel1DCT(float *Dst, int ImgWidth, int OffsetXBlocks, int OffsetYBlocks)
{
    // Block index
    const int bx = blockIdx.x + OffsetXBlocks;
    const int by = blockIdx.y + OffsetYBlocks;

    // Thread index (current coefficient)
    const int tx = threadIdx.x;
    const int ty = threadIdx.y;

    // Texture coordinates
    const float tex_x = (float)( (bx * BLOCK_SIZE) + tx ) + 0.5f;
    const float tex_y = (float)( (by * BLOCK_SIZE) + ty ) + 0.5f;

    //copy current image pixel to the first block
    CurBlockLocal1[ (ty * BLOCK_SIZE) + tx ] = tex2D(TexSrc, tex_x, tex_y);

    ......
}