Question

我从这个SITE获取warp shuffle操作的代码。我编译了它，我得到了这样的错误致命的C1070：错误的#if /＃endif对文件我很难解决这个错误。有没有人可以帮助我？任何尝试都将受到高度赞赏。谢谢！

这是代码：

#ifndef _REDUCE_KERNEL_H_
#define _REDUCE_KERNEL_H_

#include <stdio.h>


template <class T, unsigned int blockSize>
__global__ void
reduce5(T *g_idata, T *g_odata, unsigned int n)
{
    T *sdata = SharedMemory<T>();

    // perform first level of reduction,
    // reading from global memory, writing to shared memory
    unsigned int tid = threadIdx.x;
    unsigned int i = blockIdx.x*(blockSize*2) + threadIdx.x;

    T mySum = (i < n) ? g_idata[i] : 0;

    if (i + blockSize < n)
        mySum += g_idata[i+blockSize];

    sdata[tid] = mySum;
    __syncthreads();

    // do reduction in shared mem
    if ((blockSize >= 512) && (tid < 256))
    {
        sdata[tid] = mySum = mySum + sdata[tid + 256];
    }

    __syncthreads();

    if ((blockSize >= 256) &&(tid < 128))
    {
            sdata[tid] = mySum = mySum + sdata[tid + 128];
    }

     __syncthreads();

    if ((blockSize >= 128) && (tid <  64))
    {
       sdata[tid] = mySum = mySum + sdata[tid +  64];
    }

    __syncthreads();

#if (__CUDA_ARCH__ >= 300 )
    if ( tid < 32 )
    {
        // Fetch final intermediate sum from 2nd warp
        if (blockSize >=  64) mySum += sdata[tid + 32];
        // Reduce final warp using shuffle
        for (int offset = warpSize/2; offset > 0; offset /= 2) 
        {
            mySum += __shfl_down(mySum, offset);
        }
    }
#else
    // fully unroll reduction within a single warp
    if ((blockSize >=  64) && (tid < 32))
    {
        sdata[tid] = mySum = mySum + sdata[tid + 32];
    }

    __syncthreads();

    if ((blockSize >=  32) && (tid < 16))
    {
        sdata[tid] = mySum = mySum + sdata[tid + 16];
    }

    __syncthreads();

    if ((blockSize >=  16) && (tid <  8))
    {
        sdata[tid] = mySum = mySum + sdata[tid +  8];
    }

    __syncthreads();

    if ((blockSize >=   8) && (tid <  4))
    {
        sdata[tid] = mySum = mySum + sdata[tid +  4];
    }

    __syncthreads();

    if ((blockSize >=   4) && (tid <  2))
    {
        sdata[tid] = mySum = mySum + sdata[tid +  2];
    }

    __syncthreads();

    if ((blockSize >=   2) && ( tid <  1))
    {
        sdata[tid] = mySum = mySum + sdata[tid +  1];
    }

    __syncthreads();
#endif

    // write result for this block to global mem
    if (tid == 0) g_odata[blockIdx.x] = mySum;
}

Answer 1

您的文件中有一个基本的标题保护，请确保您使用#endif关闭它

#ifndef _REDUCE_KERNEL_H_
#define _REDUCE_KERNEL_H_

#include <stdio.h>

...

#endif // _REDUCE_KERNEL_H_

我可以做些什么来修复CUDA编程中的这个错误，致命的C1070：文件中#if /＃endif对不匹配？

1 个答案: