Databases
StackOverflow2013
Postsdbo
POcuda shared memory overwrite?
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POcuda shared memory overwrite?
    primarykey
    data
    text
    <p>I am trying to write a parallel prefix scan on cuda by following this <a href="http://http.developer.nvidia.com/GPUGems3/gpugems3_ch39.html" rel="nofollow">tutorial -</a> </p> <p>I am trying the work-inefficient 'double buffered one' as explained in the tutorial.</p> <p>This is what I have:</p> <pre><code>// double buffered naive. // d = number of iterations, N - size, and input. __global__ void prefixsum(int* in, int d, int N) { //get the block index int idx = blockIdx.x*blockDim.x + threadIdx.x; // allocate shared memory extern __shared__ int temp_in[], temp_out[]; // copy data to it. temp_in[idx] = in[idx]; temp_out[idx] = 0; // block until all threads copy __syncthreads(); int i = 1; for (i; i&lt;=d; i++) { if (idx &lt; N+1 &amp;&amp; idx &gt;= (int)pow(2.0f,(float)i-1)) { // copy new result to temp_out temp_out[idx] += temp_in[idx - (int)pow(2.0f,(float)i-1)] + temp_in[idx]; } else { // if the element is to remain unchanged, copy the same thing temp_out[idx] = temp_in[idx]; } // block until all theads do this __syncthreads(); // copy the result to temp_in for next iteration temp_in[idx] = temp_out[idx]; // wait for all threads to do so __syncthreads(); } //finally copy everything back to global memory in[idx] = temp_in[idx]; } </code></pre> <p>Can you point out what's wrong with this? I have written comments for what I think should happen.</p> <p>This is the kernel invocation - </p> <pre><code>prefixsum&lt;&lt;&lt;dimGrid,dimBlock&gt;&gt;&gt;(d_arr, log(SIZE)/log(2), N); </code></pre> <p>This is the grid and block allocations:</p> <pre><code>dim3 dimGrid(numBlocks); dim3 dimBlock(numThreadsPerBlock); </code></pre> <p>The problem is that I don't get the correct output for any input that's more than 8 elements long. </p>
    singulars
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. PTQuestion
    1. USGitmo
    1. USGitmo
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. COCan you add your kernel invocation? And what is the exact problem?
      singulars
      1. POcuda shared memory overwrite?
      1. USMichael Haidl
    2. COWhat is the values of `dimGrid` and `dimBlock`?
      singulars
      1. POcuda shared memory overwrite?
      1. USflipchart
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload