Skip to content

Conversation

@knowledgaction
Copy link

就是根据课程里的一些知识点,完成这次作业。

  • 跨步循环的步长为blockDim.x * gridDim.x
  • 写操作冲突,采用原子操作
  • gridDim设为设为一个合适的数值,跨步循环可以循环起来。
  • 加上同步操作。
  • 边角料法,(n + nthreads - 1 / nthreads )

@knowledgaction
Copy link
Author

还有啊,我用Win11+vs2022+cuda12.2,配环境折腾好久。而且CudaAllocator一直编译不过去,看了其他的pr找到了方法,通过的编译。挺费劲,但是还会继续用windows搞下去。新买的笔记本,不想换系统,哈哈~~

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant