Skip to content

Conversation

@Graylatzhou
Copy link
Contributor

No description provided.

}
};

template <typename T, template <typename> class ReduceOp, int thread_group_width = 32>
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

(line 50)常数最好是全大写 snake_case

Comment on lines 79 to 81
template <int elemPerThread, int BLOCK_DIM_Y, int BLOCK_DIM_X, typename T>
__global__ void Softmax_warp_impl(const T *x, T *y, int stride, int dimsize, int otherdim_size) {
float dataPerThread[elemPerThread];
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

命名规范。其他地方也都检查一下,不再重复标注了

@PanZezhong1725
Copy link
Collaborator

测试框架有重构,请rebase最新代码做相应更改

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

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[DEV] 添加Softmax算子

3 participants