Implement SparseConv3d kernel #39784
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 10 commits
February 17, 2022 09:24
|
Thanks for your contribution! |
xingfeng01
reviewed
Feb 22, 2022
| } | ||
| __syncthreads(); | ||
| for (int i = threadIdx.x; i < kernel_size; i += blockDim.x) { | ||
| atomicAdd(&counter[i], counter_buf[i]); |
There was a problem hiding this comment.
这里分块进行计数，然后在atomicAdd到global中，后面考虑进一步优化。
| 0.7473, 0.5403, 0.5391, 0.0796, 0.4734, 0.9097, 0.1712, 0.6237, 0.8837}; | ||
|
|
||
| std::vector<std::vector<int>> out_indices = { | ||
| // {0, 0, 0, 0}, |
|
|
||
| 0.7473, 0.5403, 0.5391, 0.0796, 0.4734, 0.9097, 0.1712, 0.6237, 0.8837}; | ||
|
|
||
| std::vector<std::vector<int>> out_indices = {// {0, 0, 0, 0}, |
added 2 commits
February 22, 2022 07:59
| namespace sparse { | ||
|
|
||
| // TODO(zhangkaihuo) replace this kernel with KP::InitWithDataIndex | ||
| __global__ void InitByIndexKernel(const int n, int* out1, int* out2) { |
There was a problem hiding this comment.
There was a problem hiding this comment.
等这个代码迁移到phi下面后再进行复用。
There was a problem hiding this comment.
added 2 commits
March 1, 2022 12:25
| // this kernel with phi::GatherCUDAKernel; | ||
| template <typename T, typename IndexT = int> | ||
| __global__ void GatherKernel(const T* params, | ||
| const IndexT* indices, |
xingfeng01
approved these changes
Mar 3, 2022
AnnaTrainingG
approved these changes
Mar 3, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR types
New features
PR changes
OPs
Describe
实现SparseConv3d的kenrel，算法采用Second，参考串行代码PR.
性能情况：与spconv的native实现对比gpu kernel耗时：v100上，对比单测，其中 X(2, 400,400, 15, 17), kernel(3, 3, 3, 17, 19) : fp32 1.3x加速比，fp16 1.4x加速比。