【PaddlePaddle Hackathon 4 No.35】为 Paddle 优化 prelu op 在 GPU 上的计算性能 #51131
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
|
你的PR提交成功，感谢你对开源项目的贡献! |
JamesLim-sy
reviewed
Mar 14, 2023
| @@ -43,7 +43,7 @@ __global__ void VectorizedIndexKernel(T *out, | |||
| out + data_offset, &result[0], BLOCK_NUM_X * VecSize); | |||
| } | |||
| size_t num = numel - data_offset; | |||
| if (num > 0) { | |||
| if (static_cast<int>(num) > 0) { | |||
There was a problem hiding this comment.
这里感觉不需要做 static_cast 的转换操作.
There was a problem hiding this comment.
之前跑benchmark的时候，定位了很久才发现这里一直报错，所以才修改了. @JamesLim-sy
paddle/phi/kernels/gpu/prelu_funcs.h
Outdated
| size_t channel_num_; | ||
| size_t plane_size_; | ||
| int numel_; | ||
| const T zero = static_cast<T>(0); |
There was a problem hiding this comment.
这里不必作为成员变量，在HOSTDEVICE inline PReluChannelFirstWiseCUDAFunctor函数实现内，作为下述代码行即可：
constexpr T zero = static_cast<T>(0);
There was a problem hiding this comment.
@JamesLim-sy 使用constexpr或const，在编译时会报错， 我暂时先去掉。
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Outdated suggestions cannot be applied.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
Performance optimization
PR changes
OPs
Describe
目前Paddle中的Prelu算子仍旧通过内部循环方式实现，没有用到一些性能优化的技巧，存在性能优化的空间。
设计文档: PaddlePaddle/community#370
通过使用飞桨内部kps的Elementwise Kernel 和 IndexKernel来进行计算。通过向量化读取、向量化写入对prelu算子进行优化.
完成优化后，Paddle与优化前的Paddle的性能对比效果:
完成优化后，Paddle与Pytorch的性能对比效果如下:
针对四种不同case, 优化后的性能有不同程度的提升。