-
Notifications
You must be signed in to change notification settings - Fork 272
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
【PFCC算子性能优化】添加selu算子性能优化文档 #169
Merged
Merged
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,85 @@ | ||
# Selu OP性能优化设计文档 | ||
|
||
|
||
| 基本信息 | 内容 | | ||
| ------------------------------------------------------------ | ------------------------------------------------------------ | | ||
| 提交作者<input type="checkbox" class="rowselector hidden"> | carryyu | | ||
| 提交时间<input type="checkbox" class="rowselector hidden"> | 2022-07-06 | | ||
| 版本号 | V1.0 | | ||
| 依赖飞桨版本<input type="checkbox" class="rowselector hidden"> | PaddleDevelop | | ||
| 文件名 | 20220706_Selu_op_optimization.md<br> | | ||
|
||
|
||
# 1 背景与意义 | ||
|
||
目前Paddle中的Selu是通过Eigen组合实现,没有用到一些性能优化的技巧,存在性能优化的空间。 | ||
|
||
## 1.1 飞桨现状 | ||
|
||
目前的实现有一定的性能优化空间,可以加入一些性能优化的技巧。当前性能如下表: | ||
| Case No. | input_shape | Pytorch Perf(ms) | | ||
|---|---|---| | ||
| 1 | [8, 1024, 3073] |0.4630 | | ||
| 2 | [5100, 38506] | 3.6001| | ||
| 3 | [300, 100, 128] |0.073 | | ||
|
||
|
||
|
||
## 1.2 业内方案调研 | ||
|
||
Pytorch中对应`paddle.nn.functional.selu` 的Api为 `torch.nn.functional.selu`。调研发现Pytorch中采用的是`SeluKernel` Kernel完成该OP的GPU实现。PyTorch采用的方案是1维线程设置完成整体计算,整体性能如下: | ||
| Case No. | input_shape | Pytorch Perf(ms) | | ||
|---|---|---| | ||
| 1 | [8, 1024, 3073] |0.4674 | | ||
| 2 | [5100, 38506] | 3.6438| | ||
| 3 | [300, 100, 128] |0.072 | | ||
|
||
## 1.3 对比分析 | ||
|
||
目前Paddle与Pytorch的方案几乎相同,算子性能相差不大,但理论上可以通过向量化读取和写入等手段进行优化,进一步提升算子性能。 | ||
|
||
# 2 设计方案与性能预期 | ||
|
||
|
||
|
||
## 2.1 关键模块与性能提升点 | ||
|
||
通过使用飞桨内部的Elementwise Kernel来进行计算。通过向量化读取、向量化写入以及gpu_launch_config.h中的线程配置方法对算子进行优化,预计提升5%。 | ||
|
||
## 2.2 Host端计算流程 | ||
|
||
通过gpu_launch_config.h中的线程配置方法配置1D线程。 | ||
|
||
## 2.4 Device端计算流程 | ||
|
||
设备端通过kps::ReadData和kps::WriteData对数据进行读写,再对每个值进行selu计算。 | ||
|
||
# 3 测试和验收的考量 | ||
|
||
参考:[算子性能优化验收标准](http://agroup.baidu.com/paddle-perf/md/article/4892913) | ||
|
||
|
||
|
||
# 4 可行性分析和排期规划 | ||
|
||
时间和开发排期规划,主要milestone | ||
|
||
| No. | 开发内容 | 预期时间 | | ||
|---|---|---| | ||
| 1 | 理清Paddle中OP设计思路,同类产品中最佳设计方案 | 2022-07-06 | | ||
| 2 | 完成开发文档设计 | 2022-07-07 | | ||
| 3 | 完成代码开发工作,并通过线程CI测试 | 2022-07-10 | | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 文档整体我觉得OK了,目前就是这个时间规划应该需要结合当前的进展改一下哈。 There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 已修改。 |
||
|
||
|
||
|
||
# 5 影响面 | ||
|
||
需要进一步讨论的问题,开放性问题,有争议问题;对其他模块是否有影响。 | ||
|
||
|
||
# 名词解释 | ||
|
||
|
||
# 附件及参考资料 | ||
|
||
[1]. [OP Benchmark使用指南](https://github.com/PaddlePaddle/benchmark/blob/master/api/README.md) |
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这部分感觉可以罗列一下 paddle目前的性能状态,以及对应的case配置信息