-
Notifications
You must be signed in to change notification settings - Fork 762
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
add method introduction for op-perf #4937
add method introduction for op-perf #4937
Conversation
JamesLim-sy
commented
Jun 16, 2022
•
edited
Loading
edited
- Addition of performance optimization introduction.
感谢你贡献飞桨文档,文档预览构建中,Docs-New 跑完后即可预览,预览链接:http://preview-pr-4937.paddle-docs-preview.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html |
2d756df
to
42a58b6
Compare
42a58b6
to
23c0039
Compare
a3c3a3b
to
b9d1ba5
Compare
|
||
我们推荐结合OP的使用场景设计对于的线程配置策略,如下图所示[IndexSample OP](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/index_sample_cn.html#index-sample)常用于处理2维数据, 因此使用[2维的线程配置策略](https://github.com/PaddlePaddle/Paddle/blob/30838aa698d6f3f3b0860b052f6a50ef53ac6784/paddle/phi/kernels/gpu/index_sample_kernel.cu#L82-L91)相对比1维配置策略,性能可提升20%左右。 | ||
|
||
<p align="center"> |
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.
图都挂了
@@ -0,0 +1,85 @@ | |||
# 算子性能优化 方法介绍 | |||
|
|||
飞桨作为一个开源项目, 提供高性能的计算服务是飞桨的特色之一。我们非常欢迎开发者为 Paddle 框架贡献高性能算子, 本文旨在向开发者提供一些快速实现高性能计算的方法。 |
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.
别用我们,省略主语/ 飞桨
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.
已修改
b9d1ba5
to
265f20a
Compare