提交 57960789 编写于 作者: 刘琦

Merge branch 'update_docs' into 'master'

Add responsiveness docs

See merge request !540
...@@ -20,6 +20,10 @@ targets: ...@@ -20,6 +20,10 @@ targets:
* Power consumption * Power consumption
* Chip dependent power options like big.LITTLE scheduling, Adreno GPU hints are * Chip dependent power options like big.LITTLE scheduling, Adreno GPU hints are
included as advanced API. included as advanced API.
* Responsiveness
* UI responsiveness gurantee is sometimes obligatory when runing a model.
Mechanism like automatically breaking OpenCL kernel into small units is
introduced to allow better preemption for the UI rendering task.
* Memory usage and library footprint * Memory usage and library footprint
* Graph level memory allocation optimization and buffer reuse is supported. * Graph level memory allocation optimization and buffer reuse is supported.
The core library tries to keep minium external dependencies to keep the The core library tries to keep minium external dependencies to keep the
......
...@@ -17,6 +17,9 @@ ...@@ -17,6 +17,9 @@
此外,还对启动速度进行了专门的优化。 此外,还对启动速度进行了专门的优化。
* 功耗 * 功耗
* 支持芯片的功耗管理,例如ARM的big.LITTLE调度,以及高通Adreno GPU功耗选项。 * 支持芯片的功耗管理,例如ARM的big.LITTLE调度,以及高通Adreno GPU功耗选项。
* 系统响应
* 支持自动拆解长时间的OpenCL计算任务,来保证UI渲染任务能够做到较好的抢占调度,
从而保证系统UI的相应和用户体验。
* 内存占用 * 内存占用
* 通过运用内存依赖分析技术,以及内存复用,减少内存的占用。另外,保持尽量少的外部 * 通过运用内存依赖分析技术,以及内存复用,减少内存的占用。另外,保持尽量少的外部
依赖,保证代码尺寸精简。 依赖,保证代码尺寸精简。
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册