diff --git a/README.md b/README.md
index 7b37dcf0b6a356b89137b8d02d7a1a1ca3b25687..7a0afcc10c263f74d5a11d4bac13f0268767e38a 100644
--- a/README.md
+++ b/README.md
@@ -20,6 +20,10 @@ targets:
 * Power consumption
   * Chip dependent power options like big.LITTLE scheduling, Adreno GPU hints are
     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
   * Graph level memory allocation optimization and buffer reuse is supported.
     The core library tries to keep minium external dependencies to keep the
diff --git a/README_zh.md b/README_zh.md
index a2556368d2c4ef753a335efa590dbc31ae9f9831..64af32eb084a116eae07598d96bafbafa5b4018c 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -17,6 +17,9 @@
   此外，还对启动速度进行了专门的优化。
 * 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。
+* 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
   * 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。