首页| JavaScript| HTML/CSS| Matlab| PHP| Python| Java| C/C++/VC++| C#| ASP| 其他|
购买积分 购买会员 激活码充值

您现在的位置是:虫虫源码 > 其他 > Windows平台下的GPU编程模型的性能和安全性

Windows平台下的GPU编程模型的性能和安全性

资 源 简 介

The KUTA framework faces issues rising in the OpenCL specification when executing algorithms that contain complex control, composite data structures and excessive message passing. An early motivation of this work is to tackle the problem caused by the Timeout Detection and Recovery (TDR) feature in Windows. When high volume of computations causes the GPU to become unresponsive for more than two seconds, the Windows Timeout Detection and Recovery (TDR) feature is triggered. The TDR error message "Display driver stopped responding and has recovered" is being displayed, resetting the display driver and aborting all computations. Starting from a fault-intolerant state, a program that satisfies the OpenCL specification, is tuned into a fail-safe one, through the introduction of configuration properties. These parameters are responsible for defining the safety requirements and desired system behaviors under fault conditions. Examples of these are: (i) the m

文 件 列 表

appGPU_Kernels.cl
appGPU.exe
configurator.exe
readme.docx

相 关 资 源

您 可 能 感 兴 趣 的

同 类 别 推 荐

VIP VIP