Jacket SDK

Jacket SDK

Jacket SDK

Software Development Kit

Jacket SDK makes integration of custom CUDA code into Jacket's runtime very easy. With a few Jacket-specific functions, CUDA code will benefit from Jacket's automated optimizations.

The Jacket SDK enables you to wrap CUDA kernels in a jktFunction (similar to the MATLAB mexFunction). In the jktFunction, the class and dimensions of the inputs are determined with the jkt_class and jkt_dims functions. New mxArray's are allocated using the jkt_new function. Device side pointers (GPU arrays) are initialized using the jkt_mem function, providing a safe way for Jacket to read/write to the GPU.

Compiling your Jacketized CUDA kernel results in a standard MEX file. You can call this MEX file from your MATLAB scripts and can pass in Jacket's GPU data types. Jacket will optimize the launch of your kernels and manage memory transfers. You CUDA code inherits Jacket's runtime optimizations.

This process is no more than declaring inputs and outputs, allocating memory to them, and calling the CUDA kernel.

With over 100 million CUDA-enabled GPUs sold to date, thousands of software developers are already using the free CUDA software development tools to solve problems in a variety of professional and home applications - from video and audio processing and physics simulations, to oil and gas exploration, product design,medical imaging, and scientific research. With this user community and the growing availability of CUDA kernals, Jacket's SDK is a must for domain professionals.

The base Jacket license does not require any knowledge of CUDA or other GPU programming architectures; however, for users that have or will develop CUDA kernels, Jacket SDK is a perfect capability to speed development, improve testing, and simplify deployment of complete applications and algorithms.

軟件開發工具包

Jacket SDK使得定制CUDA代碼融入Jacket的運行時很容易。隨著一些特定的Jacket功能，CUDA代碼將受益於Jacket的自動優化。

Jacket SDK使您在jktFunction（類似的MATLAB的mexFunction）包裝CUDA內核。在jktFunction, 輸入類和尺寸由jkt_class和jkt_dims功能決定。新mxArray’s的定位有jkt_new功能決定。設備端指針（GPU陣列）初始化使用的jkt_mem功能，提供一個安全的方式為Jacket讀/寫的GPU。

編譯您Jacketized的CUDA內核的致使一個標準的MEX文件。您可以從您的MATLAB字體交出這個 MEX文件，並能傳遞Jacket GPU提供的數據類型。Jacket將優化你的內核的啟動和管理內存傳輸。您CUDA代碼繼承Jacket的運行時優化。

這個過程不过是宣稱輸入和輸出，分配內存，並調用 CUDA內核。

售超過 100萬的支持CUDA的GPU，數以千計的軟件開發人員已經使用免費的CUDA軟件開發工具，以解決各種專業和家庭應用中的問題- 從視頻和音頻處理和物理模擬，石油和天然氣的勘探，產品設計，醫療成像，和科研。與此用戶社區和CUDA的内核的日益普及，Jacket SDK是網域專業人士必須拥有的。

基礎Jacket許可證不需要任何CUDA或GPU編程架構的知識; 但是，對於已經或將開發 CUDA內核的用戶，Jacket SDK是一個完美的的能力可以加快發展，提高測試，並簡化部署完整的應用和算法。