ScalaCL is the main one for Scala. It works through a set of specialised collections that'll defer work to the GPU via OpenCL.
Then there's also the ScalaCL Plugin, part of ScalaCL. Which is a compiler plugin that'll automatically rewrite some of your code to use OpenCL bindings for acceleration, no extra work required!
发布评论
评论（4）
ScalaCL 是 Scala 的主要版本。它通过一组专门的集合来工作，这些集合将通过 OpenCL 将工作推迟到 GPU。
此外还有 ScalaCL 插件，它是 ScalaCL 的一部分。这是一个编译器插件，会自动重写一些代码以使用 OpenCL 绑定进行加速，无需额外工作！
ScalaCL is the main one for Scala. It works through a set of specialised collections that'll defer work to the GPU via OpenCL.
Then there's also the ScalaCL Plugin, part of ScalaCL. Which is a compiler plugin that'll automatically rewrite some of your code to use OpenCL bindings for acceleration, no extra work required!
并且不要忘记Matlab，Mathematica 和 Fortran，所有这些都有 CUDA 支持。 Mathematica 也支持 OpenCL。
And don't forget Matlab, Mathematica and Fortran, all of which have CUDA support. Mathematica supports OpenCL too.
Java 和 Python 具有 OpenCL 的绑定。
您必须使用 CUDA 或 OpenCL 编写 GPU 代码。除非您找到了一个可以进行基本循环并行化的库。
Java and Python have bindings for OpenCL.
You will have to write the GPU code in CUDA or OpenCL. Unless you found a library that did basic parallelization of loops.
http://en.wikipedia.org/wiki/CUDA#Language_bindings 列出了 Java 的绑定（可从 Scala 使用，但需要一个适配层以使它们更可用）、.NET 和 Python。
另请参阅 https://github.com/ztellman/penumbra (Clojure) 和 http:// /blogs.msdn.com/b/satnam_singh/archive/2009/12/15/gpgpu-and-x64-multicore-programming-with-accelerator-from-f.aspx 和 http://tomasp.net/blog/accelerator-intro.aspx (F#)
http://en.wikipedia.org/wiki/CUDA#Language_bindings lists bindings for Java (usable from Scala, but will need an adapting layer to make them more usable), .NET and Python.
See also https://github.com/ztellman/penumbra (Clojure) and http://blogs.msdn.com/b/satnam_singh/archive/2009/12/15/gpgpu-and-x64-multicore-programming-with-accelerator-from-f.aspx and http://tomasp.net/blog/accelerator-intro.aspx (F#)