Jacket v1.2功能预览－支持MATLAB跨多GPU并行计算

北京科卓

　
　　不久前，AccelerEyes刚刚发布了Jacket for MATLAB的重大更新v1.1（参见：“Jacket v1.1发布－MATLAB GPU插件支持双精度浮点计算”一文），最近又有了Jacket v1.1.1小版本的改进。其中包括了“grand()”随机数生成器和针对FFT（快速傅里叶变换）的双精度支持。

                               
登录/注册后可看大图

新版本的改进如下：

增加：

+ fft is now supported for gdouble inputs.
+ grandn - GPU version of randn.
+ grand - GPU version of rand.
+ sort(X) is now supported.
+ cumsum(X) is now supported for vectors.
+ cumprod(X) is now supported for vectors.
+ permute, ipermute is now supported.
+ repmat is now supported for complex inputs.
+ The gcache command now allows users to manipulate the cache by flushing, saving or loading it.
+ The command 'ghelp' displays information about functions supported by Jacket on the MATLAB console:
     - Features different from MATLAB's implementation of the function
     - Supported syntax for the function
     - Where relevant, whether a function can be used within a gfor loop.
+ mod and rem now have complex support.
+ xor support for float data types.

修正：

+ conv2(A,B,'same') with subscripted references to A and B now produces correct results.
+ dot(A,B) performed on 2D matrices now gives an error message instead of an incorrect result.
+ Fixed a rounding issue that caused cast to work incorrectly on gsingle-to-guint32 conversion.
+ isinteger now returns a single value for an array, instead of an array of values.
+ Fixed an issue in isfloat which was causing it to return incorrect results.
+ Sign no longer gives incorrect results for real gdouble data.
+ Fixed an issue where mod did not work similar to MATLAB.
+ Fixed an issue where rem returned incorrect results.
+ Subscripted assignments of the type A(B) = C now work for real A and complex C.
+ circshift no longer gives erroneous results with shifts greater than the dimension of the input.
+ atan2 and hypot no longer cause GPU failure for real inputs of different precision types.
+ repmat(A,M,N) now returns an error message if M and N are GPU variables.
+ Fixed a bug that caused assignments of the type A = B(1:N, to crash beyond a particular subscript N.


　　使用Jacket 1.1.1需要CUDA 2.3（1.1版本对应CUDA 2.2），同时NVIDIA显卡（Tesla）驱动也要求190+版本。CUDA驱动和工具集可以从这里下载：http://www.nvidia.com/object/cuda_get.html

                               
登录/注册后可看大图

　　AccelerEyes预期下一个版本Jacket 1.2将在很短的时间内发布，它将支持运行Jacket时跨越多个GPU（以前的Jacket也能够支持一台主机上的多个GPU，不过每个只能用于加速多个进程中的一个）。Jacket 1.2结合了MATLAB's Parallel Computing Toolbox (PCT)并行计算工具箱。针对系统中的每个GPU（包括工作站和集群中的），一个PCT任务将被赋予“具有将计算工作从CPU卸载到GPU”的能力。这样就能够在任意可提供的硬件配置上发挥出最大性能（特别是配置了多块Tesla C1060计算处理器的系统）。在期盼这个版本的过程中，我们建议您尝试PCT并了解关于“它是怎样提升您的多核工作站或者集群的计算性能”。您能够从这里了解更多：MATLAB PCT

                               
登录/注册后可看大图

点击进入相关产品页面
http://www.quadro.net.cn/Pro_ProductList.aspx?id=107

北京科卓

点击发表对本文的评论
http://www.quadro.net.cn/club/read.asp?page=1&recno=4160