简体繁体 English

可以从设备内核调用CULA例程吗？

[英]Can CULA routines be called from device kernels?

原文 2013-11-13 23:01:49 2 1 c/ cuda/ gpu/ cula

So I'm trying to see if I can get some significant speedup from using a GPU to solve a small overdetermined system of equations by solving a bunch at the same time. 因此，我试图查看是否可以通过使用GPU通过同时解决一堆问题来解决一些超定方程组，从而获得显着的提速。 My current algorithm involves using an LU decomposition function from the CULA Dense library that also has to switch back and forth between the GPU and the CPU to initialize and run the CULA functions. 我当前的算法涉及使用CULA Dense库中的LU分解函数，该库还必须在GPU和CPU之间来回切换，以初始化和运行CULA函数。 I would like to be able to call the CULA functions from my CUDA kernels so that I don't have to jump back to the CPU and copy the data back. 我希望能够从CUDA内核中调用CULA函数，这样我就不必跳回CPU并将数据复制回去。 This would also allow me to create multiple threads that are working on different data sets to be solving multiple systems concurrently. 这也将允许我创建在不同数据集上工作的多个线程，以同时解决多个系统。 My question is can I call CULA functions from device functions? 我的问题是我可以从设备功能中调用CULA功能吗？ I know it's possible with CUBLAS and some of the other CUDA libraries. 我知道CUBLAS和其他一些CUDA库是可能的。

Thanks! 谢谢！

1 个解决方案

The short answer is no. 最简洁的答案是不。 The CULA library routines are designed to be called from host code, not device code. CULA库例程设计为从主机代码而非设备代码调用。

Note that CULA have their own support forums here which you may be interested in. 需要注意的是CULA有自己的支持论坛在这里，你可能会感兴趣。