简体繁体 English

是否可以使用OpenCL分配设备内存并使用指向CUDA中内存的指针？

[英]Can I allocate device memory using OpenCL and use pointers to the memory in CUDA?

原文 2015-04-16 08:52:19 0 2 c++/ memory/ cuda/ opencl

Say I use OpenCL to manage memory (so that memory management between GPU/CPU uses the same code), but my calculation uses optimized CUDA and CPU code (not OpenCL). 假设我使用OpenCL来管理内存（以便GPU / CPU之间的内存管理使用相同的代码），但是我的计算使用了优化的CUDA和CPU代码（不是OpenCL）。 Can I still use the OpenCL device memory pointers and pass them to CUDA functions/kernels? 我仍然可以使用OpenCL设备内存指针并将其传递给CUDA函数/内核吗？

2 个解决方案

AFAIK this is not possible, but there is no technical reason why you shouldn't be able to. AFAIK这是不可能的，但是没有技术原因使您不应该这样做。

NVIDIA could build an extension to the OpenCL API to interoperate with CUDA, much like the interoperability provisions for Direct3D and OpenGL. NVIDIA可以构建对OpenCL API的扩展以与CUDA进行互操作，就像Direct3D和OpenGL的互操作性条款一样。

Since both CUDA and OpenCL can interop with OpenGL you might explore that as a middle ground. 由于CUDA和OpenCL都可以与OpenGL互操作，因此您可以将其作为中间立场。 I was successfully able to access the same OpenGL texture both from OpenCL (as an image) and CUDA, so you might be able to do the same thing for a buffer of data (I'm not positive what the OpenGL representation would be though). 我已经能够从OpenCL（作为图像）和CUDA成功访问相同的OpenGL纹理，因此您可能能够对数据缓冲区执行相同的操作（我不太肯定OpenGL表示什么）。

如何在CUDA中为我的指针数组分配设备内存？ - How do I allocate device memory to my array of pointers, in CUDA?

我可以在 C++ 中使用指针分配特定的内存地址吗？ - Can I Allocate a specific memory address using pointers in c++?

我可以在CUDA设备上为包含浮点数数组的对象分配内存吗？ - Can I allocate memory on CUDA device for objects containing arrays of float numbers?

如何使用指针动态分配内存？ - How to allocate memory dynamically using pointers?

如何将动态 Memory 分配给 C++ CUDA 中的设备指针变量 - How to allocate Dynamic Memory to Device Pointer variable in C++ CUDA

为具有增加的维度（点数）的点云分配CUDA设备内存 - Allocate CUDA device memory for a point cloud with increasing dimension (number of point)

如何在主机内存上分配一半的OpenCL缓冲区，在设备内存上分配另一半？ - How to allocate one half of an OpenCL buffer on host memory and the other half on device memory?

迭代器是否分配诸如指针之类的内存？ - Do the iterators allocate memory such as pointers?

尝试使用CUDA分配内存时出现访问冲突写入位置错误 - I get access violation writing location error when trying to allocate memory using CUDA

CUDA-每次都必须分配和释放内存吗？ - CUDA - do I have to allocate and free memory each time?

暂无

暂无

声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 如何在CUDA中为我的指针数组分配设备内存？ - How do I allocate device memory to my array of pointers, in CUDA? 我可以在 C++ 中使用指针分配特定的内存地址吗？ - Can I Allocate a specific memory address using pointers in c++? 我可以在CUDA设备上为包含浮点数数组的对象分配内存吗？ - Can I allocate memory on CUDA device for objects containing arrays of float numbers? 如何使用指针动态分配内存？ - How to allocate memory dynamically using pointers? 如何将动态 Memory 分配给 C++ CUDA 中的设备指针变量 - How to allocate Dynamic Memory to Device Pointer variable in C++ CUDA 为具有增加的维度（点数）的点云分配CUDA设备内存 - Allocate CUDA device memory for a point cloud with increasing dimension (number of point) 如何在主机内存上分配一半的OpenCL缓冲区，在设备内存上分配另一半？ - How to allocate one half of an OpenCL buffer on host memory and the other half on device memory? 迭代器是否分配诸如指针之类的内存？ - Do the iterators allocate memory such as pointers? 尝试使用CUDA分配内存时出现访问冲突写入位置错误 - I get access violation writing location error when trying to allocate memory using CUDA CUDA-每次都必须分配和释放内存吗？ - CUDA - do I have to allocate and free memory each time?

相关标签

粤ICP备18138465号 © 2020-2024 STACKOOM.COM