CUDA 新删除 [英] CUDA new delete

问题描述

如果从 CUDA 4.2 中的 __device__ 或 __global__ 代码调用 new 和 delete 关键字的行为，有人能给出清楚的解释吗?

Can someone give a clear explanation of how the new and delete keywords would behave if called from __device__ or __global__ code in CUDA 4.2?

内存在哪里分配，如果它在设备上是本地的还是全局的?

Where does the memory get allocated, if its on the device is it local or global?

我试图在 GPU 上创建神经网络的问题的上下文，我想要一个链接表示(就像一个链接列表，但每个神经元都存储一个链接的链接列表，其中包含权重和指向另一个的指针神经元)，我知道我可以在内核启动之前使用 cudaMalloc 进行分配，但我希望内核控制网络的创建方式和时间.

It terms of context of the problem I am trying to create neural networks on the GPU, I want a linked representation (Like a linked list, but each neuron stores a linked list of connections that hold weights, and pointers to the other neurons), I know I could allocate using cudaMalloc before the kernel launch but I want the kernel to control how and when the networks are created.

谢谢！

推荐答案

C++ new 和 delete 对设备堆内存进行操作.该设备允许以这种方式分配一部分全局(即板载)内存.new 和 delete 的工作方式类似于 设备 malloc 和 free.

C++ new and delete operate on device heap memory. The device allows for a portion of the global (i.e. on-board) memory to be allocated in this fashion. new and delete work in a similar fashion to device malloc and free.

您可以使用 运行时 API 调用.

您可能还对 C++ new/delete 示例代码感兴趣.

这些功能需要 CC 2.0 或更高版本.

CC 2.0 or greater is required for these capabilities.

这篇关于CUDA 新删除的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！