OpenCL 原子添加操作的奇怪行为
对于一个项目，我必须深入研究 OpenCL：一切进展顺利，只是现在我需要原子操作。 我正在 Nvidia GPU 上使用最新的驱动程序执行 OpenCL 代码。 clGetDeviceInfo() 查询 CL_DEVICE_VERSION 返回我： OpenCL 1.0 CUDA，因此我想我必须参考 OpenCL 1.0 规范。
我开始在内核中的 __global int* vnumber 缓冲区上使用 atom_add 操作： atom_add(&vnumber[0], 1);。这给了我明显错误的结果。因此，作为额外的检查，我将 add 指令移到了内核的开头，以便为每个线程执行它。当内核以 512 x 512 线程启动时，vnumber[0] 的内容为：524288，正好是 2 x 512 x 512，是该值的两倍我应该得到。有趣的是，通过将添加操作更改为 atom_add(&vnumber[0], 2);，返回值是 65536，又是我应该的两倍得到。
有人已经经历过类似的事情吗？我错过了一些非常基本的东西吗？我已经检查了数据类型的正确性，但看起来没问题（我正在使用 *int 缓冲区，并使用 sizeof(cl_int) 分配它）。
For a project, I had to dive into OpenCL: things are going fairly well except now that I need atomic operations.
I'm executing the OpenCL code on top of an Nvidia GPU, with the last drivers. clGetDeviceInfo() querying CL_DEVICE_VERSION returns me:OpenCL 1.0 CUDA, hence I guess I have to refer to the OpenCL 1.0 specs.
I started using an atom_add operation in my kernel on a __global int* vnumber buffer:atom_add(&vnumber[0], 1);. This gave me clearly wrong results. Thus, as an additional check, I have moved the add instruction at the beginning of the kernel, so that it is executed for each thread. When the kernel is launched with 512 x 512 threads, the content of vnumber[0] is: 524288, which is exactly 2 x 512 x 512, two times the value that I should get. The funny thing is that by changing the add operation to atom_add(&vnumber[0], 2);, the returned value is 65536, again two times what I should get.
Did someone already experienced something similar? Am I missing something very basic? I have checked the correctness of data types but it seems ok (I'm using *int buffer, and allocating it with sizeof(cl_int)).
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（1）
您正在使用atom_add，它是本地内存的OpenCL 1.0 扩展。然而你正在传递它的全球记忆。相反，请尝试 OpenCL 1.1 的atomic_add，它适用于全局内存。
You are using atom_add, which is an OpenCL 1.0 extension for local memory. Yet you are passing it global memory. Instead, try OpenCL 1.1's atomic_add, which works with global memory.