CUDA-Learn-Notes icon indicating copy to clipboard operation
CUDA-Learn-Notes copied to clipboard

__threadfence() 作用

Open zbt78 opened this issue 9 months ago • 3 comments

佬有测试过 0x09 softmax 中的 __threadfence()吗?这个好像没办法达到grid级别线程之间的同步.

zbt78 avatar May 10 '24 16:05 zbt78