Shizhi Tang

Of course it is the best practice to check the error code after each kernel launch. You can check **invalid kernel launch arguments** by calling `cudaGetLastError` **after the kernel launches**,...

Hi, this issue did happen again. 😂 Still the same issue which causes infinite recursion on the same lines. Opening a new issue.

nsight 虽然比较新，但是因为各个功能分布在不同的子命令里，似乎反而不是那么容易上手。例如要测各个 kernel 的执行时间要用一种子命令；要分析 GPU 上的硬件指标又要用另一种子命令，并且还要用另外的命令打开分析结果。如果有比较简洁的 nsight 教程，欢迎分享。@xxcclong 有何建议？

实验平台用的 GPU 是 P100，Compute Capability 是 6.0，可以用 nvprof。我个人觉得本课程的目标不是教如何使用具体的软件：如果 nsight 确实更好用，可以改教 nsight；但如果用 nsight 只是为了兼容特定硬件，就不太有必要了。如果你要用 T4 或者 A100 的话，可以参照 nsight 的文档使用，其中的原理是一样的，只是命令不一样。另外， A100 甚至没法在中国买到了。

I fixed an irrelevant bug in my code and this bug disappeared. But it would be still be better if you can test the code above more thoroughly. Thanks.

Another approach to solve the problem (without considering AD) is to add a new schedule `uncache` and run it automatically inside `as_matmul`. As the name suggests, `uncache` undoes the `cache`...

Sorry, I found it was my mistake. Although `_ZZ3runE13__sharedStack` is a local variable, but I mistakenly mark it as `static`, so it became a global variable. Closing this issue, and...

Sorry but after I changed it to `static`, the "failed to deduce type of memset" message still occurs. This time `_ZZ3runE13__sharedStack` is a genuine local variable. Besides, it is not...

You misspelled "console" into "conosle" in line 7 of the server code, which throws an exception and what follows doesn't run.

However, I haven't figured out why the exception doesn't prompt out in the console. Anything catches the exception?