-
-
Notifications
You must be signed in to change notification settings - Fork 80
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Support mangling and demangling independently of programs #679
Labels
Comments
eyalroz
added a commit
that referenced
this issue
Oct 19, 2024
eyalroz
added a commit
that referenced
this issue
Oct 19, 2024
eyalroz
added a commit
that referenced
this issue
Oct 19, 2024
eyalroz
added a commit
that referenced
this issue
Oct 20, 2024
eyalroz
added a commit
that referenced
this issue
Oct 26, 2024
eyalroz
added a commit
that referenced
this issue
Oct 26, 2024
eyalroz
added a commit
that referenced
this issue
Oct 28, 2024
eyalroz
added a commit
that referenced
this issue
Nov 17, 2024
* Added demangling support using NVIDIA's (nearly-hidden) libcufilt * Updated the `execution_control` example to not fail needlessly when getting the full signature as the demangled name * Clarified kernel-name-mismatch error messages in `execution_control` * Caveat: Can't locate `nv_decode.h` on Windows - is that even installed?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
CUDA NVRTC programs have the API function:
which mangle a function's name (or its signature). Unfortunately:
We should try and offer a program-independent mangling and de-mangling functionality which covers everything CUDA does with mangled names (which is probably not just plain vanilla Itanium ABI).
The text was updated successfully, but these errors were encountered: