Skip to content

CUDA: Fix source location on kernel entry and enable breakpoints to be set on kernels by mangled name #6841

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.

Sign up for GitHub

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

Merged
stuartarchibald merged 7 commits into from
Jun 23, 2021
Merged

CUDA: Fix source location on kernel entry and enable breakpoints to be set on kernels by mangled name #6841

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7d226f3
Separate DIBuilder API from Numba IR API
gmarkall Mar 18, 2021
7f77680
CUDA: Mark kernel wrapper with subprogram and source location
gmarkall Mar 18, 2021
1f9d320
Add test that kernel wrapper has debug info
gmarkall Mar 18, 2021
448b0d8
CUDA: Compile modules with debug one at a time with NVVM
gmarkall Mar 18, 2021
772ed7f
Merge remote-tracking branch 'numba/master' into grm-cuda-debug-impro…
gmarkall May 25, 2021
10d57b3
Merge remote-tracking branch 'numba/master' into grm-cuda-debug-impro…
gmarkall Jun 16, 2021
02fad5d
Changes in response to PR #6841 feedback
gmarkall Jun 21, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Merge remote-tracking branch 'numba/master' into grm-cuda-debug-impro… 
…vements
  • Loading branch information
@gmarkall
gmarkall committed May 25, 2021
commit 772ed7fc5e01904346941e466fcb92b323a7fe63
7 changes: 4 additions & 3 deletions numba/cuda/compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,15 +298,16 @@ def compile(self, args):

Returns the `CompileResult`.
"""
if args not in self._compileinfos:
if args not in self.overloads:
nvvm_options = {
'debug': self.debug,
'opt': 3 if self.opt else 0
}

cres = compile_cuda(self.py_func, None, args, debug=self.debug,
inline=self.inline, nvvm_options=nvvm_options)
first_definition = not self._compileinfos
self._compileinfos[args] = cres
first_definition = not self.overloads
self.overloads[args] = cres
libs = [cres.library]

if first_definition:
Expand Down
You are viewing a condensed version of this merge commit. You can view the full changes here.