Jonathan R. Madsen
Jonathan R. Madsen
Ah I wondered if that might be the case. Can you try running it interactively and when you think it has hung, hit control-C. I put a new feature in...
Hi @jhux2, thanks for providing the second log. Yeah, it looks like Dyninst is hanging in the exact same spot both times. Let me look into this and get back...
Hi @jhux2 if you install the (newly released) v1.7.1 and interrupt the job as before, there should be line info in the backtrace -- knowing the line number it is...
What version of omnitrace?
I've figure out the source of why it is taking so long to post-process the rocm-smi data. I'll include it in the next release.
Fixed by #164
This should have been fixed by the Dyninst updates in #164. I'm going to close this issue but if you get a chance to verify it, please let me know.
> The fences induced by beginParallelFor and endParallelFor have specific string labels attached, so we should be able to filter [i.e., automatically remove] these fences out inside the tool based...
Minor tweak that might have some appeal: Create a new set of "sparse" macros for these situations, e.g. `LIKWID_MARKER_SPARSE_START` and be able to set a default "sparseness" (e.g. `LIKWID_MARKER_SPARSE_DEFAULT("KERNEL", 10)`)....
So I found a _much_ cleaner solution that requires very minimal changes, adds support two new JSON output archive types (`MinimalJSONOutputArchive` and `PrettyJSONOutputArchive`) and then just aliases `JSONOutputArchive` to `PrettyJSONOutputArchive`...