You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
If we split data/bss into 4K chunks, then it will improve parallelization of scanning
and make it more incremental (something we need for concurrent GC with GOMAXPROCS=1).
I've done it once, but it was reverted during precision changes.
When we have 1-bit/word pointer info, it will be trivial to restore:
1. Calculate number of 4K chunks.
2. Adjust scanning parfor boundary accordingly.
3. If a thread's parfor iteration index is data/bss scanning, it finds the relevant
piece of data/bass and relevant piece of data/bss pointer info and scans only that piece.
The text was updated successfully, but these errors were encountered:
The text was updated successfully, but these errors were encountered: