Roman Kennke

Same numbers on a Graviton 3   | 1 | 2 | 3 | 4 -- | -- | -- | -- | -- testByteFalseBeginning | -17.72% | 11.98% | 14.92%...

I used this change to implement 19-bit-wide class-pointers in my 4-byte-header prototype. Those are the changes on top of this PR that were needed to make that happen: https://github.com/rkennke/lilliput/commit/2f2ffeadfb566b7ab0eea2aa065140011214b90d

Thank you, that's a great change. I actually intended to do something similar soon, because the existing Parallel Full GC would not be compatible with some stuff that I need...

Ok, I see. That sounds reasonable. Have you also run the micros` test/micro/org/openjdk/bench/vm/gc/systemgc/` on it?

Ok then. I tried to fit Lilliput's SlidingForwarding and works fine. I also tried to fit Lilliput2's Compact Identity Hashcode and this does not yet quite work. The problem is...

During forward_to_new_addr(), we give each worker a contiguous set of regions to work on. > Ok then. I tried to fit Lilliput's SlidingForwarding and works fine. I also tried to...

Can you check if this fixes https://bugs.openjdk.org/browse/JDK-8320165 ?