[wahern]

There's no other way to implementation a lock-less compacting (i.e. copying) collector than by using transactional memory algorithms. Period.

I've never used C4, and I don't even program in Java. But I have personally studied and implemented transactional memory algorithms, and C4 fits perfectly into that mold. In fact, what originally made me interested in transactional memory was figuring out how C4 worked.

And I did figure it out. I figured it out even before they published their 2011 paper, which I just discovered. And unsurprisingly everything in there is precisely as I predicted. It couldn't have been otherwise once you understand the fundamentals.

[giltene]

Um. There are 30 years worth of academic publications covering concurrent compacting collectors that don't need or use transactional memory, and are implementable on commodity hardware with no emulation or specialized instructions. C4 is just one of many examples of this fact. Sure, C4 does some cool new things, but trying to move or copy memory transactionally isn't one of them.

Whatever it is you think you figured out about how C4 works seems to be wrong. You may want to re-examine those fundamentals.

[mjpt777]

I asked the question if this is based on conjecture or experimental evidence. I'm happy to base my view on experimental evidence from my own research and testing.