That seems to be the case, I do wish they'd made this requirement clear up front. There is no getting around sychronised quiescence being a blocking event, but in this case they essentially hope that either 1) you're already using a kind of scatter gather thread model like the mentioned game example - which implies an iterative discrete world, or 2) the set of threads (or tasks) interacting with the collection is simply bounded and sychronised, and/or 3) the performance is still better in aggregate even with infrequent world blocking events.
I used to work in the same industry. We used linux and gcc, so we could, and did, produce fully deterministic builds. Actually the output was fully deterministic disk images.
I did one iteration of the build system, mostly making it such that any host could build it deterministically. This was years ago so it was just chroot that started with a skeleton + GCC and procedurally built the things it needed to build the outputs. Was fairly straight forward, just an extremely short patch here and there, a 1000 line Xorg Makefile for staging Xorg builds. If I was doing it again I'd consider reusing a package manager, but each components Makefile was pretty concise. My trusty sidekick was a script that xxd'd two files into pipes that it opened using vimdiff.
In those results simdjson is roughly 60% faster.
Telling simdjson we have aligned input gives us further improvement:
About 90% faster. Example changes: