[magicalhippo]

Not OP but was curious about the "+64k" thing and found this[1] article claiming around 15% increase across several different workloads using GH200.

FWIW for those unaware like me, 64k refers to 64kB pages, in contrast to the typical 4kB.

[1]: https://www.phoronix.com/review/aarch64-64k-kernel-perf