prefetch in do_move()

[ces42]

this allows removing Position::key_after()

STC
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 24960 W: 6556 L: 6336 D: 12068
Ptnml(0-2): 59, 2554, 7056, 2730, 81

LTC
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 115080 W: 29319 L: 29204 D: 56557
Ptnml(0-2): 51, 10736, 35864, 10825, 64

STC with 2MB hash
LLR: 3.04 (-2.94,2.94) <-1.75,0.25>
Total: 182176 W: 46998 L: 46932 D: 88246
Ptnml(0-2): 526, 19711, 50544, 19785, 522

LTC with 8MB hash
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 441180 W: 111557 L: 111746 D: 217877
Ptnml(0-2): 229, 39698, 140929, 39501, 233

all of the tests were against c76c179

bench: 1379150

[github-actions]

clang-format 18 needs to be run on this PR.
If you do not have clang-format installed, the maintainer will run it when merging.
For the exact version please see https://packages.ubuntu.com/noble/clang-format-18.

(execution 12737663706 / attempt 1)

[mstembera]

I wonder if this is more consequential in cases where we are memory bound. i.e., on big NUMA hardware for which we had to write patches like this #5515

[vondele]

I doubt TT access is still significant compared to the memory pressure related to NNUE, so I can see this is no longer needed

[mstembera]

I think the memory pressure from NNUE can affect it but TT accesses are more about latency while NNUE is more about bandwidth/throughput.