[X86] AMD Zen 3 sched model: FMA ops have inverse throughput of 0.5

Now that exegesis produces meaningful snippets to measure throughtput
for instructions with tied operands:
https://github.com/llvm/llvm-project/commit/2ffe225d113031cc211d20d8d2cb82eeaa1a34a2
the measurements clearly show these instructions to have
more optimistic throughtput.

There's still some noise in the reports, especially around instructions
with memory operands. I'm not sure if we measure those correctly.

Fixes https://github.com/llvm/llvm-project/issues/59325