Add MLX backend for Apple Silicon

[ChinChangYang]

This PR adds a new neural-net backend (USE_BACKEND=MLX) targeting Apple
Silicon via Apple's MLX framework.
It implements the full nninterface.h contract (model load, batched
evaluation, FP16/FP32 paths) and ships with a Winograd 3x3 convolution
path plus an adaptive per-shape tuner that picks the fastest
implementation for each conv-3x3 shape at model load.

What's new

Backend (cpp/neuralnet/)

• mlxbackend.cpp — backend implementation. Supports variable board
  sizes via input masking (same nnXLen / nnYLen contract as other
  backends; the global COMPILE_MAX_BOARD_LEN bound still applies),
  FP16/FP32 selected by mlxUseFP16 (default auto → fp16), and the
  same input feature layout as the other backends. Mish runs FP16-safe;
  the code asserts on ACTIVATION_MISH_SCALE8 so out-of-range variants
  fail loudly rather than truncate silently.
• mlxwinograd.h — F(4×4, 3×3) Winograd transform with fused
  activation + residual add.
• mlxwinotuner.{cpp,h} — per-shape Winograd tuner with adaptive
  scoring (rotates the candidate set per shape, scores by median-time
  delta against a baked-default baseline). Logs the conv-3x3 shape
  distribution at model load.
• mlxtests.cpp — Winograd + tuner numeric-consistency tests,
  gated under runnnlayertests.

Build / wiring

• cpp/CMakeLists.txt — USE_BACKEND=MLX target. MLX needs CMake
  3.27; cmake_minimum_required stays at 3.18.2 so other backends
  keep building on older CMake. Links Homebrew's prebuilt
  libmlx.dylib; OSX deployment target is intentionally not pinned
  so the executable's minos matches the linked dylib.
• cpp/main.cpp, cpp/program/setup.cpp, cpp/command/benchmark.cpp
  — wire MLX into backend selection / benchmark.
• cpp/configs/{gtp,analysis,match,contribute}_example.cfg —
  document mlxUseFP16 (auto / true / false, default
  auto → fp16).
• Compiling.md — build instructions.

How to build

cd cpp
cmake -G Ninja -DUSE_BACKEND=MLX
ninja

Requires CMake ≥ 3.27 and brew install mlx.

Validation

Cross-backend validation against an Eigen reference (testgpuerror)
on b18c384nbt, b40v8, and humanv0 nets:

• FP32: max winrate error 0.00095%
• FP16: max winrate error 2.63%

Both well within the existing tolerances used by other backends.

Status

Draft — opening for early feedback on the backend's structure and
the tuner approach before promoting to ready-for-review.