et-backend: Q4_0 matrix-engine GEMM rewrite for prefill

Static-reuse dequant across N-tiles with K-splitting and a materialized
register-resident path for deep reuse, plus software-pipelined activation
prefetch and hart-sync fixes. Adds flush_to_l2_multi to work around the
16-line cap of a single FlushVA.

Author: RehanQasim-dev