paper(gqa): derive (m,l,O) AR per-PE cost from kernel topology

Replaces the unsourced 32 KB/layer placeholder in the analytical chart
with T*(N-1)/N where T = h_q * S_q * (d_head*2 + 8) ~ 2.1 KB
(per-PE (m, l, O) payload) and N is the participant count of the
reduce-only chain per stage. Cases 2/3/6 analytical bars now match
the simulator-measured numbers within ~10% (was 6-30x over).

Also:
- Bumps the measurement S_kv from 8 K to 64 K to verify Cases 1, 2, 3, 6
  are genuinely S_kv-independent and Cases 4, 5 scale linearly.
- In-bar descriptor on the paired chart is now wrapped to fit the bar
  width, black, no background box, and centered between the analytical
  and measured bars so the label applies to both.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

scripts/paper/measure_gqa_decode_placement_comm.py

@@ -51,7 +51,7 @@ from kernbench.topology.builder import resolve_topology
 _C = 8
 _P = 8
 _N_LAYERS = 80
-_S_KV_MEAS = 8 * 1024        # per-run simulator S_kv (small — 1/128th of headline)
+_S_KV_MEAS = 64 * 1024       # per-run simulator S_kv (1/16th of headline)
 _S_KV_HEADLINE = 1 << 20     # 1 Mi tokens, the chart's headline S_kv
 
 # Per-cube S_kv share for the d_head-TP partial-score AR cost.