wasm: cap the stack at 256KB - 16.25MB -> 0.5MB per Game Boy

zig defaults the wasm stack to 16MB, and that lands in the module's *initial*
memory, so every instance allocated 16.25MB before executing an instruction.
With several Game Boys on one page that was the dominant cost: 123MB for six.
The machine is a static and nothing here recurses deeply, so 256KB is plenty.

Per instance: 20.5MB -> 4.8MB of linear memory (six: 123MB -> 29MB). Note the
spelling - zig cc rejects -Wl,--stack-size and -zstack-size, and wants
-Wl,-z,stack-size=N.

With memory no longer the constraint, the page cap goes 6 -> 8 on measurement
rather than guesswork. Emulation-only, one thread: 12.5x realtime at 1, 3.1x
at 4, 1.5x at 8, and exactly 1.0x at 12 - i.e. ~12 is where a thread runs out
of road with nothing left for rendering. 8 holds a verified 60fps each in a
real browser with all eight leased.

Golden frames are still pixel-exact on cgb-acid2, dmg-acid2, cpu_instrs@600
and pky@400 with its .sav, and two Game Boys still lease and ping 4/4.

2 files changed, 3 insertions, 1 deletions

diff --git a/web/gbcore.js b/web/gbcore.js
index 637b939..8cecb82 100644
--- a/web/gbcore.js
+++ b/web/gbcore.js
@@ -110,6 +110,8 @@ export class GameBoy {
     this.#ex.gbw_serial_push(bytes.length);
   }
   get serialDropped() { return this.#ex.gbw_serial_dropped(); }
+  // This machine's share of wasm linear memory - what N Game Boys really cost.
+  get memBytes() { return this.#ex.memory.buffer.byteLength; }
 
   // ---- battery RAM ----
   sram() {
diff --git a/web/index.html b/web/index.html
index d182b57..1d28c89 100644
--- a/web/index.html
+++ b/web/index.html
@@ -96,7 +96,7 @@ import { GameBoy, BTN } from "./gbcore.js";
 import { Hub, ipStr, GW } from "./gbhub.js";
 
 const $ = (id) => document.getElementById(id);
-const MAX_GB = 6;          // one thread runs ~12 at full speed; leave headroom
+const MAX_GB = 8;          // CPU-bound: ~12 fit in one thread with zero headroom
 const ROM_URL = "roms/gbos.gb";
 
 const logEl = $("log");