perf: add ghostty-bench and bring terminal throughput to Zig parity

Adds crates/ghostty-bench, a port of ZIG/src/benchmark and src/synthetic:
the ghostty-bench binary (terminal-stream, terminal-parser,
codepoint-width, grapheme-break, is-symbol, osc-parser, screen-clone
with Zig's CLI) and ghostty-synthetic data generators (+ascii, +utf8,
+osc, plus a Rust-only +sgr mode).

Measured against Ghostty's own ghostty-bench built with Zig 0.15.2
(ReleaseFast) vs --profile production, the hot paths were optimized
without behaviour changes:
- Terminal::print single-lookup fast path for width-1 chars mid-line
- page grapheme allocator: bitmap first-fit instead of a linear scan
  (was 38% of utf8 stream time; randomized equivalence test added)
- plain cells skip per-cell work in clear_cells and row cloning
- ASCII fast path + strict hand-written UTF-8 decoder (exhaustive
  equivalence test against std)
- parser/OSC parser split into inlined fast and state-change paths
- RenderState allocates grapheme vectors only for grapheme rows
- Page::assert_integrity no-op stub so the production profile builds

terminal-stream is now at parity (ascii 1.08x, utf8 0.97x, SGR 1.04x of
Zig's time). Still slower: screen-clone (~2.6x, zero-filling fresh
cell Vecs vs Zig's lazily-zeroed mmap), osc-parser (1.9x), and the raw
parser on SGR data (1.5x). Full table in docs/rewrite/notes/perf-P1.md.

Test Plan:
- cargo test --workspace (no failures)
- cargo run --profile production -p ghostty-bench -- +terminal-stream
  --data=<file> and compare with Zig's ghostty-bench

crates/ghostty-bench/src/bin/ghostty-synthetic.rs

@@ -0,0 +1,64 @@
+//! `ghostty-synthetic +<ascii|utf8|osc> [--option=value ...]`: endless
+//! synthetic data on stdout (port of `synthetic/main.zig`).
+use ghostty_bench::{
+    args::Args,
+    synthetic::{OscStyle, Rng, run_ascii, run_osc, run_sgr, run_utf8},
+};
+use std::io::{BufWriter, Write};
+use std::process::ExitCode;
+
+fn run() -> Result<(), String> {
+    let argv: Vec<String> = std::env::args().skip(1).collect();
+    let mut action = None;
+    for a in &argv {
+        if let Some(name) = a.strip_prefix('+') {
+            if action.is_some() {
+                return Err("multiple actions specified".into());
+            }
+            action = Some(name.to_owned());
+        }
+    }
+    let action = action.ok_or("no action specified; available: ascii, osc, sgr, utf8")?;
+    let mut args = Args::parse(argv)?;
+    let mut rng = Rng::from_time();
+    let mut out = BufWriter::with_capacity(2048, std::io::stdout().lock());
+    let res = match action.as_str() {
+        "ascii" => {
+            args.finish()?;
+            run_ascii(&mut out, &mut rng)
+        }
+        "utf8" => {
+            args.finish()?;
+            run_utf8(&mut out, &mut rng)
+        }
+        "sgr" => {
+            args.finish()?;
+            run_sgr(&mut out, &mut rng)
+        }
+        "osc" => {
+            let p_valid = args.take("p-valid", 0.5f64)?;
+            let style = match args.take_opt_string("style")?.as_deref() {
+                None | Some("streaming") => OscStyle::Streaming,
+                Some("parser") => OscStyle::Parser,
+                Some(s) => return Err(format!("invalid value for --style: {s}")),
+            };
+            args.finish()?;
+            run_osc(&mut out, &mut rng, p_valid, style)
+        }
+        a => return Err(format!("invalid action: +{a}")),
+    };
+    res.map_err(|e| e.to_string())?;
+    // Broken pipe on flush is a normal end.
+    let _ = out.flush();
+    Ok(())
+}
+
+fn main() -> ExitCode {
+    match run() {
+        Ok(()) => ExitCode::SUCCESS,
+        Err(e) => {
+            eprintln!("error: {e}");
+            ExitCode::FAILURE
+        }
+    }
+}