bench(core): Tier-1 criterion microbenchmarks for the punktfunk/1 hot path

GPU-free, so they run in normal CI. Two layers: crypto/{seal,seal_in_place,open} on one MTU shard,
and pipeline/{gf8,gf16}/{64KB,1MB} — a whole frame through the real per-frame path end to end over
the loopback transport (FEC encode → AES-GCM seal → packetize → reassemble → FEC decode → open).
Baselines on the dev box (RTX 5070 Ti VM): AES-GCM ~1.57 GiB/s/shard; gf16 ~418 MiB/s at 1 MB vs
gf8 ~23 MiB/s (the GF(2^8) O(n^2) ceiling the GF(2^16) Leopard wall-breaker removes — exactly the
kind of regression this should catch). The GPU capture/NVENC path is out of scope here (Tier 3).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Cargo.lock

@@ -46,6 +46,12 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "anes"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4b46cbb362ab8752921c97e041f5e366ee6297bd428a31275b9fcf1e380f7299"
+
 [[package]]
 name = "annotate-snippets"
 version = "0.11.5"
@@ -371,7 +377,7 @@ dependencies = [
  "bitflags",
  "cexpr",
  "clang-sys",
- "itertools",
+ "itertools 0.13.0",
  "proc-macro2",
  "quote",
  "regex",
@@ -454,6 +460,12 @@ dependencies = [
  "system-deps",
 ]
 
+[[package]]
+name = "cast"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5"
+
 [[package]]
 name = "cbc"
 version = "0.1.2"
@@ -531,6 +543,33 @@ version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
+[[package]]
+name = "ciborium"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "42e69ffd6f0917f5c029256a24d0161db17cea3997d185db0d35926308770f0e"
+dependencies = [
+ "ciborium-io",
+ "ciborium-ll",
+ "serde",
+]
+
+[[package]]
+name = "ciborium-io"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "05afea1e0a06c9be33d539b876f1ce3692f4afea2cb41f740e7743225ed1c757"
+
+[[package]]
+name = "ciborium-ll"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57663b653d948a338bfb3eeba9bb2fd5fcfaecb9e199e87e1eda4d9e8b240fd9"
+dependencies = [
+ "ciborium-io",
+ "half",
+]
+
 [[package]]
 name = "cipher"
 version = "0.4.4"
@@ -659,6 +698,40 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "criterion"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f2b12d017a929603d80db1831cd3a24082f8137ce19c69e6447f54f5fc8d692f"
+dependencies = [
+ "anes",
+ "cast",
+ "ciborium",
+ "clap",
+ "criterion-plot",
+ "is-terminal",
+ "itertools 0.10.5",
+ "num-traits",
+ "once_cell",
+ "oorandom",
+ "regex",
+ "serde",
+ "serde_derive",
+ "serde_json",
+ "tinytemplate",
+ "walkdir",
+]
+
+[[package]]
+name = "criterion-plot"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
+dependencies = [
+ "cast",
+ "itertools 0.10.5",
+]
+
 [[package]]
 name = "crossbeam-deque"
 version = "0.8.6"
@@ -684,6 +757,12 @@ version = "0.8.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
 
+[[package]]
+name = "crunchy"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "460fbee9c2c2f33933d720630a6a0bac33ba7053db5344fac858d4b8952d77d5"
+
 [[package]]
 name = "crypto-common"
 version = "0.1.7"
@@ -1434,6 +1513,17 @@ dependencies = [
  "tracing",
 ]
 
+[[package]]
+name = "half"
+version = "2.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ea2d84b969582b4b1864a92dc5d27cd2b77b622a8d79306834f1be5ba20d84b"
+dependencies = [
+ "cfg-if",
+ "crunchy",
+ "zerocopy",
+]
+
 [[package]]
 name = "hashbrown"
 version = "0.15.5"
@@ -1604,12 +1694,32 @@ dependencies = [
  "generic-array",
 ]
 
+[[package]]
+name = "is-terminal"
+version = "0.4.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3640c1c38b8e4e43584d8df18be5fc6b0aa314ce6ebf51b53313d4306cca8e46"
+dependencies = [
+ "hermit-abi",
+ "libc",
+ "windows-sys 0.61.2",
+]
+
 [[package]]
 name = "is_terminal_polyfill"
 version = "1.70.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a6cb138bb79a146c1bd460005623e142ef0181e3d0219cb493e02f7d08a35695"
 
+[[package]]
+name = "itertools"
+version = "0.10.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473"
+dependencies = [
+ "either",
+]
+
 [[package]]
 name = "itertools"
 version = "0.13.0"
@@ -2045,6 +2155,12 @@ version = "1.70.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
 
+[[package]]
+name = "oorandom"
+version = "11.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e"
+
 [[package]]
 name = "opaque-debug"
 version = "0.3.1"
@@ -2336,6 +2452,7 @@ dependencies = [
  "aes-gcm",
  "bytes",
  "cbindgen",
+ "criterion",
  "fec-rs",
  "hmac",
  "libc",
@@ -3293,6 +3410,16 @@ dependencies = [
  "time-core",
 ]
 
+[[package]]
+name = "tinytemplate"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be4d6b5f19ff7664e8c98d03e2139cb510db9b0a60b55f8e8709b689d939b6bc"
+dependencies = [
+ "serde",
+ "serde_json",
+]
+
 [[package]]
 name = "tinyvec"
 version = "1.11.0"

crates/punktfunk-core/Cargo.toml

@@ -56,6 +56,13 @@ libc = "0.2"
 
 [dev-dependencies]
 proptest = "1"
+# Tier-1 microbenchmarks (benches/pipeline.rs). default-features off → no plotters/HTML (headless
+# CI just needs the measurement + target/criterion/**/estimates.json for the regression compare).
+criterion = { version = "0.5", default-features = false, features = ["cargo_bench_support"] }
+
+[[bench]]
+name = "pipeline"
+harness = false
 
 [build-dependencies]
 cbindgen = "0.29"

crates/punktfunk-core/benches/pipeline.rs

@@ -0,0 +1,107 @@
+//! Tier-1 microbenchmarks for the punktfunk/1 hot path — GPU-free, so they run in normal CI.
+//!
+//! Two layers:
+//!  - `crypto/*`  — the isolated AES-128-GCM primitives on one ~MTU shard.
+//!  - `pipeline/*`— a whole frame through the real per-frame path end to end over the in-process
+//!    loopback transport: FEC encode → AES-GCM seal → packetize → (loopback) → reassemble →
+//!    FEC decode → open. This is what a throughput/latency regression in the core would show up in.
+//!
+//! The GPU capture/NVENC encode path is deliberately out of scope here (no GPU in CI) — that's the
+//! Tier-3 stream benchmark on a self-hosted GPU runner. Run locally with `cargo bench -p punktfunk-core`.
+
+use criterion::{black_box, criterion_group, criterion_main, BenchmarkId, Criterion, Throughput};
+use punktfunk_core::config::{Config, FecConfig, FecScheme, ProtocolPhase, Role};
+use punktfunk_core::crypto::SessionCrypto;
+use punktfunk_core::session::Session;
+use punktfunk_core::transport::loopback_pair;
+
+const TAG_LEN: usize = 16; // AES-GCM authentication tag
+const SHARD: usize = 1452; // ~one MTU-sized data shard
+
+fn cfg(role: Role, scheme: FecScheme) -> Config {
+    Config {
+        role,
+        phase: match scheme {
+            FecScheme::Gf8 => ProtocolPhase::P1GameStream,
+            FecScheme::Gf16 => ProtocolPhase::P2Punktfunk,
+        },
+        fec: FecConfig {
+            scheme,
+            fec_percent: 25,
+            // GF(2^8) is capped at ≤255 shards/block (Moonlight-compatible); GF(2^16) Leopard goes
+            // far higher. Use a realistic, valid block size for each.
+            max_data_per_block: match scheme {
+                FecScheme::Gf8 => 128,
+                FecScheme::Gf16 => 4096,
+            },
+        },
+        shard_payload: SHARD,
+        max_frame_bytes: 8 * 1024 * 1024,
+        encrypt: true, // bench the real path — crypto is always on for punktfunk/1
+        key: [7u8; 16],
+        salt: [1, 2, 3, 4],
+        loopback_drop_period: 0, // throughput run: no induced loss (loss-harness covers recovery)
+    }
+}
+
+fn bench_crypto(c: &mut Criterion) {
+    let host = SessionCrypto::new(&[7u8; 16], [1, 2, 3, 4], Role::Host);
+    let client = SessionCrypto::new(&[7u8; 16], [1, 2, 3, 4], Role::Client);
+    let payload = vec![0xABu8; SHARD];
+    let sealed = host.seal(0, &payload).unwrap();
+
+    let mut g = c.benchmark_group("crypto");
+    g.throughput(Throughput::Bytes(SHARD as u64));
+    g.bench_function("seal", |b| {
+        let mut seq = 0u64;
+        b.iter(|| {
+            let ct = host.seal(seq, black_box(&payload)).unwrap();
+            seq += 1;
+            black_box(ct)
+        })
+    });
+    g.bench_function("seal_in_place", |b| {
+        let mut seq = 0u64;
+        let mut buf = vec![0xABu8; SHARD + TAG_LEN];
+        b.iter(|| {
+            host.seal_in_place(seq, black_box(&mut buf)).unwrap();
+            seq += 1;
+        })
+    });
+    g.bench_function("open", |b| {
+        b.iter(|| black_box(client.open(0, black_box(&sealed)).unwrap()))
+    });
+    g.finish();
+}
+
+fn bench_pipeline(c: &mut Criterion) {
+    let mut g = c.benchmark_group("pipeline");
+    // 64 KB ≈ a steady-state P-frame; 1 MB ≈ a keyframe/scene-cut. Both FEC schemes (GF(2^8)
+    // GameStream-compat vs GF(2^16) Leopard, the wall-breaker).
+    for scheme in [FecScheme::Gf8, FecScheme::Gf16] {
+        let label = match scheme {
+            FecScheme::Gf8 => "gf8",
+            FecScheme::Gf16 => "gf16",
+        };
+        for &size in &[64 * 1024usize, 1024 * 1024] {
+            g.throughput(Throughput::Bytes(size as u64));
+            g.bench_with_input(BenchmarkId::new(label, size), &size, |b, &size| {
+                let (h, cl) = loopback_pair(0, 0);
+                let mut host = Session::new(cfg(Role::Host, scheme), Box::new(h)).unwrap();
+                let mut client = Session::new(cfg(Role::Client, scheme), Box::new(cl)).unwrap();
+                let frame = vec![0x5Au8; size];
+                let mut seq = 0u64;
+                b.iter(|| {
+                    host.submit_frame(black_box(&frame), seq, 0).unwrap();
+                    let f = client.poll_frame().unwrap();
+                    seq += 1;
+                    black_box(f)
+                })
+            });
+        }
+    }
+    g.finish();
+}
+
+criterion_group!(benches, bench_crypto, bench_pipeline);
+criterion_main!(benches);