Parallel Argon2id lanes (unlock 180 ms -> 129 ms, Go 122 ms); AEAD throughput probe

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

Cargo.lock

@@ -39,6 +39,7 @@ dependencies = [
  "blake2",
  "cpufeatures",
  "password-hash",
+ "rayon",
  "zeroize",
 ]
 
@@ -211,6 +212,31 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "crossbeam-deque"
+version = "0.8.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "622f3fc73690be383c7214310406f28a90e6edeadc3cea882f9d71e495b9711a"
+dependencies = [
+ "crossbeam-epoch",
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-epoch"
+version = "0.9.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc74980687109a3b14c72fd458107bf0baa1da1a1a805e178d15501ba9b86d9d"
+dependencies = [
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-utils"
+version = "0.8.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a31eee39dddec8330830986fcd7625edb5a24ec90ea038215273bbc3adb08ac6"
+
 [[package]]
 name = "crypto-common"
 version = "0.2.2"
@@ -283,6 +309,12 @@ dependencies = [
  "zeroize",
 ]
 
+[[package]]
+name = "either"
+version = "1.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0e9c71c2167ca323c882b99918929403426e2373ea17242ff5653e0d5e1058be"
+
 [[package]]
 name = "errno"
 version = "0.3.14"
@@ -697,6 +729,26 @@ version = "0.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "63b8176103e19a2643978565ca18b50549f6101881c443590420e4dc998a3c69"
 
+[[package]]
+name = "rayon"
+version = "1.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fb39b166781f92d482534ef4b4b1b2568f42613b53e5b6c160e24cfbfa30926d"
+dependencies = [
+ "either",
+ "rayon-core",
+]
+
+[[package]]
+name = "rayon-core"
+version = "1.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22e18b0f0062d30d4230b2e85ff77fdfe4326feb054b9783a3460d8435c8ab91"
+dependencies = [
+ "crossbeam-deque",
+ "crossbeam-utils",
+]
+
 [[package]]
 name = "ring"
 version = "0.17.14"

Cargo.toml

@@ -10,7 +10,7 @@ repository = "https://github.com/andydixon/vault"
 publish = false
 
 [dependencies]
-argon2 = { version = "0.6", default-features = false, features = ["alloc", "zeroize"] }
+argon2 = { version = "0.6", default-features = false, features = ["alloc", "zeroize", "parallel"] }
 chacha20poly1305 = { version = "0.11", default-features = false, features = ["alloc", "zeroize"] }
 hkdf = "0.13"
 hmac = { version = "0.13", features = ["zeroize"] }
@@ -44,3 +44,7 @@ strip = true
 [[bench]]
 name = "micro"
 harness = false
+
+[[bench]]
+name = "aead_probe"
+harness = false

benches/aead_probe.rs

@@ -0,0 +1,25 @@
+use chacha20poly1305::aead::{AeadInOut, KeyInit};
+use chacha20poly1305::{ChaCha20Poly1305, Key, Nonce};
+use std::time::Instant;
+fn main() {
+    let c = ChaCha20Poly1305::new(&Key::from([1u8; 32]));
+    let mut buf = vec![0u8; 64 * 1024];
+    let n = 1024; // 64 MiB
+    let t = Instant::now();
+    for i in 0..n {
+        let mut nb = [0u8; 12];
+        nb[3..11].copy_from_slice(&(i as u64).to_be_bytes());
+        std::hint::black_box(c.encrypt_inout_detached(&Nonce::from(nb), &[], buf.as_mut_slice().into()).unwrap());
+    }
+    let s = t.elapsed().as_secs_f64();
+    println!("raw seal: {:.0} MB/s", (n * 65536) as f64 / s / 1e6);
+    let key = [1u8; 32];
+    let data = vec![0u8; 64 << 20];
+    let t = Instant::now();
+    let mut out = Vec::with_capacity(data.len() + (1 << 20));
+    vault::crypto::stream::seal_all(&key, &data, &mut out);
+    println!("seal_all: {:.0} MB/s", data.len() as f64 / t.elapsed().as_secs_f64() / 1e6);
+    let t = Instant::now();
+    let n = vault::crypto::stream::open_all(&key, &mut out).unwrap();
+    println!("open_all: {:.0} MB/s ({n})", data.len() as f64 / t.elapsed().as_secs_f64() / 1e6);
+}