perf: switch to ahash, indexmap-allocator-api

2026-06-10 16:15:04 -07:00 · 2026-05-25 01:50:22 +02:00
parent 8e979cfad1
commit 98fa3c33c2
8 changed files with 102 additions and 23 deletions
@@ -17,6 +17,19 @@ version = "2.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "320119579fcad9c21884f5c4861d16174d0e06250625266f50fe6898340abefa"

+[[package]]
+name = "ahash"
+version = "0.8.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
+dependencies = [
+ "cfg-if",
+ "getrandom 0.3.4",
+ "once_cell",
+ "version_check",
+ "zerocopy",
+]
+
 [[package]]
 name = "aho-corasick"
 version = "1.1.4"
@@ -420,6 +433,18 @@ version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "77ce24cb58228fbb8aa041425bb1050850ac19177686ea6e0f41a70416f56fdb"

+[[package]]
+name = "getrandom"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "899def5c37c4fd7b2664648c28120ecec138e4d395b459e5ca34f9cce2dd77fd"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi 5.3.0",
+ "wasip2",
+]
+
 [[package]]
 name = "getrandom"
 version = "0.4.2"
@@ -428,7 +453,7 @@ checksum = "0de51e6874e94e7bf76d726fc5d13ba782deca734ff60d5bb2fb2607c7406555"
 dependencies = [
 "cfg-if",
 "libc",
- "r-efi",
+ "r-efi 6.0.0",
 "rand_core",
 "wasip2",
 "wasip3",
@@ -452,6 +477,8 @@ version = "0.15.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9229cfe53dfd69f0609a49f65461bd93001ea1ef889cd5529dd176593f5338a1"
 dependencies = [
+ "allocator-api2 0.2.21",
+ "equivalent",
 "foldhash 0.1.5",
 ]

@@ -496,16 +523,27 @@ dependencies = [
 "serde_core",
 ]

+[[package]]
+name = "indexmap-allocator-api"
+version = "2.7.1"
+source = "git+https://github.com/Hans-Halverson/indexmap-allocator-api.git?rev=36852f985c01fb9f58f2d9e510655ca1dbb1f4d0#36852f985c01fb9f58f2d9e510655ca1dbb1f4d0"
+dependencies = [
+ "allocator-api2 0.2.21",
+ "equivalent",
+ "hashbrown 0.15.5",
+]
+
 [[package]]
 name = "interpreter"
 version = "0.1.0"
 dependencies = [
+ "ahash",
 "allocator-api2 0.4.0",
 "bumpalo",
 "color-eyre",
 "either",
 "hashbrown 0.17.1",
- "indexmap",
+ "indexmap-allocator-api",
 "memchr",
 "parser",
 "thiserror",
@@ -769,6 +807,7 @@ checksum = "d211803b9b6b570f68772237e415a029d5a50c65d382910b879fb19d3271f94d"
 name = "parser"
 version = "0.1.0"
 dependencies = [
+ "ahash",
 "allocator-api2 0.4.0",
 "ariadne",
 "bumpalo",
@@ -846,6 +885,12 @@ dependencies = [
 "proc-macro2",
 ]

+[[package]]
+name = "r-efi"
+version = "5.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69cdb34c158ceb288df11e18b4bd39de994f6657d83847bdffdbd7f346754b0f"
+
 [[package]]
 name = "r-efi"
 version = "6.0.0"
@@ -859,7 +904,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "d2e8e8bcc7961af1fdac401278c6a831614941f6164ee3bf4ce61b7edb162207"
 dependencies = [
 "chacha20",
- "getrandom",
+ "getrandom 0.4.2",
 "rand_core",
 ]

@@ -1036,7 +1081,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
 dependencies = [
 "fastrand",
- "getrandom",
+ "getrandom 0.4.2",
 "once_cell",
 "rustix",
 "windows-sys 0.61.2",
@@ -1324,6 +1369,12 @@ version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ba73ea9cf16a25df0c8caa16c51acb937d5712a8429db78a3ee29d5dcacd3a65"

+[[package]]
+name = "version_check"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+
 [[package]]
 name = "wasip2"
 version = "1.0.3+wasi-0.2.9"
@@ -1584,6 +1635,26 @@ version = "1.0.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cfe53a6657fd280eaa890a3bc59152892ffa3e30101319d168b781ed6529b049"

+[[package]]
+name = "zerocopy"
+version = "0.8.48"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eed437bf9d6692032087e337407a86f04cd8d6a16a37199ed57949d415bd68e9"
+dependencies = [
+ "zerocopy-derive",
+]
+
+[[package]]
+name = "zerocopy-derive"
+version = "0.8.48"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70e3cd084b1788766f53af483dd21f93881ff30d7320490ec3ef7526d203bad4"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
 [[package]]
 name = "zerofrom"
 version = "0.1.7"
@@ -30,9 +30,9 @@ smallvec = { version = "1.15.1", features = ["union", "const_generics", "const_n
 bumpalo = { version = "3.20.2", features = ["boxed", "collections", "std", "allocator-api2"] }
 hashbrown = "0.17.0"
 allocator-api2 = "0.4.0"
+ahash = "0.8.12"

 [dependencies]
-# lexer.workspace = true # FIXME(parser complete): bypass through parser
 interpreter.workspace = true
 parser.workspace = true
 color-eyre.workspace = true
@@ -14,7 +14,11 @@ parser.workspace = true
 bumpalo.workspace = true
 allocator-api2.workspace = true
 hashbrown.workspace = true
-indexmap = "2.14.0"
+ahash.workspace = true
+# I'm not particularly happy about this, but it's crucial for performance, and
+# I have audited the two commits. It's pinned to that hash to avoid possible
+# supply-chain attacks. Hopefully upstream maintainers will change their mind.
+indexmap-allocator-api = { git = 'https://github.com/Hans-Halverson/indexmap-allocator-api.git', rev = "36852f985c01fb9f58f2d9e510655ca1dbb1f4d0" }

 [lints]
 workspace = true
@@ -20,7 +20,7 @@ use crate::{
 pub struct Code<'arena> {
    pub arena: &'arena Bump,
    pub bc: Bytecode<'arena>,
-    pub consts: Consts,
+    pub consts: Consts<'arena>,
    pub symbols: SymbolTable<'arena>,
    free_regs: Vec<'arena, Reg>,
    pub reg_pointer: u16,
@@ -240,7 +240,7 @@ pub fn test_interpreter(stmnt: &Body<'_>) -> String {
    let mut c = Code {
        arena: &bump,
        bc: Bytecode::new_in(&bump),
-        consts: Consts::new(),
+        consts: Consts::new_in(&bump),
        symbols: SymbolTable::new_in(&bump),
        reg_pointer: 0,
        free_regs: Vec::new_in(&bump),
@@ -1,8 +1,9 @@
 use std::fmt::{self, Display};

+use ahash::RandomState;
 use bumpalo::{Bump, collections::Vec};
-use hashbrown::{DefaultHashBuilder, HashMap};
-use indexmap::{IndexMap, IndexSet};
+use hashbrown::HashMap;
+use indexmap_allocator_api::{IndexMap, IndexSet};
 use parser::Identifier;

 use crate::ir::{
@@ -28,7 +29,7 @@ pub struct Interpreter<'a> {
    program_counter: usize,
    registers: Registers<'a>,
    symbols: SymbolTable<'a>,
-    consts: Consts,
+    consts: Consts<'a>,
    compat: ExecMode,
 }

@@ -37,14 +38,14 @@ pub struct Registers<'a>(Vec<'a, Value>);

 #[derive(Debug)]
 pub struct SymbolTable<'a> {
-    user: IndexMap<Identifier<'a>, Value>,
+    user: IndexMap<Identifier<'a>, Value, RandomState, &'a Bump>,
    // separate table for cheap invalidation. It's an arena _visibly shrugs_.
-    records: HashMap<usize, Value, DefaultHashBuilder, &'a Bump>,
+    records: HashMap<usize, Value, RandomState, &'a Bump>,
    // etc
 }

 #[derive(Debug)]
-pub struct Consts(pub IndexSet<Value>);
+pub struct Consts<'a>(pub IndexSet<Value, RandomState, &'a Bump>);

 impl<'a> Interpreter<'a> {
    pub fn new(compat: ExecMode, code: Code<'a>) -> Self {
@@ -63,8 +64,8 @@ impl<'a> Interpreter<'a> {
 impl<'a> SymbolTable<'a> {
    pub fn new_in(arena: &'a Bump) -> Self {
        Self {
-            user: IndexMap::new(),
-            records: HashMap::new_in(arena),
+            user: IndexMap::new_in(arena),
+            records: HashMap::with_hasher_in(RandomState::new(), arena),
        }
    }
    fn lookup_user_var(&self, var: NonLocal) -> &Value {
@@ -88,9 +89,9 @@ impl<'a> SymbolTable<'a> {
    }
 }

-impl Consts {
-    pub fn new() -> Self {
-        Self(IndexSet::with_capacity(4))
+impl<'a> Consts<'a> {
+    pub fn new_in(arena: &'a Bump) -> Self {
+        Self(IndexSet::with_capacity_in(4, arena))
    }
 }

@@ -195,7 +196,7 @@ impl Display for SymbolTable<'_> {
    }
 }

-impl Display for Consts {
+impl Display for Consts<'_> {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        write!(f, "Consts:")?;
        fmt_list(f, self.0.iter(), |f, i, e| write!(f, "mem[{i}] = {e:?}"))
@@ -14,6 +14,7 @@ smallvec.workspace = true
 bumpalo.workspace = true
 hashbrown.workspace = true
 allocator-api2.workspace = true
+ahash.workspace = true
 ariadne = "0.6.0"

 [lints]
@@ -5,9 +5,10 @@

 use std::fmt::Debug;

+use ahash::RandomState;
 use bumpalo::{Bump, boxed::Box, collections::Vec};
 use either::Either;
-use hashbrown::{DefaultHashBuilder, HashMap};
+use hashbrown::HashMap;
 use lexer::{Slice, Span, Token};

 use crate::{ParsingError, Result, lex::TokenExt};
@@ -21,7 +22,7 @@ pub struct Ast<'a> {
    pub end_file: Vec<'a, Body<'a>>,
    pub rules: Vec<'a, Rule<'a>>,
    pub concurrent: Vec<'a, Rule<'a>>,
-    pub functions: HashMap<Identifier<'a>, Function<'a>, DefaultHashBuilder, &'a Bump>,
+    pub functions: HashMap<Identifier<'a>, Function<'a>, RandomState, &'a Bump>,
 }

 #[derive(Debug)]
@@ -16,6 +16,7 @@ mod tests;

 use std::{fmt::Debug, mem::replace};

+use ahash::RandomState;
 use bumpalo::{Bump, boxed::Box, collections::Vec, vec};
 use either::Either::{Left, Right};
 use hashbrown::HashMap;
@@ -685,7 +686,7 @@ impl<'a> Ast<'a> {
            end_file: Vec::new_in(arena),
            rules: Vec::new_in(arena),
            concurrent: Vec::new_in(arena),
-            functions: HashMap::new_in(arena),
+            functions: HashMap::with_hasher_in(RandomState::new(), arena),
        }
    }
 }