Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update hashbrown #445

Merged
merged 2 commits into from
Oct 24, 2024
Merged

Update hashbrown #445

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1796a74
Update hashbrown
thaliaarchi Oct 14, 2024
90e6e69
Replace ad hoc index set in TermDag with IndexSet
thaliaarchi Oct 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 16 additions & 21 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ bin = ["dep:clap", "dep:env_logger", "egraph-serialize/serde", "dep:serde_json"]
wasm-bindgen = ["instant/wasm-bindgen", "dep:getrandom"]

[dependencies]
hashbrown = { version = "0.14", features = ["raw"] }
hashbrown = { version = "0.15" }
indexmap = "2.0"
instant = "0.1"
log = "0.4"
Expand Down
48 changes: 22 additions & 26 deletions src/function/table.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ use std::{
ops::Range,
};

use hashbrown::raw::RawTable;
use hashbrown::HashTable;

use super::binary_search::binary_search_table_by_key;
use crate::{util::BuildHasher as BH, TupleOutput, Value, ValueVec};
Expand All @@ -51,11 +51,11 @@ struct TableOffset {
pub(crate) struct Table {
max_ts: u32,
n_stale: usize,
table: RawTable<TableOffset>,
table: HashTable<TableOffset>,
pub(crate) vals: Vec<(Input, TupleOutput)>,
}

/// Used for the RawTable probe sequence.
/// Used for the HashTable probe sequence.
macro_rules! search_for {
($slf:expr, $hash:expr, $inp:expr) => {
|to| {
Expand Down Expand Up @@ -97,19 +97,18 @@ impl Table {

/// Rehashes the table, invalidating any offsets stored into the table.
pub(crate) fn rehash(&mut self) {
let mut src = 0usize;
let mut dst = 0usize;
self.table.clear();
self.vals.retain(|(inp, _)| {
if inp.live() {
let hash = hash_values(inp.data());
let to = TableOffset { hash, off: dst };
self.table
.insert(hash, TableOffset { hash, off: dst }, |to| to.hash);
src += 1;
.entry(hash, |to2| to2 == &to, |to2| to2.hash)
.insert(to);
dst += 1;
true
} else {
src += 1;
false
}
});
Expand All @@ -120,16 +119,16 @@ impl Table {
/// table.
pub(crate) fn get(&self, inputs: &[Value]) -> Option<&TupleOutput> {
let hash = hash_values(inputs);
let TableOffset { off, .. } = self.table.get(hash, search_for!(self, hash, inputs))?;
debug_assert!(self.vals[*off].0.live());
Some(&self.vals[*off].1)
let &TableOffset { off, .. } = self.table.find(hash, search_for!(self, hash, inputs))?;
debug_assert!(self.vals[off].0.live());
Some(&self.vals[off].1)
}

pub(crate) fn get_mut(&mut self, inputs: &[Value]) -> Option<&mut TupleOutput> {
let hash: u64 = hash_values(inputs);
let TableOffset { off, .. } = self.table.get(hash, search_for!(self, hash, inputs))?;
debug_assert!(self.vals[*off].0.live());
Some(&mut self.vals[*off].1)
let &TableOffset { off, .. } = self.table.find(hash, search_for!(self, hash, inputs))?;
debug_assert!(self.vals[off].0.live());
Some(&mut self.vals[off].1)
}

/// Insert the given data into the table at the given timestamp. Return the
Expand Down Expand Up @@ -161,7 +160,7 @@ impl Table {
self.max_ts = ts;
let hash = hash_values(inputs);
if let Some(TableOffset { off, .. }) =
self.table.get_mut(hash, search_for!(self, hash, inputs))
self.table.find_mut(hash, search_for!(self, hash, inputs))
{
let (inp, prev) = &mut self.vals[*off];
let prev_subsumed = prev.subsumed;
Expand Down Expand Up @@ -193,14 +192,13 @@ impl Table {
subsumed,
},
));
self.table.insert(
let to = TableOffset {
hash,
TableOffset {
hash,
off: new_offset,
},
|off| off.hash,
);
off: new_offset,
};
self.table
.entry(hash, |to2| to2 == &to, |to2| to2.hash)
.insert(to);
}

/// One more than the maximum (potentially) valid offset into the table.
Expand Down Expand Up @@ -237,13 +235,11 @@ impl Table {
/// removed.
pub(crate) fn remove(&mut self, inp: &[Value], ts: u32) -> bool {
let hash = hash_values(inp);
let entry = if let Some(entry) = self.table.remove_entry(hash, search_for!(self, hash, inp))
{
entry
} else {
let Ok(entry) = self.table.find_entry(hash, search_for!(self, hash, inp)) else {
return false;
};
self.vals[entry.off].0.stale_at = ts;
let (TableOffset { off, .. }, _) = entry.remove();
self.vals[off].0.stale_at = ts;
self.n_stale += 1;
true
}
Expand Down
33 changes: 11 additions & 22 deletions src/termdag.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
use crate::{
ast::Literal,
util::{HashMap, HashSet},
util::{HashMap, HashSet, IndexSet},
Expr, GenericExpr, Symbol,
};

Expand All @@ -21,14 +21,8 @@ pub enum Term {
/// A hashconsing arena for [`Term`]s.
#[derive(Clone, PartialEq, Eq, Debug, Default)]
pub struct TermDag {
// think of nodes as a map from indices to Terms.
// invariant: the nodes map and the hashcons map are inverses.
// note that this implies:
// - no duplicates in nodes
// - every element of node is a key in hashcons
// - every key of hashcons is in nodes
pub nodes: Vec<Term>,
pub hashcons: HashMap<Term, TermId>,
/// A bidirectional map between deduplicated `Term`s and indices.
nodes: IndexSet<Term>,
Comment on lines +24 to +25
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could we change this to pub? I expose the TermDag fields in the Python bindings, because it's used when getting the extracted node(s).

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would it be better to create getters for what you need? Then it matters less what it's stored as. Since there were no other uses of the field, it looked safe to make private; a method would also make that more clear. pub is fine too, though 🤷‍♀️

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah, that sounds good to me.

Looking through the usages in Python, it seems like the only things I do with a termdag is call term_to_expr and then lookup a term based on its id (termdag.nodes[term_id])

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looking up a term by TermId is already exposed via TermDag::get. So it sounds like what you need is already public?

What about the conversion in convert_struct! in your earlier comment? Would you need a fn TermDag::iter(&self) -> impl Iterator<Item = &Term>?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Naw that's ok, I can just not expose the TermDag struct like that, and instead just expose a few methods on it.

}

#[macro_export]
Expand All @@ -54,14 +48,14 @@ impl TermDag {
///
/// Panics if the term does not already exist in this [TermDag].
pub fn lookup(&self, node: &Term) -> TermId {
*self.hashcons.get(node).unwrap()
self.nodes.get_index_of(node).unwrap()
}

/// Convert the given id to the corresponding term.
///
/// Panics if the id is not valid.
pub fn get(&self, id: TermId) -> Term {
self.nodes[id].clone()
pub fn get(&self, id: TermId) -> &Term {
self.nodes.get_index(id).unwrap()
}

/// Make and return a [`Term::App`] with the given head symbol and children,
Expand Down Expand Up @@ -97,10 +91,8 @@ impl TermDag {
}

fn add_node(&mut self, node: &Term) {
if self.hashcons.get(node).is_none() {
let idx = self.nodes.len();
self.nodes.push(node.clone());
self.hashcons.insert(node.clone(), idx);
if self.nodes.get(node).is_none() {
self.nodes.insert(node.clone());
}
}

Expand Down Expand Up @@ -138,10 +130,7 @@ impl TermDag {
Term::App(op, args) => {
let args: Vec<_> = args
.iter()
.map(|a| {
let term = self.get(*a);
self.term_to_expr(&term)
})
.map(|a| self.term_to_expr(self.get(*a)))
.collect();
Expr::call_no_span(*op, args)
}
Expand Down Expand Up @@ -215,7 +204,7 @@ mod tests {
// x, y, (g x y), and the root call to f
// so we can compute expected answer by hand:
assert_eq!(
td.nodes,
td.nodes.as_slice().iter().cloned().collect::<Vec<_>>(),
vec![
Term::Var("x".into()),
Term::Var("y".into()),
Expand All @@ -236,7 +225,7 @@ mod tests {
let (td, t) = parse_term(s);
match_term_app!(t; {
("f", [_, x, _, _]) =>
assert_eq!(td.term_to_expr(&td.get(*x)), ast::GenericExpr::Var(DUMMY_SPAN.clone(), Symbol::new("x"))),
assert_eq!(td.term_to_expr(td.get(*x)), ast::GenericExpr::Var(DUMMY_SPAN.clone(), Symbol::new("x"))),
(head, _) => panic!("unexpected head {}, in {}:{}:{}", head, file!(), line!(), column!())
})
}
Expand Down
Loading