Skip to content

Cache hash value for FrozenSets #5409

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.

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

Merged
merged 1 commit into from
Sep 23, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
10 changes: 1 addition & 9 deletions Lib/test/test_set.py
Original file line number Diff line number Diff line change
Expand Up @@ -728,15 +728,7 @@ def powerset(s):
for i in range(len(s)+1):
yield from map(frozenset, itertools.combinations(s, i))

# TODO: RUSTPYTHON
# The original test has:
# for n in range(18):
# Due to general performance overhead, hashing a frozenset takes
# about 50 times longer than in CPython. This test amplifies that
# exponentially, so the best we can do here reasonably is 13.
# Even if the internal hash function did nothing, it would still be
# about 40 times slower than CPython.
for n in range(13):
for n in range(18):
t = 2 ** n
mask = t - 1
for nums in (range, zf_range):
Expand Down
43 changes: 40 additions & 3 deletions vm/src/builtins/set.rs
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,10 @@ use crate::{
AsObject, Context, Py, PyObject, PyObjectRef, PyPayload, PyRef, PyResult, TryFromObject,
};
use once_cell::sync::Lazy;
use rustpython_common::{
atomic::{Ordering, PyAtomic, Radium},
hash,
};
use std::{fmt, ops::Deref};

pub type SetContentType = dictdatatype::Dict<()>;
Expand Down Expand Up @@ -71,9 +75,18 @@ impl PySet {
}

#[pyclass(module = false, name = "frozenset", unhashable = true)]
#[derive(Default)]
pub struct PyFrozenSet {
inner: PySetInner,
hash: PyAtomic<PyHash>,
}

impl Default for PyFrozenSet {
fn default() -> Self {
PyFrozenSet {
inner: PySetInner::default(),
hash: hash::SENTINEL.into(),
}
}
}

impl PyFrozenSet {
Expand All @@ -87,7 +100,10 @@ impl PyFrozenSet {
inner.add(elem, vm)?;
}
// FIXME: empty set check
Ok(Self { inner })
Ok(Self {
inner,
..Default::default()
})
}

pub fn elements(&self) -> Vec<PyObjectRef> {
Expand All @@ -102,6 +118,7 @@ impl PyFrozenSet {
) -> PyResult<Self> {
Ok(Self {
inner: self.inner.fold_op(others, op, vm)?,
..Default::default()
})
}

Expand All @@ -115,6 +132,7 @@ impl PyFrozenSet {
inner: self
.inner
.fold_op(std::iter::once(other.into_iterable(vm)?), op, vm)?,
..Default::default()
})
}
}
Expand Down Expand Up @@ -472,6 +490,7 @@ impl PySetInner {
op(
&PyFrozenSet {
inner: set.inner.copy(),
..Default::default()
}
.into_pyobject(vm),
vm,
Expand Down Expand Up @@ -956,6 +975,7 @@ impl PyFrozenSet {
} else {
Self {
inner: zelf.inner.copy(),
..Default::default()
}
.into_ref(&vm.ctx)
}
Expand Down Expand Up @@ -1057,6 +1077,7 @@ impl PyFrozenSet {
inner: other
.as_inner()
.difference(ArgIterable::try_from_object(vm, zelf.into())?, vm)?,
..Default::default()
}))
} else {
Ok(PyArithmeticValue::NotImplemented)
Expand Down Expand Up @@ -1107,7 +1128,23 @@ impl AsSequence for PyFrozenSet {
impl Hashable for PyFrozenSet {
#[inline]
fn hash(zelf: &crate::Py<Self>, vm: &VirtualMachine) -> PyResult<PyHash> {
zelf.inner.hash(vm)
let hash = match zelf.hash.load(Ordering::Relaxed) {
hash::SENTINEL => {
let hash = zelf.inner.hash(vm)?;
match Radium::compare_exchange(
&zelf.hash,
hash::SENTINEL,
hash::fix_sentinel(hash),
Ordering::Relaxed,
Ordering::Relaxed,
) {
Ok(_) => hash,
Err(prev_stored) => prev_stored,
}
}
hash => hash,
};
Ok(hash)
}
}

Expand Down
Loading