Skip to content

use memory prefetch in hash map building #571

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

Merged
lihao712 merged 1 commit into from
Sep 14, 2024
Merged

use memory prefetch in hash map building #571

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
30 changes: 22 additions & 8 deletions native-engine/datafusion-ext-plans/src/joins/join_hash_map.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,7 @@ impl Table {
let mut num_valid_items = 0;

// collect map items
let mut map_items = vec![];
let mut map_items = unchecked!(vec![]);
for (hash, chunk) in hashes
.into_iter()
.enumerate()
Expand Down Expand Up @@ -149,18 +149,32 @@ impl Table {
let mut map = unchecked!(Vec::with_capacity((1usize << map_mod_bits) + 16));
map.resize(1 << map_mod_bits, MapValueGroup::default());

for (hash, item) in map_items {
let mut i = (hash % (1 << map_mod_bits)) as usize;
macro_rules! entries {
[$i:expr] => (map_items[$i].0 % (1 << map_mod_bits))
}

const PREFETCH_AHEAD: usize = 4;
if map_items.len() >= PREFETCH_AHEAD {
for i in 1..PREFETCH_AHEAD - 1 {
prefetch_read_data!(&map[entries![i] as usize]);
}
}
for i in 0..map_items.len() {
if i + PREFETCH_AHEAD < map_items.len() {
prefetch_read_data!(&map[entries![i + PREFETCH_AHEAD] as usize]);
}

let mut e = entries![i] as usize;
loop {
let empty = map[i].hashes.simd_eq(Simd::splat(0));
let empty = map[e].hashes.simd_eq(Simd::splat(0));
if let Some(j) = empty.first_set() {
map[i].hashes.as_mut_array()[j] = hash;
map[i].values[j] = item;
map[e].hashes.as_mut_array()[j] = map_items[i].0;
map[e].values[j] = map_items[i].1;
break;
}

i += 1;
if i == map.len() {
e += 1;
if e == map.len() {
map.push(MapValueGroup::default());
}
}
Expand Down