Introduce EntitySet, and use it to replace the HashSet in the frontend.

lib/cretonne/src/entity/mod.rs

@@ -4,8 +4,8 @@
 //! `usize` as usual, but by *entity references* which are integers wrapped in new-types. This has
 //! a couple advantages:
 //!
-//! - Improved type safety. The various map types accept a specific key type, so there is no
+//! - Improved type safety. The various map and set types accept a specific key type, so there is
-//!   confusion about the meaning of an array index, as there is with plain arrays.
+//!   no confusion about the meaning of an array index, as there is with plain arrays.
 //! - Smaller indexes. The normal `usize` index is often 64 bits which is way too large for most
 //!   purposes. The entity reference types can be smaller, allowing for more compact data
 //!   structures.
@@ -22,6 +22,9 @@
 //!   number of entities. It tracks accurately which entities have been inserted. This is a
 //!   specialized data structure which can use a lot of memory, so read the documentation before
 //!   using it.
+//! - [`EntitySet`](struct.EntitySet.html) is used to represent a secondary set of entities.
+//!   The set is implemented as a simple vector, so it does not keep track of which entities have
+//!   been inserted into the primary map. Instead, any unknown entities are not in the set.
 //! - [`EntityList`](struct.EntityList.html) is a compact representation of lists of entity
 //!   references allocated from an associated memory pool. It has a much smaller footprint than
 //!   `Vec`.
@@ -31,11 +34,13 @@ mod list;
 mod map;
 mod primary;
 mod sparse;
+mod set;
 
 pub use self::keys::Keys;
 pub use self::list::{EntityList, ListPool};
 pub use self::map::EntityMap;
 pub use self::primary::PrimaryMap;
+pub use self::set::EntitySet;
 pub use self::sparse::{SparseSet, SparseMap, SparseMapValue};
 
 /// A type wrapping a small integer index should implement `EntityRef` so it can be used as the key

lib/cretonne/src/entity/set.rs

@@ -0,0 +1,144 @@
+//! Densely numbered entity references as set keys.
+
+use entity::{EntityRef, Keys};
+use std::marker::PhantomData;
+
+/// A set of `K` for densely indexed entity references.
+///
+/// The `EntitySet` data structure uses the dense index space to implement a set with a bitvector.
+/// Like `EntityMap`, an `EntitySet` is used to associate secondary information with entities.
+#[derive(Debug, Clone)]
+pub struct EntitySet<K>
+where
+    K: EntityRef,
+{
+    elems: Vec<u8>,
+    len: usize,
+    unused: PhantomData<K>,
+}
+
+/// Shared `EntitySet` implementation for all value types.
+impl<K> EntitySet<K>
+where
+    K: EntityRef,
+{
+    /// Create a new empty set.
+    pub fn new() -> Self {
+        EntitySet {
+            elems: Vec::new(),
+            len: 0,
+            unused: PhantomData,
+        }
+    }
+
+    /// Get the element at `k` if it exists.
+    pub fn contains(&self, k: K) -> bool {
+        let index = k.index();
+        debug_assert!(index < self.len);
+        (self.elems[index / 8] & (1 << (index % 8))) != 0
+    }
+
+    /// Is this set completely empty?
+    pub fn is_empty(&self) -> bool {
+        self.len == 0
+    }
+
+    /// Remove all entries from this set.
+    pub fn clear(&mut self) {
+        self.len = 0;
+        self.elems.clear()
+    }
+
+    /// Iterate over all the keys in this set.
+    pub fn keys(&self) -> Keys<K> {
+        Keys::new(self.len)
+    }
+
+    /// Resize the set to have `n` entries by adding default entries as needed.
+    pub fn resize(&mut self, n: usize) {
+        if n < self.len {
+            self.elems.truncate((n + 7) / 8)
+        } else {
+            // TODO: Is there a better way to grow/resize/etc.?
+            let additional = (n - self.len + 7) / 8;
+            self.elems.reserve(additional);
+            for _ in 0..additional {
+                self.elems.push(0)
+            }
+        }
+        self.len = n
+    }
+
+    /// Insert the element at `k`.
+    pub fn insert(&mut self, k: K) -> bool {
+        let index = k.index();
+        if index >= self.len {
+            self.resize(index + 1)
+        }
+        let result = !self.contains(k);
+        self.elems[index / 8] |= 1 << (index % 8);
+        result
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    // `EntityRef` impl for testing.
+    #[derive(Clone, Copy, Debug, PartialEq, Eq)]
+    struct E(u32);
+
+    impl EntityRef for E {
+        fn new(i: usize) -> Self {
+            E(i as u32)
+        }
+        fn index(self) -> usize {
+            self.0 as usize
+        }
+    }
+
+    #[test]
+    fn basic() {
+        let r0 = E(0);
+        let r1 = E(1);
+        let r2 = E(2);
+        let mut m = EntitySet::new();
+
+        let v: Vec<E> = m.keys().collect();
+        assert_eq!(v, []);
+        assert!(m.is_empty());
+
+        m.insert(r2);
+        m.insert(r1);
+
+        assert!(!m.contains(r0));
+        assert!(m.contains(r1));
+        assert!(m.contains(r2));
+        assert!(!m.is_empty());
+
+        let v: Vec<E> = m.keys().collect();
+        assert_eq!(v, [r0, r1, r2]);
+
+        m.resize(20);
+        assert!(!m.contains(E(3)));
+        assert!(!m.contains(E(4)));
+        assert!(!m.contains(E(8)));
+        assert!(!m.contains(E(15)));
+        assert!(!m.contains(E(19)));
+
+        m.insert(E(8));
+        m.insert(E(15));
+        assert!(!m.contains(E(3)));
+        assert!(!m.contains(E(4)));
+        assert!(m.contains(E(8)));
+        assert!(!m.contains(E(9)));
+        assert!(!m.contains(E(14)));
+        assert!(m.contains(E(15)));
+        assert!(!m.contains(E(16)));
+        assert!(!m.contains(E(19)));
+
+        m.clear();
+        assert!(m.is_empty());
+    }
+}

lib/frontend/src/frontend.rs

@@ -6,8 +6,7 @@ use cretonne::ir::instructions::BranchInfo;
 use cretonne::ir::function::DisplayFunction;
 use cretonne::isa::TargetIsa;
 use ssa::{SSABuilder, SideEffects, Block};
-use cretonne::entity::{EntityRef, EntityMap};
+use cretonne::entity::{EntityRef, EntityMap, EntitySet};
-use std::collections::HashSet;
 use std::hash::Hash;
 
 /// Permanent structure used for translating into Cretonne IL.
@@ -151,8 +150,8 @@ impl<'short, 'long, Variable> InstBuilderBase<'short> for FuncInstBuilder<'short
                     if let InstructionData::BranchTable { table, .. } = data {
 // Unlike all other jumps/branches, jump tables are
 // capable of having the same successor appear
-// multiple times. Use a HashSet to deduplicate.
+// multiple times, so we must deduplicate.
-                        let mut unique = HashSet::new();
+                        let mut unique = EntitySet::<Ebb>::new();
                         for dest_ebb in self.builder
                                     .func
                                     .jump_tables