Merge pull request #568 from clarfonthey/control-module-p1

Further sequester `Group`/`Tag` code

src/raw/bitmask.rs → src/control/bitmask.rs

@@ -1,4 +1,4 @@
-use super::imp::{
+use super::group::{
     BitMaskWord, NonZeroBitMaskWord, BITMASK_ITER_MASK, BITMASK_MASK, BITMASK_STRIDE,
 };
 
@@ -102,7 +102,7 @@ impl IntoIterator for BitMask {
 
 /// Iterator over the contents of a `BitMask`, returning the indices of set
 /// bits.
-#[derive(Copy, Clone)]
+#[derive(Clone)]
 pub(crate) struct BitMaskIter(pub(crate) BitMask);
 
 impl Iterator for BitMaskIter {

src/raw/generic.rs → src/control/group/generic.rs

@@ -1,5 +1,4 @@
-use super::bitmask::BitMask;
-use super::Tag;
+use super::super::{BitMask, Tag};
 use core::{mem, ptr};
 
 // Use the native word size as the group size. Using a 64-bit group size on
@@ -81,8 +80,7 @@ impl Group {
     #[inline]
     #[allow(clippy::cast_ptr_alignment)]
     pub(crate) unsafe fn load_aligned(ptr: *const Tag) -> Self {
-        // FIXME: use align_offset once it stabilizes
-        debug_assert_eq!(ptr as usize & (mem::align_of::<Self>() - 1), 0);
+        debug_assert_eq!(ptr.align_offset(mem::align_of::<Self>()), 0);
         Group(ptr::read(ptr.cast()))
     }
 
@@ -91,8 +89,7 @@ impl Group {
     #[inline]
     #[allow(clippy::cast_ptr_alignment)]
     pub(crate) unsafe fn store_aligned(self, ptr: *mut Tag) {
-        // FIXME: use align_offset once it stabilizes
-        debug_assert_eq!(ptr as usize & (mem::align_of::<Self>() - 1), 0);
+        debug_assert_eq!(ptr.align_offset(mem::align_of::<Self>()), 0);
         ptr::write(ptr.cast(), self.0);
     }
 

src/control/group/mod.rs

@@ -0,0 +1,35 @@
+cfg_if! {
+    // Use the SSE2 implementation if possible: it allows us to scan 16 buckets
+    // at once instead of 8. We don't bother with AVX since it would require
+    // runtime dispatch and wouldn't gain us much anyways: the probability of
+    // finding a match drops off drastically after the first few buckets.
+    //
+    // I attempted an implementation on ARM using NEON instructions, but it
+    // turns out that most NEON instructions have multi-cycle latency, which in
+    // the end outweighs any gains over the generic implementation.
+    if #[cfg(all(
+        target_feature = "sse2",
+        any(target_arch = "x86", target_arch = "x86_64"),
+        not(miri),
+    ))] {
+        mod sse2;
+        use sse2 as imp;
+    } else if #[cfg(all(
+        target_arch = "aarch64",
+        target_feature = "neon",
+        // NEON intrinsics are currently broken on big-endian targets.
+        // See https://github.com/rust-lang/stdarch/issues/1484.
+        target_endian = "little",
+        not(miri),
+    ))] {
+        mod neon;
+        use neon as imp;
+    } else {
+        mod generic;
+        use generic as imp;
+    }
+}
+pub(crate) use self::imp::Group;
+pub(super) use self::imp::{
+    BitMaskWord, NonZeroBitMaskWord, BITMASK_ITER_MASK, BITMASK_MASK, BITMASK_STRIDE,
+};

src/raw/neon.rs → src/control/group/neon.rs

@@ -1,5 +1,4 @@
-use super::bitmask::BitMask;
-use super::Tag;
+use super::super::{BitMask, Tag};
 use core::arch::aarch64 as neon;
 use core::mem;
 use core::num::NonZeroU64;
@@ -52,8 +51,7 @@ impl Group {
     #[inline]
     #[allow(clippy::cast_ptr_alignment)]
     pub(crate) unsafe fn load_aligned(ptr: *const Tag) -> Self {
-        // FIXME: use align_offset once it stabilizes
-        debug_assert_eq!(ptr as usize & (mem::align_of::<Self>() - 1), 0);
+        debug_assert_eq!(ptr.align_offset(mem::align_of::<Self>()), 0);
         Group(neon::vld1_u8(ptr.cast()))
     }
 
@@ -62,8 +60,7 @@ impl Group {
     #[inline]
     #[allow(clippy::cast_ptr_alignment)]
     pub(crate) unsafe fn store_aligned(self, ptr: *mut Tag) {
-        // FIXME: use align_offset once it stabilizes
-        debug_assert_eq!(ptr as usize & (mem::align_of::<Self>() - 1), 0);
+        debug_assert_eq!(ptr.align_offset(mem::align_of::<Self>()), 0);
         neon::vst1_u8(ptr.cast(), self.0);
     }
 

src/raw/sse2.rs → src/control/group/sse2.rs

@@ -1,5 +1,4 @@
-use super::bitmask::BitMask;
-use super::Tag;
+use super::super::{BitMask, Tag};
 use core::mem;
 use core::num::NonZeroU16;
 
@@ -58,8 +57,7 @@ impl Group {
     #[inline]
     #[allow(clippy::cast_ptr_alignment)]
     pub(crate) unsafe fn load_aligned(ptr: *const Tag) -> Self {
-        // FIXME: use align_offset once it stabilizes
-        debug_assert_eq!(ptr as usize & (mem::align_of::<Self>() - 1), 0);
+        debug_assert_eq!(ptr.align_offset(mem::align_of::<Self>()), 0);
         Group(x86::_mm_load_si128(ptr.cast()))
     }
 
@@ -68,8 +66,7 @@ impl Group {
     #[inline]
     #[allow(clippy::cast_ptr_alignment)]
     pub(crate) unsafe fn store_aligned(self, ptr: *mut Tag) {
-        // FIXME: use align_offset once it stabilizes
-        debug_assert_eq!(ptr as usize & (mem::align_of::<Self>() - 1), 0);
+        debug_assert_eq!(ptr.align_offset(mem::align_of::<Self>()), 0);
         x86::_mm_store_si128(ptr.cast(), self.0);
     }
 

src/control/mod.rs

@@ -0,0 +1,10 @@
+mod bitmask;
+mod group;
+mod tag;
+
+use self::bitmask::BitMask;
+pub(crate) use self::{
+    bitmask::BitMaskIter,
+    group::Group,
+    tag::{Tag, TagSliceExt},
+};

src/control/tag.rs

@@ -0,0 +1,83 @@
+use core::{fmt, mem};
+
+/// Single tag in a control group.
+#[derive(Copy, Clone, PartialEq, Eq)]
+#[repr(transparent)]
+pub(crate) struct Tag(pub(super) u8);
+impl Tag {
+    /// Control tag value for an empty bucket.
+    pub(crate) const EMPTY: Tag = Tag(0b1111_1111);
+
+    /// Control tag value for a deleted bucket.
+    pub(crate) const DELETED: Tag = Tag(0b1000_0000);
+
+    /// Checks whether a control tag represents a full bucket (top bit is clear).
+    #[inline]
+    pub(crate) const fn is_full(self) -> bool {
+        self.0 & 0x80 == 0
+    }
+
+    /// Checks whether a control tag represents a special value (top bit is set).
+    #[inline]
+    pub(crate) const fn is_special(self) -> bool {
+        self.0 & 0x80 != 0
+    }
+
+    /// Checks whether a special control value is EMPTY (just check 1 bit).
+    #[inline]
+    pub(crate) const fn special_is_empty(self) -> bool {
+        debug_assert!(self.is_special());
+        self.0 & 0x01 != 0
+    }
+
+    /// Creates a control tag representing a full bucket with the given hash.
+    #[inline]
+    #[allow(clippy::cast_possible_truncation)]
+    pub(crate) const fn full(hash: u64) -> Tag {
+        // Constant for function that grabs the top 7 bits of the hash.
+        const MIN_HASH_LEN: usize = if mem::size_of::<usize>() < mem::size_of::<u64>() {
+            mem::size_of::<usize>()
+        } else {
+            mem::size_of::<u64>()
+        };
+
+        // Grab the top 7 bits of the hash. While the hash is normally a full 64-bit
+        // value, some hash functions (such as FxHash) produce a usize result
+        // instead, which means that the top 32 bits are 0 on 32-bit platforms.
+        // So we use MIN_HASH_LEN constant to handle this.
+        let top7 = hash >> (MIN_HASH_LEN * 8 - 7);
+        Tag((top7 & 0x7f) as u8) // truncation
+    }
+}
+impl fmt::Debug for Tag {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        if self.is_special() {
+            if self.special_is_empty() {
+                f.pad("EMPTY")
+            } else {
+                f.pad("DELETED")
+            }
+        } else {
+            f.debug_tuple("full").field(&(self.0 & 0x7F)).finish()
+        }
+    }
+}
+
+/// Extension trait for slices of tags.
+pub(crate) trait TagSliceExt {
+    /// Fills the control with the given tag.
+    fn fill_tag(&mut self, tag: Tag);
+
+    /// Clears out the control.
+    #[inline]
+    fn fill_empty(&mut self) {
+        self.fill_tag(Tag::EMPTY)
+    }
+}
+impl TagSliceExt for [Tag] {
+    #[inline]
+    fn fill_tag(&mut self, tag: Tag) {
+        // SAFETY: We have access to the entire slice, so, we can write to the entire slice.
+        unsafe { self.as_mut_ptr().write_bytes(tag.0, self.len()) }
+    }
+}

src/lib.rs

@@ -63,7 +63,9 @@ doc_comment::doctest!("../README.md");
 #[macro_use]
 mod macros;
 
+mod control;
 mod raw;
+mod util;
 
 mod external_trait_impls;
 mod map;