From 20679d1e1e91104282f71e04ebcb23134e70c594 Mon Sep 17 00:00:00 2001
From: overlookmotel <theoverlookmotel@gmail.com>
Date: Tue, 30 Jan 2024 03:47:26 +0000
Subject: [PATCH] perf(parser): pad `Token` to 16 bytes (#2211)

Counter-intuitively, it seems that *increasing* the size of `Token`
improves performance slightly.

This appears to be because when `Token` is 16 bytes, copying `Token` is
a single 16-byte load/store. At present, it's 12 bytes which requires an
8-byte load/store + a 4-byte load/store.

https://godbolt.org/z/KPYsn3ab7

This suggests that either:

1. #2010 could be reverted at no cost, and the overhead of the hash
table removed.
or:
2. We need to get `Token` down to 8 bytes!

I have an idea how to *maybe* do (2), so I'd suggest leaving it as is
for now until I've been able to research that.

NB I also tried putting `#[repr(align(16))]` on `Token` so that copying
uses aligned loads/stores. That [hurt the benchmarks very
slightly](https://codspeed.io/overlookmotel/oxc/branches/lexer-pad-token),
though it might produce a gain on architectures where unaligned loads
are more expensive (ARM64 I think?). But I can't test that theory, so
have left it out.
---
 crates/oxc_parser/src/lexer/mod.rs   |  7 ++-----
 crates/oxc_parser/src/lexer/token.rs | 12 +++++++++++-
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/crates/oxc_parser/src/lexer/mod.rs b/crates/oxc_parser/src/lexer/mod.rs
index 0589f46a8..b275d657b 100644
--- a/crates/oxc_parser/src/lexer/mod.rs
+++ b/crates/oxc_parser/src/lexer/mod.rs
@@ -83,11 +83,8 @@ impl<'a> Lexer<'a> {
             source = "\0";
         }
 
-        let token = Token {
-            // the first token is at the start of file, so is allows on a new line
-            is_on_new_line: true,
-            ..Token::default()
-        };
+        // The first token is at the start of file, so is allows on a new line
+        let token = Token::new_on_new_line();
         let current = LexerCheckpoint { chars: source.chars(), token, errors_pos: 0 };
         Self {
             allocator,
diff --git a/crates/oxc_parser/src/lexer/token.rs b/crates/oxc_parser/src/lexer/token.rs
index 5d2f57641..122c5080b 100644
--- a/crates/oxc_parser/src/lexer/token.rs
+++ b/crates/oxc_parser/src/lexer/token.rs
@@ -25,14 +25,24 @@ pub struct Token {
     /// [Lexer::escaped_strings]: [super::Lexer::escaped_strings]
     /// [Lexer::escaped_templates]: [super::Lexer::escaped_templates]
     pub escaped: bool,
+
+    // Padding to fill to 16 bytes.
+    // This makes copying a `Token` 1 x xmmword load & store, rather than 1 x dword + 1 x qword
+    // and `Token::default()` is 1 x xmmword store, rather than 1 x dword + 1 x qword.
+    _padding1: u8,
+    _padding2: u32,
 }
 
 #[cfg(target_pointer_width = "64")]
 mod size_asserts {
-    oxc_index::assert_eq_size!(super::Token, [u8; 12]);
+    oxc_index::assert_eq_size!(super::Token, [u8; 16]);
 }
 
 impl Token {
+    pub(super) fn new_on_new_line() -> Self {
+        Self { is_on_new_line: true, ..Self::default() }
+    }
+
     pub fn span(&self) -> Span {
         Span::new(self.start, self.end)
     }