From 619cd613d022c5ea8e20acca5a6fa6b3913a92c4 Mon Sep 17 00:00:00 2001
From: Andreas Kling <kling@serenityos.org>
Date: Thu, 22 Oct 2020 17:43:48 +0200
Subject: [PATCH] LibJS: Give VM a cache of single-ASCII-character
 PrimitiveString

A large number of JS strings are a single ASCII character. This patch
adds a 128-entry cache for those strings to the VM. The cost of the
cache is 1536 byte of GC heap (all in same block) + 2304 bytes malloc.

This avoids a lot of GC heap allocations, and packing all of these
in the same heap block is nice for fragmentation as well.
---
 Libraries/LibJS/Runtime/PrimitiveString.cpp | 4 ++++
 Libraries/LibJS/Runtime/VM.cpp              | 7 +++++++
 Libraries/LibJS/Runtime/VM.h                | 6 ++++++
 3 files changed, 17 insertions(+)

diff --git a/Libraries/LibJS/Runtime/PrimitiveString.cpp b/Libraries/LibJS/Runtime/PrimitiveString.cpp
index 2aeb74e914..b62377925d 100644
--- a/Libraries/LibJS/Runtime/PrimitiveString.cpp
+++ b/Libraries/LibJS/Runtime/PrimitiveString.cpp
@@ -42,6 +42,10 @@ PrimitiveString* js_string(Heap& heap, String string)
 {
     if (string.is_empty())
         return &heap.vm().empty_string();
+
+    if (string.length() == 1 && (u8)string.characters()[0] < 0x80)
+        return &heap.vm().single_ascii_character_string(string.characters()[0]);
+
     return heap.allocate_without_global_object<PrimitiveString>(move(string));
 }
 
diff --git a/Libraries/LibJS/Runtime/VM.cpp b/Libraries/LibJS/Runtime/VM.cpp
index d53e4dd79f..63b31aa37a 100644
--- a/Libraries/LibJS/Runtime/VM.cpp
+++ b/Libraries/LibJS/Runtime/VM.cpp
@@ -47,6 +47,10 @@ VM::VM()
     : m_heap(*this)
 {
     m_empty_string = m_heap.allocate_without_global_object<PrimitiveString>(String::empty());
+    for (size_t i = 0; i < 128; ++i) {
+        m_single_ascii_character_strings[i] = m_heap.allocate_without_global_object<PrimitiveString>(String::format("%c", i));
+    }
+
 #define __JS_ENUMERATE(SymbolName, snake_name) \
     m_well_known_symbol_##snake_name = js_symbol(*this, "Symbol." #SymbolName, false);
     JS_ENUMERATE_WELL_KNOWN_SYMBOLS
@@ -96,6 +100,9 @@ VM::InterpreterExecutionScope::~InterpreterExecutionScope()
 void VM::gather_roots(HashTable<Cell*>& roots)
 {
     roots.set(m_empty_string);
+    for (auto* string : m_single_ascii_character_strings)
+        roots.set(string);
+
     if (m_exception)
         roots.set(m_exception);
 
diff --git a/Libraries/LibJS/Runtime/VM.h b/Libraries/LibJS/Runtime/VM.h
index 3334276640..f4adc144f9 100644
--- a/Libraries/LibJS/Runtime/VM.h
+++ b/Libraries/LibJS/Runtime/VM.h
@@ -108,6 +108,11 @@ public:
     Symbol* get_global_symbol(const String& description);
 
     PrimitiveString& empty_string() { return *m_empty_string; }
+    PrimitiveString& single_ascii_character_string(u8 character)
+    {
+        ASSERT(character < 0x80);
+        return *m_single_ascii_character_strings[character];
+    }
 
     CallFrame& push_call_frame(bool strict_mode = false)
     {
@@ -247,6 +252,7 @@ private:
     HashMap<String, Symbol*> m_global_symbol_map;
 
     PrimitiveString* m_empty_string { nullptr };
+    PrimitiveString* m_single_ascii_character_strings[128] {};
 
 #define __JS_ENUMERATE(SymbolName, snake_name) \
     Symbol* m_well_known_symbol_##snake_name { nullptr };