From 6e3ab468123c01b0bf3cac9b8fa3b9ba0f2f2a38 Mon Sep 17 00:00:00 2001
From: Robert Nagy <ronagy@icloud.com>
Date: Mon, 12 Aug 2024 23:10:08 +0200
Subject: [PATCH] buffer: optimize byteLength for short strings

PR-URL: https://github.com/nodejs/node/pull/54345
---
 src/node_buffer.cc | 32 +++++++++++++++++++++++++++-----
 1 file changed, 27 insertions(+), 5 deletions(-)

diff --git a/src/node_buffer.cc b/src/node_buffer.cc
index 6e141b974131cc..4dd660f3059325 100644
--- a/src/node_buffer.cc
+++ b/src/node_buffer.cc
@@ -35,6 +35,7 @@
 #include "v8-fast-api-calls.h"
 #include "v8.h"
 
+#include <bit>
 #include <climits>
 #include <cstring>
 #include "nbytes.h"
@@ -752,13 +753,34 @@ uint32_t FastByteLengthUtf8(Local<Value> receiver,
   if (source.length > 128) {
     return simdutf::utf8_length_from_latin1(source.data, source.length);
   }
+
   uint32_t length = source.length;
-  uint32_t result = length;
-  const uint8_t* data = reinterpret_cast<const uint8_t*>(source.data);
-  for (uint32_t i = 0; i < length; ++i) {
-    result += (data[i] >> 7);
+  const auto input = reinterpret_cast<const uint8_t*>(source.data);
+
+  uint32_t answer = length;
+  uint32_t i = 0;
+
+  for(; i + 32 <= length; i += 32) {
+    uint64_t v;
+    memcpy(&v, input + i, 8);
+    answer += std::popcount(v);
+    memcpy(&v, input + i + 8, 8);
+    answer += std::popcount(v);
+    memcpy(&v, input + i + 16, 8);
+    answer += std::popcount(v);
+    memcpy(&v, input + i + 24, 8);
+    answer += std::popcount(v);
+  }
+  for(; i + 8 <= length; i += 8) {
+    uint64_t v;
+    memcpy(&v, input + i, sizeof(v));
+    answer += std::popcount(v);
   }
-  return result;
+  for(; i + 8 <= length; i += 1) {
+    answer += ((uint8_t)input[i] >> 7);
+  }
+
+  return answer;
 }
 
 static v8::CFunction fast_byte_length_utf8(