From f607884a04b0ca06951227a01d00bc59b948d337 Mon Sep 17 00:00:00 2001
From: serge-sans-paille <sguelton@mozilla.com>
Date: Mon, 21 Nov 2022 16:01:32 +0100
Subject: [PATCH] [clang] Speedup LineOffsetMapping::get

LineOffsetMapping::get is a critical function that consistently appears
in the top 5 more computation intensive functions when running the
preprocessor.

This change brings consistent speedup of ~.5% on, preprocessing time,
see

https://llvm-compile-time-tracker.com/compare.php?from=0745b0c0354a0c8e1fefb68a3876d15db6c2e27a&to=460f3f04dac025e6952d78fce104a88151508a29&stat=instructions:u

for detailed statistics.

Differential Revision: https://reviews.llvm.org/D138474
---
 clang/lib/Basic/SourceManager.cpp | 48 ++++++++++++++++++++-------------------
 1 file changed, 25 insertions(+), 23 deletions(-)

diff --git a/clang/lib/Basic/SourceManager.cpp b/clang/lib/Basic/SourceManager.cpp
index ecb771a..f61dc0f 100644
--- a/clang/lib/Basic/SourceManager.cpp
+++ b/clang/lib/Basic/SourceManager.cpp
@@ -1281,22 +1281,21 @@ LineOffsetMapping LineOffsetMapping::get(llvm::MemoryBufferRef Buffer,
   // Line #1 starts at char 0.
   LineOffsets.push_back(0);
 
-  const unsigned char *Buf = (const unsigned char *)Buffer.getBufferStart();
+  const unsigned char *Start = (const unsigned char *)Buffer.getBufferStart();
   const unsigned char *End = (const unsigned char *)Buffer.getBufferEnd();
-  const std::size_t BufLen = End - Buf;
+  const unsigned char *Buf = Start;
 
-  unsigned I = 0;
   uint64_t Word;
 
   // scan sizeof(Word) bytes at a time for new lines.
   // This is much faster than scanning each byte independently.
-  if (BufLen > sizeof(Word)) {
+  if (End - Start > sizeof(Word)) {
     do {
-      Word = llvm::support::endian::read64(Buf + I, llvm::support::little);
+      Word = llvm::support::endian::read64(Buf, llvm::support::little);
       // no new line => jump over sizeof(Word) bytes.
       auto Mask = likelyhasbetween(Word, '\n', '\r');
       if (!Mask) {
-        I += sizeof(Word);
+        Buf += sizeof(Word);
         continue;
       }
 
@@ -1307,30 +1306,33 @@ LineOffsetMapping LineOffsetMapping::get(llvm::MemoryBufferRef Buffer,
       unsigned N =
           llvm::countTrailingZeros(Mask) - 7; // -7 because 0x80 is the marker
       Word >>= N;
-      I += N / 8 + 1;
+      Buf += N / 8 + 1;
       unsigned char Byte = Word;
-      if (Byte == '\n') {
-        LineOffsets.push_back(I);
-      } else if (Byte == '\r') {
+      switch (Byte) {
+      case 'r':
         // If this is \r\n, skip both characters.
-        if (Buf[I] == '\n')
-          ++I;
-        LineOffsets.push_back(I);
-      }
-    } while (I < BufLen - sizeof(Word) - 1);
+        if (*Buf == '\n') {
+          ++Buf;
+        }
+        LLVM_FALLTHROUGH;
+      case '\n':
+        LineOffsets.push_back(Buf - Start);
+      };
+    } while (Buf < End - sizeof(Word) - 1);
   }
 
   // Handle tail using a regular check.
-  while (I < BufLen) {
-    if (Buf[I] == '\n') {
-      LineOffsets.push_back(I + 1);
-    } else if (Buf[I] == '\r') {
+  while (Buf < End) {
+    if (*Buf == '\n') {
+      LineOffsets.push_back(Buf - Start + 1);
+    } else if (*Buf == '\r') {
       // If this is \r\n, skip both characters.
-      if (I + 1 < BufLen && Buf[I + 1] == '\n')
-        ++I;
-      LineOffsets.push_back(I + 1);
+      if (Buf + 1 < End && Buf[1] == '\n') {
+        ++Buf;
+      }
+      LineOffsets.push_back(Buf - Start + 1);
     }
-    ++I;
+    ++Buf;
   }
 
   return LineOffsetMapping(LineOffsets, Alloc);
-- 
2.7.4