From fdbf0a5af805b764927bd8b38da89ddffc67f531 Mon Sep 17 00:00:00 2001
From: "Duncan P. N. Exon Smith" <dexonsmith@apple.com>
Date: Fri, 25 Mar 2016 14:40:18 +0000
Subject: Bitcode: Collect all MDString records into a single blob

Optimize output of MDStrings in bitcode.  This emits them in big blocks
(currently 1024) in a pair of records:
  - BULK_STRING_SIZES: the sizes of the strings in the block, and
  - BULK_STRING_DATA: a single blob, which is the concatenation of all
    the strings.

Inspired by Mehdi's similar patch, http://reviews.llvm.org/D18342, this
should (a) slightly reduce bitcode size, since there is less record
overhead, and (b) greatly improve reading speed, since blobs are super
cheap to deserialize.

I needed to add support for blobs to streaming input to get the test
suite passing.
  - StreamingMemoryObject::getPointer reads ahead and returns the
    address of the blob.
  - To avoid a possible reallocation of StreamingMemoryObject::Bytes,
    BitstreamCursor::readRecord needs to move the call to JumpToEnd
    forward so that getPointer is the last bitstream operation.

llvm-svn: 264409
---
 llvm/lib/Bitcode/Reader/BitcodeReader.cpp | 34 ++++++++++++++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

(limited to 'llvm/lib/Bitcode/Reader/BitcodeReader.cpp')

diff --git a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
index bb479dbcedc..b849db4427a 100644
--- a/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
+++ b/llvm/lib/Bitcode/Reader/BitcodeReader.cpp
@@ -2363,7 +2363,7 @@ std::error_code BitcodeReader::parseMetadata(bool ModuleLevel) {
           NextMetadataNo++);
       break;
     }
-    case bitc::METADATA_STRING: {
+    case bitc::METADATA_STRING_OLD: {
       std::string String(Record.begin(), Record.end());
 
       // Test for upgrading !llvm.loop.
@@ -2373,6 +2373,38 @@ std::error_code BitcodeReader::parseMetadata(bool ModuleLevel) {
       MetadataList.assignValue(MD, NextMetadataNo++);
       break;
     }
+    case bitc::METADATA_BULK_STRING_SIZES: {
+      // This is a pair of records for an MDString block: SIZES, which is a
+      // list of string lengths; and DATA, which is a blob with all the strings
+      // concatenated together.
+      //
+      // Note: since this record type was introduced after the upgrade for
+      // !llvm.loop, we don't need to change HasSeenOldLoopTags.
+      if (Record.empty())
+        return error("Invalid record: missing bulk metadata string sizes");
+
+      StringRef Blob;
+      SmallVector<uint64_t, 1> BlobRecord;
+      Code = Stream.ReadCode();
+      unsigned BlobCode = Stream.readRecord(Code, BlobRecord, &Blob);
+      if (BlobCode != bitc::METADATA_BULK_STRING_DATA)
+        return error("Invalid record: missing bulk metadata string data");
+      if (!BlobRecord.empty())
+        return error("Invalid record: unexpected bulk metadata arguments");
+
+      for (uint64_t Size : Record) {
+        if (Blob.size() < Size)
+          return error("Invalid record: not enough bulk metadata string bytes");
+
+        // Extract the current string.
+        MetadataList.assignValue(MDString::get(Context, Blob.slice(0, Size)),
+                                 NextMetadataNo++);
+        Blob = Blob.drop_front(Size);
+      }
+      if (!Blob.empty())
+        return error("Invalid record: too many bulk metadata string bytes");
+      break;
+    }
     case bitc::METADATA_KIND: {
       // Support older bitcode files that had METADATA_KIND records in a
       // block with METADATA_BLOCK_ID.
-- 
cgit v1.2.3