Use an abbrev to reduce size of VALUE_GUID records in ThinLTO summaries (#90497)

GUID often have content in the higher bits of a 64-bit entry so using
the unabbrev encoding is inefficient (lots of VBR control bits).
Instead, use an abbrev with two 32-bit fixed width chunks.
The abbrev also helps encode the "count" in one place instead of
in every record.

Reduces size of distributed backend summary files by 8.7% in one
example app.

Co-authored-by: Jan Voung <jvoung@google.com>

1 files changed, 26 insertions, 4 deletions

diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index 6d01e3b..1aaf160 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -4299,9 +4299,20 @@ void ModuleBitcodeWriterBase::writePerModuleGlobalValueSummary() {
     return;
   }
 
+  auto Abbv = std::make_shared<BitCodeAbbrev>();
+  Abbv->Add(BitCodeAbbrevOp(bitc::FS_VALUE_GUID));
+  Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6));
+  // GUIDS often use up most of 64-bits, so encode as two Fixed 32.
+  Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32));
+  Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32));
+  unsigned ValueGuidAbbrev = Stream.EmitAbbrev(std::move(Abbv));
+
   for (const auto &GVI : valueIds()) {
     Stream.EmitRecord(bitc::FS_VALUE_GUID,
-                      ArrayRef<uint64_t>{GVI.second, GVI.first});
+                      ArrayRef<uint32_t>{GVI.second,
+                                         static_cast<uint32_t>(GVI.first >> 32),
+                                         static_cast<uint32_t>(GVI.first)},
+                      ValueGuidAbbrev);
   }
 
   if (!Index->stackIds().empty()) {
@@ -4315,7 +4326,7 @@ void ModuleBitcodeWriterBase::writePerModuleGlobalValueSummary() {
   }
 
   // Abbrev for FS_PERMODULE_PROFILE.
-  auto Abbv = std::make_shared<BitCodeAbbrev>();
+  Abbv = std::make_shared<BitCodeAbbrev>();
   Abbv->Add(BitCodeAbbrevOp(bitc::FS_PERMODULE_PROFILE));
   Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8));   // valueid
   Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8));   // flags
@@ -4467,9 +4478,20 @@ void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
   // Write the index flags.
   Stream.EmitRecord(bitc::FS_FLAGS, ArrayRef<uint64_t>{Index.getFlags()});
 
+  auto Abbv = std::make_shared<BitCodeAbbrev>();
+  Abbv->Add(BitCodeAbbrevOp(bitc::FS_VALUE_GUID));
+  Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6));
+  // GUIDS often use up most of 64-bits, so encode as two Fixed 32.
+  Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32));
+  Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32));
+  unsigned ValueGuidAbbrev = Stream.EmitAbbrev(std::move(Abbv));
+
   for (const auto &GVI : valueIds()) {
     Stream.EmitRecord(bitc::FS_VALUE_GUID,
-                      ArrayRef<uint64_t>{GVI.second, GVI.first});
+                      ArrayRef<uint32_t>{GVI.second,
+                                         static_cast<uint32_t>(GVI.first >> 32),
+                                         static_cast<uint32_t>(GVI.first)},
+                      ValueGuidAbbrev);
   }
 
   if (!StackIdIndices.empty()) {
@@ -4488,7 +4510,7 @@ void IndexBitcodeWriter::writeCombinedGlobalValueSummary() {
   }
 
   // Abbrev for FS_COMBINED_PROFILE.
-  auto Abbv = std::make_shared<BitCodeAbbrev>();
+  Abbv = std::make_shared<BitCodeAbbrev>();
   Abbv->Add(BitCodeAbbrevOp(bitc::FS_COMBINED_PROFILE));
   Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8));   // valueid
   Abbv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 8));   // modid