Make SectionPiece 8 bytes smaller on LP64.
This patch makes SectionPiece class 8 bytes smaller on platforms
on which pointer size is 8 bytes. Sean suggested in a post commit
review for r270340 that this could make a differentce, and it
actually is. Time to link clang (with debug info) improved from
6.725 seconds to 6.589 seconds or by about 2%.
Differential Revision: http://reviews.llvm.org/D20613
llvm-svn: 270717
diff --git a/lld/ELF/InputSection.h b/lld/ELF/InputSection.h
index 028c3be..2c3d3ac 100644
--- a/lld/ELF/InputSection.h
+++ b/lld/ELF/InputSection.h
@@ -87,13 +87,24 @@
// SectionPiece represents a piece of splittable section contents.
struct SectionPiece {
SectionPiece(size_t Off, ArrayRef<uint8_t> Data)
- : InputOff(Off), Data(Data), Live(!Config->GcSections) {}
- size_t size() const { return Data.size(); }
+ : InputOff(Off), Data((uint8_t *)Data.data()), Size(Data.size()),
+ Live(!Config->GcSections) {}
+
+ ArrayRef<uint8_t> data() { return {Data, Size}; }
+ size_t size() const { return Size; }
size_t InputOff;
size_t OutputOff = -1;
- ArrayRef<uint8_t> Data; // slice of the input section
- bool Live;
+
+private:
+ // We use bitfields because SplitInputSection is accessed by
+ // std::upper_bound very often.
+ // We want to save bits to make it cache friendly.
+ uint8_t *Data;
+ uint32_t Size : 31;
+
+public:
+ uint32_t Live : 1;
};
// Usually sections are copied to the output as atomic chunks of data,
diff --git a/lld/ELF/OutputSections.cpp b/lld/ELF/OutputSections.cpp
index d10488c..77dce45 100644
--- a/lld/ELF/OutputSections.cpp
+++ b/lld/ELF/OutputSections.cpp
@@ -946,7 +946,7 @@
EhInputSection<ELFT> *Sec,
ArrayRef<RelTy> &Rels) {
const endianness E = ELFT::TargetEndianness;
- if (read32<E>(Piece.Data.data() + 4) != 0)
+ if (read32<E>(Piece.data().data() + 4) != 0)
fatal("CIE expected at beginning of .eh_frame: " + Sec->getSectionName());
SymbolBody *Personality = nullptr;
@@ -954,7 +954,7 @@
Personality = &Sec->getFile()->getRelocTargetSym(*Rel);
// Search for an existing CIE by CIE contents/relocation target pair.
- CieRecord *Cie = &CieMap[{Piece.Data, Personality}];
+ CieRecord *Cie = &CieMap[{Piece.data(), Personality}];
// If not found, create a new one.
if (Cie->Piece == nullptr) {
@@ -995,11 +995,11 @@
DenseMap<size_t, CieRecord *> OffsetToCie;
for (SectionPiece &Piece : Sec->Pieces) {
// The empty record is the end marker.
- if (Piece.Data.size() == 4)
+ if (Piece.size() == 4)
return;
size_t Offset = Piece.InputOff;
- uint32_t ID = read32<E>(Piece.Data.data() + 4);
+ uint32_t ID = read32<E>(Piece.data().data() + 4);
if (ID == 0) {
OffsetToCie[Offset] = addCie(Piece, Sec, Rels);
continue;
@@ -1106,11 +1106,11 @@
const endianness E = ELFT::TargetEndianness;
for (CieRecord *Cie : Cies) {
size_t CieOffset = Cie->Piece->OutputOff;
- writeCieFde<ELFT>(Buf + CieOffset, Cie->Piece->Data);
+ writeCieFde<ELFT>(Buf + CieOffset, Cie->Piece->data());
for (SectionPiece *Fde : Cie->FdePieces) {
size_t Off = Fde->OutputOff;
- writeCieFde<ELFT>(Buf + Off, Fde->Data);
+ writeCieFde<ELFT>(Buf + Off, Fde->data());
// FDE's second word should have the offset to an associated CIE.
// Write it.
@@ -1126,7 +1126,7 @@
// we obtain two addresses and pass them to EhFrameHdr object.
if (Out<ELFT>::EhFrameHdr) {
for (CieRecord *Cie : Cies) {
- uint8_t Enc = getFdeEncoding<ELFT>(Cie->Piece->Data);
+ uint8_t Enc = getFdeEncoding<ELFT>(Cie->Piece->data());
for (SectionPiece *Fde : Cie->FdePieces) {
uintX_t Pc = getFdePc(Buf, Fde->OutputOff, Enc);
uintX_t FdeVA = this->getVA() + Fde->OutputOff;
@@ -1170,7 +1170,7 @@
for (SectionPiece &Piece : Sec->Pieces) {
if (!Piece.Live)
continue;
- uintX_t OutputOffset = Builder.add(toStringRef(Piece.Data));
+ uintX_t OutputOffset = Builder.add(toStringRef(Piece.data()));
if (!IsString || !shouldTailMerge())
Piece.OutputOff = OutputOffset;
}