//===----------------------------------------------------------------------===//
//
// This file implements a hash set that can be used to remove duplication of
-// nodes in a graph. This code was originally created by Chris Lattner for use
-// with SelectionDAGCSEMap, but was isolated to provide use across the llvm code
-// set.
+// nodes in a graph.
//
//===----------------------------------------------------------------------===//
#include "llvm/ADT/FoldingSet.h"
+#include "llvm/ADT/Hashing.h"
+#include "llvm/Support/Allocator.h"
#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/Host.h"
#include "llvm/Support/MathExtras.h"
#include <cassert>
#include <cstring>
using namespace llvm;
+//===----------------------------------------------------------------------===//
+// FoldingSetNodeIDRef Implementation
+
+/// ComputeHash - Compute a strong hash value for this FoldingSetNodeIDRef,
+/// used to lookup the node in the FoldingSetImpl.
+unsigned FoldingSetNodeIDRef::ComputeHash() const {
+ return static_cast<unsigned>(hash_combine_range(Data, Data+Size));
+}
+
+bool FoldingSetNodeIDRef::operator==(FoldingSetNodeIDRef RHS) const {
+ if (Size != RHS.Size) return false;
+ return memcmp(Data, RHS.Data, Size*sizeof(*Data)) == 0;
+}
+
+/// Used to compare the "ordering" of two nodes as defined by the
+/// profiled bits and their ordering defined by memcmp().
+bool FoldingSetNodeIDRef::operator<(FoldingSetNodeIDRef RHS) const {
+ if (Size != RHS.Size)
+ return Size < RHS.Size;
+ return memcmp(Data, RHS.Data, Size*sizeof(*Data)) < 0;
+}
+
//===----------------------------------------------------------------------===//
// FoldingSetNodeID Implementation
///
void FoldingSetNodeID::AddPointer(const void *Ptr) {
// Note: this adds pointers to the hash using sizes and endianness that
- // depend on the host. It doesn't matter however, because hashing on
- // pointer values in inherently unstable. Nothing should depend on the
+ // depend on the host. It doesn't matter, however, because hashing on
+ // pointer values is inherently unstable. Nothing should depend on the
// ordering of nodes in the folding set.
- intptr_t PtrI = (intptr_t)Ptr;
- Bits.push_back(unsigned(PtrI));
- if (sizeof(intptr_t) > sizeof(unsigned))
- Bits.push_back(unsigned(uint64_t(PtrI) >> 32));
+ Bits.append(reinterpret_cast<unsigned *>(&Ptr),
+ reinterpret_cast<unsigned *>(&Ptr+1));
}
void FoldingSetNodeID::AddInteger(signed I) {
Bits.push_back(I);
}
void FoldingSetNodeID::AddInteger(unsigned long long I) {
AddInteger(unsigned(I));
- if ((uint64_t)(int)I != I)
+ if ((uint64_t)(unsigned)I != I)
Bits.push_back(unsigned(I >> 32));
}
Pos = (Units + 1) * 4;
} else {
// Otherwise do it the hard way.
- for (Pos += 4; Pos <= Size; Pos += 4) {
- unsigned V = ((unsigned char)String[Pos - 4] << 24) |
- ((unsigned char)String[Pos - 3] << 16) |
- ((unsigned char)String[Pos - 2] << 8) |
- (unsigned char)String[Pos - 1];
- Bits.push_back(V);
+ // To be compatible with above bulk transfer, we need to take endianness
+ // into account.
+ static_assert(sys::IsBigEndianHost || sys::IsLittleEndianHost,
+ "Unexpected host endianness");
+ if (sys::IsBigEndianHost) {
+ for (Pos += 4; Pos <= Size; Pos += 4) {
+ unsigned V = ((unsigned char)String[Pos - 4] << 24) |
+ ((unsigned char)String[Pos - 3] << 16) |
+ ((unsigned char)String[Pos - 2] << 8) |
+ (unsigned char)String[Pos - 1];
+ Bits.push_back(V);
+ }
+ } else { // Little-endian host
+ for (Pos += 4; Pos <= Size; Pos += 4) {
+ unsigned V = ((unsigned char)String[Pos - 1] << 24) |
+ ((unsigned char)String[Pos - 2] << 16) |
+ ((unsigned char)String[Pos - 3] << 8) |
+ (unsigned char)String[Pos - 4];
+ Bits.push_back(V);
+ }
}
}
// With the leftover bits.
unsigned V = 0;
- // Pos will have overshot size by 4 - #bytes left over.
+ // Pos will have overshot size by 4 - #bytes left over.
+ // No need to take endianness into account here - this is always executed.
switch (Pos - Size) {
case 1: V = (V << 8) | (unsigned char)String[Size - 3]; // Fall thru.
case 2: V = (V << 8) | (unsigned char)String[Size - 2]; // Fall thru.
Bits.push_back(V);
}
+// AddNodeID - Adds the Bit data of another ID to *this.
+void FoldingSetNodeID::AddNodeID(const FoldingSetNodeID &ID) {
+ Bits.append(ID.Bits.begin(), ID.Bits.end());
+}
+
/// ComputeHash - Compute a strong hash value for this FoldingSetNodeID, used to
/// lookup the node in the FoldingSetImpl.
unsigned FoldingSetNodeID::ComputeHash() const {
- // This is adapted from SuperFastHash by Paul Hsieh.
- unsigned Hash = static_cast<unsigned>(Bits.size());
- for (const unsigned *BP = &Bits[0], *E = BP+Bits.size(); BP != E; ++BP) {
- unsigned Data = *BP;
- Hash += Data & 0xFFFF;
- unsigned Tmp = ((Data >> 16) << 11) ^ Hash;
- Hash = (Hash << 16) ^ Tmp;
- Hash += Hash >> 11;
- }
-
- // Force "avalanching" of final 127 bits.
- Hash ^= Hash << 3;
- Hash += Hash >> 5;
- Hash ^= Hash << 4;
- Hash += Hash >> 17;
- Hash ^= Hash << 25;
- Hash += Hash >> 6;
- return Hash;
+ return FoldingSetNodeIDRef(Bits.data(), Bits.size()).ComputeHash();
}
/// operator== - Used to compare two nodes to each other.
///
-bool FoldingSetNodeID::operator==(const FoldingSetNodeID &RHS)const{
- if (Bits.size() != RHS.Bits.size()) return false;
- return memcmp(&Bits[0], &RHS.Bits[0], Bits.size()*sizeof(Bits[0])) == 0;
+bool FoldingSetNodeID::operator==(const FoldingSetNodeID &RHS) const {
+ return *this == FoldingSetNodeIDRef(RHS.Bits.data(), RHS.Bits.size());
+}
+
+/// operator== - Used to compare two nodes to each other.
+///
+bool FoldingSetNodeID::operator==(FoldingSetNodeIDRef RHS) const {
+ return FoldingSetNodeIDRef(Bits.data(), Bits.size()) == RHS;
+}
+
+/// Used to compare the "ordering" of two nodes as defined by the
+/// profiled bits and their ordering defined by memcmp().
+bool FoldingSetNodeID::operator<(const FoldingSetNodeID &RHS) const {
+ return *this < FoldingSetNodeIDRef(RHS.Bits.data(), RHS.Bits.size());
}
+bool FoldingSetNodeID::operator<(FoldingSetNodeIDRef RHS) const {
+ return FoldingSetNodeIDRef(Bits.data(), Bits.size()) < RHS;
+}
+
+/// Intern - Copy this node's data to a memory region allocated from the
+/// given allocator and return a FoldingSetNodeIDRef describing the
+/// interned data.
+FoldingSetNodeIDRef
+FoldingSetNodeID::Intern(BumpPtrAllocator &Allocator) const {
+ unsigned *New = Allocator.Allocate<unsigned>(Bits.size());
+ std::uninitialized_copy(Bits.begin(), Bits.end(), New);
+ return FoldingSetNodeIDRef(New, Bits.size());
+}
//===----------------------------------------------------------------------===//
/// Helper functions for FoldingSetImpl.
static FoldingSetImpl::Node *GetNextPtr(void *NextInBucketPtr) {
// The low bit is set if this is the pointer back to the bucket.
if (reinterpret_cast<intptr_t>(NextInBucketPtr) & 1)
- return 0;
+ return nullptr;
return static_cast<FoldingSetImpl::Node*>(NextInBucketPtr);
}
/// GetBucketFor - Hash the specified node ID and return the hash bucket for
/// the specified ID.
-static void **GetBucketFor(const FoldingSetNodeID &ID,
- void **Buckets, unsigned NumBuckets) {
+static void **GetBucketFor(unsigned Hash, void **Buckets, unsigned NumBuckets) {
// NumBuckets is always a power of 2.
- unsigned BucketNum = ID.ComputeHash() & (NumBuckets-1);
+ unsigned BucketNum = Hash & (NumBuckets-1);
return Buckets + BucketNum;
}
+/// AllocateBuckets - Allocated initialized bucket memory.
+static void **AllocateBuckets(unsigned NumBuckets) {
+ void **Buckets = static_cast<void**>(calloc(NumBuckets+1, sizeof(void*)));
+ // Set the very last bucket to be a non-null "pointer".
+ Buckets[NumBuckets] = reinterpret_cast<void*>(-1);
+ return Buckets;
+}
+
//===----------------------------------------------------------------------===//
// FoldingSetImpl Implementation
+void FoldingSetImpl::anchor() {}
+
FoldingSetImpl::FoldingSetImpl(unsigned Log2InitSize) {
assert(5 < Log2InitSize && Log2InitSize < 32 &&
"Initial hash table size out of range");
NumBuckets = 1 << Log2InitSize;
- Buckets = new void*[NumBuckets+1];
- clear();
+ Buckets = AllocateBuckets(NumBuckets);
+ NumNodes = 0;
}
+
+FoldingSetImpl::FoldingSetImpl(FoldingSetImpl &&Arg)
+ : Buckets(Arg.Buckets), NumBuckets(Arg.NumBuckets), NumNodes(Arg.NumNodes) {
+ Arg.Buckets = nullptr;
+ Arg.NumBuckets = 0;
+ Arg.NumNodes = 0;
+}
+
+FoldingSetImpl &FoldingSetImpl::operator=(FoldingSetImpl &&RHS) {
+ free(Buckets); // This may be null if the set is in a moved-from state.
+ Buckets = RHS.Buckets;
+ NumBuckets = RHS.NumBuckets;
+ NumNodes = RHS.NumNodes;
+ RHS.Buckets = nullptr;
+ RHS.NumBuckets = 0;
+ RHS.NumNodes = 0;
+ return *this;
+}
+
FoldingSetImpl::~FoldingSetImpl() {
- delete [] Buckets;
+ free(Buckets);
}
+
void FoldingSetImpl::clear() {
// Set all but the last bucket to null pointers.
memset(Buckets, 0, NumBuckets*sizeof(void*));
NumBuckets <<= 1;
// Clear out new buckets.
- Buckets = new void*[NumBuckets+1];
- clear();
+ Buckets = AllocateBuckets(NumBuckets);
+ NumNodes = 0;
// Walk the old buckets, rehashing nodes into their new place.
- FoldingSetNodeID ID;
+ FoldingSetNodeID TempID;
for (unsigned i = 0; i != OldNumBuckets; ++i) {
void *Probe = OldBuckets[i];
if (!Probe) continue;
while (Node *NodeInBucket = GetNextPtr(Probe)) {
// Figure out the next link, remove NodeInBucket from the old link.
Probe = NodeInBucket->getNextInBucket();
- NodeInBucket->SetNextInBucket(0);
+ NodeInBucket->SetNextInBucket(nullptr);
// Insert the node into the new bucket, after recomputing the hash.
- GetNodeProfile(ID, NodeInBucket);
- InsertNode(NodeInBucket, GetBucketFor(ID, Buckets, NumBuckets));
- ID.clear();
+ InsertNode(NodeInBucket,
+ GetBucketFor(ComputeNodeHash(NodeInBucket, TempID),
+ Buckets, NumBuckets));
+ TempID.clear();
}
}
- delete[] OldBuckets;
+ free(OldBuckets);
}
/// FindNodeOrInsertPos - Look up the node specified by ID. If it exists,
FoldingSetImpl::Node
*FoldingSetImpl::FindNodeOrInsertPos(const FoldingSetNodeID &ID,
void *&InsertPos) {
-
- void **Bucket = GetBucketFor(ID, Buckets, NumBuckets);
+ unsigned IDHash = ID.ComputeHash();
+ void **Bucket = GetBucketFor(IDHash, Buckets, NumBuckets);
void *Probe = *Bucket;
- InsertPos = 0;
+ InsertPos = nullptr;
- FoldingSetNodeID OtherID;
+ FoldingSetNodeID TempID;
while (Node *NodeInBucket = GetNextPtr(Probe)) {
- GetNodeProfile(OtherID, NodeInBucket);
- if (OtherID == ID)
+ if (NodeEquals(NodeInBucket, ID, IDHash, TempID))
return NodeInBucket;
+ TempID.clear();
Probe = NodeInBucket->getNextInBucket();
- OtherID.clear();
}
// Didn't find the node, return null with the bucket as the InsertPos.
InsertPos = Bucket;
- return 0;
+ return nullptr;
}
/// InsertNode - Insert the specified node into the folding set, knowing that it
/// is not already in the map. InsertPos must be obtained from
/// FindNodeOrInsertPos.
void FoldingSetImpl::InsertNode(Node *N, void *InsertPos) {
- assert(N->getNextInBucket() == 0);
+ assert(!N->getNextInBucket());
// Do we need to grow the hashtable?
if (NumNodes+1 > NumBuckets*2) {
GrowHashTable();
- FoldingSetNodeID ID;
- GetNodeProfile(ID, N);
- InsertPos = GetBucketFor(ID, Buckets, NumBuckets);
+ FoldingSetNodeID TempID;
+ InsertPos = GetBucketFor(ComputeNodeHash(N, TempID), Buckets, NumBuckets);
}
++NumNodes;
// If this is the first insertion into this bucket, its next pointer will be
// null. Pretend as if it pointed to itself, setting the low bit to indicate
// that it is a pointer to the bucket.
- if (Next == 0)
+ if (!Next)
Next = reinterpret_cast<void*>(reinterpret_cast<intptr_t>(Bucket)|1);
// Set the node's next pointer, and make the bucket point to the node.
// Because each bucket is a circular list, we don't need to compute N's hash
// to remove it.
void *Ptr = N->getNextInBucket();
- if (Ptr == 0) return false; // Not in folding set.
+ if (!Ptr) return false; // Not in folding set.
--NumNodes;
- N->SetNextInBucket(0);
+ N->SetNextInBucket(nullptr);
// Remember what N originally pointed to, either a bucket or another node.
void *NodeNextPtr = Ptr;
/// instead.
FoldingSetImpl::Node *FoldingSetImpl::GetOrInsertNode(FoldingSetImpl::Node *N) {
FoldingSetNodeID ID;
- GetNodeProfile(ID, N);
+ GetNodeProfile(N, ID);
void *IP;
if (Node *E = FindNodeOrInsertPos(ID, IP))
return E;
FoldingSetIteratorImpl::FoldingSetIteratorImpl(void **Bucket) {
// Skip to the first non-null non-self-cycle bucket.
while (*Bucket != reinterpret_cast<void*>(-1) &&
- (*Bucket == 0 || GetNextPtr(*Bucket) == 0))
+ (!*Bucket || !GetNextPtr(*Bucket)))
++Bucket;
NodePtr = static_cast<FoldingSetNode*>(*Bucket);
do {
++Bucket;
} while (*Bucket != reinterpret_cast<void*>(-1) &&
- (*Bucket == 0 || GetNextPtr(*Bucket) == 0));
+ (!*Bucket || !GetNextPtr(*Bucket)));
NodePtr = static_cast<FoldingSetNode*>(*Bucket);
}
// FoldingSetBucketIteratorImpl Implementation
FoldingSetBucketIteratorImpl::FoldingSetBucketIteratorImpl(void **Bucket) {
- Ptr = (*Bucket == 0 || GetNextPtr(*Bucket) == 0) ? (void*) Bucket : *Bucket;
+ Ptr = (!*Bucket || !GetNextPtr(*Bucket)) ? (void*) Bucket : *Bucket;
}