TensorFlow内存管理bfc算法实例

static const int kInvalidChunkHandle = -1;
...
struct Chunk {
  size_t size = 0; // Full size of buffer.

  // We sometimes give chunks that are larger than needed to reduce
  // fragmentation. requested_size keeps track of what the client
  // actually wanted so we can understand whether our splitting
  // strategy is efficient.
  size_t requested_size = 0;

  // allocation_id is set to -1 when the chunk is not in use. It is assigned a
  // value greater than zero before the chunk is returned from
  // AllocateRaw, and this value is unique among values assigned by
  // the parent allocator.
  int64 allocation_id = -1;
  void* ptr = nullptr; // pointer to granted subbuffer.

  // If not kInvalidChunkHandle, the memory referred to by 'prev' is directly
  // preceding the memory used by this chunk. E.g., It should start
  // at 'ptr - prev->size'
  ChunkHandle prev = kInvalidChunkHandle;

  // If not kInvalidChunkHandle, the memory referred to by 'next' is directly
  // following the memory used by this chunk. E.g., It should be at
  // 'ptr + size'
  ChunkHandle next = kInvalidChunkHandle;

  // What bin are we in"htmlcode">

// A Bin is a collection of similar-sized free chunks.
struct Bin {
  // All chunks in this bin have >= bin_size memory.
  size_t bin_size = 0;

  struct ChunkComparator {
    explicit ChunkComparator(BFCAllocator* allocator)
      : allocator_(allocator) {}
    // Sort first by size and then use pointer address as a tie breaker.
    bool operator()(const ChunkHandle ha,
            const ChunkHandle hb) const NO_THREAD_SAFETY_ANALYSIS {
      const Chunk* a = allocator_->ChunkFromHandle(ha);
      const Chunk* b = allocator_->ChunkFromHandle(hb);
      if (a->size != b->size) {
        return a->size < b->size;
      }
      return a->ptr < b->ptr;
    }

    private:
      BFCAllocator* allocator_; // The parent allocator
  };

  typedef std::set<ChunkHandle, ChunkComparator> FreeChunkSet;
  // List of free chunks within the bin, sorted by chunk size.
  // Chunk * not owned.
  FreeChunkSet free_chunks;
  Bin(BFCAllocator* allocator, size_t bs)
    : bin_size(bs), free_chunks(ChunkComparator(allocator)) {}
};



AllocationRegion
AllocationRegion给一个连续的内存区域做指针到ChunkHandle的映射。
RegionManager
RegionManager聚集了一个或多个AllocationRegion，并提供一个从指针到基础ChunkHandle的间接层，这个间接层可在多个不连续的内存区域进行分配。
3. 分配大小
将每次分配的内存大小调整为kMinAllocationSize的N倍，这样所有内存地址都是很好地按字节对齐了。


// kMinAllocationSize = 256
static const size_t kMinAllocationBits = 8;
static const size_t kMinAllocationSize = 1 << kMinAllocationBits;
...
size_t BFCAllocator::RoundedBytes(size_t bytes) {
  size_t rounded_bytes =
    (kMinAllocationSize *
    ((bytes + kMinAllocationSize - 1) / kMinAllocationSize));
  DCHECK_EQ(size_t{0}, rounded_bytes % kMinAllocationSize);
  return rounded_bytes;
}


4. 初始化bin


typedef int BinNum;
static const int kInvalidBinNum = -1;
static const int kNumBins = 21;
...
// 二进制2^8往左移0，1，2位
// (static_cast<size_t>(256) << 0) = 256
// (static_cast<size_t>(256) << 1) = 512
// (static_cast<size_t>(256) << 2) = 1024
size_t BinNumToSize(BinNum index) {
  return static_cast<size_t>(256) << index;
}
...
char bins_space_[sizeof(Bin) * kNumBins];
// Map from bin size to Bin
Bin* BinFromIndex(BinNum index) {
  return reinterpret_cast<Bin*>(&(bins_space_[index * sizeof(Bin)]));
}
...
// We create bins to fit all possible ranges that cover the
// memory_limit_ starting from allocations up to 256 bytes to
// allocations up to (and including) the memory limit.
for (BinNum b = 0; b < kNumBins; b++) {
  size_t bin_size = BinNumToSize(b);
  VLOG(1) << "Creating bin of max chunk size "
      << strings::HumanReadableNumBytes(bin_size);
  new (BinFromIndex(b)) Bin(this, bin_size);
  CHECK_EQ(BinForSize(bin_size), BinFromIndex(b));
  CHECK_EQ(BinForSize(bin_size + 255), BinFromIndex(b));
  CHECK_EQ(BinForSize(bin_size * 2 - 1), BinFromIndex(b));
  if (b + 1 < kNumBins) {
    CHECK_NE(BinForSize(bin_size * 2), BinFromIndex(b));
  }
}


5. 查找bin


// 求属于第几个bin
BinNum BinNumForSize(size_t bytes) {
  uint64 v = std::max<size_t>(bytes, 256)  kMinAllocationBits;
  int b = std::min(kNumBins - 1, Log2FloorNonZero(v));
  return b;
}
// 最高位非零的二进制位数，eg: 0001 0101B 为5
inline int Log2FloorNonZero(uint64 n) {
#if defined(__GNUC__)
  return 63 ^ __builtin_clzll(n);
#elif defined(PLATFORM_WINDOWS)
  unsigned long index;
  _BitScanReverse64(&index, n);
  return index;
#else
  int r = 0;
  while (n > 0) {
    r++;
    n = 1;
  }
  return r;
#endif
}


6. 查找Chunk


// 先加锁
mutex_lock l(lock_);
void* ptr = FindChunkPtr(bin_num, rounded_bytes, num_bytes);
if (ptr != nullptr) {
  return ptr;
}
// FindChunkPtr函数内部
void* BFCAllocator::FindChunkPtr(BinNum bin_num, size_t rounded_bytes,
                 size_t num_bytes) {
  // First identify the first bin that could satisfy rounded_bytes.
  for (; bin_num < kNumBins; bin_num++) {
    // Start searching from the first bin for the smallest chunk that fits
    // rounded_bytes.
    Bin* b = BinFromIndex(bin_num);
    for (auto citer = b->free_chunks.begin(); citer != b->free_chunks.end();
        ++citer) {
      // 从之前得到的Bin索引开始，查找合适的空闲Chunk：
      const BFCAllocator::ChunkHandle h = (*citer);
      BFCAllocator::Chunk* chunk = ChunkFromHandle(h);
      DCHECK(!chunk->in_use());
      if (chunk->size >= rounded_bytes) {
        // We found an existing chunk that fits us that wasn't in use, so remove
        // it from the free bin structure prior to using.
        RemoveFreeChunkIterFromBin(&b->free_chunks, citer);

        // If we can break the size of the chunk into two reasonably
        // large pieces, do so.
        //
        // TODO(vrv): What should be the criteria when deciding when
        // to split"Returning: " << chunk->ptr;
        if (VLOG_IS_ON(4)) {
          LOG(INFO) << "A: " << RenderOccupancy();
        }
        return chunk->ptr;
      }
    }
  }
  return nullptr;
}



7. 拆分Chunk
如果Chunk的大小大于等于申请内存大小的2倍，那么将该Chunk拆分成2个：第一个Chunk的大小等于申请内存大小，第二个Chunk作为它的直接后继。


if (chunk->size >= rounded_bytes * 2) {
  SplitChunk(h, rounded_bytes);
  chunk = ChunkFromHandle(h); // Update chunk pointer in case it moved
}

void BFCAllocator::SplitChunk(BFCAllocator::ChunkHandle h, size_t num_bytes) {
  // Allocate the new chunk before we do any ChunkFromHandle
  ChunkHandle h_new_chunk = AllocateChunk();

  Chunk* c = ChunkFromHandle(h);
  CHECK(!c->in_use() && (c->bin_num == kInvalidBinNum));

  // Create a new chunk starting num_bytes after c
  BFCAllocator::Chunk* new_chunk = ChunkFromHandle(h_new_chunk);
  new_chunk->ptr = static_cast<void*>(static_cast<char*>(c->ptr) + num_bytes);
  region_manager_.set_handle(new_chunk->ptr, h_new_chunk);

  // Set the new sizes of the chunks.
  new_chunk->size = c->size - num_bytes;
  c->size = num_bytes;

  // The new chunk is not in use.
  new_chunk->allocation_id = -1;

  // Maintain the pointers.
  // c <-> c_neighbor becomes
  // c <-> new_chunk <-> c_neighbor
  BFCAllocator::ChunkHandle h_neighbor = c->next;
  new_chunk->prev = h;
  new_chunk->next = h_neighbor;
  c->next = h_new_chunk;
  if (h_neighbor != kInvalidChunkHandle) {
    Chunk* c_neighbor = ChunkFromHandle(h_neighbor);
    c_neighbor->prev = h_new_chunk;
  }

  // Add the newly free chunk to the free bin.
  InsertFreeChunkIntoBin(h_new_chunk);
}



8. 回收chunk
加锁，获得ChunkHandle


mutex_lock l(lock_);
BFCAllocator::ChunkHandle h = region_manager_.get_handle(ptr);
FreeAndMaybeCoalesce(h);


FreeAndMaybeCoalesce


void BFCAllocator::FreeAndMaybeCoalesce(BFCAllocator::ChunkHandle h) {
  Chunk* c = ChunkFromHandle(h);
  CHECK(c->in_use() && (c->bin_num == kInvalidBinNum));

  // Mark the chunk as no longer in use
  c->allocation_id = -1;

  // Updates the stats.
  stats_.bytes_in_use -= c->size;

  // This chunk is no longer in-use, consider coalescing the chunk
  // with adjacent chunks.
  ChunkHandle chunk_to_reassign = h;

  // If the next chunk is free, coalesce the two
  if (c->next != kInvalidChunkHandle) {
    Chunk* cnext = ChunkFromHandle(c->next);
    if (!cnext->in_use()) {
    //   VLOG(8) << "Chunk at " << cnext->ptr << " merging with c " <<
    //   c->ptr;

    chunk_to_reassign = h;

    // Deletes c->next
    RemoveFreeChunkFromBin(c->next);
    Merge(h, ChunkFromHandle(h)->next);
    }
  }

  // If the previous chunk is free, coalesce the two
  c = ChunkFromHandle(h);
  if (c->prev != kInvalidChunkHandle) {
    Chunk* cprev = ChunkFromHandle(c->prev);
    if (!cprev->in_use()) {
    //   VLOG(8) << "Chunk at " << c->ptr << " merging into c->prev "
    //    << cprev->ptr;

    chunk_to_reassign = c->prev;

    // Deletes c
    RemoveFreeChunkFromBin(c->prev);
    Merge(ChunkFromHandle(h)->prev, h);
    c = ChunkFromHandle(h);
    }
  }

  InsertFreeChunkIntoBin(chunk_to_reassign);
}



Merge


// Merges h1 and h2 when Chunk(h1)->next is h2 and Chunk(h2)->prev is c1.
// We merge Chunk(h2) into Chunk(h1).
void BFCAllocator::Merge(BFCAllocator::ChunkHandle h1,
             BFCAllocator::ChunkHandle h2) {
  Chunk* c1 = ChunkFromHandle(h1);
  Chunk* c2 = ChunkFromHandle(h2);
  // We can only merge chunks that are not in use.
  CHECK(!c1->in_use() && !c2->in_use());

  // c1's prev doesn't change, still points to the same ptr, and is
  // still not in use.

  // Fix up neighbor pointers
  //
  // c1 <-> c2 <-> c3 should become
  // c1 <-> c3

  BFCAllocator::ChunkHandle h3 = c2->next;
  c1->next = h3;
  CHECK(c2->prev == h1);
  if (h3 != kInvalidChunkHandle) {
    BFCAllocator::Chunk* c3 = ChunkFromHandle(h3);
    c3->prev = h1;
  }

  // Set the new size
  c1->size += c2->size;

  DeleteChunk(h2);
}



以上这篇TensorFlow内存管理bfc算法实例就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。