[OFFLOAD] Add support for indexed per-thread containers

[adurang]

Split from #158900 it adds a PerThreadContainer that can use STL-like indexed containers based on a slightly refactored PerThreadTable.

[llvmbot]

@llvm/pr-subscribers-offload

Author: Alex Duran (adurang)

Changes

Split from #158900 it adds a PerThreadContainer that can use STL-like indexed containers based on a slightly refactored PerThreadTable.

---

Full diff: https://github.com/llvm/llvm-project/pull/164263.diff

2 Files Affected:

• (modified) offload/include/OpenMP/InteropAPI.h (+1-7)
• (modified) offload/include/PerThreadTable.h (+153-2)

diff --git a/offload/include/OpenMP/InteropAPI.h b/offload/include/OpenMP/InteropAPI.h
index 53ac4be2e2e98..c1957d8205839 100644
--- a/offload/include/OpenMP/InteropAPI.h
+++ b/offload/include/OpenMP/InteropAPI.h
@@ -160,17 +160,11 @@ struct InteropTableEntry {
     Interops.push_back(obj);
   }
 
-  template <class ClearFuncTy> void clear(ClearFuncTy f) {
-    for (auto &Obj : Interops) {
-      f(Obj);
-    }
-  }
-
   /// vector interface
   int size() const { return Interops.size(); }
   iterator begin() { return Interops.begin(); }
   iterator end() { return Interops.end(); }
-  iterator erase(iterator it) { return Interops.erase(it); }
+  void clear() { Interops.clear(); }
 };
 
 struct InteropTblTy
diff --git a/offload/include/PerThreadTable.h b/offload/include/PerThreadTable.h
index 45b196171b4c8..2b2327985a78c 100644
--- a/offload/include/PerThreadTable.h
+++ b/offload/include/PerThreadTable.h
@@ -16,6 +16,60 @@
 #include <list>
 #include <memory>
 #include <mutex>
+#include <type_traits>
+
+template <typename ObjectType> struct PerThread {
+  struct PerThreadData {
+    std::unique_ptr<ObjectType> ThreadEntry;
+  };
+
+  std::mutex Mutex;
+  std::list<std::shared_ptr<PerThreadData>> ThreadDataList;
+
+  // define default constructors, disable copy and move constructors
+  PerThread() = default;
+  PerThread(const PerThread &) = delete;
+  PerThread(PerThread &&) = delete;
+  PerThread &operator=(const PerThread &) = delete;
+  PerThread &operator=(PerThread &&) = delete;
+  ~PerThread() {
+    std::lock_guard<std::mutex> Lock(Mutex);
+    ThreadDataList.clear();
+  }
+
+private:
+  PerThreadData &getThreadData() {
+    static thread_local std::shared_ptr<PerThreadData> ThreadData = nullptr;
+    if (!ThreadData) {
+      ThreadData = std::make_shared<PerThreadData>();
+      std::lock_guard<std::mutex> Lock(Mutex);
+      ThreadDataList.push_back(ThreadData);
+    }
+    return *ThreadData;
+  }
+
+protected:
+  ObjectType &getThreadEntry() {
+    auto &ThData = getThreadData();
+    if (ThData.ThEntry)
+      return *ThData.ThEntry;
+    ThData.ThEntry = std::make_unique<ObjectType>();
+    return *ThData.ThEntry;
+  }
+
+public:
+  ObjectType &get() { return getThreadEntry(); }
+
+  template <class F> void clear(F f) {
+    std::lock_guard<std::mutex> Lock(Mutex);
+    for (auto ThData : ThreadDataList) {
+      if (!ThData->ThEntry)
+        continue;
+      f(*ThData->ThEntry);
+    }
+    ThreadDataList.clear();
+  }
+};
 
 // Using an STL container (such as std::vector) indexed by thread ID has
 // too many race conditions issues so we store each thread entry into a
@@ -23,10 +77,32 @@
 // T is the container type used to store the objects, e.g., std::vector,
 // std::set, etc. by each thread. O is the type of the stored objects e.g.,
 // omp_interop_val_t *, ...
-
 template <typename ContainerType, typename ObjectType> struct PerThreadTable {
   using iterator = typename ContainerType::iterator;
 
+  template <typename, typename = std::void_t<>>
+  struct has_iterator : std::false_type {};
+  template <typename T>
+  struct has_iterator<T, std::void_t<typename T::iterator>> : std::true_type {};
+
+  template <typename T, typename = std::void_t<>>
+  struct has_clear : std::false_type {};
+  template <typename T>
+  struct has_clear<T, std::void_t<decltype(std::declval<T>().clear())>>
+      : std::true_type {};
+
+  template <typename T, typename = std::void_t<>>
+  struct has_clearAll : std::false_type {};
+  template <typename T>
+  struct has_clearAll<T, std::void_t<decltype(std::declval<T>().clearAll(1))>>
+      : std::true_type {};
+
+  template <typename, typename = std::void_t<>>
+  struct is_associative : std::false_type {};
+  template <typename T>
+  struct is_associative<T, std::void_t<typename T::mapped_type>>
+      : std::true_type {};
+
   struct PerThreadData {
     size_t NElements = 0;
     std::unique_ptr<ContainerType> ThEntry;
@@ -71,6 +147,11 @@ template <typename ContainerType, typename ObjectType> struct PerThreadTable {
     return ThData.NElements;
   }
 
+  void setNElements(size_t Size) {
+    auto &NElements = getThreadNElements();
+    NElements = Size;
+  }
+
 public:
   void add(ObjectType obj) {
     auto &Entry = getThreadEntry();
@@ -104,11 +185,81 @@ template <typename ContainerType, typename ObjectType> struct PerThreadTable {
     for (auto ThData : ThreadDataList) {
       if (!ThData->ThEntry || ThData->NElements == 0)
         continue;
-      ThData->ThEntry->clear(f);
+      if constexpr (has_clearAll<ContainerType>::value) {
+        ThData->ThEntry->clearAll(f);
+      } else if constexpr (has_iterator<ContainerType>::value &&
+                           has_clear<ContainerType>::value) {
+        for (auto &Obj : *ThData->ThEntry) {
+          if constexpr (is_associative<ContainerType>::value) {
+            f(Obj.second);
+          } else {
+            f(Obj);
+          }
+        }
+        ThData->ThEntry->clear();
+      } else {
+        static_assert(true, "Container type not supported");
+      }
       ThData->NElements = 0;
     }
     ThreadDataList.clear();
   }
 };
 
+template <typename T, typename = std::void_t<>> struct ContainerValueType {
+  using type = typename T::value_type;
+};
+template <typename T>
+struct ContainerValueType<T, std::void_t<typename T::mapped_type>> {
+  using type = typename T::mapped_type;
+};
+
+template <typename ContainerType, size_t reserveSize = 0>
+struct PerThreadContainer
+    : public PerThreadTable<ContainerType,
+                            typename ContainerValueType<ContainerType>::type> {
+
+  // helpers
+  template <typename T, typename = std::void_t<>> struct indexType {
+    using type = typename T::size_type;
+  };
+  template <typename T> struct indexType<T, std::void_t<typename T::key_type>> {
+    using type = typename T::key_type;
+  };
+  template <typename T, typename = std::void_t<>>
+  struct has_resize : std::false_type {};
+  template <typename T>
+  struct has_resize<T, std::void_t<decltype(std::declval<T>().resize(1))>>
+      : std::true_type {};
+
+  template <typename T, typename = std::void_t<>>
+  struct has_reserve : std::false_type {};
+  template <typename T>
+  struct has_reserve<T, std::void_t<decltype(std::declval<T>().reserve(1))>>
+      : std::true_type {};
+
+  using IndexType = typename indexType<ContainerType>::type;
+  using ObjectType = typename ContainerValueType<ContainerType>::type;
+
+  // Get the object for the given index in the current thread
+  ObjectType &get(IndexType Index) {
+    auto &Entry = this->getThreadEntry();
+
+    // specialized code for vector-like containers
+    if constexpr (has_resize<ContainerType>::value) {
+      if (Index >= Entry.size()) {
+        if constexpr (has_reserve<ContainerType>::value && reserveSize > 0) {
+          if (Entry.capacity() < reserveSize)
+            Entry.reserve(reserveSize);
+        }
+        // If the index is out of bounds, try resize the container
+        Entry.resize(Index + 1);
+      }
+    }
+    ObjectType &Ret = Entry[Index];
+    this->setNElements(Entry.size());
+    return Ret;
+  }
+};
+
 #endif

[adurang]

@jhuber6 I fixed the containers, removed most locks and made some cleanup. I also added a new routine that handles deinit with Errors.

About the locking, all the current cases require the fine-grain locking so I'm not sure if it's worth it to add the option I mentioned at this point (but we could do that later).

[adurang]

@kevinsala @jhuber6 @shiltian afaics all comments have been addressed, is there anything else to do here?

[kevinsala]

It's undefined behavior to destroy the mutex while it's locked:

The behavior of a program is undefined if a mutex is destroyed while still owned by any threads, or a thread terminates while owning a mutex.

Given that there is no function to test the mutex, you may use:

assert(M.try_lock() && (M.unlock(), true) && "Cannot ...");