[llvm] [OFFLOAD] Add support for indexed per-thread containers (PR #164263)

[Alex Duran via llvm-commits]

================
@@ -14,26 +14,106 @@
 #define OFFLOAD_PERTHREADTABLE_H
 
 #include <list>
+#include <llvm/ADT/SmallVector.h>
+#include <llvm/Support/Error.h>
 #include <memory>
 #include <mutex>
+#include <type_traits>
+
+template <typename ObjectType> struct PerThread {
+  struct PerThreadData {
+    std::unique_ptr<ObjectType> ThreadEntry;
+  };
+
+  std::mutex Mutex;
+  llvm::SmallVector<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() {
+    assert(Mutex.try_lock() && (Mutex.unlock(), true) &&
+           "Cannot be deleted while other threads are adding entries");
+    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() {
+    PerThreadData &ThreadData = getThreadData();
+    if (ThreadData.ThreadEntry)
+      return *ThreadData.ThreadEntry;
+    ThreadData.ThreadEntry = std::make_unique<ObjectType>();
+    return *ThreadData.ThreadEntry;
+  }
+
+public:
+  ObjectType &get() { return getThreadEntry(); }
+
+  template <class ClearFuncTy> void clear(ClearFuncTy ClearFunc) {
+    assert(Mutex.try_lock() && (Mutex.unlock(), true) &&
+           "Clear cannot be called while other threads are adding entries");
+    for (std::shared_ptr<PerThreadData> ThreadData : ThreadDataList) {
+      if (!ThreadData->ThreadEntry)
+        continue;
+      ClearFunc(*ThreadData->ThreadEntry);
+    }
+    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
 // thread_local variable.
 // 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;
----------------
adurang wrote:

We had some static analyzer tools complaining about using size not being safe. It also allows to avoid to create the containers just to check if there are no elements. So, for example if no interop construct is used none of associated stuff to keep the objects is done.

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