Fix stale device global initializers on RTC program reuse

Prevent stale MDeviceGlobalInitializers entries from colliding with new entries
when program handles are reused in RuntimeCompiled kernel loops. Implement
explicit cleanup via removeDeviceGlobalInitializer() during program teardown.

Author: kweronsx

sycl/source/detail/context_impl.cpp

@@ -262,6 +262,31 @@ void context_impl::addDeviceGlobalInitializer(
   }
 }
 
+void context_impl::removeDeviceGlobalInitializer(
+    ur_program_handle_t Program, const RTDeviceBinaryImage *BinImage) {
+  std::lock_guard<std::mutex> Lock(MDeviceGlobalInitializersMutex);
+
+  for (auto It = MDeviceGlobalInitializers.begin();
+       It != MDeviceGlobalInitializers.end();) {
+    const bool ProgramMatches = It->first.first == Program;
+    const bool ImageMatches = !BinImage || It->second.MBinImage == BinImage;
+
+    if (!ProgramMatches || !ImageMatches) {
+      ++It;
+      continue;
+    }
+
+    {
+      std::lock_guard<std::mutex> InitLock(It->second.MDeviceGlobalInitMutex);
+      if (!It->second.MDeviceGlobalsFullyInitialized)
+        --MDeviceGlobalNotInitializedCnt;
+      It->second.ClearEvents(getAdapter());
+    }
+
+    It = MDeviceGlobalInitializers.erase(It);
+  }
+}
+
 std::vector<ur_event_handle_t> context_impl::initializeDeviceGlobals(
     ur_program_handle_t NativePrg, queue_impl &QueueImpl,
     detail::kernel_bundle_impl *KernelBundleImplPtr) {

sycl/source/detail/context_impl.hpp

@@ -194,6 +194,12 @@ class context_impl : public std::enable_shared_from_this<context_impl> {
                                   devices_range Devs,
                                   const RTDeviceBinaryImage *BinImage);
 
+  /// Removes device global initializers for a program. If BinImage is not
+  /// null, only initializers associated with that image are removed.
+  void
+  removeDeviceGlobalInitializer(ur_program_handle_t Program,
+                                const RTDeviceBinaryImage *BinImage = nullptr);
+
   /// Initializes device globals for a program on the associated queue.
   std::vector<ur_event_handle_t>
   initializeDeviceGlobals(ur_program_handle_t NativePrg, queue_impl &QueueImpl,

sycl/source/detail/program_manager/program_manager.cpp

@@ -1846,6 +1846,7 @@ void ProgramManager::removeImages(sycl_device_binaries DeviceBinary) {
         auto CurIt = It++;
         if (CurIt->second.second == Img) {
           if (auto ContextImpl = CurIt->second.first.lock()) {
+            ContextImpl->removeDeviceGlobalInitializer(CurIt->first, Img);
             ContextImpl->getKernelProgramCache().removeAllRelatedEntries(
                 Img->getImageID());
           }