diff --git a/openmp/libomptarget/plugins/cuda/src/rtl.cpp b/openmp/libomptarget/plugins/cuda/src/rtl.cpp --- a/openmp/libomptarget/plugins/cuda/src/rtl.cpp +++ b/openmp/libomptarget/plugins/cuda/src/rtl.cpp @@ -19,6 +19,7 @@ #include #include #include +#include #include #include "Debug.h" @@ -224,22 +225,32 @@ size_t Next = 0; /// Mutex to guard the pool. std::mutex Mutex; - /// Pool of resources. + /// Pool of resources. The difference between \p Resources and \p Pool is, + /// when a resource is acquired and released, it is all on \p Resources. When + /// a batch of new resources are needed, they are both added to \p Resources + /// and \p Pool. The reason for this setting is, \p Resources could contain + /// redundant elements because resources are not released, which can cause + /// double free. This setting makes sure that \p Pool always has every + /// resource allocated from the device. std::vector Resources; + std::vector Pool; /// A reference to the corresponding allocator. AllocTy Allocator; /// If `Resources` is used up, we will fill in more resources. It assumes that /// the new size `Size` should be always larger than the current size. bool resize(size_t Size) { + assert(Resources.size() == Pool.size() && "size mismatch"); auto CurSize = Resources.size(); assert(Size > CurSize && "Unexpected smaller size"); + Pool.reserve(Size); Resources.reserve(Size); for (auto I = CurSize; I < Size; ++I) { ElementTy NewItem; int Ret = Allocator.create(NewItem); if (Ret != OFFLOAD_SUCCESS) return false; + Pool.push_back(NewItem); Resources.push_back(NewItem); } return true; @@ -300,8 +311,9 @@ /// Released all stored resources and clear the pool. /// Note: This function is not thread safe. Be sure to guard it if necessary. void clear() noexcept { - for (auto &R : Resources) + for (auto &R : Pool) (void)Allocator.destroy(R); + Pool.clear(); Resources.clear(); } };