Fix GPU interpolation cache lifetime leaks

AMSS_NCKU_source/Block.C

@@ -13,6 +13,7 @@ using namespace std;
 #include "misc.h"
 #ifdef USE_GPU
 #include "bssn_gpu.h"
+#include "bssn_cuda_ops.h"
 #endif
 
 Block::Block(int DIM, int *shapei, double *bboxi, int ranki, int ingfsi, int fngfsi, int levi, const int cgpui) : rank(ranki), ingfs(ingfsi), fngfs(fngfsi), lev(levi), cgpu(cgpui)
@@ -106,6 +107,8 @@ Block::~Block()
   {
 #ifdef USE_GPU
     bssn_gpu_clear_cached_device_buffers();
+    bssn_cuda_release_rk4_caches();
+    bssn_cuda_release_interp_caches();
 #endif
     for (int i = 0; i < dim; i++)
       delete[] X[i];