Device support for TA::Tensor

examples/device/CMakeLists.txt

@@ -25,7 +25,7 @@
 
 if(TILEDARRAY_HAS_CUDA OR TILEDARRAY_HAS_HIP)
 
-    foreach(_exec device_task ta_dense_device ta_cc_abcd_device ta_vector_device ta_reduce_device)
+    foreach(_exec device_task ta_dense_device ta_dense_um_tensor ta_cc_abcd_device ta_vector_device ta_reduce_device)
 
         # Add executable
         add_ta_executable(${_exec} "${_exec}.cpp" "tiledarray")

examples/device/device_task.cpp

@@ -3,13 +3,13 @@
 //
 
 #include <TiledArray/device/blas.h>
-#include <TiledArray/device/btas_um_tensor.h>
+#include <TiledArray/device/um_tensor.h>
 #include <TiledArray/device/device_task_fn.h>
 
 #include <tiledarray.h>
 
 using value_type = double;
-using tensor_type = TiledArray::btasUMTensorVarray<value_type>;
+using tensor_type = TiledArray::UMTensor<value_type>;
 using tile_type = TiledArray::Tile<tensor_type>;
 
 /// verify the elements in tile is equal to value
@@ -31,21 +31,17 @@ void verify(const tile_type& tile, value_type value, std::size_t index) {
 tile_type scale(const tile_type& arg, value_type a,
                 TiledArray::device::Stream stream, std::size_t index) {
   /// make result Tensor
-  using Storage = typename tile_type::tensor_type::storage_type;
-  Storage result_storage;
   auto result_range = arg.range();
-  TiledArray::make_device_storage(result_storage, arg.size(), stream);
 
-  typename tile_type::tensor_type result(std::move(result_range),
-                                         std::move(result_storage));
+  typename tile_type::tensor_type result(std::move(result_range));
 
   /// copy the original Tensor
   auto& queue = TiledArray::BLASQueuePool::queue(stream);
 
   blas::copy(result.size(), arg.data(), 1,
-             TiledArray::device_data(result.storage()), 1, queue);
+             TiledArray::device_data(result), 1, queue);
 
-  blas::scal(result.size(), a, TiledArray::device_data(result.storage()), 1,
+  blas::scal(result.size(), a, TiledArray::device_data(result), 1,
              queue);
 
   //  std::stringstream stream_str;

examples/device/ta_cc_abcd_device.cpp

@@ -17,7 +17,7 @@
  *
  */
 
-#include <TiledArray/device/btas_um_tensor.h>
+#include <TiledArray/device/um_tensor.h>
 #include <TiledArray/version.h>
 #include <tiledarray.h>
 #include <iostream>
@@ -185,8 +185,7 @@ void cc_abcd(TA::World& world, const TA::TiledRange1& trange_occ,
   const double n_gflop =
       flops_per_fma * std::pow(n_occ, 2) * std::pow(n_uocc, 4) / 1e9;
 
-  using deviceTile =
-      btas::Tensor<T, TA::Range, TiledArray::device_um_btas_varray<T>>;
+  using deviceTile = TA::UMTensor<T>;
   using deviceMatrix = TA::DistArray<TA::Tile<deviceTile>>;
 
   // Construct tensors