Move eigen to third party (#282)

* remove useless statement

* Add eigen to third_party dir

* remove reducdant lines

third_party/eigen/unsupported/doc/examples/SYCL/CMakeLists.txt

@@ -0,0 +1,38 @@
+FILE(GLOB examples_SRCS "*.cpp")
+
+set(EIGEN_SYCL ON)
+list(APPEND CMAKE_EXE_LINKER_FLAGS -pthread)
+if(EIGEN_SYCL_TRISYCL)
+  set(CMAKE_CXX_STANDARD 14)
+  set(STD_CXX_FLAG "-std=c++1z")
+else(EIGEN_SYCL_TRISYCL)
+  if(MSVC)
+    # Set the host and device compilers C++ standard to C++14. On Windows setting this to C++11
+    # can cause issues with the ComputeCpp device compiler parsing Visual Studio Headers.
+    set(CMAKE_CXX_STANDARD 14)
+    list(APPEND COMPUTECPP_USER_FLAGS -DWIN32)
+  else()
+    set(CMAKE_CXX_STANDARD 11)
+    list(APPEND COMPUTECPP_USER_FLAGS -Wall)
+  endif()
+  # The following flags are not supported by Clang and can cause warnings
+  # if used with -Werror so they are removed here.
+  if(COMPUTECPP_USE_COMPILER_DRIVER)
+    set(CMAKE_CXX_COMPILER ${ComputeCpp_DEVICE_COMPILER_EXECUTABLE})
+    string(REPLACE "-Wlogical-op" "" CMAKE_CXX_FLAGS ${CMAKE_CXX_FLAGS})
+    string(REPLACE "-Wno-psabi" "" CMAKE_CXX_FLAGS ${CMAKE_CXX_FLAGS})
+    string(REPLACE "-ansi" "" CMAKE_CXX_FLAGS ${CMAKE_CXX_FLAGS})
+  endif()
+  list(APPEND COMPUTECPP_USER_FLAGS
+      -DEIGEN_NO_ASSERTION_CHECKING=1
+      -no-serial-memop
+      -Xclang
+      -cl-mad-enable)
+endif(EIGEN_SYCL_TRISYCL)
+
+FOREACH(example_src ${examples_SRCS})
+  GET_FILENAME_COMPONENT(example ${example_src} NAME_WE)
+  ei_add_test_internal(${example} example_${example})
+  ADD_DEPENDENCIES(unsupported_examples example_${example})
+ENDFOREACH(example_src)
+set(EIGEN_SYCL OFF)

third_party/eigen/unsupported/doc/examples/SYCL/CwiseMul.cpp

@@ -0,0 +1,74 @@
+#include <iostream>
+#define EIGEN_USE_SYCL
+#include <unsupported/Eigen/CXX11/Tensor>
+
+using Eigen::array;
+using Eigen::SyclDevice;
+using Eigen::Tensor;
+using Eigen::TensorMap;
+
+int main() {
+  using DataType = float;
+  using IndexType = int64_t;
+  constexpr auto DataLayout = Eigen::RowMajor;
+
+  auto devices = Eigen::get_sycl_supported_devices();
+  const auto device_selector = *devices.begin();
+  Eigen::QueueInterface queueInterface(device_selector);
+  auto sycl_device = Eigen::SyclDevice(&queueInterface);
+
+  // create the tensors to be used in the operation
+  IndexType sizeDim1 = 3;
+  IndexType sizeDim2 = 3;
+  IndexType sizeDim3 = 3;
+  array<IndexType, 3> tensorRange = {{sizeDim1, sizeDim2, sizeDim3}};
+
+  // initialize the tensors with the data we want manipulate to
+  Tensor<DataType, 3, DataLayout, IndexType> in1(tensorRange);
+  Tensor<DataType, 3, DataLayout, IndexType> in2(tensorRange);
+  Tensor<DataType, 3, DataLayout, IndexType> out(tensorRange);
+
+  // set up some random data in the tensors to be multiplied
+  in1 = in1.random();
+  in2 = in2.random();
+
+  // allocate memory for the tensors
+  DataType* gpu_in1_data = static_cast<DataType*>(
+      sycl_device.allocate(in1.size() * sizeof(DataType)));
+  DataType* gpu_in2_data = static_cast<DataType*>(
+      sycl_device.allocate(in2.size() * sizeof(DataType)));
+  DataType* gpu_out_data = static_cast<DataType*>(
+      sycl_device.allocate(out.size() * sizeof(DataType)));
+
+  //
+  TensorMap<Tensor<DataType, 3, DataLayout, IndexType>> gpu_in1(gpu_in1_data,
+                                                                tensorRange);
+  TensorMap<Tensor<DataType, 3, DataLayout, IndexType>> gpu_in2(gpu_in2_data,
+                                                                tensorRange);
+  TensorMap<Tensor<DataType, 3, DataLayout, IndexType>> gpu_out(gpu_out_data,
+                                                                tensorRange);
+
+  // copy the memory to the device and do the c=a*b calculation
+  sycl_device.memcpyHostToDevice(gpu_in1_data, in1.data(),
+                                 (in1.size()) * sizeof(DataType));
+  sycl_device.memcpyHostToDevice(gpu_in2_data, in2.data(),
+                                 (in2.size()) * sizeof(DataType));
+  gpu_out.device(sycl_device) = gpu_in1 * gpu_in2;
+  sycl_device.memcpyDeviceToHost(out.data(), gpu_out_data,
+                                 (out.size()) * sizeof(DataType));
+  sycl_device.synchronize();
+
+  // print out the results
+  for (IndexType i = 0; i < sizeDim1; ++i) {
+    for (IndexType j = 0; j < sizeDim2; ++j) {
+      for (IndexType k = 0; k < sizeDim3; ++k) {
+        std::cout << "device_out"
+                  << "(" << i << ", " << j << ", " << k
+                  << ") : " << out(i, j, k) << " vs host_out"
+                  << "(" << i << ", " << j << ", " << k
+                  << ") : " << in1(i, j, k) * in2(i, j, k) << "\n";
+      }
+    }
+  }
+  printf("c=a*b Done\n");
+}