[SYCL] Rebasing the SYCL support branch on top of the Einge upstream master branch.

* Unifying all loadLocalTile from lhs and rhs to an extract_block function.
* Adding get_tensor operation which was missing in TensorContractionMapper.
* Adding the -D method missing from cmake for Disable_Skinny Contraction operation.
* Wrapping all the indices in TensorScanSycl into Scan parameter struct.
* Fixing typo in Device SYCL
* Unifying load to private register for tall/skinny no shared
* Unifying load to vector tile for tensor-vector/vector-tensor operation
* Removing all the LHS/RHS class for extracting data from global
* Removing Outputfunction from TensorContractionSkinnyNoshared.
* Combining the local memory version of tall/skinny and normal tensor contraction into one kernel.
* Combining the no-local memory version of tall/skinny and normal tensor contraction into one kernel.
* Combining General Tensor-Vector and VectorTensor contraction into one kernel.
* Making double buffering optional for Tensor contraction when local memory is version is used.
* Modifying benchmark to accept custom Reduction Sizes
* Disabling AVX optimization for SYCL backend on the host to allow SSE optimization to the host
* Adding Test for SYCL
* Modifying SYCL CMake

5 files changed, 117 insertions, 0 deletions

diff --git a/unsupported/doc/Overview.dox b/unsupported/doc/Overview.dox
index 45464a545..bae51dcf6 100644
--- a/unsupported/doc/Overview.dox
+++ b/unsupported/doc/Overview.dox
@@ -11,6 +11,8 @@ Click on the \e Modules tab at the top of this page to get a list of all unsuppo
 
 Don't miss the <a href="../index.html">official Eigen documentation</a>.
 
+ \subpage SYCL_EIGEN "SYCL backend for Eigen"
+
 */
 
 /*
@@ -26,3 +28,4 @@ subject to be included in %Eigen in the future.
 /// \internal \brief Namespace containing low-level routines from the %Eigen library.
 namespace internal {}
 }
+
diff --git a/unsupported/doc/SYCL.dox b/unsupported/doc/SYCL.dox
new file mode 100644
index 000000000..2295adf21
--- /dev/null
+++ b/unsupported/doc/SYCL.dox
@@ -0,0 +1,9 @@
+/** \page SYCL_EIGEN Eigen SYCL Backend
+
+Useful information for Eigen SYCL Backend:
+
+- <a href="https://developer.codeplay.com/computecppce/latest/getting-started-with-eigen">Getting Started with Eigen</a> 
+
+- <a href="https://developer.codeplay.com/computecppce/latest/options-for-building-eigen-sycl">Options for Building Eigen SYCL</a>  
+
+*/
diff --git a/unsupported/doc/examples/CMakeLists.txt b/unsupported/doc/examples/CMakeLists.txt
index bee2b8ad4..7bb67736c 100644
--- a/unsupported/doc/examples/CMakeLists.txt
+++ b/unsupported/doc/examples/CMakeLists.txt
@@ -18,3 +18,7 @@ foreach(example_src ${examples_SRCS})
   )
   add_dependencies(unsupported_examples example_${example})
 endforeach(example_src)
+
+if(EIGEN_TEST_SYCL)
+  add_subdirectory(SYCL)
+endif(EIGEN_TEST_SYCL)
diff --git a/unsupported/doc/examples/SYCL/CMakeLists.txt b/unsupported/doc/examples/SYCL/CMakeLists.txt
new file mode 100644
index 000000000..bef4f1925
--- /dev/null
+++ b/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)
diff --git a/unsupported/doc/examples/SYCL/CwiseMul.cpp b/unsupported/doc/examples/SYCL/CwiseMul.cpp
new file mode 100644
index 000000000..31eb104c6
--- /dev/null
+++ b/unsupported/doc/examples/SYCL/CwiseMul.cpp
@@ -0,0 +1,63 @@
+#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");
+}
\ No newline at end of file