[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

1 files changed, 101 insertions, 28 deletions

diff --git a/unsupported/test/CMakeLists.txt b/unsupported/test/CMakeLists.txt
index 3d9ac9263..9db965ad8 100644
--- a/unsupported/test/CMakeLists.txt
+++ b/unsupported/test/CMakeLists.txt
@@ -111,40 +111,113 @@ ei_add_test(special_functions)
 
 if(EIGEN_TEST_CXX11)
   if(EIGEN_TEST_SYCL)
+    set(EIGEN_SYCL ON)
+    # Forward CMake options as preprocessor definitions
+    if(EIGEN_SYCL_USE_DEFAULT_SELECTOR)
+      add_definitions(-DEIGEN_SYCL_USE_DEFAULT_SELECTOR=${EIGEN_SYCL_USE_DEFAULT_SELECTOR})
+    endif()
+    if(EIGEN_SYCL_NO_LOCAL_MEM)
+      add_definitions(-DEIGEN_SYCL_NO_LOCAL_MEM=${EIGEN_SYCL_NO_LOCAL_MEM})
+    endif()
+    if(EIGEN_SYCL_LOCAL_MEM)
+      add_definitions(-DEIGEN_SYCL_LOCAL_MEM=${EIGEN_SYCL_LOCAL_MEM})
+    endif()
+    if(EIGEN_SYCL_MAX_GLOBAL_RANGE)
+      add_definitions(-DEIGEN_SYCL_MAX_GLOBAL_RANGE=${EIGEN_SYCL_MAX_GLOBAL_RANGE})
+    endif()
+    if(EIGEN_SYCL_LOCAL_THREAD_DIM0)
+      add_definitions(-DEIGEN_SYCL_LOCAL_THREAD_DIM0=${EIGEN_SYCL_LOCAL_THREAD_DIM0})
+    endif()
+    if(EIGEN_SYCL_LOCAL_THREAD_DIM1)
+      add_definitions(-DEIGEN_SYCL_LOCAL_THREAD_DIM1=${EIGEN_SYCL_LOCAL_THREAD_DIM1})
+    endif()
+    if(EIGEN_SYCL_REG_M)
+      add_definitions(-DEIGEN_SYCL_REG_M=${EIGEN_SYCL_REG_M})
+    endif()
+    if(EIGEN_SYCL_REG_N)
+      add_definitions(-DEIGEN_SYCL_REG_N=${EIGEN_SYCL_REG_N})
+    endif()
+    if(EIGEN_SYCL_USE_PROGRAM_CLASS)
+      add_definitions(-DEIGEN_SYCL_USE_PROGRAM_CLASS=${EIGEN_SYCL_USE_PROGRAM_CLASS})
+    endif()
+    if(EIGEN_SYCL_ASYNC_EXECUTION)
+      add_definitions(-DEIGEN_SYCL_ASYNC_EXECUTION=${EIGEN_SYCL_ASYNC_EXECUTION})
+    endif()
+    if(EIGEN_SYCL_DISABLE_SKINNY)
+      add_definitions(-DEIGEN_SYCL_DISABLE_SKINNY=${EIGEN_SYCL_DISABLE_SKINNY})
+    endif()
+    if(EIGEN_SYCL_DISABLE_DOUBLE_BUFFER)
+    add_definitions(-DEIGEN_SYCL_DISABLE_DOUBLE_BUFFER=${EIGEN_SYCL_DISABLE_DOUBLE_BUFFER})
+  endif()
+    if(EIGEN_SYCL_DISABLE_RANK1)
+      add_definitions(-DEIGEN_SYCL_DISABLE_RANK1=${EIGEN_SYCL_DISABLE_RANK1})
+    endif()
+    if(EIGEN_SYCL_DISABLE_SCALAR)
+      add_definitions(-DEIGEN_SYCL_DISABLE_SCALAR=${EIGEN_SYCL_DISABLE_SCALAR})
+    endif()
+    if(EIGEN_SYCL_DISABLE_GEMV)
+      add_definitions(-DEIGEN_SYCL_DISABLE_GEMV=${EIGEN_SYCL_DISABLE_GEMV})
+    endif()
+    if(EIGEN_SYCL_DISABLE_ARM_GPU_CACHE_OPTIMISATION)
+      add_definitions(-DEIGEN_SYCL_DISABLE_ARM_GPU_CACHE_OPTIMISATION=${EIGEN_SYCL_DISABLE_ARM_GPU_CACHE_OPTIMISATION})
+    endif()
+
     if(EIGEN_SYCL_TRISYCL)
       set(CMAKE_CXX_STANDARD 14)
       set(STD_CXX_FLAG "-std=c++1z")
     else()
-      # It should be safe to always run these tests as there is some fallback code for
-      # older compiler that don't support cxx11.
-      # This is already set if EIGEN_TEST_CXX11 is enabled:
-      # set(CMAKE_CXX_STANDARD 11)
-      # set(STD_CXX_FLAG "-std=c++11")
+      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()
 
-    ei_add_test_sycl(cxx11_tensor_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_forced_eval_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_broadcast_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_device_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_reduction_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_morphing_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_shuffling_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_padding_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_builtins_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_contract_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_concatenation_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_reverse_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_convolution_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_striding_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_chipping_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_layout_swap_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_inflation_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_generator_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_patch_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_image_patch_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_volume_patch_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_argmax_sycl ${STD_CXX_FLAG})
-    ei_add_test_sycl(cxx11_tensor_custom_op_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_image_op_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_math_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_forced_eval_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_broadcast_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_device_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_reduction_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_morphing_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_shuffling_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_padding_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_builtins_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_contract_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_concatenation_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_reverse_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_convolution_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_striding_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_chipping_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_layout_swap_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_inflation_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_random_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_generator_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_patch_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_image_patch_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_volume_patch_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_argmax_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_custom_op_sycl ${STD_CXX_FLAG})
+    ei_add_test(cxx11_tensor_scan_sycl ${STD_CXX_FLAG})
+    set(EIGEN_SYCL OFF)
   endif()
 
   ei_add_test(cxx11_eventcount "-pthread" "${CMAKE_THREAD_LIBS_INIT}")