[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, 2 insertions, 2 deletions

diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorMorphing.h b/unsupported/Eigen/CXX11/src/Tensor/TensorMorphing.h
index 700337539..d3628f94e 100644
--- a/unsupported/Eigen/CXX11/src/Tensor/TensorMorphing.h
+++ b/unsupported/Eigen/CXX11/src/Tensor/TensorMorphing.h
@@ -421,7 +421,7 @@ template <typename Index, typename Device, bool BlockAccess> struct MemcpyTrigge
 #ifdef EIGEN_USE_GPU
 template <typename Index, bool BlockAccess> struct MemcpyTriggerForSlicing<Index, GpuDevice, BlockAccess>  {
   EIGEN_DEVICE_FUNC MemcpyTriggerForSlicing(const GpuDevice&) { }
-  EIGEN_DEVICE_FUNC bool operator ()(Index total, Index contiguous) const { return contiguous > 4*1024*1024; }
+  EIGEN_DEVICE_FUNC bool operator ()(Index, Index contiguous) const { return contiguous > 4*1024*1024; }
 };
 #endif
 
@@ -430,7 +430,7 @@ template <typename Index, bool BlockAccess> struct MemcpyTriggerForSlicing<Index
 #ifdef EIGEN_USE_SYCL
 template <typename Index, bool BlockAccess> struct MemcpyTriggerForSlicing<Index, Eigen::SyclDevice, BlockAccess>  {
   EIGEN_DEVICE_FUNC MemcpyTriggerForSlicing(const SyclDevice&) { }
-  EIGEN_DEVICE_FUNC bool operator ()(Index total, Index contiguous) const { return contiguous > 4*1024*1024; }
+  EIGEN_DEVICE_FUNC bool operator ()(Index, Index contiguous) const { return contiguous > 4*1024*1024; }
 };
 #endif