From 00f32752f7d0b193c6788691c3cf0b76457a044d Mon Sep 17 00:00:00 2001 From: Mehdi Goli Date: Thu, 28 Nov 2019 10:08:54 +0000 Subject: [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 --- unsupported/test/cxx11_tensor_forced_eval_sycl.cpp | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'unsupported/test/cxx11_tensor_forced_eval_sycl.cpp') diff --git a/unsupported/test/cxx11_tensor_forced_eval_sycl.cpp b/unsupported/test/cxx11_tensor_forced_eval_sycl.cpp index 74d38a644..a55a5ad8a 100644 --- a/unsupported/test/cxx11_tensor_forced_eval_sycl.cpp +++ b/unsupported/test/cxx11_tensor_forced_eval_sycl.cpp @@ -36,8 +36,8 @@ void test_forced_eval_sycl(const Eigen::SyclDevice &sycl_device) { DataType * gpu_in2_data = static_cast(sycl_device.allocate(in2.dimensions().TotalSize()*sizeof(DataType))); DataType * gpu_out_data = static_cast(sycl_device.allocate(out.dimensions().TotalSize()*sizeof(DataType))); - in1 = in1.random() + in1.constant(10.0f); - in2 = in2.random() + in2.constant(10.0f); + in1 = in1.random() + in1.constant(static_cast(10.0f)); + in2 = in2.random() + in2.constant(static_cast(10.0f)); // creating TensorMap from tensor Eigen::TensorMap> gpu_in1(gpu_in1_data, tensorRange); @@ -72,5 +72,6 @@ template void tensorForced_evalperDev EIGEN_DECLARE_TEST(cxx11_tensor_forced_eval_sycl) { for (const auto& device :Eigen::get_sycl_supported_devices()) { CALL_SUBTEST(tensorForced_evalperDevice(device)); + CALL_SUBTEST(tensorForced_evalperDevice(device)); } } -- cgit v1.2.3