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_custom_op_sycl.cpp | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'unsupported/test/cxx11_tensor_custom_op_sycl.cpp') diff --git a/unsupported/test/cxx11_tensor_custom_op_sycl.cpp b/unsupported/test/cxx11_tensor_custom_op_sycl.cpp index cc3b02448..d947ead83 100644 --- a/unsupported/test/cxx11_tensor_custom_op_sycl.cpp +++ b/unsupported/test/cxx11_tensor_custom_op_sycl.cpp @@ -80,6 +80,8 @@ static void test_custom_unary_op_sycl(const Eigen::SyclDevice &sycl_device) VERIFY_IS_EQUAL(out(i, j), 0); } } + sycl_device.deallocate(gpu_in1_data); +sycl_device.deallocate(gpu_out_data); } template @@ -147,6 +149,9 @@ static void test_custom_binary_op_sycl(const Eigen::SyclDevice &sycl_device) } } } + sycl_device.deallocate(gpu_in1_data); + sycl_device.deallocate(gpu_in2_data); + sycl_device.deallocate(gpu_out_data); } template void custom_op_perDevice(Dev_selector s){ -- cgit v1.2.3