diff options
author | Mehdi Goli <mehdi.goli@codeplay.com> | 2019-11-28 10:08:54 +0000 |
---|---|---|
committer | Mehdi Goli <mehdi.goli@codeplay.com> | 2019-11-28 10:08:54 +0000 |
commit | 00f32752f7d0b193c6788691c3cf0b76457a044d (patch) | |
tree | 792e46110f0751ea8802fa9d403d1472d5977ac3 /unsupported/doc/examples/SYCL/CwiseMul.cpp | |
parent | ea51a9eace7e4f0ea839e61eb2df85ccfb94aee8 (diff) |
[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
Diffstat (limited to 'unsupported/doc/examples/SYCL/CwiseMul.cpp')
-rw-r--r-- | unsupported/doc/examples/SYCL/CwiseMul.cpp | 63 |
1 files changed, 63 insertions, 0 deletions
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 |