devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Clang-format tests, examples, libraries, benchmarks, etc.

Browse Source
This commit is contained in:
Antonio Sánchez
2023-12-05 21:22:55 +00:00
committed by Rasmus Munk Larsen
parent 3252ecc7a4
commit 46e9cdb7fe
876 changed files with 33453 additions and 37795 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
unsupported/doc/examples/SYCL/CwiseMul.cpp
View File

@@ -7,8 +7,7 @@ using Eigen::SyclDevice;
using Eigen::Tensor;
using Eigen::TensorMap;
int main()
{
int main() {
using DataType = float;
using IndexType = int64_t;
constexpr auto DataLayout = Eigen::RowMajor;
@@ -17,7 +16,7 @@ int main()
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;
@@ -25,37 +24,38 @@ int main()
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);
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)));
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));
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.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 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";
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";
}
}
}