#Create folder; Assume is as $DPCPP_HOME
mkdir $HOME/install
cd $HOME/install

# Build INTEL's LLVM
# get sycl branch
git clone https://github.com/intel/llvm.git -b sycl
cd llvm

# OPTIONAL STEP. Warning LLVM undergoes a lot changes. 
# In case, recent commit did not work, use the below that worked for me
# 082cde6 - (HEAD, origin/sycl, origin/HEAD, sycl) [CI][1/3] Add Ubuntu 22 containers build (#7106) <Pavel Chupin>
git checkout 082cde6

# configure
python ./buildbot/configure.py --cuda -t release --cmake-gen "Unix Makefiles"

# Assuming no error. Build takes 20mins. Get a coffee!
cd build
make sycl-toolchain -j `nproc`
make install

# assumes $HOME/install/llvm installation

#include <sycl/sycl.hpp>

int main() {
  // Creating buffer of 4 ints to be used inside the kernel code
  sycl::buffer<sycl::cl_int, 1> Buffer(4);

  // Creating SYCL queue
  sycl::queue Queue;

  // Size of index space for kernel
  sycl::range<1> NumOfWorkItems{Buffer.size()};

  // Submitting command group(work) to queue
  Queue.submit([&](sycl::handler &cgh) {
    // Getting write only access to the buffer on a device
    auto Accessor = Buffer.get_access<sycl::access::mode::write>(cgh);
    // Executing kernel
    cgh.parallel_for<class FillBuffer>(
        NumOfWorkItems, [=](sycl::id<1> WIid) {
          // Fill buffer with indexes
          Accessor[WIid] = (sycl::cl_int)WIid.get(0);
        });
  });

  // Getting read only access to the buffer on the host.
  // Implicit barrier waiting for queue to complete the work.
  const auto HostAccessor = Buffer.get_access<sycl::access::mode::read>();

  // Check the results
  bool MismatchFound = false;
  for (size_t I = 0; I < Buffer.size(); ++I) {
    if (HostAccessor[I] != I) {
      std::cout << "The result is incorrect for element: " << I
                << " , expected: " << I << " , got: " << HostAccessor[I]
                << std::endl;
      MismatchFound = true;
    }
  }

  if (!MismatchFound) {
    std::cout << "The results are correct!" << std::endl;
  }

  return MismatchFound;
}

# do it
export PATH=$HOME/install/llvm/build/bin:$PATH
export LD_LIBRARY_PATH=$HOME/install/llvm/build/lib:$LD_LIBRARY_PATH

# verify
$ clang++ --version
clang version 16.0.0
  

#complie
clang++ -fsycl -fsycl-targets=nvptx64-nvidia-cuda simple-sycl-app.cpp -o simple-sycl-app-cuda

#run
./simple-sycl-app-cuda
The results are correct!

...
# configure
python3 ./buildbot/configure.py --cuda -t release --cmake-gen "Unix Makefiles" --cmake-opt="-DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda-11.5"

...

# compile
clang++ -fsycl -fsycl-targets=nvptx64-nvidia-cuda simple-sycl-app.cpp -o simple-sycl-app-cuda --cuda-path=/usr/local/cuda-11.5/