Simple xample to test SYCL on A100 on csd3

setup.sh

+#!/bin/sh
+
+module purge
+module use /usr/local/software/spack/spack-modules/dpcpp-cuda-20220220/linux-centos8-x86_64_v3/
+module load dpcpp
+module load gcc/11.2.0
+
+clang++ -fsycl -fsycl-targets=nvptx64-nvidia-cuda test-sycl.cpp -o test-sycl
+./test-sycl

test-sycl.cpp

+#include <CL/sycl.hpp>
+#include <iostream>
+using namespace sycl;
+
+void print_device_info(const sycl::queue& Q) {
+    std::cout << "Selected device: " << Q.get_device().get_info<info::device::name>() << "\n";
+    std::cout << "Device vendor: " << Q.get_device().get_info<info::device::vendor>() << "\n";
+    std::cout << '\n';
+}
+int main() {
+    queue Q1;                       // implicit device selection (might be the host device)
+    queue Q2 { host_selector {} };  // Create queue to use the host device explicitly
+//    queue Q3 { cpu_selector {} };   // Create queue to use the CPU device explicitly
+    queue Q4 { gpu_selector {} };   // Create queue to use the GPU device explicitly
+    print_device_info(Q1);
+    print_device_info(Q2);
+//    print_device_info(Q3);
+    print_device_info(Q4);
+    return 0;
+}