uNetworking/libvc

DevicePool devicePool;
for (Device &device : devicePool.getDevices()) {
    cout << "Found device: " << device.getName() << " from vendor: 0x"
         << hex << device.getVendorId() << dec << endl;

    try {
            // Allocate a buffer & clear it
            Buffer buffer(device, sizeof(double) * 10240);
            buffer.fill(0);

            // Compile the compute shader & prepare to use the buffer as argument
            Program program(device, "shaders/comp.spv", {BUFFER});
            Arguments args(program, {buffer});

            // Create and build the command buffer, making use of the program and arguments
            CommandBuffer commands(device, program, args);
            for (int i = 0; i < 100000; i++) {
                commands.dispatch(10);
                commands.barrier();
            }
            commands.end();

            // Time the execution on the GPU
            for (int i = 0; i < 5; i++) {
                steady_clock::time_point start = steady_clock::now();
                device.submit(commands);
                device.wait();
                cout << duration_cast<milliseconds>(steady_clock::now() - start).count() << "ms" << endl;
            }

            // Download results and show the first scalar
            double results[10240];
            buffer.download(results);
            cout << "Result: " << results[0] << endl;

    } catch(vc::Error e) {
        cout << "vc::Error thrown" << endl;
    }
}