GPU backend

Adds GPU backend and "CUDA" feature to all the tests. As of MR creation, there were no forks in tested IRs so only vanilla non-parallel (single block, single thread) codegen has been tested.

hercules_cg/src/device.rs

@@ -11,6 +11,8 @@ pub fn device_placement(functions: &Vec<Function>, callgraph: &CallGraph) -> Vec
     let mut devices = vec![];
 
     for (idx, function) in functions.into_iter().enumerate() {
+        devices.push(Device::CUDA);
+        continue;
         if let Some(device) = function.device {
             devices.push(device);
         } else if function.entry || callgraph.num_callees(FunctionID::new(idx)) != 0 {