[GENERAL] Merged v1.0alpha into master. Added features are:

- A100 support via mma.16816
- Thread swizzling for conflict-free shared memory accesses without
padding
- Complete overhaul of the LLVM code generation in
codegen/selection/generator.cc to remove overengineering
- Added debugging capabilities in the Python binding
- Compilation error for kernels that spill

lib/ir/print.cc

@@ -65,7 +65,12 @@ void print(module &mod, std::ostream& os) {
             os << get_name(ops[i], cnt++);
           os << (i < num_ops - 1?", ":"");
         }
-        os << ";" << std::endl;
+        os << ";";
+//        os << " (";
+//        for(ir::user* usr: inst->get_users())
+//          os << get_name(usr, cnt++) << ", " ;
+//        os << " )";
+        os << std::endl;
       }
     }
     os << "}" << std::endl;