While there are no tools which use macOS as a target environment, NVIDIA is making a macOS host version of cuda-gdb available from which you can launch debugging sessions on supported target platforms.
Note that NVIDIA® CUDA Toolkit 11.0 (and later) no longer supports development or running applications on macOS. Just like GDB, CUDA-GDB provides a console-based debugging interface you can use from the command line on your local system or any remote system on which you have Telnet or SSH access. If you prefer debugging with a GUI frontend, CUDA-GDB also supports integration with DDD, EMACS, Nsight Eclipse Edition or the new Nsight Visual Studio Code Edition If you already use GDB to debug your CPU application then getting started with CUDA-GDB involves learning just a few additional debugger commands. CUDA-GDB delivers a seamless debugging experience that allows you to debug both the CPU and GPU portions of your application simultaneously. When developing massively parallel applications on the GPU, you need a debugger capable of handling thousands of threads running simultaneously on each GPU in the system.