Known Issues
Defining a breakpoint at a location before a kernel (i.e. inside the host code) causes the breakpoint to be also defined at the start of the kernel. This is analogous to defining a breakpoint at a comment line or an empty line and the breakpoint being defined for the next source line.
While a workload submitted to a subdevice of a GPU is being debugged, no other workload can be executed or debugged on the same subdevice.
If the current SIMD lane becomes inactive within a thread, the thread might silently switch its current SIMD lane to its first active SIMD lane.
The next and step commands may take several seconds to complete execution.
The debugger may stop responding if you disable displaced-stepping before the start of a GPU kernel.