Comment by lallysingh

My profiling tool: github.com/lally/ppt

I needed really high quality performance telemetry ("profiling" is a mixed choice) for my PhD. You specify the payload type in an IDL and it generates types and transport code. Fill in a struct and hit save(). If the process is being observed, this'll copy the struct to a lock-free ring buffer that the observer injected in. Includes CPU performance counter support.