* use perf_counter_ns to measure performance; meausure within time not count * fixes * remove nightly * set 60 secs by default * fix output html * code review fixes * fix runtime duration * remove unneeded inference * cleanup
* use perf_counter_ns to measure performance; meausure within time not count * fixes * remove nightly * set 60 secs by default * fix output html * code review fixes * fix runtime duration * remove unneeded inference * cleanup