The Execution Time Difference Between Event_Profiling and Steady Clock

I am trying to profile my code and I am getting different results each time I run the code.

auto start = std::chrono::steady_clock::now();
foo()      
auto end = std::chrono::steady_clock::now();
time = std::chrono::duration_cast<std::chrono::nanoseconds>(end - start).count();

why is this giving me different results than using

start_kernel_time = event.get_profiling_info<info::event_profiling::command_start>();
end_kernel_time = event.get_profiling_info<info::event_profiling::command_end>();
time_kernel = (end_kernel_time - start_kernel_time) / kNs; // kNs = 1e9

I run the code several times and interesting thing is steady_clock version first printed out 6.7 seconds and then in the second run printed out 0.07 seconds ( unrealistic) then the event profiling was printed the ~0.64 seconds which made more sense. Why it is different ?

I am using oneapi 2023 with icpx compiler

Non viene indicato alcun file sorgente, test o punto di ingresso di esempio. Inizia riproducendo i due frammenti di misurazione dei tempi con la configurazione indicata di oneAPI 2023 e icpx, quindi confronta l’intervallo del steady clock dell’host con event_profiling command_start e command_end; il lavoro è completo quando vengono documentati la causa della discrepanza e un modo affidabile per misurare il tempo di esecuzione.