Re: gdb benchmarking and profiling

[Stan Shebs <shebs at apple dot com>]

Andrew Cagney wrote:
> 
> I don't know that bandwidth is still the most common problem (except
> where an architecture has millions of registers :-).  Rather it is
> latency.  Latency shows up in the number of round trips needed to
> achieve anything useful.  A few extra bytes here or there are in the
> noise :-)

That's a good point - it would be very interesting to add some
machinery to monitor latency.  Collect milli/microsecond timings
just above low-level calls, accumulate the amount of time spent
waiting on turnarounds.  In fact, if you leave it in permanently
and report it to users, it would help answer the why-is-stepping-
slow-today-type questions.

Stan