Hi Everyone,

I have a question about statistics for you all.

Daniel pointed out that GEMS has a Historgram statistics type similar
to M5's Distribution with one difference.  M5's distribution (which
was modeled on simplescalar) has a fixed number of buckets which are
fixed in size at initialization time.  Additionally, it has an
overflow and underflow bucket to capture samples that are out of the
distribution's range.  The GEMS Histogram has a fixed number of
variable sized buckets.  Initially, each bucket would be very small,
and if you get a new sample that doesn't have a bucket to go into, you
double the size of the buckets (and shift the values around) until
there is a bucket which can accept the sample.

I've implemented the Histogram statistic type because it will be
useful for Ruby integration and seems like a useful concept.  My
question is, does the Distribution make sense if we have the
Histogram?  Should I move all Distributions to Histograms and drop
Distribution?  I can keep both, but I'm inclined to believe that this
Histogram is superior in most cases.

Does anyone have any opinion?

  Nate
_______________________________________________
m5-dev mailing list
[email protected]
http://m5sim.org/mailman/listinfo/m5-dev

Reply via email to