Date: | Wed, 26 Nov 2008 13:47:43 -0600 |
---|---|
From: | "Dan Gibson" <degibson@xxxxxxxx> |
Subject: | Re: [Gems-users] Ruby_cycles varying in a wide range |
On Wed, Nov 26, 2008 at 9:07 AM, Ricardo Quislant del Barrio <quislant@xxxxxxxxx> wrote:Yes, it is. You have published some results that haven't got that I have not published any results on Labyrinth. Those folks that have typically run multiple runs to get rid of variance due to timing-sensitive paths, and then report 95% confidence intervals. Timing variance is known to change entire execution paths inside of benchmarks that are sensitive to it. That is why I am wondering: Is Labyrinth deterministic? As in, does the result of the Labyrinth benchmark change under different coherence/transactional timing?
-- http://www.cs.wisc.edu/~gibson [esc]:wq! |
[← Prev in Thread] | Current Thread | [Next in Thread→] |
---|---|---|
|
Previous by Date: | Re: [Gems-users] Ruby_cycles varying in a wide range, Ricardo Quislant del Barrio |
---|---|
Next by Date: | [Gems-users] Determining capacity and cold start misses using RUBY., Ashwath Narasimhan |
Previous by Thread: | Re: [Gems-users] Ruby_cycles varying in a wide range, Ricardo Quislant del Barrio |
Next by Thread: | Re: [Gems-users] Ruby_cycles varying in a wide range, Ricardo Quislant del Barrio |
Indexes: | [Date] [Thread] |