[concurrency-interest] help show speed-up on a trivial but manual array-map operation?
radhakrishnan.mohan at gmail.com
Tue Mar 13 01:11:45 EDT 2012
The 'References' section of this paper mentiones another paper "
which describes a tool suite(http://icl.cs.utk.edu/projects/papi) to get
performance information from hardware counters.
Figure 3. in this paper shows a Java frontend to analyze cache misses.
Seems it could be useful for basic research.
On Fri, Mar 9, 2012 at 6:54 PM, Michael Hicks <mwh at cs.umd.edu> wrote:
> Mitkowicz et al also present a very interesting cautionary tale in this
> From the paper: changing the order in which you link your .o files can
> change performance by up to 10% Given that many compiler optimizations
> make "improvements" in the range of 5% makes this result a bit disturbing.
> On Mar 9, 2012, at 8:20 AM, Doug Lea wrote:
> > On 03/09/12 08:11, Doug Lea wrote:
> >> 1. Microbenchmarking artifacts: The results of the
> >> computations are never used so JVMs can kill some of the
> >> code. The attached edited version includes a "checkSum" method
> >> that combats this.
> > Plus, as I should have checked before, the use of a linear
> > stream of initial values is also subject to microbenchmarking
> > artifacts. Filling with random values instead combats this.
> > The main moral is that reliably measuring anything on modern
> > systems is harder than you'd think it should be.
> > -Doug
> > <VecAdd.java>_______________________________________________
> > Concurrency-interest mailing list
> > Concurrency-interest at cs.oswego.edu
> > http://cs.oswego.edu/mailman/listinfo/concurrency-interest
> Concurrency-interest mailing list
> Concurrency-interest at cs.oswego.edu
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Concurrency-interest