[Users] [Commits] [svn:einsteintoolkit] TOVSolver/trunk/ (Rev. 137)

Erik Schnetter schnetter at cct.lsu.edu
Thu Jul 11 12:06:32 CDT 2013


On 2013-07-11, at 12:54 , Frank Loeffler <knarf at cct.lsu.edu> wrote:

> On Thu, Jul 11, 2013 at 05:21:08PM +0200, Roland Haas wrote:
>> I believe Jenkins only tracks on the granularity level of commits to the
>> master git repository.
> 
> Me too, but I (probably incorrectly) assumed that the git repository
> would create one commit for every commit happening in the ET, and thus
> would test every change separately.
> 
>> It should should not be difficult to walk the list of commits and check
>> where it fails though, I just don't have the time to do so right now.
> 
> Not difficult - sure, but it takes time. Ideally it should take the time
> of the one committing the changes. Anyway - it's r555 of GRHydro: add
> grid function for sqrt(detg).


In case this grid function is expected to be a performance improvement:

I would guess that calculating sqrt(det(g_ij)) takes about 20 to 30 cycles, if the 3-metric g_ij is in the D1 cache, i.e. if the 3-metric is already used in the same loop. Accessing a grid function element that is stored in memory (assuming it remains in the L3 cache) costs about 50 cycles.

Of course, the details will vary between systems, and will depend on which cache level holds the data, and what optimizations the compiler can apply to the loop. Don't take these numbers at face value. The point here is that, although sqrt may "look expensive", it may well be cheaper to re-calculate than to pre-calculate and store it.

-erik

-- 
Erik Schnetter <schnetter at cct.lsu.edu>
http://www.perimeterinstitute.ca/personal/eschnetter/

My email is as private as my paper mail. I therefore support encrypting
and signing email messages. Get my PGP key from http://keys.gnupg.net.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 203 bytes
Desc: Message signed with OpenPGP using GPGMail
Url : http://lists.einsteintoolkit.org/pipermail/users/attachments/20130711/395a4cdb/attachment.bin 


More information about the Users mailing list