> On Jan 26, 2016, at 11:05 AM, Satish Balay <[email protected]> wrote:
> 
> On Tue, 26 Jan 2016, Barry Smith wrote:
> 
>> 
>>> On Jan 26, 2016, at 10:39 AM, Barry Smith <[email protected]> wrote:
>>> 
>>> 
>>>> On Jan 26, 2016, at 12:33 AM, Justin Chang <[email protected]> wrote:
>>>> 
>>>> Hi developers,
>>>> 
>>>> Is there any particular reason why PETSc ./configure always compiles and 
>>>> installs Ctetgen even if no updates are made to the source code?
>>> 
>>> Yes
>> 
>>    Matt reworked tetgen to use the PETSc include files thus ctetgen cannot 
>> be built before the PETSc configure files are generated and written. Hence 
>> it is compiling ctetgen using the package.postProcess() method instead of 
>> the usual method used for building other packages. The postProcess() is less 
>> mature and doesn't yet have checks to prevent unnecessary recompiles etc. 
>> Someday it may be improved.
> 
> Since petscconf.h is regenereated [each time configure is run] -
> rebuilding ctetgen [every time] is the correct thing to do - per
> dependencies.

  Yes, but if petscconf.h is identical a super smart dependency checker would 
see it was unchanged.  Worth doing? Probably not.
> 
> The build [of ctetgen] uses legacy makefiles - that don't generate/use
> proper dependencies. [and if the proper dependencies are
> generated/used - there will be a rebuild each time - due to the
> changed petscconf.h anyway.]
> 
> Satish
> 
>>> 
>>>> Not that it's a big deal or anything, but it just gives me that same 
>>>> uncomfortable itchy feeling of seeing my high school math teacher erase 
>>>> everything from the chalk board except for that one corner.
>>>> 
>>>> Thanks,
>>>> Justin

Reply via email to