[graphite] Remove checks for flag_loop_strip_mine, flag_loop_block, flag_loop_interchange in graphite_trans_bb_block.

[Tobias Grosser]

Hi Jack,

On Fri, 2008-08-15 at 09:58 -0400, Jack Howarth wrote:
> Tobias,
>      I am seeing the following results with the proposed patch from...
> 
> http://gcc.gnu.org/ml/gcc-patches/2008-08/msg01000.html
> 
> applied over gcc trunk with the previous graphite patch and all of
> the subsequent changes in graphite branch applied...
> 
[..]
> ================================================================================
> 
> On i686-apple-darwin9. I am surprised that I'm not seeing any
> major performance changes one way or another with the new
> loop optimizations. Does this match what you are seeing from
> the Polyhedron 2005 benchmarks?
>                               Jack

At the moment I can not give you a good answer to your question, as I
worked mainly on the front end part. So may be Sebastian or Jan can give
you some hints.
As the front end is working now (except unknown bugs and new features),
I will have a look at some backend work (Rename of scalar variables to
the new cloog iterators, for some more complicated cases). So I hope to
be able to answer your questions the next weeks.

My first impression (and that's a wild guess) is, that we don't change
anything at the moment.

The problem seems to be that cloog-ppl does not remove all unused
conditions. So there remain conditions in the cloog AST and, as our
backend at the moment is not able to build conditions, we do not
generate any code.

Jan/Sebastian can you look at this one?

Tobias