Re: PRE (sometimes) confuses ivopts/scev?

[Ulrich Weigand <uweigand at de dot ibm dot com>]

Daniel Berlin wrote:

> On Mon, 24 Jan 2005, Richard Guenther wrote:
> 
> > Daniel Berlin wrote:
> >> 
> >> Just as a followup, sebastian's patch is at (the actual patch is ta the 
> >> end of the message. You sahouldn't need the other two parts he's pasted in 
> >> front of it anymore, i believe)
> >> http://gcc.gnu.org/ml/gcc-patches/2004-11/msg02444.html
> >
> > This patch applied, but didn't help, I'll try to get more details and 
> > hopefully a reduced testcase.
> >
> >> it should be applied because it helps us detect more simple evolutions 
> >> properly.
> >> " during a bootstrap
> >> there are about 7000 cases that are in fact just simple affine
> >> evolution functions, but that are mishandled for the moment because
> >> the scalar evolution analyzer was not enough smart to transform them."
> >> 
> >> In addition, the patch to teach PRE to stop creating *more* wraparounds is 
> >> also in the mail archives, see 
> >> http://gcc.gnu.org/ml/gcc-patches/2004-11/msg02222.html
> >
> > This patch doesn't apply any more.
> 
> Yes, i know.
> The attached should apply.

I'm also seeing the effect of PRE generating wrap-around variables
in my mgrid test case.  It causes the final loop to look like:

__label_000600:;
  D.922 = (<unnamed type>) i1;
  D.464 = (int8) (int4) (D.922 + 4294967295);
  i1 = (int4) (D.922 + 1);
  D.469 = (int8) i1;
  prephitmp.55 = offset.11 + D.469 + prephitmp.32;
  D.507 = (*v)[prephitmp.131] - D.453 * (*u)[prephitmp.131] - D.462 * ((*u)[offset.11 + D.464 + prephitmp.32] + (*u)[prephitmp.55] + (*u)[prephitmp.67] + (*u)[prephitmp.79] + (*u)[prephitmp.83] + (*u)[prephitmp.87]);
  prephitmp.67 = offset.11 + D.469 + pretmp.62;
  prephitmp.79 = offset.11 + D.469 + prephitmp.132;
  prephitmp.83 = offset.11 + D.469 + prephitmp.129;
  prephitmp.87 = offset.11 + D.469 + prephitmp.130;
  D.561 = D.507 - D.508 * ((*u)[offset.11 + D.464 + pretmp.62] + (*u)[prephitmp.67] + (*u)[offset.11 + D.464 + prephitmp.132] + (*u)[prephitmp.79] + (*u)[prephitmp.93] + (*u)[prephitmp.99] + (*u)[prephitmp.105] + (*u)[prephitmp.111] + (*u)[offset.11 + D.464 + prephitmp.129] + (*u)[offset.11 + D.464 + prephitmp.130] + (*u)[prephitmp.83] + (*u)[prephitmp.87]);
  prephitmp.93 = offset.11 + D.469 + pretmp.88;
  prephitmp.99 = offset.11 + D.469 + prephitmp.40;
  prephitmp.105 = offset.11 + D.469 + pretmp.100;
  prephitmp.111 = offset.11 + D.469 + prephitmp.48;
  (*r)[prephitmp.131] = D.561 - D.562 * ((*u)[offset.11 + D.464 + pretmp.88] + (*u)[prephitmp.93] + (*u)[offset.11 + D.464 + prephitmp.40] + (*u)[prephitmp.99] + (*u)[offset.11 + D.464 + pretmp.100] + (*u)[prephitmp.105] + (*u)[offset.11 + D.464 + prephitmp.48] + (*u)[prephitmp.111]);
  if (D.412 == (int4) ((<unnamed type>) i1 + 4294967295)) goto <L8>; else goto <L29>;

All those prephitmp variables try to reuse a value from the previous
loop iteration in the next one, which only succeeds in creating
enormous reigster pressure ...


Unfortunately your patch doesn't change this because the variables
fail the 

      if (firstinsideloop ^ secondinsideloop
          && is_gimple_min_invariant (avail[outsideloopblock->index])
          && !is_gimple_min_invariant (avail[insideloopblock->index]))

test -- the outsideloop value is not invariant (because it varies
with the next outer loop).

Why is this test required in the first place?  If I remove it, I get

__label_000600:;
  D.439 = (int8) i1;
  D.446 = offset.11 + D.439 + D.444;
  D.833 = (<unnamed type>) i1;
  D.464 = (int8) (int4) (D.833 + 4294967295);
  i1 = (int4) (D.833 + 1);
  D.469 = (int8) i1;
  (*r)[D.446] = (*v)[D.446] - D.453 * (*u)[D.446] - D.462 * ((*u)[offset.11 + D.444 + D.464] + (*u)[offset.11 + D.444 + D.469] + (*u)[offset.11 + D.439 + D.477] + (*u)[offset.11 + D.439 + D.485] + (*u)[offset.11 + D.439 + D.493] + (*u)[offset.11 + D.439 + D.501]) - D.508 * ((*u)[offset.11 + D.464 + D.477] + (*u)[offset.11 + D.469 + D.477] + (*u)[offset.11 + D.464 + D.485] + (*u)[offset.11 + D.469 + D.485] + (*u)[offset.11 + D.439 + D.524] + (*u)[offset.11 + D.439 + D.529] + (*u)[offset.11 + D.439 + D.534] + (*u)[offset.11 + D.439 + D.539] + (*u)[offset.11 + D.464 + D.493] + (*u)[offset.11 + D.464 + D.501] + (*u)[offset.11 + D.469 + D.493] + (*u)[offset.11 + D.469 + D.501]) - D.562 * ((*u)[offset.11 + D.464 + D.524] + (*u)[offset.11 + D.469 + D.524] + (*u)[offset.11 + D.464 + D.529] + (*u)[offset.11 + D.469 + D.529] + (*u)[offset.11 + D.464 + D.534] + (*u)[offset.11 + D.469 + D.534] + (*u)[offset.11 + D.464 + D.539] + (*u)[offset.11 + D.469 + D.539]);
  if (D.412 == (int4) ((<unnamed type>) i1 + 4294967295)) goto <L8>; else goto __label_000600;

which at least has somewhat reduced register pressure ...


Bye,
Ulrich

-- 
  Dr. Ulrich Weigand
  Linux on zSeries Development
  Ulrich.Weigand@de.ibm.com