OpenE2K
/
gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

re PR tree-optimization/77498 (Performance drop after r239414 on spec2000/172mgrid) 

2017-03-30  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/77498
	* tree-ssa-pre.c (phi_translate_1): Do not allow simplifications
	to non-constants over backedges.

	* gfortran.dg/pr77498.f: New testcase.

From-SVN: r246583
This commit is contained in:
Richard Biener 2017-03-30 07:15:39 +00:00 committed by Richard Biener
parent e0aa80e05e
commit 28c0240778
4 changed files with 61 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
gcc/ChangeLog
View File

@ -1,3 +1,9 @@
2017-03-30 Richard Biener <rguenther@suse.de>
PR tree-optimization/77498
* tree-ssa-pre.c (phi_translate_1): Do not allow simplifications
to non-constants over backedges.
2017-03-29 Segher Boessenkool <segher@kernel.crashing.org>
PR rtl-optimization/80233

5
gcc/testsuite/ChangeLog
View File

@ -1,3 +1,8 @@
2017-03-30 Richard Biener <rguenther@suse.de>
PR tree-optimization/77498
* gfortran.dg/pr77498.f: New testcase.
2017-03-29 Marek Polacek <polacek@redhat.com>
PR c/79730

36
gcc/testsuite/gfortran.dg/pr77498.f Normal file
View File

@ -0,0 +1,36 @@
! { dg-do compile }
! { dg-options "-O2 -ffast-math -fdump-tree-pre" }
subroutine foo(U,V,R,N,A)
integer N
real*8 U(N,N,N),V(N,N,N),R(N,N,N),A(0:3)
integer I3, I2, I1
C
do I3=2,N-1
do I2=2,N-1
do I1=2,N-1
R(I1,I2,I3)=V(I1,I2,I3)
* -A(0)*( U(I1, I2, I3 ) )
* -A(1)*( U(I1-1,I2, I3 ) + U(I1+1,I2, I3 )
* + U(I1, I2-1,I3 ) + U(I1, I2+1,I3 )
* + U(I1, I2, I3-1) + U(I1, I2, I3+1) )
* -A(2)*( U(I1-1,I2-1,I3 ) + U(I1+1,I2-1,I3 )
* + U(I1-1,I2+1,I3 ) + U(I1+1,I2+1,I3 )
* + U(I1, I2-1,I3-1) + U(I1, I2+1,I3-1)
* + U(I1, I2-1,I3+1) + U(I1, I2+1,I3+1)
* + U(I1-1,I2, I3-1) + U(I1-1,I2, I3+1)
* + U(I1+1,I2, I3-1) + U(I1+1,I2, I3+1) )
* -A(3)*( U(I1-1,I2-1,I3-1) + U(I1+1,I2-1,I3-1)
* + U(I1-1,I2+1,I3-1) + U(I1+1,I2+1,I3-1)
* + U(I1-1,I2-1,I3+1) + U(I1+1,I2-1,I3+1)
* + U(I1-1,I2+1,I3+1) + U(I1+1,I2+1,I3+1) )
enddo
enddo
enddo
return
end
! PRE shouldn't do predictive commonings job here (and in a bad way)
! ??? It still does but not as bad as it could. Less prephitmps
! would be better, pcom does it with 6.
! { dg-final { scan-tree-dump-times "# prephitmp" 9 "pre" } }

18
gcc/tree-ssa-pre.c
View File

@ -1468,10 +1468,20 @@ phi_translate_1 (pre_expr expr, bitmap_set_t set1, bitmap_set_t set2,
leader for it. */
if (constant->kind != CONSTANT)
{
unsigned value_id = get_expr_value_id (constant);
constant = find_leader_in_sets (value_id, set1, set2);
if (constant)
return constant;
/* Do not allow simplifications to non-constants over
backedges as this will likely result in a loop PHI node
to be inserted and increased register pressure.
See PR77498 - this avoids doing predcoms work in
a less efficient way. */
if (find_edge (pred, phiblock)->flags & EDGE_DFS_BACK)
;
else
{
unsigned value_id = get_expr_value_id (constant);
constant = find_leader_in_sets (value_id, set1, set2);
if (constant)
return constant;
}
}
else
return constant;