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

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 85b1c37eadd42d3ea981db7ca0973c1fe99114e6..3333bfd146852e0cece9066459f02cdb35deccb7 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -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

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index d8e6f875c42e6c45173b8718e69fbab549bb2339..5d33ce78b67a1384d1cf97e218d7ee7f4110bcd0 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -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

diff --git a/gcc/testsuite/gfortran.dg/pr77498.f b/gcc/testsuite/gfortran.dg/pr77498.f
new file mode 100644 (file)
index 0000000..f957b57
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/pr77498.f
@@ -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" } }

diff --git a/gcc/tree-ssa-pre.c b/gcc/tree-ssa-pre.c
index ff59d53667885bea3abc0bcc4cd9f44417b86e4c..c6aa5879739aca73c2924beffd8f1a160e731d68 100644 (file)
--- a/gcc/tree-ssa-pre.c
+++ b/gcc/tree-ssa-pre.c
@@ -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;