]> gcc.gnu.org Git - gcc.git/commit
vect: Move suggested_unroll_factor applying [PR105940]
authorKewen Lin <linkw@linux.ibm.com>
Tue, 14 Jun 2022 05:57:01 +0000 (00:57 -0500)
committerKewen Lin <linkw@linux.ibm.com>
Tue, 14 Jun 2022 05:57:01 +0000 (00:57 -0500)
commitf907cf4c07cf51863dadbe90894e2ae3382bada5
tree9afc821b19f134f4909206476dc0b1edc47e46f6
parent077438933cf94f00cc5edf974338c11ba4bf7a39
vect: Move suggested_unroll_factor applying [PR105940]

As PR105940 shown, when rs6000 port tries to assign
m_suggested_unroll_factor by 4 or so, there will be ICE on:

  exact_div (LOOP_VINFO_VECT_FACTOR (loop_vinfo),
             loop_vinfo->suggested_unroll_factor);

In function vect_analyze_loop_2, the current place of
suggested_unroll_factor applying can't guarantee it's
applied for all cases.  As the case shows, vectorizer
could retry with SLP forced off, the vf is reset by
saved_vectorization_factor which isn't applied with
suggested_unroll_factor before.  It means it can end
up with one vf which neglects suggested_unroll_factor.
I think it's off design, we should move the applying
of suggested_unroll_factor after start_over.

PR tree-optimization/105940

gcc/ChangeLog:

* tree-vect-loop.cc (vect_analyze_loop_2): Move the place of
applying suggested_unroll_factor after start_over.
gcc/tree-vect-loop.cc
This page took 0.061377 seconds and 6 git commands to generate.