aboutsummaryrefslogtreecommitdiff
path: root/gcc/tree-vect-patterns.cc
diff options
context:
space:
mode:
authorKewen Lin <linkw@linux.ibm.com>2022-06-14 00:57:01 -0500
committerKewen Lin <linkw@linux.ibm.com>2022-06-14 00:57:01 -0500
commitf907cf4c07cf51863dadbe90894e2ae3382bada5 (patch)
tree9afc821b19f134f4909206476dc0b1edc47e46f6 /gcc/tree-vect-patterns.cc
parent077438933cf94f00cc5edf974338c11ba4bf7a39 (diff)
downloadgcc-f907cf4c07cf51863dadbe90894e2ae3382bada5.zip
gcc-f907cf4c07cf51863dadbe90894e2ae3382bada5.tar.gz
gcc-f907cf4c07cf51863dadbe90894e2ae3382bada5.tar.bz2
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.
Diffstat (limited to 'gcc/tree-vect-patterns.cc')
0 files changed, 0 insertions, 0 deletions