diff options
| author | Richard Biener <rguenther@suse.de> | 2023-11-21 09:50:54 +0100 |
|---|---|---|
| committer | Richard Biener <rguenther@suse.de> | 2023-11-21 15:31:56 +0100 |
| commit | ae156936cf4f15d9cc2b7d4e39f2e6b8fe22a9c3 (patch) | |
| tree | 09a865a5620bc852c66c01f522949b2173669930 | |
| parent | 1d82fc2e6824bf83159389729c31a942f7b91b04 (diff) | |
| download | gcc-ae156936cf4f15d9cc2b7d4e39f2e6b8fe22a9c3.zip gcc-ae156936cf4f15d9cc2b7d4e39f2e6b8fe22a9c3.tar.gz gcc-ae156936cf4f15d9cc2b7d4e39f2e6b8fe22a9c3.tar.bz2 | |
Move VF based dependence check
The following moves the check whether the maximum vectorization
factor determined by data dependence analysis is in conflict with
the chosen vectorization factor to after the point where we applied
both the SLP and the unrolling adjustment to the vectorization
factor. We check the latter before applying unrolling, but the
SLP adjustment can result in both missed optimization and wrong-code.
* tree-vect-loop.cc (vect_analyze_loop_2): Move check
of VF against max_vf until VF is final.
| -rw-r--r-- | gcc/tree-vect-loop.cc | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index 58679e91..a73a533 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -2817,9 +2817,6 @@ vect_analyze_loop_2 (loop_vec_info loop_vinfo, bool &fatal, "can't determine vectorization factor.\n"); return ok; } - if (max_vf != MAX_VECTORIZATION_FACTOR - && maybe_lt (max_vf, LOOP_VINFO_VECT_FACTOR (loop_vinfo))) - return opt_result::failure_at (vect_location, "bad data dependence.\n"); /* Compute the scalar iteration cost. */ vect_compute_single_scalar_iteration_cost (loop_vinfo); @@ -2881,6 +2878,10 @@ start_over: LOOP_VINFO_INT_NITERS (loop_vinfo)); } + if (max_vf != MAX_VECTORIZATION_FACTOR + && maybe_lt (max_vf, LOOP_VINFO_VECT_FACTOR (loop_vinfo))) + return opt_result::failure_at (vect_location, "bad data dependence.\n"); + loop_vinfo->vector_costs = init_cost (loop_vinfo, false); /* Analyze the alignment of the data-refs in the loop. |