diff options
| author | Richard Sandiford <richard.sandiford@arm.com> | 2019-11-06 12:29:47 +0000 |
|---|---|---|
| committer | Richard Sandiford <rsandifo@gcc.gnu.org> | 2019-11-06 12:29:47 +0000 |
| commit | 8ec5b16a9a3dbd6d825596c22f1bc32646de28fe (patch) | |
| tree | be1152f63c2f69541e90e1c894d5b1089a6adbac | |
| parent | 72d6aeecd95ec49fff1d258e4631167a03351cbb (diff) | |
| download | gcc-8ec5b16a9a3dbd6d825596c22f1bc32646de28fe.zip gcc-8ec5b16a9a3dbd6d825596c22f1bc32646de28fe.tar.gz gcc-8ec5b16a9a3dbd6d825596c22f1bc32646de28fe.tar.bz2 | |
Check the VF is small enough for an epilogue loop
The number of iterations of an epilogue loop is always smaller than the
VF of the main loop. vect_analyze_loop_costing was taking this into
account when deciding whether the loop is cheap enough to vectorise,
but that has no effect with the unlimited cost model. We need to use
a separate check for correctness as well.
This can happen if the sizes returned by autovectorize_vector_sizes
happen to be out of order, e.g. because the target prefers smaller
vectors. It can also happen with later patches if two vectorisation
attempts happen to end up with the same VF.
2019-11-06 Richard Sandiford <richard.sandiford@arm.com>
gcc/
* tree-vect-loop.c (vect_analyze_loop_2): When vectorizing an
epilogue loop, make sure that the VF is small enough or that
the epilogue loop can be fully-masked.
From-SVN: r277880
| -rw-r--r-- | gcc/ChangeLog | 6 | ||||
| -rw-r--r-- | gcc/tree-vect-loop.c | 10 |
2 files changed, 16 insertions, 0 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index a8a8968..d04b6be 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,5 +1,11 @@ 2019-11-06 Richard Sandiford <richard.sandiford@arm.com> + * tree-vect-loop.c (vect_analyze_loop_2): When vectorizing an + epilogue loop, make sure that the VF is small enough or that + the epilogue loop can be fully-masked. + +2019-11-06 Richard Sandiford <richard.sandiford@arm.com> + * tree-vect-loop.c (vect_analyze_loop): Break out of the main loop when we've finished, rather than returning directly from the loop. Use a local variable to track whether we're still diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index f804904..ec0bd2c 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -2143,6 +2143,16 @@ start_over: " support peeling for gaps.\n"); } + /* If we're vectorizing an epilogue loop, we either need a fully-masked + loop or a loop that has a lower VF than the main loop. */ + if (LOOP_VINFO_EPILOGUE_P (loop_vinfo) + && !LOOP_VINFO_FULLY_MASKED_P (loop_vinfo) + && maybe_ge (LOOP_VINFO_VECT_FACTOR (loop_vinfo), + LOOP_VINFO_VECT_FACTOR (orig_loop_vinfo))) + return opt_result::failure_at (vect_location, + "Vectorization factor too high for" + " epilogue loop.\n"); + /* Check the costings of the loop make vectorizing worthwhile. */ res = vect_analyze_loop_costing (loop_vinfo); if (res < 0) |