diff options
| author | Andre Vieira <andre.simoesdiasvieira@arm.com> | 2021-06-03 13:55:24 +0100 |
|---|---|---|
| committer | Andre Vieira <andre.simoesdiasvieira@arm.com> | 2021-06-03 13:55:24 +0100 |
| commit | 7ed1cd9665d8ca0fa07b2483e604c25e704584af (patch) | |
| tree | 55c9ffd6adcd0b3464eeef16875b0e535b86bd08 | |
| parent | f4242710c7966a965bbd14cd50ecdba28fd5717e (diff) | |
| download | gcc-7ed1cd9665d8ca0fa07b2483e604c25e704584af.zip gcc-7ed1cd9665d8ca0fa07b2483e604c25e704584af.tar.gz gcc-7ed1cd9665d8ca0fa07b2483e604c25e704584af.tar.bz2 | |
vect: Use main loop's thresholds and VF to narrow upper_bound of epilogue
This patch uses the knowledge of the conditions to enter an epilogue loop to
help come up with a potentially more restricive upper bound.
gcc/ChangeLog:
* tree-vect-loop.c (vect_transform_loop): Use main loop's various'
thresholds to narrow the upper bound on epilogue iterations.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/sve/part_vect_single_iter_epilog.c: New test.
| -rw-r--r-- | gcc/testsuite/gcc.target/aarch64/sve/part_vect_single_iter_epilog.c | 11 | ||||
| -rw-r--r-- | gcc/tree-vect-loop.c | 31 |
2 files changed, 36 insertions, 6 deletions
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/part_vect_single_iter_epilog.c b/gcc/testsuite/gcc.target/aarch64/sve/part_vect_single_iter_epilog.c new file mode 100644 index 0000000..a03229e --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/sve/part_vect_single_iter_epilog.c @@ -0,0 +1,11 @@ +/* { dg-do compile } */ +/* { dg-options "-O3 --param vect-partial-vector-usage=1" } */ + +void +foo (short * __restrict__ a, short * __restrict__ b, short * __restrict__ c, int n) +{ + for (int i = 0; i < n; ++i) + c[i] = a[i] + b[i]; +} + +/* { dg-final { scan-assembler-times {\twhilelo\tp[0-9]+.h, wzr, [xw][0-9]+} 1 } } */ diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index ff7673d..ba36348 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -9740,12 +9740,31 @@ vect_transform_loop (loop_vec_info loop_vinfo, gimple *loop_vectorized_call) /* In these calculations the "- 1" converts loop iteration counts back to latch counts. */ if (loop->any_upper_bound) - loop->nb_iterations_upper_bound - = (final_iter_may_be_partial - ? wi::udiv_ceil (loop->nb_iterations_upper_bound + bias_for_lowest, - lowest_vf) - 1 - : wi::udiv_floor (loop->nb_iterations_upper_bound + bias_for_lowest, - lowest_vf) - 1); + { + loop_vec_info main_vinfo = LOOP_VINFO_ORIG_LOOP_INFO (loop_vinfo); + loop->nb_iterations_upper_bound + = (final_iter_may_be_partial + ? wi::udiv_ceil (loop->nb_iterations_upper_bound + bias_for_lowest, + lowest_vf) - 1 + : wi::udiv_floor (loop->nb_iterations_upper_bound + bias_for_lowest, + lowest_vf) - 1); + if (main_vinfo) + { + unsigned int bound; + poly_uint64 main_iters + = upper_bound (LOOP_VINFO_VECT_FACTOR (main_vinfo), + LOOP_VINFO_COST_MODEL_THRESHOLD (main_vinfo)); + main_iters + = upper_bound (main_iters, + LOOP_VINFO_VERSIONING_THRESHOLD (main_vinfo)); + if (can_div_away_from_zero_p (main_iters, + LOOP_VINFO_VECT_FACTOR (loop_vinfo), + &bound)) + loop->nb_iterations_upper_bound + = wi::umin ((widest_int) (bound - 1), + loop->nb_iterations_upper_bound); + } + } if (loop->any_likely_upper_bound) loop->nb_iterations_likely_upper_bound = (final_iter_may_be_partial |