diff options
| author | Wilco Dijkstra <wdijkstr@arm.com> | 2016-11-14 11:51:33 +0000 |
|---|---|---|
| committer | Wilco Dijkstra <wilco@gcc.gnu.org> | 2016-11-14 11:51:33 +0000 |
| commit | db4a1c18ceb5aede224c92ec4c86723f6fb93514 (patch) | |
| tree | 4db5c2ad9238d945e3706325100f5638472d8299 | |
| parent | 725bbb80d69c0c0c72b2e83100f6c57dbf38e3e2 (diff) | |
| download | gcc-db4a1c18ceb5aede224c92ec4c86723f6fb93514.tar.gz | |
The existing vector costs stop some beneficial vectorization.
The existing vector costs stop some beneficial vectorization. This is mostly
due to vector statement cost being set to 3 as well as vector loads having a
higher cost than scalar loads. This means that even when we vectorize 4x, it
is possible that the cost of a vectorized loop is similar to the scalar
version, and we fail to vectorize.
Using a cost of 3 for a vector operation suggests they are 3 times as
expensive as scalar operations. Since most vector operations have a
similar throughput as scalar operations, this is not correct.
Using slightly lower values for these heuristics now allows this loop
and many others to be vectorized. On a proprietary benchmark the gain
from vectorizing this loop is around 15-30% which shows vectorizing it is
indeed beneficial.
* config/aarch64/aarch64.c (cortexa57_vector_cost):
Change vec_stmt_cost, vec_align_load_cost and vec_unalign_load_cost.
From-SVN: r242383
| -rw-r--r-- | gcc/ChangeLog | 5 | ||||
| -rw-r--r-- | gcc/config/aarch64/aarch64.c | 6 |
2 files changed, 8 insertions, 3 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index a4f6a34f8f1..b3967a245de 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,8 @@ +2016-11-14 Wilco Dijkstra <wdijkstr@arm.com> + + * config/aarch64/aarch64.c (cortexa57_vector_cost): + Change vec_stmt_cost, vec_align_load_cost and vec_unalign_load_cost. + 2016-11-14 Richard Biener <rguenther@suse.de> PR tree-optimization/78312 diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c index b7d4640826a..bd97c5b701c 100644 --- a/gcc/config/aarch64/aarch64.c +++ b/gcc/config/aarch64/aarch64.c @@ -398,12 +398,12 @@ static const struct cpu_vector_cost cortexa57_vector_cost = 1, /* scalar_stmt_cost */ 4, /* scalar_load_cost */ 1, /* scalar_store_cost */ - 3, /* vec_stmt_cost */ + 2, /* vec_stmt_cost */ 3, /* vec_permute_cost */ 8, /* vec_to_scalar_cost */ 8, /* scalar_to_vec_cost */ - 5, /* vec_align_load_cost */ - 5, /* vec_unalign_load_cost */ + 4, /* vec_align_load_cost */ + 4, /* vec_unalign_load_cost */ 1, /* vec_unalign_store_cost */ 1, /* vec_store_cost */ 1, /* cond_taken_branch_cost */ |