From f648c88b12ab498c8a60fb16eaccbdeff68ce927 Mon Sep 17 00:00:00 2001 From: Yvan Roux Date: Tue, 6 Sep 2016 14:41:14 +0200 Subject: gcc/ Backport from trunk r236632. 2016-05-24 Richard Sandiford * tree-vect-stmts.c (vectorizable_load): Reorder checks so that load_lanes/grouped_load classification comes first. Don't check whether the vectorization factor is a multiple of the group size for load_lanes. gcc/testsuite/ Backport from trunk r236632. 2016-05-24 Richard Sandiford * gcc.dg/vect/vect-load-lanes-peeling-1.c: New test. Change-Id: I990689cf9c5b4f1d721e51c4d76157d5670b97e5 --- .../gcc.dg/vect/vect-load-lanes-peeling-1.c | 13 +++++++++++ gcc/tree-vect-stmts.c | 25 +++++++++++----------- 2 files changed, 25 insertions(+), 13 deletions(-) create mode 100644 gcc/testsuite/gcc.dg/vect/vect-load-lanes-peeling-1.c diff --git a/gcc/testsuite/gcc.dg/vect/vect-load-lanes-peeling-1.c b/gcc/testsuite/gcc.dg/vect/vect-load-lanes-peeling-1.c new file mode 100644 index 00000000000..c9cd104e8e5 --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/vect-load-lanes-peeling-1.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target vect_int } */ +/* { dg-require-effective-target vect_load_lanes } */ + +void +f (int *__restrict a, int *__restrict b) +{ + for (int i = 0; i < 96; ++i) + a[i] = b[i * 3] + b[i * 3 + 1] + b[i * 3 + 2]; +} + +/* { dg-final { scan-tree-dump-not "Data access with gaps" "vect" } } */ +/* { dg-final { scan-tree-dump-not "epilog loop required" "vect" } } */ diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c index f765f6ee6bc..44b2e138326 100644 --- a/gcc/tree-vect-stmts.c +++ b/gcc/tree-vect-stmts.c @@ -6323,6 +6323,17 @@ vectorizable_load (gimple *stmt, gimple_stmt_iterator *gsi, gimple **vec_stmt, gcc_assert (!nested_in_vect_loop && !STMT_VINFO_GATHER_SCATTER_P (stmt_info)); first_stmt = GROUP_FIRST_ELEMENT (stmt_info); + group_size = GROUP_SIZE (vinfo_for_stmt (first_stmt)); + + if (!slp + && !PURE_SLP_STMT (stmt_info) + && !STMT_VINFO_STRIDED_P (stmt_info)) + { + if (vect_load_lanes_supported (vectype, group_size)) + load_lanes_p = true; + else if (!vect_grouped_load_supported (vectype, group_size)) + return false; + } /* If this is single-element interleaving with an element distance that leaves unused vector loads around punt - we at least create @@ -6350,7 +6361,7 @@ vectorizable_load (gimple *stmt, gimple_stmt_iterator *gsi, gimple **vec_stmt, if (loop_vinfo && ! STMT_VINFO_STRIDED_P (stmt_info) && (GROUP_GAP (vinfo_for_stmt (first_stmt)) != 0 - || (!slp && vf % GROUP_SIZE (vinfo_for_stmt (first_stmt)) != 0))) + || (!slp && !load_lanes_p && vf % group_size != 0))) { if (dump_enabled_p ()) dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location, @@ -6370,8 +6381,6 @@ vectorizable_load (gimple *stmt, gimple_stmt_iterator *gsi, gimple **vec_stmt, if (slp && SLP_TREE_LOAD_PERMUTATION (slp_node).exists ()) slp_perm = true; - group_size = GROUP_SIZE (vinfo_for_stmt (first_stmt)); - /* ??? The following is overly pessimistic (as well as the loop case above) in the case we can statically determine the excess elements loaded are within the bounds of a decl that is accessed. @@ -6384,16 +6393,6 @@ vectorizable_load (gimple *stmt, gimple_stmt_iterator *gsi, gimple **vec_stmt, return false; } - if (!slp - && !PURE_SLP_STMT (stmt_info) - && !STMT_VINFO_STRIDED_P (stmt_info)) - { - if (vect_load_lanes_supported (vectype, group_size)) - load_lanes_p = true; - else if (!vect_grouped_load_supported (vectype, group_size)) - return false; - } - /* Invalidate assumptions made by dependence analysis when vectorization on the unrolled body effectively re-orders stmts. */ if (!PURE_SLP_STMT (stmt_info) -- cgit v1.2.3