diff options
| author | Alejandro Martinez <alejandro.martinezvicente@arm.com> | 2019-05-28 13:48:44 +0000 |
|---|---|---|
| committer | Alejandro Martinez <alejandro@gcc.gnu.org> | 2019-05-28 13:48:44 +0000 |
| commit | 997636716c5dde7d59d026726a6f58918069f122 (patch) | |
| tree | d18d1d7f5388bc0bb743583ce506e284c8eb60d3 /gcc/tree-vect-data-refs.c | |
| parent | 8b4e7143550cd1f3f4b1dca005a5e656506979d9 (diff) | |
| download | gcc-997636716c5dde7d59d026726a6f58918069f122.zip gcc-997636716c5dde7d59d026726a6f58918069f122.tar.gz gcc-997636716c5dde7d59d026726a6f58918069f122.tar.bz2 | |
Current vectoriser doesn't support masked loads for SLP.
Current vectoriser doesn't support masked loads for SLP. We should add that, to
allow things like:
void
f (int *restrict x, int *restrict y, int *restrict z, int n)
{
for (int i = 0; i < n; i += 2)
{
x[i] = y[i] ? z[i] : 1;
x[i + 1] = y[i + 1] ? z[i + 1] : 2;
}
}
to be vectorized using contiguous loads rather than LD2 and ST2.
This patch was motivated by SVE, but it is completely generic and should apply
to any architecture with masked loads.
From-SVN: r271704
Diffstat (limited to 'gcc/tree-vect-data-refs.c')
| -rw-r--r-- | gcc/tree-vect-data-refs.c | 18 |
1 files changed, 14 insertions, 4 deletions
diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c index d71a39f..55d87f8 100644 --- a/gcc/tree-vect-data-refs.c +++ b/gcc/tree-vect-data-refs.c @@ -2863,10 +2863,12 @@ strip_conversion (tree op) } /* Return true if vectorizable_* routines can handle statements STMT1_INFO - and STMT2_INFO being in a single group. */ + and STMT2_INFO being in a single group. When ALLOW_SLP_P, masked loads can + be grouped in SLP mode. */ static bool -can_group_stmts_p (stmt_vec_info stmt1_info, stmt_vec_info stmt2_info) +can_group_stmts_p (stmt_vec_info stmt1_info, stmt_vec_info stmt2_info, + bool allow_slp_p) { if (gimple_assign_single_p (stmt1_info->stmt)) return gimple_assign_single_p (stmt2_info->stmt); @@ -2888,7 +2890,8 @@ can_group_stmts_p (stmt_vec_info stmt1_info, stmt_vec_info stmt2_info) like those created by build_mask_conversion. */ tree mask1 = gimple_call_arg (call1, 2); tree mask2 = gimple_call_arg (call2, 2); - if (!operand_equal_p (mask1, mask2, 0)) + if (!operand_equal_p (mask1, mask2, 0) + && (ifn == IFN_MASK_STORE || !allow_slp_p)) { mask1 = strip_conversion (mask1); if (!mask1) @@ -2974,7 +2977,7 @@ vect_analyze_data_ref_accesses (vec_info *vinfo) || data_ref_compare_tree (DR_BASE_ADDRESS (dra), DR_BASE_ADDRESS (drb)) != 0 || data_ref_compare_tree (DR_OFFSET (dra), DR_OFFSET (drb)) != 0 - || !can_group_stmts_p (stmtinfo_a, stmtinfo_b)) + || !can_group_stmts_p (stmtinfo_a, stmtinfo_b, true)) break; /* Check that the data-refs have the same constant size. */ @@ -3059,6 +3062,13 @@ vect_analyze_data_ref_accesses (vec_info *vinfo) DR_GROUP_NEXT_ELEMENT (lastinfo) = stmtinfo_b; lastinfo = stmtinfo_b; + STMT_VINFO_SLP_VECT_ONLY (stmtinfo_a) + = !can_group_stmts_p (stmtinfo_a, stmtinfo_b, false); + + if (dump_enabled_p () && STMT_VINFO_SLP_VECT_ONLY (stmtinfo_a)) + dump_printf_loc (MSG_NOTE, vect_location, + "Load suitable for SLP vectorization only.\n"); + if (init_b == init_prev && !to_fixup.add (DR_GROUP_FIRST_ELEMENT (stmtinfo_a)) && dump_enabled_p ()) |