aboutsummaryrefslogtreecommitdiff
path: root/gcc/tree-vect-loop.c
diff options
context:
space:
mode:
authorTamar Christina <tamar.christina@arm.com>2021-07-14 14:54:26 +0100
committerTamar Christina <tamar.christina@arm.com>2021-07-14 14:54:26 +0100
commitab0a6b213abf6843b59cdea6399030e828109551 (patch)
treea351721ec47290ef4a9aed4819bf722fbf31cb98 /gcc/tree-vect-loop.c
parentcc11b924bfe7752edbba052ca71653f46a60887a (diff)
downloadgcc-ab0a6b213abf6843b59cdea6399030e828109551.zip
gcc-ab0a6b213abf6843b59cdea6399030e828109551.tar.gz
gcc-ab0a6b213abf6843b59cdea6399030e828109551.tar.bz2
Vect: Add support for dot-product where the sign for the multiplicant changes.
This patch adds support for a dot product where the sign of the multiplication arguments differ. i.e. one is signed and one is unsigned but the precisions are the same. #define N 480 #define SIGNEDNESS_1 unsigned #define SIGNEDNESS_2 signed #define SIGNEDNESS_3 signed #define SIGNEDNESS_4 unsigned SIGNEDNESS_1 int __attribute__ ((noipa)) f (SIGNEDNESS_1 int res, SIGNEDNESS_3 char *restrict a, SIGNEDNESS_4 char *restrict b) { for (__INTPTR_TYPE__ i = 0; i < N; ++i) { int av = a[i]; int bv = b[i]; SIGNEDNESS_2 short mult = av * bv; res += mult; } return res; } The operations are performed as if the operands were extended to a 32-bit value. As such this operation isn't valid if there is an intermediate conversion to an unsigned value. i.e. if SIGNEDNESS_2 is unsigned. more over if the signs of SIGNEDNESS_3 and SIGNEDNESS_4 are flipped the same optab is used but the operands are flipped in the optab expansion. To support this the patch extends the dot-product detection to optionally ignore operands with different signs and stores this information in the optab subtype which is now made a bitfield. The subtype can now additionally controls which optab an EXPR can expand to. gcc/ChangeLog: * optabs.def (usdot_prod_optab): New. * doc/md.texi: Document it and clarify other dot prod optabs. * optabs-tree.h (enum optab_subtype): Add optab_vector_mixed_sign. * optabs-tree.c (optab_for_tree_code): Support usdot_prod_optab. * optabs.c (expand_widen_pattern_expr): Likewise. * tree-cfg.c (verify_gimple_assign_ternary): Likewise. * tree-vect-loop.c (vectorizable_reduction): Query dot-product kind. * tree-vect-patterns.c (vect_supportable_direct_optab_p): Take optional optab subtype. (vect_widened_op_tree): Optionally ignore mismatch types. (vect_recog_dot_prod_pattern): Support usdot_prod_optab.
Diffstat (limited to 'gcc/tree-vect-loop.c')
-rw-r--r--gcc/tree-vect-loop.c8
1 files changed, 7 insertions, 1 deletions
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index e978015..fc3dab0 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -6661,6 +6661,12 @@ vectorizable_reduction (loop_vec_info loop_vinfo,
bool lane_reduc_code_p
= (code == DOT_PROD_EXPR || code == WIDEN_SUM_EXPR || code == SAD_EXPR);
int op_type = TREE_CODE_LENGTH (code);
+ enum optab_subtype optab_query_kind = optab_vector;
+ if (code == DOT_PROD_EXPR
+ && TYPE_SIGN (TREE_TYPE (gimple_assign_rhs1 (stmt)))
+ != TYPE_SIGN (TREE_TYPE (gimple_assign_rhs2 (stmt))))
+ optab_query_kind = optab_vector_mixed_sign;
+
scalar_dest = gimple_assign_lhs (stmt);
scalar_type = TREE_TYPE (scalar_dest);
@@ -7189,7 +7195,7 @@ vectorizable_reduction (loop_vec_info loop_vinfo,
bool ok = true;
/* 4.1. check support for the operation in the loop */
- optab optab = optab_for_tree_code (code, vectype_in, optab_vector);
+ optab optab = optab_for_tree_code (code, vectype_in, optab_query_kind);
if (!optab)
{
if (dump_enabled_p ())