Fix PR43430: vectorize conditionals with multiple types
Michael Matz
matz@suse.de
Tue Sep 7 13:35:00 GMT 2010
Hi,
for this testcase we need to emit multiple vectorized conditional
statement per original statement (ncopies > 1). This patch implements the
support for that in case the conditional isn't part of a reduction (I'm
didn't 100% follow the code under which conditions reduc_index is != 0 and
what reduc_def then is, exactly).
Regstrapped on x86_64-linux, no regressions. Okay?
Ciao,
Michael.
--
PR tree-optimization/43430
* tree-vect-stmts.c (vectorizable_condition): Support multiple
copies for conditional statements if it's not part of a reduction.
testsuite/
PR tree-optimization/43430
* gcc.dg/vect/pr43430-2.c: New test.
Index: tree-vect-stmts.c
===================================================================
--- tree-vect-stmts.c (revision 163773)
+++ tree-vect-stmts.c (working copy)
@@ -4011,16 +4011,18 @@ vectorizable_condition (gimple stmt, gim
loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
enum machine_mode vec_mode;
tree def;
- enum vect_def_type dt;
+ enum vect_def_type dt, dts[4];
int nunits = TYPE_VECTOR_SUBPARTS (vectype);
int ncopies = LOOP_VINFO_VECT_FACTOR (loop_vinfo) / nunits;
enum tree_code code;
+ stmt_vec_info prev_stmt_info = NULL;
+ int j;
/* FORNOW: unsupported in basic block SLP. */
gcc_assert (loop_vinfo);
gcc_assert (ncopies >= 1);
- if (ncopies > 1)
+ if (reduc_index && ncopies > 1)
return false; /* FORNOW */
if (!STMT_VINFO_RELEVANT_P (stmt_info))
@@ -4107,29 +4109,68 @@ vectorizable_condition (gimple stmt, gim
vec_dest = vect_create_destination_var (scalar_dest, vectype);
/* Handle cond expr. */
- vec_cond_lhs =
- vect_get_vec_def_for_operand (TREE_OPERAND (cond_expr, 0), stmt, NULL);
- vec_cond_rhs =
- vect_get_vec_def_for_operand (TREE_OPERAND (cond_expr, 1), stmt, NULL);
- if (reduc_index == 1)
- vec_then_clause = reduc_def;
- else
- vec_then_clause = vect_get_vec_def_for_operand (then_clause, stmt, NULL);
- if (reduc_index == 2)
- vec_else_clause = reduc_def;
- else
- vec_else_clause = vect_get_vec_def_for_operand (else_clause, stmt, NULL);
-
- /* Arguments are ready. Create the new vector stmt. */
- vec_compare = build2 (TREE_CODE (cond_expr), vectype,
- vec_cond_lhs, vec_cond_rhs);
- vec_cond_expr = build3 (VEC_COND_EXPR, vectype,
- vec_compare, vec_then_clause, vec_else_clause);
-
- *vec_stmt = gimple_build_assign (vec_dest, vec_cond_expr);
- new_temp = make_ssa_name (vec_dest, *vec_stmt);
- gimple_assign_set_lhs (*vec_stmt, new_temp);
- vect_finish_stmt_generation (stmt, *vec_stmt, gsi);
+ for (j = 0; j < ncopies; j++)
+ {
+ gimple new_stmt;
+ if (j == 0)
+ {
+ gimple gtemp;
+ vec_cond_lhs =
+ vect_get_vec_def_for_operand (TREE_OPERAND (cond_expr, 0),
+ stmt, NULL);
+ vect_is_simple_use (TREE_OPERAND (cond_expr, 0), loop_vinfo,
+ NULL, >emp, &def, &dts[0]);
+ vec_cond_rhs =
+ vect_get_vec_def_for_operand (TREE_OPERAND (cond_expr, 1),
+ stmt, NULL);
+ vect_is_simple_use (TREE_OPERAND (cond_expr, 1), loop_vinfo,
+ NULL, >emp, &def, &dts[1]);
+ if (reduc_index == 1)
+ vec_then_clause = reduc_def;
+ else
+ {
+ vec_then_clause = vect_get_vec_def_for_operand (then_clause,
+ stmt, NULL);
+ vect_is_simple_use (then_clause, loop_vinfo,
+ NULL, >emp, &def, &dts[2]);
+ }
+ if (reduc_index == 2)
+ vec_else_clause = reduc_def;
+ else
+ {
+ vec_else_clause = vect_get_vec_def_for_operand (else_clause,
+ stmt, NULL);
+ vect_is_simple_use (else_clause, loop_vinfo,
+ NULL, >emp, &def, &dts[3]);
+ }
+ }
+ else
+ {
+ vec_cond_lhs = vect_get_vec_def_for_stmt_copy (dts[0], vec_cond_lhs);
+ vec_cond_rhs = vect_get_vec_def_for_stmt_copy (dts[1], vec_cond_rhs);
+ vec_then_clause = vect_get_vec_def_for_stmt_copy (dts[2],
+ vec_then_clause);
+ vec_else_clause = vect_get_vec_def_for_stmt_copy (dts[3],
+ vec_else_clause);
+ }
+
+ /* Arguments are ready. Create the new vector stmt. */
+ vec_compare = build2 (TREE_CODE (cond_expr), vectype,
+ vec_cond_lhs, vec_cond_rhs);
+ vec_cond_expr = build3 (VEC_COND_EXPR, vectype,
+ vec_compare, vec_then_clause, vec_else_clause);
+
+ new_stmt = gimple_build_assign (vec_dest, vec_cond_expr);
+ new_temp = make_ssa_name (vec_dest, new_stmt);
+ gimple_assign_set_lhs (new_stmt, new_temp);
+ vect_finish_stmt_generation (stmt, new_stmt, gsi);
+ if (j == 0)
+ STMT_VINFO_VEC_STMT (stmt_info) = *vec_stmt = new_stmt;
+ else
+ STMT_VINFO_RELATED_STMT (prev_stmt_info) = new_stmt;
+
+ prev_stmt_info = vinfo_for_stmt (new_stmt);
+ }
return true;
}
Index: testsuite/gcc.dg/vect/pr43430-2.c
===================================================================
--- testsuite/gcc.dg/vect/pr43430-2.c (revision 0)
+++ testsuite/gcc.dg/vect/pr43430-2.c (revision 0)
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-options "-O3 -fno-vect-cost-model -fdump-tree-vect-details" } */
+typedef unsigned char uint8_t;
+vsad16_c (void *c, uint8_t * s1, uint8_t * s2, int stride, int h)
+{
+ int score = 0;
+ int x, y;
+ for (x = 0; x < 16; x++)
+ score += ((s1[x] - s1[x + stride] + s2[x + stride]) >= 0 ?
+ s1[x] + s2[x + stride] :
+ s2[x + stride]);
+ return score;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_condition } } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
More information about the Gcc-patches
mailing list