Hi,
This patch adds a missing handling of MAX/MIN_EXPR in SLP reduction.
Boostrapped and tested on powerpc64-suse-linux.
Committed to trunk.
Ira
ChangeLog:
PR tree-optimization/50414
* tree-vect-slp.c (vect_get_constant_vectors): Handle MAX_EXPR and
MIN_EXPR.
testsuite/ChangeLog:
PR tree-optimization/50414
* gfortran.dg/vect/Ofast-pr50414.f90: New.
* gfortran.dg/vect/vect.exp: Run Ofast-* tests with -Ofast.
* gcc.dg/vect/no-scevccp-noreassoc-slp-reduc-7.c: New.
Index: tree-vect-slp.c
===================================================================
--- tree-vect-slp.c (revision 178939)
+++ tree-vect-slp.c (working copy)
@@ -1902,6 +1902,8 @@ vect_get_constant_vectors (tree op, slp_tree slp_n
bool constant_p, is_store;
tree neutral_op = NULL;
enum tree_code code = gimple_assign_rhs_code (stmt);
+ gimple def_stmt;
+ struct loop *loop;
if (STMT_VINFO_DEF_TYPE (stmt_vinfo) == vect_reduction_def)
{
@@ -1943,8 +1945,16 @@ vect_get_constant_vectors (tree op, slp_tree slp_n
neutral_op = build_int_cst (TREE_TYPE (op), -1);
break;
+ case MAX_EXPR:
+ case MIN_EXPR:
+ def_stmt = SSA_NAME_DEF_STMT (op);
+ loop = (gimple_bb (stmt))->loop_father;
+ neutral_op = PHI_ARG_DEF_FROM_EDGE (def_stmt,
+ loop_preheader_edge (loop));
+ break;
+
default:
- neutral_op = NULL;
+ neutral_op = NULL;
}
}
@@ -1997,8 +2007,8 @@ vect_get_constant_vectors (tree op, slp_tree slp_n
if (reduc_index != -1)
{
- struct loop *loop = (gimple_bb (stmt))->loop_father;
- gimple def_stmt = SSA_NAME_DEF_STMT (op);
+ loop = (gimple_bb (stmt))->loop_father;
+ def_stmt = SSA_NAME_DEF_STMT (op);
gcc_assert (loop);
Index: testsuite/gfortran.dg/vect/Ofast-pr50414.f90
===================================================================
--- testsuite/gfortran.dg/vect/Ofast-pr50414.f90 (revision 0)
+++ testsuite/gfortran.dg/vect/Ofast-pr50414.f90 (revision 0)
@@ -0,0 +1,11 @@
+! { dg-do compile }
+
+ SUBROUTINE SUB (A,L,YMAX)
+ DIMENSION A(L)
+ YMA=A(1)
+ DO 2 I=1,L,2
+ 2 YMA=MAX(YMA,A(I),A(I+1))
+ CALL PROUND(YMA)
+ END
+
+! { dg-final { cleanup-tree-dump "vect" } }
Index: testsuite/gfortran.dg/vect/vect.exp
===================================================================
--- testsuite/gfortran.dg/vect/vect.exp (revision 178939)
+++ testsuite/gfortran.dg/vect/vect.exp (working copy)
@@ -84,6 +84,12 @@ lappend DEFAULT_VECTCFLAGS "-O3"
dg-runtest [lsort [glob -nocomplain
$srcdir/$subdir/O3-*.\[fF\]{,90,95,03,08} ]] \
"" $DEFAULT_VECTCFLAGS
+# With -Ofast
+set DEFAULT_VECTCFLAGS $SAVED_DEFAULT_VECTCFLAGS
+lappend DEFAULT_VECTCFLAGS "-Ofast"
+dg-runtest [lsort [glob -nocomplain
$srcdir/$subdir/Ofast-*.\[fF\]{,90,95,03,08} ]] \
+ "" $DEFAULT_VECTCFLAGS
+
# Clean up.
set dg-do-what-default ${save-dg-do-what-default}
Index: testsuite/gcc.dg/vect/no-scevccp-noreassoc-slp-reduc-7.c
===================================================================
--- testsuite/gcc.dg/vect/no-scevccp-noreassoc-slp-reduc-7.c (revision 0)
+++ testsuite/gcc.dg/vect/no-scevccp-noreassoc-slp-reduc-7.c (revision 0)
@@ -0,0 +1,42 @@
+/* { dg-require-effective-target vect_int } */
+
+#include <stdarg.h>
+#include "tree-vect.h"
+
+#define N 16
+#define MAX 121
+
+unsigned int ub[N] = {0,3,6,9,12,15,18,121,24,27,113,33,36,39,42,45};
+
+/* Vectorization of reduction using loop-aware SLP (with unrolling). */
+
+__attribute__ ((noinline))
+int main1 (int n)
+{
+ int i;
+ unsigned int max = 50;
+
+ for (i = 0; i < n; i++) {
+ max = max < ub[2*i] ? ub[2*i] : max;
+ max = max < ub[2*i + 1] ? ub[2*i + 1] : max;
+ }
+
+ /* Check results: */
+ if (max != MAX)
+ abort ();
+
+ return 0;
+}
+
+int main (void)
+{
+ check_vect ();
+
+ main1 (N/2);
+ return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" {
xfail vect_no_int_max } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1
"vect" { xfail vect_no_int_max } } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
+
