Hi,
When we use LTO for fortran we may have a mix 32bit and 1bit scalar booleans.
It means we may have conversion of one scalar type to another which confuses
vectorizer because values with different scalar boolean type may get the same
vectype. This patch transforms such conversions into comparison.
I managed to make a small fortran test which gets vectorized with this patch
but I didn't find how I can run fortran test with LTO and then scan tree dump
to check it is vectorized. BTW here is a loop from the test:
real*8 a(18)
logical b(18)
integer i
do i=1,18
if(a(i).gt.0.d0) then
b(i)=.true.
else
b(i)=.false.
endif
enddo
Bootstrapped and tested on x86_64-unknown-linux-gnu. OK for trunk?
Thanks,
Ilya
--
gcc/
2015-11-12 Ilya Enkovich <enkovich....@gmail.com>
* tree-vect-patterns.c (vect_recog_mask_conversion_pattern):
Transform useless boolean conversion into assignment.
diff --git a/gcc/tree-vect-patterns.c b/gcc/tree-vect-patterns.c
index b9d900c..62070da 100644
--- a/gcc/tree-vect-patterns.c
+++ b/gcc/tree-vect-patterns.c
@@ -3674,6 +3674,38 @@ vect_recog_mask_conversion_pattern (vec<gimple *>
*stmts, tree *type_in,
if (TREE_CODE (TREE_TYPE (lhs)) != BOOLEAN_TYPE)
return NULL;
+ /* Check conversion between boolean types of different sizes.
+ If no vectype is specified, then we have a regular mask
+ assignment with no actual conversion. */
+ if (rhs_code == CONVERT_EXPR
+ && !STMT_VINFO_DATA_REF (stmt_vinfo)
+ && !STMT_VINFO_VECTYPE (stmt_vinfo))
+ {
+ if (TREE_CODE (rhs1) != SSA_NAME)
+ return NULL;
+
+ rhs1_type = search_type_for_mask (rhs1, vinfo);
+ if (!rhs1_type)
+ return NULL;
+
+ vectype1 = get_mask_type_for_scalar_type (rhs1_type);
+
+ if (!vectype1)
+ return NULL;
+
+ lhs = vect_recog_temp_ssa_var (TREE_TYPE (lhs), NULL);
+ pattern_stmt = gimple_build_assign (lhs, rhs1);
+
+ *type_out = vectype1;
+ *type_in = vectype1;
+ stmts->safe_push (last_stmt);
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "vect_recog_mask_conversion_pattern: detected:\n");
+
+ return pattern_stmt;
+ }
+
if (rhs_code != BIT_IOR_EXPR
&& rhs_code != BIT_XOR_EXPR
&& rhs_code != BIT_AND_EXPR)
