Hi!
On the following testcase, there are in *.optimized dump 14 nop conversions
(from signed to unsigned and back), while this patch decreases that number
to just 4; for bitwise ops it really doesn't matter if they are performed in
signed or unsigned, so the patch (in GIMPLE only, there are some comments
about it being undesirable during GENERIC earlier), if it sees both
bitop operands nop converted from the same types performs the bitop in their
non-converted type and converts the result (i.e. 2 conversions into 1),
similarly, if a bitop has one operand nop converted from something, the
other not and the result is converted back to the type of the nop converted
operand before conversion, it is possible to replace those 2 conversions
with just a single conversion of the other operand.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
2020-04-27 Jakub Jelinek <ja...@redhat.com>
PR tree-optimization/94718
* match.pd (bitop (convert @0) (convert? @1)): For GIMPLE, if we can,
replace two nop conversions on bit_{and,ior,xor} argument
and result with just one conversion on the result or another argument.
* gcc.dg/tree-ssa/pr94718-3.c: New test.
--- gcc/match.pd.jj 2020-04-24 19:12:56.969197128 +0200
+++ gcc/match.pd 2020-04-27 16:54:48.340656033 +0200
@@ -1311,7 +1311,7 @@ (define_operator_list COND_TERNARY
We combine the above two cases by using a conditional convert. */
(for bitop (bit_and bit_ior bit_xor)
(simplify
- (bitop (convert @0) (convert? @1))
+ (bitop (convert@2 @0) (convert?@3 @1))
(if (((TREE_CODE (@1) == INTEGER_CST
&& INTEGRAL_TYPE_P (TREE_TYPE (@0))
&& int_fits_type_p (@1, TREE_TYPE (@0)))
@@ -1330,8 +1330,24 @@ (define_operator_list COND_TERNARY
|| GET_MODE_CLASS (TYPE_MODE (type)) != MODE_INT
/* Or if the precision of TO is not the same as the precision
of its mode. */
- || !type_has_mode_precision_p (type)))
- (convert (bitop @0 (convert @1))))))
+ || !type_has_mode_precision_p (type)
+ /* In GIMPLE, getting rid of 2 conversions for one new results
+ in smaller IL. */
+ || (GIMPLE
+ && TREE_CODE (@1) != INTEGER_CST
+ && tree_nop_conversion_p (type, TREE_TYPE (@0))
+ && single_use (@2)
+ && single_use (@3))))
+ (convert (bitop @0 (convert @1)))))
+ /* In GIMPLE, getting rid of 2 conversions for one new results
+ in smaller IL. */
+ (simplify
+ (convert (bitop:cs@2 (nop_convert:s @0) @1))
+ (if (GIMPLE
+ && TREE_CODE (@1) != INTEGER_CST
+ && tree_nop_conversion_p (type, TREE_TYPE (@2))
+ && types_match (type, @0))
+ (bitop @0 (convert @1)))))
(for bitop (bit_and bit_ior)
rbitop (bit_ior bit_and)
--- gcc/testsuite/gcc.dg/tree-ssa/pr94718-3.c.jj 2020-04-27
16:59:33.650366084 +0200
+++ gcc/testsuite/gcc.dg/tree-ssa/pr94718-3.c 2020-04-27 16:58:46.634073029
+0200
@@ -0,0 +1,45 @@
+/* PR tree-optimization/94718 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-ipa-icf -fdump-tree-optimized" } */
+/* { dg-final { scan-tree-dump-times " \\\(int\\\) " 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " \\\(unsigned int\\\) " 2 "optimized" }
} */
+
+int
+f1 (int x, int y)
+{
+ return (int) ((unsigned) x | (unsigned) y);
+}
+
+int
+f2 (int x, int y)
+{
+ unsigned a = x;
+ unsigned b = y;
+ return a | b;
+}
+
+int
+f3 (int x, unsigned y)
+{
+ return (int) ((unsigned) x | y);
+}
+
+int
+f4 (int x, unsigned y)
+{
+ unsigned a = x;
+ return a | y;
+}
+
+unsigned
+f5 (int x, unsigned y)
+{
+ return (unsigned) (x | (int) y);
+}
+
+unsigned
+f6 (int x, unsigned y)
+{
+ int a = y;
+ return x | a;
+}
Jakub
