[gcc r12-1107] Recognize popcount also when a double width operation is needed.

[gcc r12-1107] Recognize popcount also when a double width operation is needed.

[Joern Rennecke]

https://gcc.gnu.org/g:5b43f6ace51c08dc2bae3c91a2a11300356c573d

commit r12-1107-g5b43f6ace51c08dc2bae3c91a2a11300356c573d
Author: Joern Rennecke <joern.rennecke@riscy-ip.com>
Date:   Fri May 28 09:34:07 2021 +0100

    Recognize popcount also when a double width operation is needed.
    
    2021-05-28  Joern Rennecke  <joern.rennecke@riscy-ip.com>
    gcc/
            * match.pd <popcount & / + pattern matching>:
            When generating popcount directly fails, try doing it in two halves.
    gcc/testsuite/
            * gcc.dg/tree-ssa/popcount4ll.c: Remove lp64 condition.
            Adjust scanning pattern for !lp64.
            * gcc.dg/tree-ssa/popcount5ll.c: Likewise.
            * gcc.dg/tree-ssa/popcount4l.c: Adjust scanning pattern
            for ! int32plus.
    
    Co-Authored-By: Richard Biener  <rguenther@suse.de>

Diff:
---
 gcc/match.pd                                | 29 +++++++++++++++++++++++++----
 gcc/testsuite/gcc.dg/tree-ssa/popcount4l.c  |  3 ++-
 gcc/testsuite/gcc.dg/tree-ssa/popcount4ll.c |  5 +++--
 gcc/testsuite/gcc.dg/tree-ssa/popcount5ll.c |  5 +++--
 4 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/gcc/match.pd b/gcc/match.pd
index b60e2703f60..d06ff170684 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -6642,10 +6642,31 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
 	&& tree_to_uhwi (@3) == c2
 	&& tree_to_uhwi (@9) == c3
 	&& tree_to_uhwi (@7) == c3
-	&& tree_to_uhwi (@11) == c4
-	&& direct_internal_fn_supported_p (IFN_POPCOUNT, type,
-					   OPTIMIZE_FOR_BOTH))
-    (convert (IFN_POPCOUNT:type @0)))))
+	&& tree_to_uhwi (@11) == c4)
+    (if (direct_internal_fn_supported_p (IFN_POPCOUNT, type,
+					 OPTIMIZE_FOR_BOTH))
+     (convert (IFN_POPCOUNT:type @0))
+     /* Try to do popcount in two halves.  PREC must be at least
+	five bits for this to work without extension before adding.  */
+     (with {
+       tree half_type = NULL_TREE;
+       opt_machine_mode m = mode_for_size ((prec + 1) / 2, MODE_INT, 1);
+       int half_prec = 8;
+       if (m.exists ()
+	   && m.require () != TYPE_MODE (type))
+	 {
+	   half_prec = GET_MODE_PRECISION (as_a <scalar_int_mode> (m));
+	   half_type = build_nonstandard_integer_type (half_prec, 1);
+	 }
+       gcc_assert (half_prec > 2);
+      }
+      (if (half_type != NULL_TREE
+	   && direct_internal_fn_supported_p (IFN_POPCOUNT, half_type,
+					      OPTIMIZE_FOR_BOTH))
+       (convert (plus
+	 (IFN_POPCOUNT:half_type (convert @0))
+	 (IFN_POPCOUNT:half_type (convert (rshift @0
+	    { build_int_cst (integer_type_node, half_prec); } )))))))))))
 
 /* __builtin_ffs needs to deal on many targets with the possible zero
    argument.  If we know the argument is always non-zero, __builtin_ctz + 1
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/popcount4l.c b/gcc/testsuite/gcc.dg/tree-ssa/popcount4l.c
index 69fb2d1134d..269e56e90f9 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/popcount4l.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/popcount4l.c
@@ -25,6 +25,7 @@ int popcount64c(unsigned long x)
     return (x * h01) >> shift;
 }
 
-/* { dg-final { scan-tree-dump-times "\.POPCOUNT" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "\.POPCOUNT" 1 "optimized" { target int32plus } } } */
+/* { dg-final { scan-tree-dump "\.POPCOUNT" "optimized" { target { ! int32plus } } } } */
 
 
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/popcount4ll.c b/gcc/testsuite/gcc.dg/tree-ssa/popcount4ll.c
index c1588be68e4..7abadf6df04 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/popcount4ll.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/popcount4ll.c
@@ -1,4 +1,4 @@
-/* { dg-do compile { target { lp64 } } } */
+/* { dg-do compile } */
 /* { dg-require-effective-target popcountll } */
 /* { dg-options "-O2 -fdump-tree-optimized" } */
 
@@ -16,4 +16,5 @@ int popcount64c(unsigned long long x)
     return (x * h01) >> shift;
 }
 
-/* { dg-final { scan-tree-dump-times "\.POPCOUNT" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "\.POPCOUNT" 1 "optimized" { target { lp64 } } } } */
+/* { dg-final { scan-tree-dump-times "\.POPCOUNT" 2 "optimized" { target { ! lp64 } } } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/popcount5ll.c b/gcc/testsuite/gcc.dg/tree-ssa/popcount5ll.c
index edb191bf894..2afe08124fe 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/popcount5ll.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/popcount5ll.c
@@ -1,5 +1,5 @@
 /* PR tree-optimization/94800 */
-/* { dg-do compile { target { lp64 } } } */
+/* { dg-do compile } */
 /* { dg-require-effective-target popcountll } */
 /* { dg-options "-O2 -fdump-tree-optimized" } */
 
@@ -19,4 +19,5 @@ int popcount64c(unsigned long long x)
     return x >> shift;
 }
 
-/* { dg-final { scan-tree-dump-times "\.POPCOUNT" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "\.POPCOUNT" 1 "optimized" { target { lp64 } } } } */
+/* { dg-final { scan-tree-dump-times "\.POPCOUNT" 2 "optimized" { target { ! lp64 } } } } */