[gcc r15-274] tree-optimization/110490 - bitcount for narrow modes

[Stefan Schulze Frielinghaus via Gcc-cvs]

https://gcc.gnu.org/g:e1f56c67a82172730c377a96a46e8d75445e6a48

commit r15-274-ge1f56c67a82172730c377a96a46e8d75445e6a48
Author: Stefan Schulze Frielinghaus <stefa...@linux.ibm.com>
Date:   Tue May 7 14:12:55 2024 +0200

    tree-optimization/110490 - bitcount for narrow modes
    
    Bitcount operations popcount, clz, and ctz are emulated for narrow modes
    in case an operation is only supported for wider modes.  Beside that ctz
    may be emulated via clz in expand_ctz.  Reflect this in
    expression_expensive_p.
    
    I considered the emulation of ctz via clz as not expensive since this
    basically reduces to ctz (x) = c - (clz (x & ~x)) where c is the mode
    precision minus 1 which should be faster than a loop.
    
    gcc/ChangeLog:
    
            PR tree-optimization/110490
            * tree-scalar-evolution.cc (expression_expensive_p): Also
            consider mode widening for popcount, clz, and ctz.

Diff:
---
 gcc/tree-scalar-evolution.cc | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/gcc/tree-scalar-evolution.cc b/gcc/tree-scalar-evolution.cc
index b0a5e09a77c..622c7246c1b 100644
--- a/gcc/tree-scalar-evolution.cc
+++ b/gcc/tree-scalar-evolution.cc
@@ -3458,6 +3458,28 @@ bitcount_call:
                  && (optab_handler (optab, word_mode)
                      != CODE_FOR_nothing))
                  break;
+             /* If popcount is available for a wider mode, we emulate the
+                operation for a narrow mode by first zero-extending the value
+                and then computing popcount in the wider mode.  Analogue for
+                ctz.  For clz we do the same except that we additionally have
+                to subtract the difference of the mode precisions from the
+                result.  */
+             if (is_a <scalar_int_mode> (mode, &int_mode))
+               {
+                 machine_mode wider_mode_iter;
+                 FOR_EACH_WIDER_MODE (wider_mode_iter, mode)
+                   if (optab_handler (optab, wider_mode_iter)
+                       != CODE_FOR_nothing)
+                     goto check_call_args;
+                 /* Operation ctz may be emulated via clz in expand_ctz.  */
+                 if (optab == ctz_optab)
+                   {
+                     FOR_EACH_WIDER_MODE_FROM (wider_mode_iter, mode)
+                       if (optab_handler (clz_optab, wider_mode_iter)
+                           != CODE_FOR_nothing)
+                         goto check_call_args;
+                   }
+               }
              return true;
            }
          break;
@@ -3469,6 +3491,7 @@ bitcount_call:
          break;
        }
 
+check_call_args:
       FOR_EACH_CALL_EXPR_ARG (arg, iter, expr)
        if (expression_expensive_p (arg, cond_overflow_p, cache, op_cost))
          return true;