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 --git a/gcc/tree-scalar-evolution.cc b/gcc/tree-scalar-evolution.cc
index b0a5e09a77c106c6f1ceb7e0a1e7f7b904db92d4..622c7246c1b96197e1bcac4c0dcc95e01be7588e 100644 (file)
--- 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;