Use conditional internal functions in if-conversion

This patch uses IFN_COND_* to vectorise conditionally-executed,
potentially-trapping arithmetic, such as most floating-point
ops with -ftrapping-math.  E.g.:

    if (cond) { ... x = a + b; ... }

becomes:

    ...
    x = .COND_ADD (cond, a, b, else_value);
    ...

When this transformation is done on its own, the value of x for
!cond isn't important, so else_value is simply the target's
preferred_else_value (i.e. the value it can handle the most
efficiently).

However, the patch also looks for the equivalent of:

    y = cond ? x : c;

in which the "then" value is the result of the conditionally-executed
operation and the "else" value "c" is some value that is available at x.
In that case we can instead use:

    x = .COND_ADD (cond, a, b, c);

and replace uses of y with uses of x.

The patch also looks for:

    y = !cond ? c : x;

which can be transformed in the same way.  This involved adding a new
utility function inverse_conditions_p, which was already open-coded
in a more limited way in match.pd.

2018-07-12  Richard Sandiford  <richard.sandiford@linaro.org>

gcc/
	* fold-const.h (inverse_conditions_p): Declare.
	* fold-const.c (inverse_conditions_p): New function.
	* match.pd: Use inverse_conditions_p.  Add folds of view_converts
	that test the inverse condition of a conditional internal function.
	* internal-fn.h (vectorized_internal_fn_supported_p): Declare.
	* internal-fn.c (internal_fn_mask_index): Handle conditional
	internal functions.
	(vectorized_internal_fn_supported_p): New function.
	* tree-if-conv.c: Include internal-fn.h and fold-const.h.
	(any_pred_load_store): Replace with...
	(need_to_predicate): ...this new variable.
	(redundant_ssa_names): New variable.
	(ifcvt_can_use_mask_load_store): Move initial checks to...
	(ifcvt_can_predicate): ...this new function.  Handle tree codes
	for which a conditional internal function exists.
	(if_convertible_gimple_assign_stmt_p): Use ifcvt_can_predicate
	instead of ifcvt_can_use_mask_load_store.  Update after variable
	name change.
	(predicate_load_or_store): New function, split out from
	predicate_mem_writes.
	(check_redundant_cond_expr): New function.
	(value_available_p): Likewise.
	(predicate_rhs_code): Likewise.
	(predicate_mem_writes): Rename to...
	(predicate_statements): ...this.  Use predicate_load_or_store
	and predicate_rhs_code.
	(combine_blocks, tree_if_conversion): Update after above name changes.
	(ifcvt_local_dce): Handle redundant_ssa_names.
	* tree-vect-patterns.c (vect_recog_mask_conversion_pattern): Handle
	general conditional functions.
	* tree-vect-stmts.c (vectorizable_call): Likewise.

gcc/testsuite/
	* gcc.dg/vect/vect-cond-arith-4.c: New test.
	* gcc.dg/vect/vect-cond-arith-5.c: Likewise.
	* gcc.target/aarch64/sve/cond_arith_1.c: Likewise.
	* gcc.target/aarch64/sve/cond_arith_1_run.c: Likewise.
	* gcc.target/aarch64/sve/cond_arith_2.c: Likewise.
	* gcc.target/aarch64/sve/cond_arith_2_run.c: Likewise.
	* gcc.target/aarch64/sve/cond_arith_3.c: Likewise.
	* gcc.target/aarch64/sve/cond_arith_3_run.c: Likewise.

From-SVN: r262589

1 files changed, 22 insertions, 1 deletions

diff --git a/gcc/internal-fn.c b/gcc/internal-fn.c
index 15755ea..8ede9ca 100644
--- a/gcc/internal-fn.c
+++ b/gcc/internal-fn.c
@@ -3466,7 +3466,8 @@ internal_fn_mask_index (internal_fn fn)
       return 4;
 
     default:
-      return -1;
+      return (conditional_internal_fn_code (fn) != ERROR_MARK
+	      || get_unconditional_internal_fn (fn) != IFN_LAST ? 0 : -1);
     }
 }
 
@@ -3531,6 +3532,26 @@ expand_internal_call (gcall *stmt)
   expand_internal_call (gimple_call_internal_fn (stmt), stmt);
 }
 
+/* If TYPE is a vector type, return true if IFN is a direct internal
+   function that is supported for that type.  If TYPE is a scalar type,
+   return true if IFN is a direct internal function that is supported for
+   the target's preferred vector version of TYPE.  */
+
+bool
+vectorized_internal_fn_supported_p (internal_fn ifn, tree type)
+{
+  scalar_mode smode;
+  if (!VECTOR_TYPE_P (type) && is_a <scalar_mode> (TYPE_MODE (type), &smode))
+    {
+      machine_mode vmode = targetm.vectorize.preferred_simd_mode (smode);
+      if (VECTOR_MODE_P (vmode))
+	type = build_vector_type_for_mode (type, vmode);
+    }
+
+  return (VECTOR_MODE_P (TYPE_MODE (type))
+	  && direct_internal_fn_supported_p (ifn, type, OPTIMIZE_FOR_SPEED));
+}
+
 void
 expand_PHI (internal_fn, gcall *)
 {