diff mbox series

[pushed,v2,20/25] aarch64: Generalise _m rules for SVE intrinsics

Message ID 20231205101323.1914247-21-richard.sandiford@arm.com
State New
Headers show
Series aarch64: Add support for SME | expand

Commit Message

Richard Sandiford Dec. 5, 2023, 10:13 a.m. UTC 
In SVE there was a simple rule that unary merging (_m) intrinsics
had a separate initial argument to specify the values of inactive
lanes, whereas other merging functions took inactive lanes from
the first operand to the operation.

That rule began to break down in SVE2, and it continues to do
so in SME.  This patch therefore adds a virtual function to
specify whether the separate initial argument is present or not.
The old rule is still the default.

gcc/
	* config/aarch64/aarch64-sve-builtins.h
	(function_shape::has_merge_argument_p): New member function.
	* config/aarch64/aarch64-sve-builtins.cc:
	(function_resolver::check_gp_argument): Use it.
	(function_expander::get_fallback_value): Likewise.
	* config/aarch64/aarch64-sve-builtins-shapes.cc
	(apply_predication): Likewise.
	(unary_convert_narrowt_def::has_merge_argument_p): New function.
---
 gcc/config/aarch64/aarch64-sve-builtins-shapes.cc | 10 ++++++++--
 gcc/config/aarch64/aarch64-sve-builtins.cc        |  4 ++--
 gcc/config/aarch64/aarch64-sve-builtins.h         | 13 +++++++++++++
 3 files changed, 23 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/gcc/config/aarch64/aarch64-sve-builtins-shapes.cc b/gcc/config/aarch64/aarch64-sve-builtins-shapes.cc
index 2c25b122f05..68708712001 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins-shapes.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins-shapes.cc
@@ -66,8 +66,8 @@  apply_predication (const function_instance &instance, tree return_type,
 	 the same type as the result.  For unary_convert_narrowt it also
 	 provides the "bottom" half of active elements, and is present
 	 for all types of predication.  */
-      if ((argument_types.length () == 2 && instance.pred == PRED_m)
-	  || instance.shape == shapes::unary_convert_narrowt)
+      auto nargs = argument_types.length () - 1;
+      if (instance.shape->has_merge_argument_p (instance, nargs))
 	argument_types.quick_insert (0, return_type);
     }
 }
@@ -3271,6 +3271,12 @@  SHAPE (unary_convert)
    predicate.  */
 struct unary_convert_narrowt_def : public overloaded_base<1>
 {
+  bool
+  has_merge_argument_p (const function_instance &, unsigned int) const override
+  {
+    return true;
+  }
+
   void
   build (function_builder &b, const function_group_info &group) const override
   {
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.cc b/gcc/config/aarch64/aarch64-sve-builtins.cc
index d5ac1dc76c5..7950977c14b 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins.cc
@@ -2287,7 +2287,7 @@  function_resolver::check_gp_argument (unsigned int nops,
   if (pred != PRED_none)
     {
       /* Unary merge operations should use resolve_unary instead.  */
-      gcc_assert (nops != 1 || pred != PRED_m);
+      gcc_assert (!shape->has_merge_argument_p (*this, nops));
       nargs = nops + 1;
       if (!check_num_arguments (nargs)
 	  || !require_vector_type (i, VECTOR_TYPE_svbool_t))
@@ -2997,7 +2997,7 @@  function_expander::get_fallback_value (machine_mode mode, unsigned int nops,
 
   gcc_assert (pred == PRED_m || pred == PRED_x);
   if (merge_argno == DEFAULT_MERGE_ARGNO)
-    merge_argno = nops == 1 && pred == PRED_m ? 0 : 1;
+    merge_argno = shape->has_merge_argument_p (*this, nops) ? 0 : 1;
 
   if (merge_argno == 0)
     return args[argno++];
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.h b/gcc/config/aarch64/aarch64-sve-builtins.h
index e770a4042fe..b0218bbad6e 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.h
+++ b/gcc/config/aarch64/aarch64-sve-builtins.h
@@ -712,6 +712,9 @@  public:
 class function_shape
 {
 public:
+  virtual bool has_merge_argument_p (const function_instance &,
+				     unsigned int) const;
+
   virtual bool explicit_type_suffix_p (unsigned int) const = 0;
 
   /* True if the group suffix is present in overloaded names.
@@ -987,6 +990,16 @@  function_base::vectors_per_tuple (const function_instance &instance) const
   return instance.group_suffix ().vectors_per_tuple;
 }
 
+/* Return true if INSTANCE (which has NARGS arguments) has an initial
+   vector argument whose only purpose is to specify the values of
+   inactive lanes.  */
+inline bool
+function_shape::has_merge_argument_p (const function_instance &instance,
+				      unsigned int nargs) const
+{
+  return nargs == 1 && instance.pred == PRED_m;
+}
+
 /* Return the mode of the result of a call.  */
 inline machine_mode
 function_expander::result_mode () const