[PATCH] aarch64: gimple fold aes[ed] [PR114522]

[Andrew Pinski]

Instead of waiting to get combine/rtl optimizations fixed here. This fixes the
builtins at the gimple level. It should provide for slightly faster compile time
since we have a simplification earlier on.

Built and tested for aarch64-linux-gnu.

gcc/ChangeLog:

	PR target/114522
	* config/aarch64/aarch64-builtins.cc (aarch64_fold_aes_op): New function.
	(aarch64_general_gimple_fold_builtin): Call aarch64_fold_aes_op for crypto_aese
	and crypto_aesd.

Signed-off-by: Andrew Pinski <quic_apinski@quicinc.com>
---
 gcc/config/aarch64/aarch64-builtins.cc | 30 ++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/gcc/config/aarch64/aarch64-builtins.cc b/gcc/config/aarch64/aarch64-builtins.cc
index 6d5479c2e44..ab67194575d 100644
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -4722,6 +4722,31 @@ aarch64_fold_combine (gcall *stmt)
   return gimple_build_assign (gimple_call_lhs (stmt), ctor);
 }
 
+/* Fold a call to vaeseq_u8 and vaesdq_u8.
+   That is `vaeseq_u8 (x ^ y, 0)` gets folded
+   into `vaeseq_u8 (x, y)`.*/
+static gimple *
+aarch64_fold_aes_op (gcall *stmt)
+{
+  tree arg0 = gimple_call_arg (stmt, 0);
+  tree arg1 = gimple_call_arg (stmt, 1);
+  if (integer_zerop (arg0))
+    arg0 = arg1;
+  else if (!integer_zerop (arg1))
+    return nullptr;
+  if (TREE_CODE (arg0) != SSA_NAME)
+    return nullptr;
+  if (!has_single_use (arg0))
+    return nullptr;
+  gimple *s = SSA_NAME_DEF_STMT (arg0);
+  if (!is_gimple_assign (s)
+      || gimple_assign_rhs_code (s) != BIT_XOR_EXPR)
+    return nullptr;
+  gimple_call_set_arg (stmt, 0, gimple_assign_rhs1 (s));
+  gimple_call_set_arg (stmt, 1, gimple_assign_rhs2 (s));
+  return stmt;
+}
+
 /* Fold a call to vld1, given that it loads something of type TYPE.  */
 static gimple *
 aarch64_fold_load (gcall *stmt, tree type)
@@ -4983,6 +5008,11 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode, gcall *stmt,
 	gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt));
 	break;
 
+      VAR1 (BINOPU, crypto_aese, 0, DEFAULT, v16qi)
+      VAR1 (BINOPU, crypto_aesd, 0, DEFAULT, v16qi)
+	new_stmt = aarch64_fold_aes_op (stmt);
+	break;
+
       /* Lower sqrt builtins to gimple/internal function sqrt. */
       BUILTIN_VHSDF_DF (UNOP, sqrt, 2, FP)
 	new_stmt = gimple_build_call_internal (IFN_SQRT,
-- 
2.43.0