From patchwork Tue Dec 18 13:33:35 2012
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Subject: [ARM,2/3] Add vectorization support for rounding functions
Date: Tue, 18 Dec 2012 03:33:35 -0000
From: Kyrylo Tkachov <kyrylo.tkachov@arm.com>
X-Patchwork-Id: 207114
Message-Id: <002601cddd24$47dfc1a0$d79f44e0$@tkachov@arm.com>
To: <gcc-patches@gcc.gnu.org>
Cc: "Ramana Radhakrishnan" <Ramana.Radhakrishnan@arm.com>,
 "Richard Earnshaw" <Richard.Earnshaw@arm.com>

Hi all,

This patch adds support for the vectorisation of the rounding functions:
floorf, ceilf, truncf, roundf. These can be implemented using the ARMv8 NEON
instructions: vrintm, vrintp, vrintz, vrinta.
This is done by defining the TARGET_VECTORIZE_BUILTINS and
TARGET_VECTORIZE_BUILTIN_VECTORIZED_FUNCTION macros and the function
arm_builtin_vectorized_function that returns the decl of the vector form
of a builtin function, or NULL_TREE if no vector variant exists.

No regressions on arm-none-eabi with AEM.

Ok for trunk?

gcc/ChangeLog

2012-12-18  Kyrylo Tkachov  <kyrylo.tkachov at arm.com>

	* config/arm/arm-protos.h (arm_builtin_vectorized_function):
	  New function prototype.
	* config/arm/arm.c (TARGET_VECTORIZE_BUILTINS): Define.
	  (TARGET_VECTORIZE_BUILTIN_VECTORIZED_FUNCTION): Likewise.
	  (arm_builtin_vectorized_function): New function.


diff --git a/gcc/config/arm/arm-protos.h b/gcc/config/arm/arm-protos.h
index d942c5b..0754066 100644
--- a/gcc/config/arm/arm-protos.h
+++ b/gcc/config/arm/arm-protos.h
@@ -80,6 +80,7 @@ extern char *neon_output_shift_immediate (const char *, char, rtx *,
 extern void neon_pairwise_reduce (rtx, rtx, enum machine_mode,
 				  rtx (*) (rtx, rtx, rtx));
 extern rtx neon_make_constant (rtx);
+extern tree arm_builtin_vectorized_function (tree, tree, tree);
 extern void neon_expand_vector_init (rtx, rtx);
 extern void neon_lane_bounds (rtx, HOST_WIDE_INT, HOST_WIDE_INT);
 extern void neon_const_bounds (rtx, HOST_WIDE_INT, HOST_WIDE_INT);
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 84ce56f..8193e4f 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -607,6 +607,13 @@ static const struct attribute_spec arm_attribute_table[] =
 #undef TARGET_CLASS_LIKELY_SPILLED_P
 #define TARGET_CLASS_LIKELY_SPILLED_P arm_class_likely_spilled_p
 
+#undef TARGET_VECTORIZE_BUILTINS
+#define TARGET_VECTORIZE_BUILTINS
+
+#undef TARGET_VECTORIZE_BUILTIN_VECTORIZED_FUNCTION
+#define TARGET_VECTORIZE_BUILTIN_VECTORIZED_FUNCTION \
+  arm_builtin_vectorized_function
+
 #undef TARGET_VECTOR_ALIGNMENT
 #define TARGET_VECTOR_ALIGNMENT arm_vector_alignment
 
@@ -25593,6 +25600,60 @@ arm_have_conditional_execution (void)
   return !TARGET_THUMB1;
 }
 
+tree
+arm_builtin_vectorized_function (tree fndecl, tree type_out, tree type_in)
+{
+  enum machine_mode in_mode, out_mode;
+  int in_n, out_n;
+
+  if (TREE_CODE (type_out) != VECTOR_TYPE
+      || TREE_CODE (type_in) != VECTOR_TYPE
+      || !(TARGET_NEON && TARGET_FPU_ARMV8 && flag_unsafe_math_optimizations))
+    return NULL_TREE;
+
+  out_mode = TYPE_MODE (TREE_TYPE (type_out));
+  out_n = TYPE_VECTOR_SUBPARTS (type_out);
+  in_mode = TYPE_MODE (TREE_TYPE (type_in));
+  in_n = TYPE_VECTOR_SUBPARTS (type_in);
+
+/* ARM_CHECK_BUILTIN_MODE and ARM_FIND_VRINT_VARIANT are used to find the
+   decl of the vectorized builtin for the appropriate vector mode.
+   NULL_TREE is returned if no such builtin is available.  */
+#undef ARM_CHECK_BUILTIN_MODE
+#define ARM_CHECK_BUILTIN_MODE(C) \
+  (out_mode == SFmode && out_n == C \
+   && in_mode == SFmode && in_n == C)
+
+#undef ARM_FIND_VRINT_VARIANT
+#define ARM_FIND_VRINT_VARIANT(N) \
+  (ARM_CHECK_BUILTIN_MODE (2) \
+    ? arm_builtin_decl(ARM_BUILTIN_NEON_##N##v2sf, false) \
+    : (ARM_CHECK_BUILTIN_MODE (4) \
+      ? arm_builtin_decl(ARM_BUILTIN_NEON_##N##v4sf, false) \
+      : NULL_TREE))
+
+  if (DECL_BUILT_IN_CLASS (fndecl) == BUILT_IN_NORMAL)
+    {
+      enum built_in_function fn = DECL_FUNCTION_CODE (fndecl);
+      switch (fn)
+        {
+          case BUILT_IN_FLOORF:
+            return ARM_FIND_VRINT_VARIANT (vrintm);
+          case BUILT_IN_CEILF:
+            return ARM_FIND_VRINT_VARIANT (vrintp);
+          case BUILT_IN_TRUNCF:
+            return ARM_FIND_VRINT_VARIANT (vrintz);
+          case BUILT_IN_ROUNDF:
+            return ARM_FIND_VRINT_VARIANT (vrinta);
+          default:
+            return NULL_TREE;
+        }
+    }
+  return NULL_TREE;
+}
+#undef ARM_CHECK_BUILTIN_MODE
+#undef ARM_FIND_VRINT_VARIANT
+
 /* The AAPCS sets the maximum alignment of a vector to 64 bits.  */
 static HOST_WIDE_INT
 arm_vector_alignment (const_tree type)