From c31cdc3d85e365ce0d233fe40bee40a8bd672b11 Mon Sep 17 00:00:00 2001
From: Alfie Richards <Alfie.Richards@arm.com>
Date: Wed, 11 Sep 2024 12:32:06 +0200
Subject: [PATCH] arm: [MVE intrinsics] Add load_ext intrinsic shape

This patch adds the extending load shape.
It also adds/fixes comments for the load and store shapes.

2024-09-11  Alfie Richards <Alfie.Richards@arm.com>
	    Christophe Lyon  <christophe.lyon@arm.com>

	gcc/
	* config/arm/arm-mve-builtins-shapes.cc:
	(load_ext): New.
	* config/arm/arm-mve-builtins-shapes.h:
	(load_ext): New.
---
 gcc/config/arm/arm-mve-builtins-shapes.cc | 30 ++++++++++++++++++++---
 gcc/config/arm/arm-mve-builtins-shapes.h  |  1 +
 2 files changed, 28 insertions(+), 3 deletions(-)

diff --git a/gcc/config/arm/arm-mve-builtins-shapes.cc b/gcc/config/arm/arm-mve-builtins-shapes.cc
index 0a108cf0127e..12e62122ae4e 100644
--- a/gcc/config/arm/arm-mve-builtins-shapes.cc
+++ b/gcc/config/arm/arm-mve-builtins-shapes.cc
@@ -1461,7 +1461,9 @@ struct inherent_def : public nonoverloaded_base
 };
 SHAPE (inherent)
 
-/* sv<t0>_t svfoo[_t0](const <t0>_t *)
+/* <T0>_t vfoo[_t0](const <s0>_t *)
+
+   where <s0> is the scalar name of <T0>.
 
    Example: vld1q.
    int8x16_t [__arm_]vld1q[_s8](int8_t const *base)
@@ -1493,6 +1495,24 @@ struct load_def : public overloaded_base<0>
 };
 SHAPE (load)
 
+/* <T0>_t foo_t0 (const <X>_t *)
+
+   where <X> is determined by the function base name.
+
+   Example: vldrq.
+   int32x4_t [__arm_]vldrwq_s32 (int32_t const *base)
+   uint32x4_t [__arm_]vldrhq_z_u32 (uint16_t const *base, mve_pred16_t p)  */
+struct load_ext_def : public nonoverloaded_base
+{
+  void
+  build (function_builder &b, const function_group_info &group,
+	 bool preserve_user_namespace) const override
+  {
+    build_all (b, "t0,al", group, MODE_none, preserve_user_namespace);
+  }
+};
+SHAPE (load_ext)
+
 /* <T0>_t vfoo[_t0](<T0>_t)
    <T0>_t vfoo_n_t0(<sT0>_t)
 
@@ -1542,14 +1562,18 @@ struct mvn_def : public overloaded_base<0>
 };
 SHAPE (mvn)
 
-/* void vfoo[_t0](<X>_t *, v<t0>[xN]_t)
+/* void vfoo[_t0](<X>_t *, <T0>[xN]_t)
 
    where <X> might be tied to <t0> (for non-truncating stores) or might
    depend on the function base name (for truncating stores).
 
    Example: vst1q.
    void [__arm_]vst1q[_s8](int8_t *base, int8x16_t value)
-   void [__arm_]vst1q_p[_s8](int8_t *base, int8x16_t value, mve_pred16_t p)  */
+   void [__arm_]vst1q_p[_s8](int8_t *base, int8x16_t value, mve_pred16_t p)
+
+   Example: vstrb.
+   void [__arm_]vstrbq[_s16](int8_t *base, int16x8_t value)
+   void [__arm_]vstrbq_p[_s16](int8_t *base, int16x8_t value, mve_pred16_t p)  */
 struct store_def : public overloaded_base<0>
 {
   void
diff --git a/gcc/config/arm/arm-mve-builtins-shapes.h b/gcc/config/arm/arm-mve-builtins-shapes.h
index e53381d8f36c..db7c63117289 100644
--- a/gcc/config/arm/arm-mve-builtins-shapes.h
+++ b/gcc/config/arm/arm-mve-builtins-shapes.h
@@ -62,6 +62,7 @@ namespace arm_mve
     extern const function_shape *const create;
     extern const function_shape *const inherent;
     extern const function_shape *const load;
+    extern const function_shape *const load_ext;
     extern const function_shape *const mvn;
     extern const function_shape *const store;
     extern const function_shape *const ternary;
-- 
2.47.2