From 33cb400b2e7266e65030869254366217e51494aa Mon Sep 17 00:00:00 2001
From: Tamar Christina <tamar.christina@arm.com>
Date: Fri, 20 Sep 2024 17:03:54 +0100
Subject: [PATCH] AArch64: Define VECTOR_STORE_FLAG_VALUE.

This defines VECTOR_STORE_FLAG_VALUE to CONST1_RTX for AArch64
so we simplify vector comparisons in AArch64.

With this enabled

res:
        movi    v0.4s, 0
        cmeq    v0.4s, v0.4s, v0.4s
        ret

is simplified to:

res:
        mvni    v0.4s, 0
        ret

gcc/ChangeLog:

	* config/aarch64/aarch64.h (VECTOR_STORE_FLAG_VALUE): New.

gcc/testsuite/ChangeLog:

	* gcc.dg/rtl/aarch64/vector-eq.c: New test.
---
 gcc/config/aarch64/aarch64.h                 | 10 +++++++
 gcc/testsuite/gcc.dg/rtl/aarch64/vector-eq.c | 29 ++++++++++++++++++++
 2 files changed, 39 insertions(+)
 create mode 100644 gcc/testsuite/gcc.dg/rtl/aarch64/vector-eq.c

diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h
index 2dfb999bea5..a99e7bb6c47 100644
--- a/gcc/config/aarch64/aarch64.h
+++ b/gcc/config/aarch64/aarch64.h
@@ -156,6 +156,16 @@
 
 #define PCC_BITFIELD_TYPE_MATTERS	1
 
+/* Use the same RTL truth representation for vector elements as we do
+   for scalars.  This maintains the property that a comparison like
+   eq:V4SI is a composition of 4 individual eq:SIs, just like plus:V4SI
+   is a composition of 4 individual plus:SIs.
+
+   This means that Advanced SIMD comparisons are represented in RTL as
+   (neg (op ...)).  */
+
+#define VECTOR_STORE_FLAG_VALUE(MODE) CONST1_RTX (GET_MODE_INNER (MODE))
+
 #ifndef USED_FOR_TARGET
 
 /* Define an enum of all features (ISA modes, architectures and extensions).
diff --git a/gcc/testsuite/gcc.dg/rtl/aarch64/vector-eq.c b/gcc/testsuite/gcc.dg/rtl/aarch64/vector-eq.c
new file mode 100644
index 00000000000..8e0d7773620
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/rtl/aarch64/vector-eq.c
@@ -0,0 +1,29 @@
+/* { dg-do compile { target aarch64-*-* } } */
+/* { dg-additional-options "-O2" } */
+/* { dg-final { check-function-bodies "**" "" "" } } */
+
+/*
+** foo:
+**	mvni	v0.4s, 0
+**	ret
+*/
+__Uint32x4_t __RTL (startwith ("vregs")) foo (void)
+{
+(function "foo"
+  (insn-chain
+    (block 2
+      (edge-from entry (flags "FALLTHRU"))
+      (cnote 1 [bb 2] NOTE_INSN_BASIC_BLOCK)
+      (cnote 2 NOTE_INSN_FUNCTION_BEG)
+      (cinsn 3 (set (reg:V4SI <0>) (const_vector:V4SI [(const_int 0) (const_int 0) (const_int 0) (const_int 0)])))
+      (cinsn 4 (set (reg:V4SI <1>) (reg:V4SI <0>)))
+      (cinsn 5 (set (reg:V4SI <2>)
+		    (neg:V4SI (eq:V4SI (reg:V4SI <0>) (reg:V4SI <1>)))))
+      (cinsn 6 (set (reg:V4SI v0) (reg:V4SI <2>)))
+      (edge-to exit (flags "FALLTHRU"))
+    )
+  )
+  (crtl (return_rtx (reg/i:V4SI v0)))
+)
+}
+