From e2e0b85c1e7cb53fd720df0d09278e3d485c733e Mon Sep 17 00:00:00 2001
From: Tejas Belagod <tbelagod@arm.com>
Date: Mon, 9 Aug 2021 11:33:30 +0100
Subject: PR101609: Use the correct iterator for AArch64 vector right shift
 pattern

Loops containing long long shifts fail to vectorize due to the vectorizer
not being able to recognize long long right shifts. This is due to a bug
in the iterator used for the vashr and vlshr patterns in aarch64-simd.md.

2021-08-09  Tejas Belagod  <tejas.belagod@arm.com>

gcc/ChangeLog
	PR target/101609
	* config/aarch64/aarch64-simd.md (vlshr<mode>3, vashr<mode>3): Use
	the right iterator.

gcc/testsuite/ChangeLog
	* gcc.target/aarch64/vect-shr-reg.c: New testcase.
	* gcc.target/aarch64/vect-shr-reg-run.c: Likewise.
---
 gcc/config/aarch64/aarch64-simd.md                 | 15 +++---
 .../gcc.target/aarch64/vect-shr-reg-run.c          | 53 ++++++++++++++++++++++
 gcc/testsuite/gcc.target/aarch64/vect-shr-reg.c    | 30 ++++++++++++
 3 files changed, 89 insertions(+), 9 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/vect-shr-reg-run.c
 create mode 100644 gcc/testsuite/gcc.target/aarch64/vect-shr-reg.c

(limited to 'gcc')

diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index c5638d0..48eddf6 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -1299,13 +1299,10 @@
   DONE;
 })
 
-;; Using mode VDQ_BHSI as there is no V2DImode neg!
-;; Negating individual lanes most certainly offsets the
-;; gain from vectorization.
 (define_expand "vashr<mode>3"
- [(match_operand:VDQ_BHSI 0 "register_operand")
-  (match_operand:VDQ_BHSI 1 "register_operand")
-  (match_operand:VDQ_BHSI 2 "register_operand")]
+ [(match_operand:VDQ_I 0 "register_operand")
+  (match_operand:VDQ_I 1 "register_operand")
+  (match_operand:VDQ_I 2 "register_operand")]
  "TARGET_SIMD"
 {
   rtx neg = gen_reg_rtx (<MODE>mode);
@@ -1333,9 +1330,9 @@
 )
 
 (define_expand "vlshr<mode>3"
- [(match_operand:VDQ_BHSI 0 "register_operand")
-  (match_operand:VDQ_BHSI 1 "register_operand")
-  (match_operand:VDQ_BHSI 2 "register_operand")]
+ [(match_operand:VDQ_I 0 "register_operand")
+  (match_operand:VDQ_I 1 "register_operand")
+  (match_operand:VDQ_I 2 "register_operand")]
  "TARGET_SIMD"
 {
   rtx neg = gen_reg_rtx (<MODE>mode);
diff --git a/gcc/testsuite/gcc.target/aarch64/vect-shr-reg-run.c b/gcc/testsuite/gcc.target/aarch64/vect-shr-reg-run.c
new file mode 100644
index 0000000..3190448
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/vect-shr-reg-run.c
@@ -0,0 +1,53 @@
+/* { dg-do run } */
+/* { dg-options "-O3 -march=armv8.2-a" } */
+
+#include "vect-shr-reg.c"
+
+int
+main(void)
+{
+  int64_t a[16];
+  int64_t b[16];
+  int64_t c[17];
+
+  uint64_t ua[16];
+  uint64_t ub[16];
+  uint64_t uc[17];
+
+  int64_t res_a[16];
+  uint64_t res_ua[16];
+
+  int i;
+
+  /* Set up inputs.  */
+  for (i = 0; i < 16; i++)
+    {
+      b[i] = -2;
+      c[i] = 34;
+      ub[i] = 0xffffffffffffffff;
+      uc[i] = 52;
+    }
+
+  /* Set up reference values.  */
+  for (i = 0; i < 16; i++)
+    {
+      res_a[i] = -1LL;
+      res_ua[i] = 0x0fffLL;
+    }
+
+  /* Do the shifts.  */
+  f (ua, ub, uc);
+  g (a, b, c);
+
+  /* Compare outputs against reference values.  */
+  for (i = 0; i < 16; i++)
+    {
+      if (a[i] != res_a[i])
+	__builtin_abort ();
+
+      if (ua[i] != res_ua[i])
+	__builtin_abort ();
+    }
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/vect-shr-reg.c b/gcc/testsuite/gcc.target/aarch64/vect-shr-reg.c
new file mode 100644
index 0000000..5736daf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/vect-shr-reg.c
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -march=armv8.2-a" } */
+
+#include <stdint.h>
+#include <stdio.h>
+
+#pragma GCC target "+nosve"
+
+int __attribute__((noinline))
+f(uint64_t *__restrict a, uint64_t *__restrict b, uint64_t *__restrict c)
+{
+  int i;
+
+  for (i = 0; i < 16; i++)
+    a[i] = b[i] >> c[i];
+}
+
+
+int __attribute__((noinline))
+g(int64_t *__restrict a, int64_t *__restrict b, int64_t *__restrict c)
+{
+  int i;
+
+  for (i = 0; i < 16; i++)
+    a[i] = b[i] >> c[i];
+}
+
+/* { dg-final { scan-assembler "neg\\tv" } } */
+/* { dg-final { scan-assembler "ushl\\tv" } } */
+/* { dg-final { scan-assembler "sshl\\tv" } } */
-- 
cgit v1.1