Patchwork [ARM] Improve ARM memset inlining

login
register
mail settings
Submitter Bin.Cheng
Date July 21, 2014, 12:34 p.m.
Message ID <CAHFci28usaet-O4ZpAmUSCg-z+TeH7MuU0_WNTwcm+Z0MeAraw@mail.gmail.com>
Download mbox | patch
Permalink /patch/372057/
State New
Headers show

Comments

Bin.Cheng - July 21, 2014, 12:34 p.m.
On Tue, Jul 8, 2014 at 10:57 AM, Bin.Cheng <amker.cheng@gmail.com> wrote:
> On Tue, Jul 8, 2014 at 9:56 AM, Ramana Radhakrishnan
> <ramana.radhakrishnan@arm.com> wrote:

>
> 2014-07-08  Bin Cheng  <bin.cheng@arm.com>
>
>     PR target/55701
>     * config/arm/arm.md (setmem): New pattern.
>     * config/arm/arm-protos.h (struct tune_params): New fields.
>     (arm_gen_setmem): New prototype.
>     * config/arm/arm.c (arm_slowmul_tune): Initialize new fields.
>     (arm_fastmul_tune, arm_strongarm_tune, arm_xscale_tune): Ditto.
>     (arm_9e_tune, arm_v6t2_tune, arm_cortex_tune): Ditto.
>     (arm_cortex_a8_tune, arm_cortex_a7_tune): Ditto.
>     (arm_cortex_a15_tune, arm_cortex_a53_tune): Ditto.
>     (arm_cortex_a57_tune, arm_cortex_a5_tune): Ditto.
>     (arm_cortex_a9_tune, arm_cortex_a12_tune): Ditto.
>     (arm_v7m_tune, arm_v6m_tune, arm_fa726te_tune): Ditto.
>     (arm_const_inline_cost): New function.
>     (arm_block_set_max_insns): New function.
>     (arm_block_set_non_vect_profit_p): New function.
>     (arm_block_set_vect_profit_p): New function.
>     (arm_block_set_unaligned_vect): New function.
>     (arm_block_set_aligned_vect): New function.
>     (arm_block_set_unaligned_non_vect): New function.
>     (arm_block_set_aligned_non_vect): New function.
>     (arm_block_set_vect, arm_gen_setmem): New functions.
>
> gcc/testsuite/ChangeLog
> 2014-07-08  Bin Cheng  <bin.cheng@arm.com>
>
>     PR target/55701
>     * gcc.target/arm/memset-inline-1.c: New test.
>     * gcc.target/arm/memset-inline-2.c: New test.
>     * gcc.target/arm/memset-inline-3.c: New test.
>     * gcc.target/arm/memset-inline-4.c: New test.
>     * gcc.target/arm/memset-inline-5.c: New test.
>     * gcc.target/arm/memset-inline-6.c: New test.
>     * gcc.target/arm/memset-inline-7.c: New test.
>     * gcc.target/arm/memset-inline-8.c: New test.
>     * gcc.target/arm/memset-inline-9.c: New test.

Committed attached patch as r212893.

Thanks,
bin

Patch

Index: gcc/testsuite/gcc.target/arm/memset-inline-5.c
===================================================================
--- gcc/testsuite/gcc.target/arm/memset-inline-5.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/memset-inline-5.c	(revision 0)
@@ -0,0 +1,78 @@ 
+/* { dg-do run } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mcpu=cortex-a9" } { "" } } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mtune=cortex-a9" } { "" } } */
+/* { dg-options "-save-temps -O2 -fno-inline" } */
+/* { dg-add-options "arm_neon" } */
+
+#include <string.h>
+#include <stdlib.h>
+
+#define LEN (100)
+int a[LEN];
+int b[LEN];
+int c[LEN];
+int d[LEN];
+void
+foo1 (void)
+{
+    memset (a, -1, 16);
+    return;
+}
+
+void
+foo2 (void)
+{
+  memset (b, 1, 25);
+  return;
+}
+
+void
+foo3 (void)
+{
+  memset (c, -1, 19);
+  return;
+}
+
+void
+foo4 (void)
+{
+  memset (d, 1, 23);
+  return;
+}
+
+void
+check (signed char *arr, int idx, int len, int v)
+{
+  int i;
+  for (i = 0; i < idx; i++)
+    if (arr[i] != v)
+      abort ();
+
+  for (i = idx; i < len; i++)
+    if (arr[i] != 0)
+      abort ();
+}
+
+int
+main(void)
+{
+  foo1 ();
+  check ((signed char *)a, 16, sizeof (a), -1);
+
+  foo2 ();
+  check ((signed char *)b, 25, sizeof (b), 1);
+
+  foo3 ();
+  check ((signed char *)c, 19, sizeof (c), -1);
+
+  foo4 ();
+  check ((signed char *)d, 23, sizeof (d), 1);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-not "bl?\[ \t\]+memset" { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { scan-assembler "vst1" { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { scan-assembler-not "vstr"  { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { cleanup-saved-temps } } */
+
Index: gcc/testsuite/gcc.target/arm/memset-inline-6.c
===================================================================
--- gcc/testsuite/gcc.target/arm/memset-inline-6.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/memset-inline-6.c	(revision 0)
@@ -0,0 +1,68 @@ 
+/* { dg-do run } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mcpu=cortex-a9" } { "" } } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mtune=cortex-a9" } { "" } } */
+/* { dg-options "-save-temps -O2 -fno-inline" } */
+/* { dg-add-options "arm_neon" } */
+
+#include <string.h>
+#include <stdlib.h>
+
+#define LEN (100)
+int a[LEN];
+int b[LEN];
+int c[LEN];
+void
+foo1 (void)
+{
+    memset (a, -1, 20);
+    return;
+}
+
+void
+foo2 (void)
+{
+  memset (b, 1, 24);
+  return;
+}
+
+void
+foo3 (void)
+{
+  memset (c, -1, 32);
+  return;
+}
+
+void
+check (signed char *arr, int idx, int len, int v)
+{
+  int i;
+  for (i = 0; i < idx; i++)
+    if (arr[i] != v)
+      abort ();
+
+  for (i = idx; i < len; i++)
+    if (arr[i] != 0)
+      abort ();
+}
+
+int
+main(void)
+{
+  foo1 ();
+  check ((signed char *)a, 20, sizeof (a), -1);
+
+  foo2 ();
+  check ((signed char *)b, 24, sizeof (b), 1);
+
+  foo3 ();
+  check ((signed char *)c, 32, sizeof (c), -1);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-not "bl?\[ \t\]+memset" { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { scan-assembler-times "vst1" 3 { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { scan-assembler-times "vstr" 4 { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { cleanup-saved-temps } } */
+
+
Index: gcc/testsuite/gcc.target/arm/memset-inline-7.c
===================================================================
--- gcc/testsuite/gcc.target/arm/memset-inline-7.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/memset-inline-7.c	(revision 0)
@@ -0,0 +1,171 @@ 
+/* { dg-do run } */
+/* { dg-options "-O2" } */
+
+#include <string.h>
+#include <stdlib.h>
+
+#define LEN (100)
+short a[LEN];
+int b[LEN];
+
+void
+init (signed char *arr, int len)
+{
+  int i;
+  for (i = 0; i < len; i++)
+    arr[i] = 0;
+}
+
+void
+check (signed char *arr, int idx, int len, int v)
+{
+  int i;
+  for (i = 0; i < idx; i++)
+    if (arr[i] != v)
+      abort ();
+
+  for (i = idx; i < len; i++)
+    if (arr[i] != 0)
+      abort ();
+}
+
+#define TEST(a,l,v)			\
+	init ((signed char*)(a), sizeof (a));		\
+	memset ((a), (v), (l));				\
+	check ((signed char *)(a), (l), sizeof (a), (v));
+int
+main(void)
+{
+  TEST (a, 1, -1);
+  TEST (a, 2, -1);
+  TEST (a, 3, -1);
+  TEST (a, 4, -1);
+  TEST (a, 5, -1);
+  TEST (a, 6, -1);
+  TEST (a, 7, -1);
+  TEST (a, 8, -1);
+  TEST (a, 9, 1);
+  TEST (a, 10, -1);
+  TEST (a, 11, 1);
+  TEST (a, 12, -1);
+  TEST (a, 13, 1);
+  TEST (a, 14, -1);
+  TEST (a, 15, 1);
+  TEST (a, 16, -1);
+  TEST (a, 17, 1);
+  TEST (a, 18, -1);
+  TEST (a, 19, 1);
+  TEST (a, 20, -1);
+  TEST (a, 21, 1);
+  TEST (a, 22, -1);
+  TEST (a, 23, 1);
+  TEST (a, 24, -1);
+  TEST (a, 25, 1);
+  TEST (a, 26, -1);
+  TEST (a, 27, 1);
+  TEST (a, 28, -1);
+  TEST (a, 29, 1);
+  TEST (a, 30, -1);
+  TEST (a, 31, 1);
+  TEST (a, 32, -1);
+  TEST (a, 33, 1);
+  TEST (a, 34, -1);
+  TEST (a, 35, 1);
+  TEST (a, 36, -1);
+  TEST (a, 37, 1);
+  TEST (a, 38, -1);
+  TEST (a, 39, 1);
+  TEST (a, 40, -1);
+  TEST (a, 41, 1);
+  TEST (a, 42, -1);
+  TEST (a, 43, 1);
+  TEST (a, 44, -1);
+  TEST (a, 45, 1);
+  TEST (a, 46, -1);
+  TEST (a, 47, 1);
+  TEST (a, 48, -1);
+  TEST (a, 49, 1);
+  TEST (a, 50, -1);
+  TEST (a, 51, 1);
+  TEST (a, 52, -1);
+  TEST (a, 53, 1);
+  TEST (a, 54, -1);
+  TEST (a, 55, 1);
+  TEST (a, 56, -1);
+  TEST (a, 57, 1);
+  TEST (a, 58, -1);
+  TEST (a, 59, 1);
+  TEST (a, 60, -1);
+  TEST (a, 61, 1);
+  TEST (a, 62, -1);
+  TEST (a, 63, 1);
+  TEST (a, 64, -1);
+
+  TEST (b, 1, -1);
+  TEST (b, 2, -1);
+  TEST (b, 3, -1);
+  TEST (b, 4, -1);
+  TEST (b, 5, -1);
+  TEST (b, 6, -1);
+  TEST (b, 7, -1);
+  TEST (b, 8, -1);
+  TEST (b, 9, 1);
+  TEST (b, 10, -1);
+  TEST (b, 11, 1);
+  TEST (b, 12, -1);
+  TEST (b, 13, 1);
+  TEST (b, 14, -1);
+  TEST (b, 15, 1);
+  TEST (b, 16, -1);
+  TEST (b, 17, 1);
+  TEST (b, 18, -1);
+  TEST (b, 19, 1);
+  TEST (b, 20, -1);
+  TEST (b, 21, 1);
+  TEST (b, 22, -1);
+  TEST (b, 23, 1);
+  TEST (b, 24, -1);
+  TEST (b, 25, 1);
+  TEST (b, 26, -1);
+  TEST (b, 27, 1);
+  TEST (b, 28, -1);
+  TEST (b, 29, 1);
+  TEST (b, 30, -1);
+  TEST (b, 31, 1);
+  TEST (b, 32, -1);
+  TEST (b, 33, 1);
+  TEST (b, 34, -1);
+  TEST (b, 35, 1);
+  TEST (b, 36, -1);
+  TEST (b, 37, 1);
+  TEST (b, 38, -1);
+  TEST (b, 39, 1);
+  TEST (b, 40, -1);
+  TEST (b, 41, 1);
+  TEST (b, 42, -1);
+  TEST (b, 43, 1);
+  TEST (b, 44, -1);
+  TEST (b, 45, 1);
+  TEST (b, 46, -1);
+  TEST (b, 47, 1);
+  TEST (b, 48, -1);
+  TEST (b, 49, 1);
+  TEST (b, 50, -1);
+  TEST (b, 51, 1);
+  TEST (b, 52, -1);
+  TEST (b, 53, 1);
+  TEST (b, 54, -1);
+  TEST (b, 55, 1);
+  TEST (b, 56, -1);
+  TEST (b, 57, 1);
+  TEST (b, 58, -1);
+  TEST (b, 59, 1);
+  TEST (b, 60, -1);
+  TEST (b, 61, 1);
+  TEST (b, 62, -1);
+  TEST (b, 63, 1);
+  TEST (b, 64, -1);
+
+  return 0;
+}
+
Index: gcc/testsuite/gcc.target/arm/memset-inline-8.c
===================================================================
--- gcc/testsuite/gcc.target/arm/memset-inline-8.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/memset-inline-8.c	(revision 0)
@@ -0,0 +1,44 @@ 
+/* { dg-do run } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mcpu=cortex-a9" } { "" } } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mtune=cortex-a9" } { "" } } */
+/* { dg-options "-save-temps -O2 -fno-inline"  } */
+/* { dg-add-options "arm_neon" } */
+
+#include <string.h>
+#include <stdlib.h>
+
+#define LEN (100)
+short a[LEN];
+void
+foo (void)
+{
+    memset (a, -1, 14);
+    return;
+}
+
+void
+check (signed char *arr, int idx, int len, int v)
+{
+  int i;
+  for (i = 0; i < idx; i++)
+    if (arr[i] != v)
+      abort ();
+
+  for (i = idx; i < len; i++)
+    if (arr[i] != 0)
+      abort ();
+}
+
+int
+main(void)
+{
+  foo ();
+  check ((signed char *)a, 14, sizeof (a), -1);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-not "bl?\[ \t\]*memset" { target { ! arm_thumb1_ok } } } } */
+/* { dg-final { scan-assembler "vst1" { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { scan-assembler-not "vstr" { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { cleanup-saved-temps } } */
Index: gcc/testsuite/gcc.target/arm/memset-inline-1.c
===================================================================
--- gcc/testsuite/gcc.target/arm/memset-inline-1.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/memset-inline-1.c	(revision 0)
@@ -0,0 +1,39 @@ 
+/* { dg-do run } */
+/* { dg-options "-save-temps -O2 -fno-inline"  } */
+
+#include <string.h>
+#include <stdlib.h>
+
+#define LEN (100)
+short a[LEN];
+void
+foo (void)
+{
+    memset (a, -1, 14);
+    return;
+}
+
+void
+check (signed char *arr, int idx, int len, int v)
+{
+  int i;
+  for (i = 0; i < idx; i++)
+    if (arr[i] != v)
+      abort ();
+
+  for (i = idx; i < len; i++)
+    if (arr[i] != 0)
+      abort ();
+}
+
+int
+main(void)
+{
+  foo ();
+  check ((signed char *)a, 14, sizeof (a), -1);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-not "bl?\[ \t\]*memset" { target { ! arm_thumb1_ok } } } } */
+/* { dg-final { cleanup-saved-temps } } */
Index: gcc/testsuite/gcc.target/arm/memset-inline-9.c
===================================================================
--- gcc/testsuite/gcc.target/arm/memset-inline-9.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/memset-inline-9.c	(revision 0)
@@ -0,0 +1,42 @@ 
+/* { dg-do run } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mcpu=cortex-a9" } { "" } } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mtune=cortex-a9" } { "" } } */
+/* { dg-options "-save-temps -Os -fno-inline" } */
+/* { dg-add-options "arm_neon" } */
+
+#include <string.h>
+#include <stdlib.h>
+
+#define LEN (100)
+short a[LEN];
+void
+foo (void)
+{
+  memset (a, -1, 14);
+  return;
+}
+
+void
+check (signed char *arr, int idx, int len, int v)
+{
+  int i;
+  for (i = 0; i < idx; i++)
+    if (arr[i] != v)
+      abort ();
+
+  for (i = idx; i < len; i++)
+    if (arr[i] != 0)
+      abort ();
+}
+
+int
+main(void)
+{
+  foo ();
+  check ((signed char *)a, 14, sizeof (a), -1);
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not "bl?\[ \t\]*memset" { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { scan-assembler "vst1" { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { cleanup-saved-temps } } */
Index: gcc/testsuite/gcc.target/arm/memset-inline-2.c
===================================================================
--- gcc/testsuite/gcc.target/arm/memset-inline-2.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/memset-inline-2.c	(revision 0)
@@ -0,0 +1,38 @@ 
+/* { dg-do run } */
+/* { dg-options "-save-temps -Os -fno-inline" } */
+
+#include <string.h>
+#include <stdlib.h>
+
+#define LEN (100)
+short a[LEN];
+void
+foo (void)
+{
+  memset (a, -1, 14);
+  return;
+}
+
+void
+check (signed char *arr, int idx, int len, int v)
+{
+  int i;
+  for (i = 0; i < idx; i++)
+    if (arr[i] != v)
+      abort ();
+
+  for (i = idx; i < len; i++)
+    if (arr[i] != 0)
+      abort ();
+}
+
+int
+main(void)
+{
+  foo ();
+  check ((signed char *)a, 14, sizeof (a), -1);
+
+  return 0;
+}
+/* { dg-final { scan-assembler "bl?\[ \t\]*memset" { target { ! arm_neon } } } } */
+/* { dg-final { cleanup-saved-temps } } */
Index: gcc/testsuite/gcc.target/arm/memset-inline-3.c
===================================================================
--- gcc/testsuite/gcc.target/arm/memset-inline-3.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/memset-inline-3.c	(revision 0)
@@ -0,0 +1,40 @@ 
+/* { dg-do run } */
+/* { dg-options "-save-temps -O2 -fno-inline" } */
+
+#include <string.h>
+#include <stdlib.h>
+
+#define LEN (100)
+short a[LEN];
+void
+foo (void)
+{
+    memset (a, -1, 7);
+    return;
+}
+
+void
+check (signed char *arr, int idx, int len, int v)
+{
+  int i;
+  for (i = 0; i < idx; i++)
+    if (arr[i] != v)
+      abort ();
+
+  for (i = idx; i < len; i++)
+    if (arr[i] != 0)
+      abort ();
+}
+
+int
+main(void)
+{
+  foo ();
+  check ((signed char *)a, 7, sizeof (a), -1);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-not "bl?\[ \t\]*memset" { target { ! arm_thumb1_ok } } } } */
+/* { dg-final { scan-assembler-not "strh" { target { ! arm_thumb1 } } } } */
+/* { dg-final { scan-assembler-not "strb" { target { ! arm_thumb1 } } } } */
Index: gcc/testsuite/gcc.target/arm/memset-inline-4.c
===================================================================
--- gcc/testsuite/gcc.target/arm/memset-inline-4.c	(revision 0)
+++ gcc/testsuite/gcc.target/arm/memset-inline-4.c	(revision 0)
@@ -0,0 +1,68 @@ 
+/* { dg-do run } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mcpu=cortex-a9" } { "" } } */
+/* { dg-skip-if "Don't inline memset using neon instructions on cortex-a9" { *-*-* } { "-mtune=cortex-a9" } { "" } } */
+/* { dg-options "-save-temps -O2 -fno-inline" } */
+/* { dg-add-options "arm_neon" } */
+
+#include <string.h>
+#include <stdlib.h>
+
+#define LEN (100)
+int a[LEN];
+int b[LEN];
+int c[LEN];
+void
+foo1 (void)
+{
+    memset (a, -1, 8);
+    return;
+}
+
+void
+foo2 (void)
+{
+  memset (b, 1, 12);
+  return;
+}
+
+void
+foo3 (void)
+{
+  memset (c, 1, 13);
+  return;
+}
+
+void
+check (signed char *arr, int idx, int len, int v)
+{
+  int i;
+  for (i = 0; i < idx; i++)
+    if (arr[i] != v)
+      abort ();
+
+  for (i = idx; i < len; i++)
+    if (arr[i] != 0)
+      abort ();
+}
+
+int
+main(void)
+{
+  int i;
+
+  foo1 ();
+  check ((signed char *)a, 8, sizeof (a), -1);
+
+  foo2 ();
+  check ((signed char *)b, 12, sizeof (b), 1);
+
+  foo3 ();
+  check ((signed char *)c, 13, sizeof (c), 1);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-not "bl?\[ \t\]+memset" { target { ! arm_thumb1_ok } } } } */
+/* { dg-final { scan-assembler-times "vst1\.8" 1 { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { scan-assembler "vstr" { target { arm_little_endian && arm_neon } } } } */
+/* { dg-final { cleanup-saved-temps } } */
Index: gcc/config/arm/arm.c
===================================================================
--- gcc/config/arm/arm.c	(revision 212750)
+++ gcc/config/arm/arm.c	(working copy)
@@ -1698,7 +1698,9 @@  const struct tune_params arm_slowmul_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_fastmul_tune =
@@ -1715,7 +1717,9 @@  const struct tune_params arm_fastmul_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 /* StrongARM has early execution of branches, so a sequence that is worth
@@ -1735,7 +1739,9 @@  const struct tune_params arm_strongarm_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_xscale_tune =
@@ -1752,7 +1758,9 @@  const struct tune_params arm_xscale_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_9e_tune =
@@ -1769,7 +1777,9 @@  const struct tune_params arm_9e_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_v6t2_tune =
@@ -1786,7 +1796,9 @@  const struct tune_params arm_v6t2_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 /* Generic Cortex tuning.  Use more specific tunings if appropriate.  */
@@ -1804,7 +1816,9 @@  const struct tune_params arm_cortex_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_cortex_a8_tune =
@@ -1821,7 +1835,9 @@  const struct tune_params arm_cortex_a8_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  true,						/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_cortex_a7_tune =
@@ -1838,7 +1854,9 @@  const struct tune_params arm_cortex_a7_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,			/* Vectorizer costs.  */
   false,					/* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  true,						/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_cortex_a15_tune =
@@ -1855,7 +1873,9 @@  const struct tune_params arm_cortex_a15_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  true, true                                    /* Prefer 32-bit encodings.  */
+  true, true,                                   /* Prefer 32-bit encodings.  */
+  true,						/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_cortex_a53_tune =
@@ -1872,7 +1892,9 @@  const struct tune_params arm_cortex_a53_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,			/* Vectorizer costs.  */
   false,					/* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_cortex_a57_tune =
@@ -1889,7 +1911,9 @@  const struct tune_params arm_cortex_a57_tune =
   {true, true},                                /* Prefer non short circuit.  */
   &arm_default_vec_cost,                       /* Vectorizer costs.  */
   false,                                       /* Prefer Neon for 64-bits bitops.  */
-  true, true                                   /* Prefer 32-bit encodings.  */
+  true, true,                                  /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 /* Branches can be dual-issued on Cortex-A5, so conditional execution is
@@ -1909,7 +1933,9 @@  const struct tune_params arm_cortex_a5_tune =
   {false, false},				/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  true,						/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_cortex_a9_tune =
@@ -1926,7 +1952,9 @@  const struct tune_params arm_cortex_a9_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_cortex_a12_tune =
@@ -1943,7 +1971,9 @@  const struct tune_params arm_cortex_a12_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  true,						/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 /* armv7m tuning.  On Cortex-M4 cores for example, MOVW/MOVT take a single
@@ -1967,7 +1997,9 @@  const struct tune_params arm_v7m_tune =
   {false, false},				/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 /* The arm_v6m_tune is duplicated from arm_cortex_tune, rather than
@@ -1986,7 +2018,9 @@  const struct tune_params arm_v6m_tune =
   {false, false},				/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 const struct tune_params arm_fa726te_tune =
@@ -2003,7 +2037,9 @@  const struct tune_params arm_fa726te_tune =
   {true, true},					/* Prefer non short circuit.  */
   &arm_default_vec_cost,                        /* Vectorizer costs.  */
   false,                                        /* Prefer Neon for 64-bits bitops.  */
-  false, false                                  /* Prefer 32-bit encodings.  */
+  false, false,                                 /* Prefer 32-bit encodings.  */
+  false,					/* Prefer Neon for stringops.  */
+  8						/* Maximum insns to inline memset.  */
 };
 
 
@@ -16899,6 +16935,14 @@  arm_const_double_inline_cost (rtx val)
 			      NULL_RTX, NULL_RTX, 0, 0));
 }
 
+/* Cost of loading a SImode constant.  */
+static inline int
+arm_const_inline_cost (enum rtx_code code, rtx val)
+{
+  return arm_gen_constant (code, SImode, NULL_RTX, INTVAL (val),
+                           NULL_RTX, NULL_RTX, 1, 0);
+}
+
 /* Return true if it is worthwhile to split a 64-bit constant into two
    32-bit operations.  This is the case if optimizing for size, or
    if we have load delay slots, or if one 32-bit part can be done with
@@ -31514,6 +31565,519 @@  arm_validize_comparison (rtx *comparison, rtx * op
 
 }
 
+/* Maximum number of instructions to set block of memory.  */
+static int
+arm_block_set_max_insns (void)
+{
+  if (optimize_function_for_size_p (cfun))
+    return 4;
+  else
+    return current_tune->max_insns_inline_memset;
+}
+
+/* Return TRUE if it's profitable to set block of memory for
+   non-vectorized case.  VAL is the value to set the memory
+   with.  LENGTH is the number of bytes to set.  ALIGN is the
+   alignment of the destination memory in bytes.  UNALIGNED_P
+   is TRUE if we can only set the memory with instructions
+   meeting alignment requirements.  USE_STRD_P is TRUE if we
+   can use strd to set the memory.  */
+static bool
+arm_block_set_non_vect_profit_p (rtx val,
+				 unsigned HOST_WIDE_INT length,
+				 unsigned HOST_WIDE_INT align,
+				 bool unaligned_p, bool use_strd_p)
+{
+  int num = 0;
+  /* For leftovers in bytes of 0-7, we can set the memory block using
+     strb/strh/str with minimum instruction number.  */
+  const int leftover[8] = {0, 1, 1, 2, 1, 2, 2, 3};
+
+  if (unaligned_p)
+    {
+      num = arm_const_inline_cost (SET, val);
+      num += length / align + length % align;
+    }
+  else if (use_strd_p)
+    {
+      num = arm_const_double_inline_cost (val);
+      num += (length >> 3) + leftover[length & 7];
+    }
+  else
+    {
+      num = arm_const_inline_cost (SET, val);
+      num += (length >> 2) + leftover[length & 3];
+    }
+
+  /* We may be able to combine last pair STRH/STRB into a single STR
+     by shifting one byte back.  */
+  if (unaligned_access && length > 3 && (length & 3) == 3)
+    num--;
+
+  return (num <= arm_block_set_max_insns ());
+}
+
+/* Return TRUE if it's profitable to set block of memory for
+   vectorized case.  LENGTH is the number of bytes to set.
+   ALIGN is the alignment of destination memory in bytes.
+   MODE is the vector mode used to set the memory.  */
+static bool
+arm_block_set_vect_profit_p (unsigned HOST_WIDE_INT length,
+			     unsigned HOST_WIDE_INT align,
+			     enum machine_mode mode)
+{
+  int num;
+  bool unaligned_p = ((align & 3) != 0);
+  unsigned int nelt = GET_MODE_NUNITS (mode);
+
+  /* Instruction loading constant value.  */
+  num = 1;
+  /* Instructions storing the memory.  */
+  num += (length + nelt - 1) / nelt;
+  /* Instructions adjusting the address expression.  Only need to
+     adjust address expression if it's 4 bytes aligned and bytes
+     leftover can only be stored by mis-aligned store instruction.  */
+  if (!unaligned_p && (length & 3) != 0)
+    num++;
+
+  /* Store the first 16 bytes using vst1:v16qi for the aligned case.  */
+  if (!unaligned_p && mode == V16QImode)
+    num--;
+
+  return (num <= arm_block_set_max_insns ());
+}
+
+/* Set a block of memory using vectorization instructions for the
+   unaligned case.  We fill the first LENGTH bytes of the memory
+   area starting from DSTBASE with byte constant VALUE.  ALIGN is
+   the alignment requirement of memory.  Return TRUE if succeeded.  */
+static bool
+arm_block_set_unaligned_vect (rtx dstbase,
+			      unsigned HOST_WIDE_INT length,
+			      unsigned HOST_WIDE_INT value,
+			      unsigned HOST_WIDE_INT align)
+{
+  unsigned int i, j, nelt_v16, nelt_v8, nelt_mode;
+  rtx dst, mem;
+  rtx val_elt, val_vec, reg;
+  rtx rval[MAX_VECT_LEN];
+  rtx (*gen_func) (rtx, rtx);
+  enum machine_mode mode;
+  unsigned HOST_WIDE_INT v = value;
+
+  gcc_assert ((align & 0x3) != 0);
+  nelt_v8 = GET_MODE_NUNITS (V8QImode);
+  nelt_v16 = GET_MODE_NUNITS (V16QImode);
+  if (length >= nelt_v16)
+    {
+      mode = V16QImode;
+      gen_func = gen_movmisalignv16qi;
+    }
+  else
+    {
+      mode = V8QImode;
+      gen_func = gen_movmisalignv8qi;
+    }
+  nelt_mode = GET_MODE_NUNITS (mode);
+  gcc_assert (length >= nelt_mode);
+  /* Skip if it isn't profitable.  */
+  if (!arm_block_set_vect_profit_p (length, align, mode))
+    return false;
+
+  dst = copy_addr_to_reg (XEXP (dstbase, 0));
+  mem = adjust_automodify_address (dstbase, mode, dst, 0);
+
+  v = sext_hwi (v, BITS_PER_WORD);
+  val_elt = GEN_INT (v);
+  for (j = 0; j < nelt_mode; j++)
+    rval[j] = val_elt;
+
+  reg = gen_reg_rtx (mode);
+  val_vec = gen_rtx_CONST_VECTOR (mode, gen_rtvec_v (nelt_mode, rval));
+  /* Emit instruction loading the constant value.  */
+  emit_move_insn (reg, val_vec);
+
+  /* Handle nelt_mode bytes in a vector.  */
+  for (i = 0; (i + nelt_mode <= length); i += nelt_mode)
+    {
+      emit_insn ((*gen_func) (mem, reg));
+      if (i + 2 * nelt_mode <= length)
+	emit_insn (gen_add2_insn (dst, GEN_INT (nelt_mode)));
+    }
+
+  /* If there are not less than nelt_v8 bytes leftover, we must be in
+     V16QI mode.  */
+  gcc_assert ((i + nelt_v8) > length || mode == V16QImode);
+
+  /* Handle (8, 16) bytes leftover.  */
+  if (i + nelt_v8 < length)
+    {
+      emit_insn (gen_add2_insn (dst, GEN_INT (length - i)));
+      /* We are shifting bytes back, set the alignment accordingly.  */
+      if ((length & 1) != 0 && align >= 2)
+	set_mem_align (mem, BITS_PER_UNIT);
+
+      emit_insn (gen_movmisalignv16qi (mem, reg));
+    }
+  /* Handle (0, 8] bytes leftover.  */
+  else if (i < length && i + nelt_v8 >= length)
+    {
+      if (mode == V16QImode)
+	{
+	  reg = gen_lowpart (V8QImode, reg);
+	  mem = adjust_automodify_address (dstbase, V8QImode, dst, 0);
+	}
+      emit_insn (gen_add2_insn (dst, GEN_INT ((length - i)
+					      + (nelt_mode - nelt_v8))));
+      /* We are shifting bytes back, set the alignment accordingly.  */
+      if ((length & 1) != 0 && align >= 2)
+	set_mem_align (mem, BITS_PER_UNIT);
+
+      emit_insn (gen_movmisalignv8qi (mem, reg));
+    }
+
+  return true;
+}
+
+/* Set a block of memory using vectorization instructions for the
+   aligned case.  We fill the first LENGTH bytes of the memory area
+   starting from DSTBASE with byte constant VALUE.  ALIGN is the
+   alignment requirement of memory.  Return TRUE if succeeded.  */
+static bool
+arm_block_set_aligned_vect (rtx dstbase,
+			    unsigned HOST_WIDE_INT length,
+			    unsigned HOST_WIDE_INT value,
+			    unsigned HOST_WIDE_INT align)
+{
+  unsigned int i, j, nelt_v8, nelt_v16, nelt_mode;
+  rtx dst, addr, mem;
+  rtx val_elt, val_vec, reg;
+  rtx rval[MAX_VECT_LEN];
+  enum machine_mode mode;
+  unsigned HOST_WIDE_INT v = value;
+
+  gcc_assert ((align & 0x3) == 0);
+  nelt_v8 = GET_MODE_NUNITS (V8QImode);
+  nelt_v16 = GET_MODE_NUNITS (V16QImode);
+  if (length >= nelt_v16 && unaligned_access && !BYTES_BIG_ENDIAN)
+    mode = V16QImode;
+  else
+    mode = V8QImode;
+
+  nelt_mode = GET_MODE_NUNITS (mode);
+  gcc_assert (length >= nelt_mode);
+  /* Skip if it isn't profitable.  */
+  if (!arm_block_set_vect_profit_p (length, align, mode))
+    return false;
+
+  dst = copy_addr_to_reg (XEXP (dstbase, 0));
+
+  v = sext_hwi (v, BITS_PER_WORD);
+  val_elt = GEN_INT (v);
+  for (j = 0; j < nelt_mode; j++)
+    rval[j] = val_elt;
+
+  reg = gen_reg_rtx (mode);
+  val_vec = gen_rtx_CONST_VECTOR (mode, gen_rtvec_v (nelt_mode, rval));
+  /* Emit instruction loading the constant value.  */
+  emit_move_insn (reg, val_vec);
+
+  i = 0;
+  /* Handle first 16 bytes specially using vst1:v16qi instruction.  */
+  if (mode == V16QImode)
+    {
+      mem = adjust_automodify_address (dstbase, mode, dst, 0);
+      emit_insn (gen_movmisalignv16qi (mem, reg));
+      i += nelt_mode;
+      /* Handle (8, 16) bytes leftover using vst1:v16qi again.  */
+      if (i + nelt_v8 < length && i + nelt_v16 > length)
+	{
+	  emit_insn (gen_add2_insn (dst, GEN_INT (length - nelt_mode)));
+	  mem = adjust_automodify_address (dstbase, mode, dst, 0);
+	  /* We are shifting bytes back, set the alignment accordingly.  */
+	  if ((length & 0x3) == 0)
+	    set_mem_align (mem, BITS_PER_UNIT * 4);
+	  else if ((length & 0x1) == 0)
+	    set_mem_align (mem, BITS_PER_UNIT * 2);
+	  else
+	    set_mem_align (mem, BITS_PER_UNIT);
+
+	  emit_insn (gen_movmisalignv16qi (mem, reg));
+	  return true;
+	}
+      /* Fall through for bytes leftover.  */
+      mode = V8QImode;
+      nelt_mode = GET_MODE_NUNITS (mode);
+      reg = gen_lowpart (V8QImode, reg);
+    }
+
+  /* Handle 8 bytes in a vector.  */
+  for (; (i + nelt_mode <= length); i += nelt_mode)
+    {
+      addr = plus_constant (Pmode, dst, i);
+      mem = adjust_automodify_address (dstbase, mode, addr, i);
+      emit_move_insn (mem, reg);
+    }
+
+  /* Handle single word leftover by shifting 4 bytes back.  We can
+     use aligned access for this case.  */
+  if (i + UNITS_PER_WORD == length)
+    {
+      addr = plus_constant (Pmode, dst, i - UNITS_PER_WORD);
+      mem = adjust_automodify_address (dstbase, mode,
+				       addr, i - UNITS_PER_WORD);
+      /* We are shifting 4 bytes back, set the alignment accordingly.  */
+      if (align > UNITS_PER_WORD)
+	set_mem_align (mem, BITS_PER_UNIT * UNITS_PER_WORD);
+
+      emit_move_insn (mem, reg);
+    }
+  /* Handle (0, 4), (4, 8) bytes leftover by shifting bytes back.
+     We have to use unaligned access for this case.  */
+  else if (i < length)
+    {
+      emit_insn (gen_add2_insn (dst, GEN_INT (length - nelt_mode)));
+      mem = adjust_automodify_address (dstbase, mode, dst, 0);
+      /* We are shifting bytes back, set the alignment accordingly.  */
+      if ((length & 1) == 0)
+	set_mem_align (mem, BITS_PER_UNIT * 2);
+      else
+	set_mem_align (mem, BITS_PER_UNIT);
+
+      emit_insn (gen_movmisalignv8qi (mem, reg));
+    }
+
+  return true;
+}
+
+/* Set a block of memory using plain strh/strb instructions, only
+   using instructions allowed by ALIGN on processor.  We fill the
+   first LENGTH bytes of the memory area starting from DSTBASE
+   with byte constant VALUE.  ALIGN is the alignment requirement
+   of memory.  */
+static bool
+arm_block_set_unaligned_non_vect (rtx dstbase,
+				  unsigned HOST_WIDE_INT length,
+				  unsigned HOST_WIDE_INT value,
+				  unsigned HOST_WIDE_INT align)
+{
+  unsigned int i;
+  rtx dst, addr, mem;
+  rtx val_exp, val_reg, reg;
+  enum machine_mode mode;
+  HOST_WIDE_INT v = value;
+
+  gcc_assert (align == 1 || align == 2);
+
+  if (align == 2)
+    v |= (value << BITS_PER_UNIT);
+
+  v = sext_hwi (v, BITS_PER_WORD);
+  val_exp = GEN_INT (v);
+  /* Skip if it isn't profitable.  */
+  if (!arm_block_set_non_vect_profit_p (val_exp, length,
+					align, true, false))
+    return false;
+
+  dst = copy_addr_to_reg (XEXP (dstbase, 0));
+  mode = (align == 2 ? HImode : QImode);
+  val_reg = force_reg (SImode, val_exp);
+  reg = gen_lowpart (mode, val_reg);
+
+  for (i = 0; (i + GET_MODE_SIZE (mode) <= length); i += GET_MODE_SIZE (mode))
+    {
+      addr = plus_constant (Pmode, dst, i);
+      mem = adjust_automodify_address (dstbase, mode, addr, i);
+      emit_move_insn (mem, reg);
+    }
+
+  /* Handle single byte leftover.  */
+  if (i + 1 == length)
+    {
+      reg = gen_lowpart (QImode, val_reg);
+      addr = plus_constant (Pmode, dst, i);
+      mem = adjust_automodify_address (dstbase, QImode, addr, i);
+      emit_move_insn (mem, reg);
+      i++;
+    }
+
+  gcc_assert (i == length);
+  return true;
+}
+
+/* Set a block of memory using plain strd/str/strh/strb instructions,
+   to permit unaligned copies on processors which support unaligned
+   semantics for those instructions.  We fill the first LENGTH bytes
+   of the memory area starting from DSTBASE with byte constant VALUE.
+   ALIGN is the alignment requirement of memory.  */
+static bool
+arm_block_set_aligned_non_vect (rtx dstbase,
+				unsigned HOST_WIDE_INT length,
+				unsigned HOST_WIDE_INT value,
+				unsigned HOST_WIDE_INT align)
+{
+  unsigned int i;
+  rtx dst, addr, mem;
+  rtx val_exp, val_reg, reg;
+  unsigned HOST_WIDE_INT v;
+  bool use_strd_p;
+
+  use_strd_p = (length >= 2 * UNITS_PER_WORD && (align & 3) == 0
+		&& TARGET_LDRD && current_tune->prefer_ldrd_strd);
+
+  v = (value | (value << 8) | (value << 16) | (value << 24));
+  if (length < UNITS_PER_WORD)
+    v &= (0xFFFFFFFF >> (UNITS_PER_WORD - length) * BITS_PER_UNIT);
+
+  if (use_strd_p)
+    v |= (v << BITS_PER_WORD);
+  else
+    v = sext_hwi (v, BITS_PER_WORD);
+
+  val_exp = GEN_INT (v);
+  /* Skip if it isn't profitable.  */
+  if (!arm_block_set_non_vect_profit_p (val_exp, length,
+					align, false, use_strd_p))
+    {
+      if (!use_strd_p)
+	return false;
+
+      /* Try without strd.  */
+      v = (v >> BITS_PER_WORD);
+      v = sext_hwi (v, BITS_PER_WORD);
+      val_exp = GEN_INT (v);
+      use_strd_p = false;
+      if (!arm_block_set_non_vect_profit_p (val_exp, length,
+					    align, false, use_strd_p))
+	return false;
+    }
+
+  i = 0;
+  dst = copy_addr_to_reg (XEXP (dstbase, 0));
+  /* Handle double words using strd if possible.  */
+  if (use_strd_p)
+    {
+      val_reg = force_reg (DImode, val_exp);
+      reg = val_reg;
+      for (; (i + 8 <= length); i += 8)
+	{
+	  addr = plus_constant (Pmode, dst, i);
+	  mem = adjust_automodify_address (dstbase, DImode, addr, i);
+	  emit_move_insn (mem, reg);
+	}
+    }
+  else
+    val_reg = force_reg (SImode, val_exp);
+
+  /* Handle words.  */
+  reg = (use_strd_p ? gen_lowpart (SImode, val_reg) : val_reg);
+  for (; (i + 4 <= length); i += 4)
+    {
+      addr = plus_constant (Pmode, dst, i);
+      mem = adjust_automodify_address (dstbase, SImode, addr, i);
+      if ((align & 3) == 0)
+	emit_move_insn (mem, reg);
+      else
+	emit_insn (gen_unaligned_storesi (mem, reg));
+    }
+
+  /* Merge last pair of STRH and STRB into a STR if possible.  */
+  if (unaligned_access && i > 0 && (i + 3) == length)
+    {
+      addr = plus_constant (Pmode, dst, i - 1);
+      mem = adjust_automodify_address (dstbase, SImode, addr, i - 1);
+      /* We are shifting one byte back, set the alignment accordingly.  */
+      if ((align & 1) == 0)
+	set_mem_align (mem, BITS_PER_UNIT);
+
+      /* Most likely this is an unaligned access, and we can't tell at
+	 compilation time.  */
+      emit_insn (gen_unaligned_storesi (mem, reg));
+      return true;
+    }
+
+  /* Handle half word leftover.  */
+  if (i + 2 <= length)
+    {
+      reg = gen_lowpart (HImode, val_reg);
+      addr = plus_constant (Pmode, dst, i);
+      mem = adjust_automodify_address (dstbase, HImode, addr, i);
+      if ((align & 1) == 0)
+	emit_move_insn (mem, reg);
+      else
+	emit_insn (gen_unaligned_storehi (mem, reg));
+
+      i += 2;
+    }
+
+  /* Handle single byte leftover.  */
+  if (i + 1 == length)
+    {
+      reg = gen_lowpart (QImode, val_reg);
+      addr = plus_constant (Pmode, dst, i);
+      mem = adjust_automodify_address (dstbase, QImode, addr, i);
+      emit_move_insn (mem, reg);
+    }
+
+  return true;
+}
+
+/* Set a block of memory using vectorization instructions for both
+   aligned and unaligned cases.  We fill the first LENGTH bytes of
+   the memory area starting from DSTBASE with byte constant VALUE.
+   ALIGN is the alignment requirement of memory.  */
+static bool
+arm_block_set_vect (rtx dstbase,
+		    unsigned HOST_WIDE_INT length,
+		    unsigned HOST_WIDE_INT value,
+		    unsigned HOST_WIDE_INT align)
+{
+  /* Check whether we need to use unaligned store instruction.  */
+  if (((align & 3) != 0 || (length & 3) != 0)
+      /* Check whether unaligned store instruction is available.  */
+      && (!unaligned_access || BYTES_BIG_ENDIAN))
+    return false;
+
+  if ((align & 3) == 0)
+    return arm_block_set_aligned_vect (dstbase, length, value, align);
+  else
+    return arm_block_set_unaligned_vect (dstbase, length, value, align);
+}
+
+/* Expand string store operation.  Firstly we try to do that by using
+   vectorization instructions, then try with ARM unaligned access and
+   double-word store if profitable.  OPERANDS[0] is the destination,
+   OPERANDS[1] is the number of bytes, operands[2] is the value to
+   initialize the memory, OPERANDS[3] is the known alignment of the
+   destination.  */
+bool
+arm_gen_setmem (rtx *operands)
+{
+  rtx dstbase = operands[0];
+  unsigned HOST_WIDE_INT length;
+  unsigned HOST_WIDE_INT value;
+  unsigned HOST_WIDE_INT align;
+
+  if (!CONST_INT_P (operands[2]) || !CONST_INT_P (operands[1]))
+    return false;
+
+  length = UINTVAL (operands[1]);
+  if (length > 64)
+    return false;
+
+  value = (UINTVAL (operands[2]) & 0xFF);
+  align = UINTVAL (operands[3]);
+  if (TARGET_NEON && length >= 8
+      && current_tune->string_ops_prefer_neon
+      && arm_block_set_vect (dstbase, length, value, align))
+    return true;
+
+  if (!unaligned_access && (align & 3) != 0)
+    return arm_block_set_unaligned_non_vect (dstbase, length, value, align);
+
+  return arm_block_set_aligned_non_vect (dstbase, length, value, align);
+}
+
 /* Implement the TARGET_ASAN_SHADOW_OFFSET hook.  */
 
 static unsigned HOST_WIDE_INT
Index: gcc/config/arm/arm.md
===================================================================
--- gcc/config/arm/arm.md	(revision 212750)
+++ gcc/config/arm/arm.md	(working copy)
@@ -6716,6 +6716,20 @@ 
 })
 
 
+(define_expand "setmemsi"
+  [(match_operand:BLK 0 "general_operand" "")
+   (match_operand:SI 1 "const_int_operand" "")
+   (match_operand:SI 2 "const_int_operand" "")
+   (match_operand:SI 3 "const_int_operand" "")]
+  "TARGET_32BIT"
+{
+  if (arm_gen_setmem (operands))
+    DONE;
+
+  FAIL;
+})
+
+
 ;; Move a block of memory if it is word aligned and MORE than 2 words long.
 ;; We could let this apply for blocks of less than this, but it clobbers so
 ;; many registers that there is then probably a better way.
Index: gcc/config/arm/arm-protos.h
===================================================================
--- gcc/config/arm/arm-protos.h	(revision 212750)
+++ gcc/config/arm/arm-protos.h	(working copy)
@@ -278,6 +278,10 @@  struct tune_params
   /* Prefer 32-bit encoding instead of 16-bit encoding where subset of flags
      would be set.  */
   bool disparage_partial_flag_setting_t16_encodings;
+  /* Prefer to inline string operations like memset by using Neon.  */
+  bool string_ops_prefer_neon;
+  /* Maximum number of instructions to inline calls to memset.  */
+  int max_insns_inline_memset;
 };
 
 extern const struct tune_params *current_tune;
@@ -290,6 +294,7 @@  extern void arm_emit_coreregs_64bit_shift (enum rt
 extern bool arm_validize_comparison (rtx *, rtx *, rtx *);
 #endif /* RTX_CODE */
 
+extern bool arm_gen_setmem (rtx *);
 extern void arm_expand_vec_perm (rtx target, rtx op0, rtx op1, rtx sel);
 extern bool arm_expand_vec_perm_const (rtx target, rtx op0, rtx op1, rtx sel);