[PATCH] [arm] Implement Armv8.1-M low overhead loops

[PATCH] [arm] Implement Armv8.1-M low overhead loops

[Andrea Corallo]

[-- Attachment #1: Type: text/plain, Size: 1315 bytes --]

Hi all,

This patch enables the Armv8.1-M Mainline LOB (low overhead branch) extension
low overhead loops (LOL) feature by using the loop-doloop pass
that it shares with the Swing Modulo Scheduler.

bootstrapped arm-none-linux-gnueabihf, does not introduce testsuite regressions.

Andrea

gcc/ChangeLog:

2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
2020-??-??  Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
2020-??-??  Iain Apreotesei  <iain.apreotesei@arm.com>

        * config/arm/arm.c (TARGET_INVALID_WITHIN_DOLOOP):
        (arm_invalid_within_doloop): Implement invalid_within_doloop hook.
        * config/arm/arm.h (TARGET_HAVE_LOB): Add new macro.
        * config/arm/thumb2.md (*doloop_end, doloop_begin, dls_insn):
        Add new patterns.
        * config/arm/unspecs.md: Add new unspec.

gcc/testsuite/ChangeLog:

2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
2020-??-??  Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
2020-??-??  Iain Apreotesei  <iain.apreotesei@arm.com>

        * gcc.target/arm/lob.h: New header.
        * gcc.target/arm/lob1.c: New testcase.
        * gcc.target/arm/lob2.c: Likewise.
        * gcc.target/arm/lob3.c: Likewise.
        * gcc.target/arm/lob4.c: Likewise.
        * gcc.target/arm/lob5.c: Likewise.
        * gcc.target/arm/lob6.c: Likewise.


[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: lol.patch --]
[-- Type: text/x-diff, Size: 12343 bytes --]

diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h
index e07cf03538c..1269f40bd77 100644
--- a/gcc/config/arm/arm.h
+++ b/gcc/config/arm/arm.h
@@ -586,6 +586,9 @@ extern int arm_arch_bf16;
 \f
 /* Target machine storage Layout.  */
 
+/* Nonzero if this chip provides Armv8.1-M Mainline
+   LOB (low overhead branch features) extension instructions.  */
+#define TARGET_HAVE_LOB (arm_arch8_1m_main)
 
 /* Define this macro if it is advisable to hold scalars in registers
    in a wider mode than that declared by the program.  In such cases,
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 9cc7bc0e562..d0b50d544e3 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -833,6 +833,9 @@ static const struct attribute_spec arm_attribute_table[] =
 #undef TARGET_CONSTANT_ALIGNMENT
 #define TARGET_CONSTANT_ALIGNMENT arm_constant_alignment
 
+#undef TARGET_INVALID_WITHIN_DOLOOP
+#define TARGET_INVALID_WITHIN_DOLOOP arm_invalid_within_doloop
+
 #undef TARGET_MD_ASM_ADJUST
 #define TARGET_MD_ASM_ADJUST arm_md_asm_adjust
 \f
@@ -32937,6 +32940,39 @@ arm_ge_bits_access (void)
   return true;
 }
 
+/* NULL if INSN insn is valid within a low-overhead loop.
+   Otherwise return why doloop cannot be applied.  */
+
+static const char *
+arm_invalid_within_doloop (const rtx_insn *insn)
+{
+  if (!TARGET_HAVE_LOB)
+    return default_invalid_within_doloop (insn);
+
+  if (CALL_P (insn))
+    return "Function call in the loop.";
+
+  if (tablejump_p (insn, NULL, NULL) || computed_jump_p (insn))
+    return "Computed branch in the loop.";
+
+  if (INSN_P (insn)
+      && GET_CODE (PATTERN (insn)) == PARALLEL)
+    {
+      rtx parallel = PATTERN (insn);
+      rtx clobber;
+      int j;
+      for (j = XVECLEN (parallel, 0) - 1; j >= 0; j--)
+	{
+	  clobber = XVECEXP (parallel, 0, j);
+	  if (GET_CODE (clobber) == CLOBBER
+	      && GET_CODE (XEXP (clobber, 0)) == REG
+	      && REGNO (XEXP (clobber, 0)) == LR_REGNUM)
+	    return "LR is used inside loop.";
+	}
+    }
+  return NULL;
+}
+
 #if CHECKING_P
 namespace selftest {
 
diff --git a/gcc/config/arm/thumb2.md b/gcc/config/arm/thumb2.md
index b0d3bd1cf1c..44b1a264dba 100644
--- a/gcc/config/arm/thumb2.md
+++ b/gcc/config/arm/thumb2.md
@@ -1555,8 +1555,11 @@
       using a certain 'count' register and (2) the loop count can be
       adjusted by modifying this register prior to the loop.
       ??? The possible introduction of a new block to initialize the
-      new IV can potentially affect branch optimizations.  */
-   if (optimize > 0 && flag_modulo_sched)
+      new IV can potentially affect branch optimizations.
+
+      Also used to implement the low over head loops feature, which is part of
+      the Armv8.1-M Mainline Low Overhead Branch (LOB) extension.  */
+   if (optimize > 0 && (flag_modulo_sched || TARGET_HAVE_LOB))
    {
      rtx s0;
      rtx bcomp;
@@ -1569,6 +1572,11 @@
        FAIL;
 
      s0 = operands [0];
+
+     /* Low over head loop instructions require the first operand to be LR.  */
+     if (TARGET_HAVE_LOB)
+       s0 = gen_rtx_REG (SImode, LR_REGNUM);
+
      if (TARGET_THUMB2)
        insn = emit_insn (gen_thumb2_addsi3_compare0 (s0, s0, GEN_INT (-1)));
      else
@@ -1650,3 +1658,29 @@
   "TARGET_HAVE_MVE"
   "lsrl%?\\t%Q0, %R0, %1"
   [(set_attr "predicable" "yes")])
+
+(define_insn "*doloop_end"
+  [(parallel [(set (pc)
+                   (if_then_else
+                       (ne (reg:SI LR_REGNUM) (const_int 1))
+                     (label_ref (match_operand 0 "" ""))
+                     (pc)))
+              (set (reg:SI LR_REGNUM)
+                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
+  "TARGET_32BIT && TARGET_HAVE_LOB && !flag_modulo_sched"
+  "le\tlr, %l0")
+
+(define_expand "doloop_begin"
+  [(match_operand 0 "" "")
+   (match_operand 1 "" "")]
+  "TARGET_32BIT && TARGET_HAVE_LOB && !flag_modulo_sched"
+  {
+    emit_insn (gen_dls_insn (operands[0], operands[0]));
+    DONE;
+  })
+
+(define_insn "dls_insn"
+  [(set (match_operand:SI 0 "" "")
+        (unspec:SI [(match_operand:SI 1 "s_register_operand" "r")] UNSPEC_DLS))]
+  "TARGET_32BIT && TARGET_HAVE_LOB && !flag_modulo_sched"
+  "dls\tlr, %1")
diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md
index 8f4a705f43e..df5ecb73192 100644
--- a/gcc/config/arm/unspecs.md
+++ b/gcc/config/arm/unspecs.md
@@ -154,6 +154,7 @@
   UNSPEC_SMUADX		; Represent the SMUADX operation.
   UNSPEC_SSAT16		; Represent the SSAT16 operation.
   UNSPEC_USAT16		; Represent the USAT16 operation.
+  UNSPEC_DLS		; Used for DLS (Do Loop Start), Armv8.1-M Mainline instruction
 ])
 
 
diff --git a/gcc/testsuite/gcc.target/arm/lob.h b/gcc/testsuite/gcc.target/arm/lob.h
new file mode 100644
index 00000000000..feaae7cc899
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob.h
@@ -0,0 +1,15 @@
+#include <string.h>
+
+/* Common code for lob tests.  */
+
+#define NO_LOB asm volatile ("@ clobber lr" : : : "lr" )
+
+#define N 10000
+
+static void
+reset_data (int *a, int *b, int *c)
+{
+  memset (a, -1, N * sizeof (*a));
+  memset (b, -1, N * sizeof (*b));
+  memset (c, -1, N * sizeof (*c));
+}
diff --git a/gcc/testsuite/gcc.target/arm/lob1.c b/gcc/testsuite/gcc.target/arm/lob1.c
new file mode 100644
index 00000000000..8ffaaa29878
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob1.c
@@ -0,0 +1,82 @@
+/* Check that GCC generates Armv8.1-M low over head loop instructions
+   for some simple loops.  */
+/* { dg-do run } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int
+foo (int a, int b)
+{
+  return a + b;
+}
+
+void __attribute__((noinline))
+loop1 (int *a, int *b, int *c)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = a[i] + b[i];
+    }
+}
+
+void __attribute__((noinline))
+loop2 (int *a, int *b, int *c)
+{
+  int i = 0;
+  while (i < N)
+    {
+      a[i] = i - 2;
+      b[i] = i * 5;
+      c[i] = a[i] + b[i];
+      i++;
+    }
+}
+
+void __attribute__((noinline))
+loop3 (int *a, int *b, int *c)
+{
+  int i = 0;
+  do
+    {
+      a[i] = i - 4;
+      b[i] = i * 3;
+      c[i] = a[i] + b[i];
+      i++;
+    } while (i < N);
+}
+
+void
+check (int *a, int *b, int *c)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (c[i] != a[i] + b[i])
+	abort ();
+    }
+}
+
+int main (void)
+{
+  reset_data (a, b, c);
+  loop1 (a, b ,c);
+  check (a, b ,c);
+  reset_data (a, b, c);
+  loop2 (a, b ,c);
+  check (a, b ,c);
+  reset_data (a, b, c);
+  loop3 (a, b ,c);
+  check (a, b ,c);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times {dls\s\S*,\s\S*} 3 } } */
+/* { dg-final { scan-assembler-times {le\slr,\s\S*} 3 } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob2.c b/gcc/testsuite/gcc.target/arm/lob2.c
new file mode 100644
index 00000000000..046d92fcad1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob2.c
@@ -0,0 +1,30 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if a non-inlineable function call takes place inside the loop.  */
+/* { dg-do compile } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int __attribute__ ((noinline))
+foo (int a, int b)
+{
+  return a + b;
+}
+
+int main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = foo (a[i], b[i]);
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob3.c b/gcc/testsuite/gcc.target/arm/lob3.c
new file mode 100644
index 00000000000..77f89ad9c70
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob3.c
@@ -0,0 +1,26 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if causes VFP emulation library calls to happen inside the loop.  */
+/* { dg-do compile } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps -mfloat-abi=soft" } */
+/* { dg-require-effective-target arm_softfloat } */
+#include <stdlib.h>
+#include "lob.h"
+
+double a[N];
+double b[N];
+double c[N];
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = a[i] + b[i];
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob4.c b/gcc/testsuite/gcc.target/arm/lob4.c
new file mode 100644
index 00000000000..88be61f3c76
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob4.c
@@ -0,0 +1,32 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if LR is modified within the loop.  */
+/* { dg-do compile } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps -mfloat-abi=soft" } */
+/* { dg-require-effective-target arm_softfloat } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+static __attribute__ ((always_inline)) inline int
+foo (int a, int b)
+{
+  NO_LOB;
+  return a + b;
+}
+
+int main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = foo(a[i], b[i]);
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob5.c b/gcc/testsuite/gcc.target/arm/lob5.c
new file mode 100644
index 00000000000..cd91c3252d3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob5.c
@@ -0,0 +1,33 @@
+/* Check that GCC does not generates Armv8.1-M low over head loop
+   instructions.  Innermost loop has no fixed number of iterations
+   therefore is not optimizable.  Outer loops are not optimized.  */
+/* { dg-do compile } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+
+      int k = b[i];
+      while (k != 0)
+	{
+	  if (k % 2 == 0)
+	    c[i - 1] = k % 2;
+	  k /= 2;
+	}
+      c[i] = a[i] - b[i];
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob6.c b/gcc/testsuite/gcc.target/arm/lob6.c
new file mode 100644
index 00000000000..4bcedc8bd60
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob6.c
@@ -0,0 +1,94 @@
+/* Check that GCC generates Armv8.1-M low over head loop instructions
+   with some less trivial loops and the result is correct.  */
+/* { dg-do run } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+#define TEST_CODE1				\
+  {						\
+    for (int i = 0; i < N; i++)			\
+      {						\
+	a[i] = i;				\
+	b[i] = i * 2;				\
+						\
+	for (int k = 0; k < N; k++)		\
+	  {					\
+	    MAYBE_LOB;				\
+	    c[k] = k / 2;			\
+	  }					\
+	c[i] = a[i] - b[i];			\
+      }						\
+  }
+
+#define TEST_CODE2				\
+  {						\
+    for (int i = 0; i < N / 2; i++)		\
+      {						\
+	MAYBE_LOB;				\
+	if (c[i] % 2 == 0)			\
+	  break;				\
+	a[i]++;					\
+	b[i]++;					\
+      }						\
+  }
+
+int a1[N];
+int b1[N];
+int c1[N];
+
+int a2[N];
+int b2[N];
+int c2[N];
+
+#define MAYBE_LOB
+void __attribute__((noinline))
+loop1 (int *a, int *b, int *c)
+  TEST_CODE1;
+
+void __attribute__((noinline))
+loop2 (int *a, int *b, int *c)
+  TEST_CODE2;
+
+#undef MAYBE_LOB
+#define MAYBE_LOB NO_LOB
+
+void
+ref1 (int *a, int *b, int *c)
+  TEST_CODE1;
+
+void
+ref2 (int *a, int *b, int *c)
+  TEST_CODE2;
+
+void
+check (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (a1[i] != a2[i]
+	  && b1[i] != b2[i]
+	  && c1[i] != c2[i])
+	abort ();
+    }
+}
+
+int main (void)
+{
+  reset_data (a1, b1, c1);
+  reset_data (a2, b2, c2);
+  loop1 (a1, b1, c1);
+  ref1 (a2, b2, c2);
+  check ();
+
+  reset_data (a1, b1, c1);
+  reset_data (a2, b2, c2);
+  loop2 (a1, b1, c1);
+  ref2 (a2, b2, c2);
+  check ();
+
+  return 0;
+}
+/* { dg-final { scan-assembler-times {dls\s\S*,\s\S*} 2 } } */
+/* { dg-final { scan-assembler-times {le\slr,\s\S*} 2 } } */

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Richard Earnshaw (lists)]

On 11/02/2020 10:14, Andrea Corallo wrote:
> Hi all,
> 
> This patch enables the Armv8.1-M Mainline LOB (low overhead branch) extension
> low overhead loops (LOL) feature by using the loop-doloop pass
> that it shares with the Swing Modulo Scheduler.
> 
> bootstrapped arm-none-linux-gnueabihf, does not introduce testsuite regressions.
> 
> Andrea
> 
> gcc/ChangeLog:
> 
> 2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
> 2020-??-??  Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
> 2020-??-??  Iain Apreotesei  <iain.apreotesei@arm.com>
> 
>          * config/arm/arm.c (TARGET_INVALID_WITHIN_DOLOOP):
>          (arm_invalid_within_doloop): Implement invalid_within_doloop hook.
>          * config/arm/arm.h (TARGET_HAVE_LOB): Add new macro.
>          * config/arm/thumb2.md (*doloop_end, doloop_begin, dls_insn):
>          Add new patterns.
>          * config/arm/unspecs.md: Add new unspec.
> 

A date should only appear before the first author in a multi-author 
patch, other authors should then be indented to align with the name of 
that first author.

> gcc/testsuite/ChangeLog:
> 
> 2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
> 2020-??-??  Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
> 2020-??-??  Iain Apreotesei  <iain.apreotesei@arm.com>
> 
>          * gcc.target/arm/lob.h: New header.
>          * gcc.target/arm/lob1.c: New testcase.
>          * gcc.target/arm/lob2.c: Likewise.
>          * gcc.target/arm/lob3.c: Likewise.
>          * gcc.target/arm/lob4.c: Likewise.
>          * gcc.target/arm/lob5.c: Likewise.
>          * gcc.target/arm/lob6.c: Likewise.
> 

+(define_insn "*doloop_end"
+  [(parallel [(set (pc)
+                   (if_then_else
+                       (ne (reg:SI LR_REGNUM) (const_int 1))
+                     (label_ref (match_operand 0 "" ""))
+                     (pc)))
+              (set (reg:SI LR_REGNUM)
+                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
+  "TARGET_32BIT && TARGET_HAVE_LOB && !flag_modulo_sched"
+  "le\tlr, %l0")

Is it deliberate that this pattern name has a '*' prefix?  doloop_end is 
a named expansion pattern according to md.texi.

Also, hard-coded register names should be prefixed with '%|' (so "%|lr", 
not just "lr"), just in case the assembler dialect requires something 
(ELF doesn't but others have).  Also for dls_insn.

For the tests, your 'require-effective-taret' tests look insufficient to 
prevent problems when testing a multilib environment, you'll need (at 
least) checks that a) passing -marm has not happened and b) that the 
architecture, or a specific CPU isn't being passed on the command line.

R.

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Andrea Corallo]

Hi Richard,

"Richard Earnshaw (lists)" <Richard.Earnshaw@arm.com> writes:

>> gcc/ChangeLog:
>> 2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
>> 2020-??-??  Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
>> 2020-??-??  Iain Apreotesei  <iain.apreotesei@arm.com>
>>          * config/arm/arm.c (TARGET_INVALID_WITHIN_DOLOOP):
>>          (arm_invalid_within_doloop): Implement invalid_within_doloop hook.
>>          * config/arm/arm.h (TARGET_HAVE_LOB): Add new macro.
>>          * config/arm/thumb2.md (*doloop_end, doloop_begin, dls_insn):
>>          Add new patterns.
>>          * config/arm/unspecs.md: Add new unspec.
>>
>
> A date should only appear before the first author in a multi-author
> patch, other authors should then be indented to align with the name of
> that first author.

Ack

> +(define_insn "*doloop_end"
> +  [(parallel [(set (pc)
> +                   (if_then_else
> +                       (ne (reg:SI LR_REGNUM) (const_int 1))
> +                     (label_ref (match_operand 0 "" ""))
> +                     (pc)))
> +              (set (reg:SI LR_REGNUM)
> +                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
> +  "TARGET_32BIT && TARGET_HAVE_LOB && !flag_modulo_sched"
> +  "le\tlr, %l0")
>
> Is it deliberate that this pattern name has a '*' prefix?  doloop_end
> is a named expansion pattern according to md.texi.

Yes, this should be expanded already by the define_expand we have in
thumb2.md.  Perhaps I'll call it 'doloop_end_internal' and add a
comment.

> Also, hard-coded register names should be prefixed with '%|' (so
> "%|lr", not just "lr"), just in case the assembler dialect requires
> something (ELF doesn't but others have).  Also for dls_insn.

Ack

> For the tests, your 'require-effective-taret' tests look insufficient
> to prevent problems when testing a multilib environment, you'll need
> (at least) checks that a) passing -marm has not happened and b) that
> the architecture, or a specific CPU isn't being passed on the command
> line.

Ack

Thanks for reviewing I'll update the patch.

Andrea

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Roman Zhuykov]

Hello!

11.02.2020 16:40, Andrea Corallo wrote:
> Hi Richard,
>
> "Richard Earnshaw (lists)" <Richard.Earnshaw@arm.com> writes:
>
>>> gcc/ChangeLog:
>>> 2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
>>> 2020-??-??  Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
>>> 2020-??-??  Iain Apreotesei  <iain.apreotesei@arm.com>
>>>          * config/arm/arm.c (TARGET_INVALID_WITHIN_DOLOOP):
>>>          (arm_invalid_within_doloop): Implement invalid_within_doloop hook.
>>>          * config/arm/arm.h (TARGET_HAVE_LOB): Add new macro.
>>>          * config/arm/thumb2.md (*doloop_end, doloop_begin, dls_insn):
>>>          Add new patterns.
>>>          * config/arm/unspecs.md: Add new unspec.
>>>
>> A date should only appear before the first author in a multi-author
>> patch, other authors should then be indented to align with the name of
>> that first author.
> Ack
This patch is stage1 material, right?
>
>> +(define_insn "*doloop_end"
>> +  [(parallel [(set (pc)
>> +                   (if_then_else
>> +                       (ne (reg:SI LR_REGNUM) (const_int 1))
>> +                     (label_ref (match_operand 0 "" ""))
>> +                     (pc)))
>> +              (set (reg:SI LR_REGNUM)
>> +                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
>> +  "TARGET_32BIT && TARGET_HAVE_LOB && !flag_modulo_sched"
>> +  "le\tlr, %l0")
I'm not an expert in .md files, but having that "!flag_modulo_sched"
condition seems wrong to me.  What was the issue on SMS side to add that?
Currently, there are fake doloop_end pattern on ARM.  It is generated
only when flag_modulo_sched is set and actually expands to more than one
instruction.  This old approach have its pros and cons.  When we
HAVE_LOB, target allows us to use a real doloop_end instruction, fake
one is not needed at all.  In this case compiler should use real
instruction regardless whether SMS in on or off.

I hope in stage1 after upgrading modulo scheduler, we will restart old
discussion about removing fake doloop_end pattern for ARM:
https://gcc.gnu.org/ml/gcc-patches/2011-07/msg01812.html
https://gcc.gnu.org/ml/gcc-patches/2012-01/msg00195.html
Aarch64 also have such a fake pattern since 2014, probably its removal
also will be considered.

Roman
>> Is it deliberate that this pattern name has a '*' prefix?  doloop_end
>> is a named expansion pattern according to md.texi.
> Yes, this should be expanded already by the define_expand we have in
> thumb2.md.  Perhaps I'll call it 'doloop_end_internal' and add a
> comment.
>
>> Also, hard-coded register names should be prefixed with '%|' (so
>> "%|lr", not just "lr"), just in case the assembler dialect requires
>> something (ELF doesn't but others have).  Also for dls_insn.
> Ack
>
>> For the tests, your 'require-effective-taret' tests look insufficient
>> to prevent problems when testing a multilib environment, you'll need
>> (at least) checks that a) passing -marm has not happened and b) that
>> the architecture, or a specific CPU isn't being passed on the command
>> line.
> Ack
>
> Thanks for reviewing I'll update the patch.
>
> Andrea

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Andrea Corallo]

Hi Roman,

Roman Zhuykov <zhroma@ispras.ru> writes:

> This patch is stage1 material, right?

Yes

>>
>>> +(define_insn "*doloop_end"
>>> +  [(parallel [(set (pc)
>>> +                   (if_then_else
>>> +                       (ne (reg:SI LR_REGNUM) (const_int 1))
>>> +                     (label_ref (match_operand 0 "" ""))
>>> +                     (pc)))
>>> +              (set (reg:SI LR_REGNUM)
>>> +                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
>>> +  "TARGET_32BIT && TARGET_HAVE_LOB && !flag_modulo_sched"
>>> +  "le\tlr, %l0")
> I'm not an expert in .md files, but having that "!flag_modulo_sched"
> condition seems wrong to me.  What was the issue on SMS side to add
> that?

With this patch the first insn of the low loop overhead 'doloop_begin'
is expanded by 'doloop_modify' in loop-doloop.c.  The same does not
happen with SMS.  My understanding is that to have it working in that
case too the machine dependent reorg pass should add it later.  Am I
correct on this?

Thanks
  Andrea

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Andrea Corallo]

[-- Attachment #1: Type: text/plain, Size: 1836 bytes --]

Hi all,

Second version of the patch here addressing comments.

This patch enables the Armv8.1-M Mainline LOB (low overhead branch) extension
low overhead loops (LOL) feature by using the 'loop-doloop' pass.

Given the following function:

void
loop (int *a)
{
  for (int i = 0; i < 1000; i++)
    a[i] = i;
}

'doloop_begin' and 'doloop_end' patterns translates into 'dls' and 'le' 
giving:

 loop:
         movw    r2, #10000
         movs    r3, #0
         subs    r0, r0, #4
         push    {lr}
         dls     lr, r2
 .L2:
         str     r3, [r0, #4]!
         adds    r3, r3, #1
         le      lr, .L2
         ldr     pc, [sp], #4

SMS is disabled in tests not to break them when SMS does loop versioning.

bootstrapped arm-none-linux-gnueabihf, do not introduce testsuite regressions.

Andrea

gcc/ChangeLog:

2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
            Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
            Iain Apreotesei  <iain.apreotesei@arm.com>

        * config/arm/arm.c (TARGET_INVALID_WITHIN_DOLOOP):
        (arm_invalid_within_doloop): Implement invalid_within_doloop hook.
        * config/arm/arm.h (TARGET_HAVE_LOB): Add new macro.
        * config/arm/thumb2.md (*doloop_end, doloop_begin, dls_insn):
        Add new patterns.
        * config/arm/unspecs.md: Add new unspec.

gcc/testsuite/ChangeLog:

2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
            Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
            Iain Apreotesei  <iain.apreotesei@arm.com>

        * gcc.target/arm/lob.h: New header.
        * gcc.target/arm/lob1.c: New testcase.
        * gcc.target/arm/lob2.c: Likewise.
        * gcc.target/arm/lob3.c: Likewise.
        * gcc.target/arm/lob4.c: Likewise.
        * gcc.target/arm/lob5.c: Likewise.
        * gcc.target/arm/lob6.c: Likewise.


[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: lol.patch --]
[-- Type: text/x-diff, Size: 13133 bytes --]

diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h
index e07cf03538c5..1269f40bd77c 100644
--- a/gcc/config/arm/arm.h
+++ b/gcc/config/arm/arm.h
@@ -586,6 +586,9 @@ extern int arm_arch_bf16;
 \f
 /* Target machine storage Layout.  */
 
+/* Nonzero if this chip provides Armv8.1-M Mainline
+   LOB (low overhead branch features) extension instructions.  */
+#define TARGET_HAVE_LOB (arm_arch8_1m_main)
 
 /* Define this macro if it is advisable to hold scalars in registers
    in a wider mode than that declared by the program.  In such cases,
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 9cc7bc0e5621..7c2a7b7e9e97 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -833,6 +833,9 @@ static const struct attribute_spec arm_attribute_table[] =
 #undef TARGET_CONSTANT_ALIGNMENT
 #define TARGET_CONSTANT_ALIGNMENT arm_constant_alignment
 
+#undef TARGET_INVALID_WITHIN_DOLOOP
+#define TARGET_INVALID_WITHIN_DOLOOP arm_invalid_within_doloop
+
 #undef TARGET_MD_ASM_ADJUST
 #define TARGET_MD_ASM_ADJUST arm_md_asm_adjust
 \f
@@ -32937,6 +32940,27 @@ arm_ge_bits_access (void)
   return true;
 }
 
+/* NULL if INSN insn is valid within a low-overhead loop.
+   Otherwise return why doloop cannot be applied.  */
+
+static const char *
+arm_invalid_within_doloop (const rtx_insn *insn)
+{
+  if (!TARGET_HAVE_LOB)
+    return default_invalid_within_doloop (insn);
+
+  if (CALL_P (insn))
+    return "Function call in the loop.";
+
+  if (tablejump_p (insn, NULL, NULL) || computed_jump_p (insn))
+    return "Computed branch in the loop.";
+
+  if (reg_mentioned_p (gen_rtx_REG (SImode, LR_REGNUM), insn))
+    return "LR is used inside loop.";
+
+  return NULL;
+}
+
 #if CHECKING_P
 namespace selftest {
 
diff --git a/gcc/config/arm/thumb2.md b/gcc/config/arm/thumb2.md
index b0d3bd1cf1c4..4aff1a0838d8 100644
--- a/gcc/config/arm/thumb2.md
+++ b/gcc/config/arm/thumb2.md
@@ -1555,8 +1555,11 @@
       using a certain 'count' register and (2) the loop count can be
       adjusted by modifying this register prior to the loop.
       ??? The possible introduction of a new block to initialize the
-      new IV can potentially affect branch optimizations.  */
-   if (optimize > 0 && flag_modulo_sched)
+      new IV can potentially affect branch optimizations.
+
+      Also used to implement the low over head loops feature, which is part of
+      the Armv8.1-M Mainline Low Overhead Branch (LOB) extension.  */
+   if (optimize > 0 && (flag_modulo_sched || TARGET_HAVE_LOB))
    {
      rtx s0;
      rtx bcomp;
@@ -1569,6 +1572,11 @@
        FAIL;
 
      s0 = operands [0];
+
+     /* Low over head loop instructions require the first operand to be LR.  */
+     if (TARGET_HAVE_LOB)
+       s0 = gen_rtx_REG (SImode, LR_REGNUM);
+
      if (TARGET_THUMB2)
        insn = emit_insn (gen_thumb2_addsi3_compare0 (s0, s0, GEN_INT (-1)));
      else
@@ -1650,3 +1658,30 @@
   "TARGET_HAVE_MVE"
   "lsrl%?\\t%Q0, %R0, %1"
   [(set_attr "predicable" "yes")])
+
+;; Originally expanded by 'doloop_end'.
+(define_insn "doloop_end_internal"
+  [(parallel [(set (pc)
+                   (if_then_else
+                       (ne (reg:SI LR_REGNUM) (const_int 1))
+                     (label_ref (match_operand 0 "" ""))
+                     (pc)))
+              (set (reg:SI LR_REGNUM)
+                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
+  "TARGET_32BIT && TARGET_HAVE_LOB"
+  "le\t%|lr, %l0")
+
+(define_expand "doloop_begin"
+  [(match_operand 0 "" "")
+   (match_operand 1 "" "")]
+  "TARGET_32BIT && TARGET_HAVE_LOB"
+  {
+    emit_insn (gen_dls_insn (operands[0]));
+    DONE;
+  })
+
+(define_insn "dls_insn"
+  [(set (reg:SI LR_REGNUM)
+        (unspec:SI [(match_operand:SI 0 "s_register_operand" "r")] UNSPEC_DLS))]
+  "TARGET_32BIT && TARGET_HAVE_LOB"
+  "dls\t%|lr, %0")
diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md
index 8f4a705f43ef..df5ecb731925 100644
--- a/gcc/config/arm/unspecs.md
+++ b/gcc/config/arm/unspecs.md
@@ -154,6 +154,7 @@
   UNSPEC_SMUADX		; Represent the SMUADX operation.
   UNSPEC_SSAT16		; Represent the SSAT16 operation.
   UNSPEC_USAT16		; Represent the USAT16 operation.
+  UNSPEC_DLS		; Used for DLS (Do Loop Start), Armv8.1-M Mainline instruction
 ])
 
 
diff --git a/gcc/testsuite/gcc.target/arm/lob.h b/gcc/testsuite/gcc.target/arm/lob.h
new file mode 100644
index 000000000000..feaae7cc8995
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob.h
@@ -0,0 +1,15 @@
+#include <string.h>
+
+/* Common code for lob tests.  */
+
+#define NO_LOB asm volatile ("@ clobber lr" : : : "lr" )
+
+#define N 10000
+
+static void
+reset_data (int *a, int *b, int *c)
+{
+  memset (a, -1, N * sizeof (*a));
+  memset (b, -1, N * sizeof (*b));
+  memset (c, -1, N * sizeof (*c));
+}
diff --git a/gcc/testsuite/gcc.target/arm/lob1.c b/gcc/testsuite/gcc.target/arm/lob1.c
new file mode 100644
index 000000000000..e4913519942f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob1.c
@@ -0,0 +1,85 @@
+/* Check that GCC generates Armv8.1-M low over head loop instructions
+   for some simple loops.  */
+/* { dg-do run } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int
+foo (int a, int b)
+{
+  return a + b;
+}
+
+void __attribute__((noinline))
+loop1 (int *a, int *b, int *c)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = a[i] + b[i];
+    }
+}
+
+void __attribute__((noinline))
+loop2 (int *a, int *b, int *c)
+{
+  int i = 0;
+  while (i < N)
+    {
+      a[i] = i - 2;
+      b[i] = i * 5;
+      c[i] = a[i] + b[i];
+      i++;
+    }
+}
+
+void __attribute__((noinline))
+loop3 (int *a, int *b, int *c)
+{
+  int i = 0;
+  do
+    {
+      a[i] = i - 4;
+      b[i] = i * 3;
+      c[i] = a[i] + b[i];
+      i++;
+    } while (i < N);
+}
+
+void
+check (int *a, int *b, int *c)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (c[i] != a[i] + b[i])
+	abort ();
+    }
+}
+
+int
+main (void)
+{
+  reset_data (a, b, c);
+  loop1 (a, b ,c);
+  check (a, b ,c);
+  reset_data (a, b, c);
+  loop2 (a, b ,c);
+  check (a, b ,c);
+  reset_data (a, b, c);
+  loop3 (a, b ,c);
+  check (a, b ,c);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times {dls\s\S*,\s\S*} 3 } } */
+/* { dg-final { scan-assembler-times {le\slr,\s\S*} 3 } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob2.c b/gcc/testsuite/gcc.target/arm/lob2.c
new file mode 100644
index 000000000000..e81286694804
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob2.c
@@ -0,0 +1,33 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if a non-inlineable function call takes place inside the loop.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int __attribute__ ((noinline))
+foo (int a, int b)
+{
+  return a + b;
+}
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = foo (a[i], b[i]);
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob3.c b/gcc/testsuite/gcc.target/arm/lob3.c
new file mode 100644
index 000000000000..69d22b2f023a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob3.c
@@ -0,0 +1,28 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if causes VFP emulation library calls to happen inside the loop.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps -mfloat-abi=soft" } */
+/* { dg-require-effective-target arm_softfloat } */
+#include <stdlib.h>
+#include "lob.h"
+
+double a[N];
+double b[N];
+double c[N];
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = a[i] + b[i];
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob4.c b/gcc/testsuite/gcc.target/arm/lob4.c
new file mode 100644
index 000000000000..62be52e31007
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob4.c
@@ -0,0 +1,35 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if LR is modified within the loop.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps -mfloat-abi=soft" } */
+/* { dg-require-effective-target arm_softfloat } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+static __attribute__ ((always_inline)) inline int
+foo (int a, int b)
+{
+  NO_LOB;
+  return a + b;
+}
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = foo(a[i], b[i]);
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob5.c b/gcc/testsuite/gcc.target/arm/lob5.c
new file mode 100644
index 000000000000..ad8a1b961e40
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob5.c
@@ -0,0 +1,36 @@
+/* Check that GCC does not generates Armv8.1-M low over head loop
+   instructions.  Innermost loop has no fixed number of iterations
+   therefore is not optimizable.  Outer loops are not optimized.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+
+      int k = b[i];
+      while (k != 0)
+	{
+	  if (k % 2 == 0)
+	    c[i - 1] = k % 2;
+	  k /= 2;
+	}
+      c[i] = a[i] - b[i];
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob6.c b/gcc/testsuite/gcc.target/arm/lob6.c
new file mode 100644
index 000000000000..1dbcaff1670d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob6.c
@@ -0,0 +1,97 @@
+/* Check that GCC generates Armv8.1-M low over head loop instructions
+   with some less trivial loops and the result is correct.  */
+/* { dg-do run } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+#define TEST_CODE1				\
+  {						\
+    for (int i = 0; i < N; i++)			\
+      {						\
+	a[i] = i;				\
+	b[i] = i * 2;				\
+						\
+	for (int k = 0; k < N; k++)		\
+	  {					\
+	    MAYBE_LOB;				\
+	    c[k] = k / 2;			\
+	  }					\
+	c[i] = a[i] - b[i];			\
+      }						\
+  }
+
+#define TEST_CODE2				\
+  {						\
+    for (int i = 0; i < N / 2; i++)		\
+      {						\
+	MAYBE_LOB;				\
+	if (c[i] % 2 == 0)			\
+	  break;				\
+	a[i]++;					\
+	b[i]++;					\
+      }						\
+  }
+
+int a1[N];
+int b1[N];
+int c1[N];
+
+int a2[N];
+int b2[N];
+int c2[N];
+
+#define MAYBE_LOB
+void __attribute__((noinline))
+loop1 (int *a, int *b, int *c)
+  TEST_CODE1;
+
+void __attribute__((noinline))
+loop2 (int *a, int *b, int *c)
+  TEST_CODE2;
+
+#undef MAYBE_LOB
+#define MAYBE_LOB NO_LOB
+
+void
+ref1 (int *a, int *b, int *c)
+  TEST_CODE1;
+
+void
+ref2 (int *a, int *b, int *c)
+  TEST_CODE2;
+
+void
+check (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (a1[i] != a2[i]
+	  && b1[i] != b2[i]
+	  && c1[i] != c2[i])
+	abort ();
+    }
+}
+
+int
+main (void)
+{
+  reset_data (a1, b1, c1);
+  reset_data (a2, b2, c2);
+  loop1 (a1, b1, c1);
+  ref1 (a2, b2, c2);
+  check ();
+
+  reset_data (a1, b1, c1);
+  reset_data (a2, b2, c2);
+  loop2 (a1, b1, c1);
+  ref2 (a2, b2, c2);
+  check ();
+
+  return 0;
+}
+/* { dg-final { scan-assembler-times {dls\s\S*,\s\S*} 2 } } */
+/* { dg-final { scan-assembler-times {le\slr,\s\S*} 2 } } */

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Kyrill Tkachov]

Hi Andrea,

On 2/19/20 1:01 PM, Andrea Corallo wrote:
> Hi all,
>
> Second version of the patch here addressing comments.
>
> This patch enables the Armv8.1-M Mainline LOB (low overhead branch) 
> extension
> low overhead loops (LOL) feature by using the 'loop-doloop' pass.
>
> Given the following function:
>
> void
> loop (int *a)
> {
>   for (int i = 0; i < 1000; i++)
>     a[i] = i;
> }
>
> 'doloop_begin' and 'doloop_end' patterns translates into 'dls' and 'le'
> giving:
>
>  loop:
>          movw    r2, #10000
>          movs    r3, #0
>          subs    r0, r0, #4
>          push    {lr}
>          dls     lr, r2
>  .L2:
>          str     r3, [r0, #4]!
>          adds    r3, r3, #1
>          le      lr, .L2
>          ldr     pc, [sp], #4
>
> SMS is disabled in tests not to break them when SMS does loop versioning.
>
> bootstrapped arm-none-linux-gnueabihf, do not introduce testsuite 
> regressions.


This should be aimed at GCC 11 at this point.

Some comments inline...


>
> Andrea
>
> gcc/ChangeLog:
>
> 2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
>             Mihail-Calin Ionescu <mihail.ionescu@arm.com>
>             Iain Apreotesei  <iain.apreotesei@arm.com>
>
>         * config/arm/arm.c (TARGET_INVALID_WITHIN_DOLOOP):
>         (arm_invalid_within_doloop): Implement invalid_within_doloop hook.
>         * config/arm/arm.h (TARGET_HAVE_LOB): Add new macro.
>         * config/arm/thumb2.md (*doloop_end, doloop_begin, dls_insn):
>         Add new patterns.
>         * config/arm/unspecs.md: Add new unspec.
>
> gcc/testsuite/ChangeLog:
>
> 2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
>             Mihail-Calin Ionescu <mihail.ionescu@arm.com>
>             Iain Apreotesei  <iain.apreotesei@arm.com>
>
>         * gcc.target/arm/lob.h: New header.
>         * gcc.target/arm/lob1.c: New testcase.
>         * gcc.target/arm/lob2.c: Likewise.
>         * gcc.target/arm/lob3.c: Likewise.
>         * gcc.target/arm/lob4.c: Likewise.
>         * gcc.target/arm/lob5.c: Likewise.
>         * gcc.target/arm/lob6.c: Likewise.
>

lol.patch

diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h
index e07cf03538c5..1269f40bd77c 100644
--- a/gcc/config/arm/arm.h
+++ b/gcc/config/arm/arm.h
@@ -586,6 +586,9 @@ extern int arm_arch_bf16;
  
  /* Target machine storage Layout.  */
  
+/* Nonzero if this chip provides Armv8.1-M Mainline
+   LOB (low overhead branch features) extension instructions.  */
+#define TARGET_HAVE_LOB (arm_arch8_1m_main)
  
  /* Define this macro if it is advisable to hold scalars in registers
     in a wider mode than that declared by the program.  In such cases,
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 9cc7bc0e5621..7c2a7b7e9e97 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -833,6 +833,9 @@ static const struct attribute_spec arm_attribute_table[] =
  #undef TARGET_CONSTANT_ALIGNMENT
  #define TARGET_CONSTANT_ALIGNMENT arm_constant_alignment
  
+#undef TARGET_INVALID_WITHIN_DOLOOP
+#define TARGET_INVALID_WITHIN_DOLOOP arm_invalid_within_doloop
+
  #undef TARGET_MD_ASM_ADJUST
  #define TARGET_MD_ASM_ADJUST arm_md_asm_adjust
  
@@ -32937,6 +32940,27 @@ arm_ge_bits_access (void)
    return true;
  }
  
+/* NULL if INSN insn is valid within a low-overhead loop.
+   Otherwise return why doloop cannot be applied.  */
+
+static const char *
+arm_invalid_within_doloop (const rtx_insn *insn)
+{
+  if (!TARGET_HAVE_LOB)
+    return default_invalid_within_doloop (insn);
+
+  if (CALL_P (insn))
+    return "Function call in the loop.";
+
+  if (tablejump_p (insn, NULL, NULL) || computed_jump_p (insn))
+    return "Computed branch in the loop.";
+
+  if (reg_mentioned_p (gen_rtx_REG (SImode, LR_REGNUM), insn))
+    return "LR is used inside loop.";
+
+  return NULL;
+}
+
  #if CHECKING_P
  namespace selftest {
  
diff --git a/gcc/config/arm/thumb2.md b/gcc/config/arm/thumb2.md
index b0d3bd1cf1c4..4aff1a0838d8 100644
--- a/gcc/config/arm/thumb2.md
+++ b/gcc/config/arm/thumb2.md
@@ -1555,8 +1555,11 @@
        using a certain 'count' register and (2) the loop count can be
        adjusted by modifying this register prior to the loop.
        ??? The possible introduction of a new block to initialize the
-      new IV can potentially affect branch optimizations.  */
-   if (optimize > 0 && flag_modulo_sched)
+      new IV can potentially affect branch optimizations.
+
+      Also used to implement the low over head loops feature, which is part of
+      the Armv8.1-M Mainline Low Overhead Branch (LOB) extension.  */
+   if (optimize > 0 && (flag_modulo_sched || TARGET_HAVE_LOB))
     {
       rtx s0;
       rtx bcomp;
@@ -1569,6 +1572,11 @@
         FAIL;
  
       s0 = operands [0];
+
+     /* Low over head loop instructions require the first operand to be LR.  */
+     if (TARGET_HAVE_LOB)
+       s0 = gen_rtx_REG (SImode, LR_REGNUM);
+
       if (TARGET_THUMB2)
         insn = emit_insn (gen_thumb2_addsi3_compare0 (s0, s0, GEN_INT (-1)));
       else
@@ -1650,3 +1658,30 @@
    "TARGET_HAVE_MVE"
    "lsrl%?\\t%Q0, %R0, %1"
    [(set_attr "predicable" "yes")])
+
+;; Originally expanded by 'doloop_end'.
+(define_insn "doloop_end_internal"

We usually prefer to name these patterns with a '*' in front to prevent the gen* machinery from generating gen_* unneeded expanders for them if they're not used.


+  [(parallel [(set (pc)
+                   (if_then_else
+                       (ne (reg:SI LR_REGNUM) (const_int 1))
+                     (label_ref (match_operand 0 "" ""))
+                     (pc)))
+              (set (reg:SI LR_REGNUM)
+                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
+  "TARGET_32BIT && TARGET_HAVE_LOB"
+  "le\t%|lr, %l0")
+
+(define_expand "doloop_begin"
+  [(match_operand 0 "" "")
+   (match_operand 1 "" "")]
+  "TARGET_32BIT && TARGET_HAVE_LOB"
+  {
+    emit_insn (gen_dls_insn (operands[0]));
+    DONE;
+  })
+
+(define_insn "dls_insn"
+  [(set (reg:SI LR_REGNUM)
+        (unspec:SI [(match_operand:SI 0 "s_register_operand" "r")] UNSPEC_DLS))]
+  "TARGET_32BIT && TARGET_HAVE_LOB"
+  "dls\t%|lr, %0")
diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md
index 8f4a705f43ef..df5ecb731925 100644
--- a/gcc/config/arm/unspecs.md
+++ b/gcc/config/arm/unspecs.md
@@ -154,6 +154,7 @@
    UNSPEC_SMUADX		; Represent the SMUADX operation.
    UNSPEC_SSAT16		; Represent the SSAT16 operation.
    UNSPEC_USAT16		; Represent the USAT16 operation.
+  UNSPEC_DLS		; Used for DLS (Do Loop Start), Armv8.1-M Mainline instruction
  ])
  
  
diff --git a/gcc/testsuite/gcc.target/arm/lob.h b/gcc/testsuite/gcc.target/arm/lob.h
new file mode 100644
index 000000000000..feaae7cc8995
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob.h
@@ -0,0 +1,15 @@
+#include <string.h>
+
+/* Common code for lob tests.  */
+
+#define NO_LOB asm volatile ("@ clobber lr" : : : "lr" )
+
+#define N 10000
+
+static void
+reset_data (int *a, int *b, int *c)
+{
+  memset (a, -1, N * sizeof (*a));
+  memset (b, -1, N * sizeof (*b));
+  memset (c, -1, N * sizeof (*c));
+}
diff --git a/gcc/testsuite/gcc.target/arm/lob1.c b/gcc/testsuite/gcc.target/arm/lob1.c
new file mode 100644
index 000000000000..e4913519942f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob1.c
@@ -0,0 +1,85 @@
+/* Check that GCC generates Armv8.1-M low over head loop instructions
+   for some simple loops.  */
+/* { dg-do run } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */


We need to avoid running this test on targets that don't support LOB. This needs an appropriate effective target check (see the existing *_hw ones in lib/target-supports.exp)

Thanks,
Kyrill

+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int
+foo (int a, int b)
+{
+  return a + b;
+}
+
+void __attribute__((noinline))
+loop1 (int *a, int *b, int *c)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = a[i] + b[i];
+    }
+}
+
+void __attribute__((noinline))
+loop2 (int *a, int *b, int *c)
+{
+  int i = 0;
+  while (i < N)
+    {
+      a[i] = i - 2;
+      b[i] = i * 5;
+      c[i] = a[i] + b[i];
+      i++;
+    }
+}
+
+void __attribute__((noinline))
+loop3 (int *a, int *b, int *c)
+{
+  int i = 0;
+  do
+    {
+      a[i] = i - 4;
+      b[i] = i * 3;
+      c[i] = a[i] + b[i];
+      i++;
+    } while (i < N);
+}
+
+void
+check (int *a, int *b, int *c)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (c[i] != a[i] + b[i])
+	abort ();
+    }
+}
+
+int
+main (void)
+{
+  reset_data (a, b, c);
+  loop1 (a, b ,c);
+  check (a, b ,c);
+  reset_data (a, b, c);
+  loop2 (a, b ,c);
+  check (a, b ,c);
+  reset_data (a, b, c);
+  loop3 (a, b ,c);
+  check (a, b ,c);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times {dls\s\S*,\s\S*} 3 } } */
+/* { dg-final { scan-assembler-times {le\slr,\s\S*} 3 } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob2.c b/gcc/testsuite/gcc.target/arm/lob2.c
new file mode 100644
index 000000000000..e81286694804
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob2.c
@@ -0,0 +1,33 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if a non-inlineable function call takes place inside the loop.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int __attribute__ ((noinline))
+foo (int a, int b)
+{
+  return a + b;
+}
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = foo (a[i], b[i]);
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob3.c b/gcc/testsuite/gcc.target/arm/lob3.c
new file mode 100644
index 000000000000..69d22b2f023a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob3.c
@@ -0,0 +1,28 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if causes VFP emulation library calls to happen inside the loop.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps -mfloat-abi=soft" } */
+/* { dg-require-effective-target arm_softfloat } */
+#include <stdlib.h>
+#include "lob.h"
+
+double a[N];
+double b[N];
+double c[N];
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = a[i] + b[i];
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob4.c b/gcc/testsuite/gcc.target/arm/lob4.c
new file mode 100644
index 000000000000..62be52e31007
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob4.c
@@ -0,0 +1,35 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if LR is modified within the loop.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps -mfloat-abi=soft" } */
+/* { dg-require-effective-target arm_softfloat } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+static __attribute__ ((always_inline)) inline int
+foo (int a, int b)
+{
+  NO_LOB;
+  return a + b;
+}
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = foo(a[i], b[i]);
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob5.c b/gcc/testsuite/gcc.target/arm/lob5.c
new file mode 100644
index 000000000000..ad8a1b961e40
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob5.c
@@ -0,0 +1,36 @@
+/* Check that GCC does not generates Armv8.1-M low over head loop
+   instructions.  Innermost loop has no fixed number of iterations
+   therefore is not optimizable.  Outer loops are not optimized.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+
+      int k = b[i];
+      while (k != 0)
+	{
+	  if (k % 2 == 0)
+	    c[i - 1] = k % 2;
+	  k /= 2;
+	}
+      c[i] = a[i] - b[i];
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob6.c b/gcc/testsuite/gcc.target/arm/lob6.c
new file mode 100644
index 000000000000..1dbcaff1670d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob6.c
@@ -0,0 +1,97 @@
+/* Check that GCC generates Armv8.1-M low over head loop instructions
+   with some less trivial loops and the result is correct.  */
+/* { dg-do run } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-skip-if "do not run SMS to prevent loop versioning" { *-*-* } { "-fmodulo-sched" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+#define TEST_CODE1				\
+  {						\
+    for (int i = 0; i < N; i++)			\
+      {						\
+	a[i] = i;				\
+	b[i] = i * 2;				\
+						\
+	for (int k = 0; k < N; k++)		\
+	  {					\
+	    MAYBE_LOB;				\
+	    c[k] = k / 2;			\
+	  }					\
+	c[i] = a[i] - b[i];			\
+      }						\
+  }
+
+#define TEST_CODE2				\
+  {						\
+    for (int i = 0; i < N / 2; i++)		\
+      {						\
+	MAYBE_LOB;				\
+	if (c[i] % 2 == 0)			\
+	  break;				\
+	a[i]++;					\
+	b[i]++;					\
+      }						\
+  }
+
+int a1[N];
+int b1[N];
+int c1[N];
+
+int a2[N];
+int b2[N];
+int c2[N];
+
+#define MAYBE_LOB
+void __attribute__((noinline))
+loop1 (int *a, int *b, int *c)
+  TEST_CODE1;
+
+void __attribute__((noinline))
+loop2 (int *a, int *b, int *c)
+  TEST_CODE2;
+
+#undef MAYBE_LOB
+#define MAYBE_LOB NO_LOB
+
+void
+ref1 (int *a, int *b, int *c)
+  TEST_CODE1;
+
+void
+ref2 (int *a, int *b, int *c)
+  TEST_CODE2;
+
+void
+check (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (a1[i] != a2[i]
+	  && b1[i] != b2[i]
+	  && c1[i] != c2[i])
+	abort ();
+    }
+}
+
+int
+main (void)
+{
+  reset_data (a1, b1, c1);
+  reset_data (a2, b2, c2);
+  loop1 (a1, b1, c1);
+  ref1 (a2, b2, c2);
+  check ();
+
+  reset_data (a1, b1, c1);
+  reset_data (a2, b2, c2);
+  loop2 (a1, b1, c1);
+  ref2 (a2, b2, c2);
+  check ();
+
+  return 0;
+}
+/* { dg-final { scan-assembler-times {dls\s\S*,\s\S*} 2 } } */
+/* { dg-final { scan-assembler-times {le\slr,\s\S*} 2 } } */

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Roman Zhuykov]

Andrea Corallo writes:

> With this patch the first insn of the low loop overhead 'doloop_begin'
> is expanded by 'doloop_modify' in loop-doloop.c.  The same does not
> happen with SMS.

That certainly works correct as in your first patch, doloop_begin
pattern also have "!flag_modulo_sched" condition.

> My understanding is that to have it working in that
> case too the machine dependent reorg pass should add it later.  Am I
> correct on this?

IMHO, this is not needed is your case.  Currently, list of platforms
(actually, gcc/config subfolders) which have doloop_end is rather big:
aarch64*, arc, arm*, bfin, c6x, ia64, pdp11, pru, rs6000, s390, sh,
tilegx*, tilepro, v850 and xtensa.  I marked three of them with a star -
they actually have a fake pattern, which is applied only with SMS. 
Reorg_loops from hw-doloop.c (see also
https://gcc.gnu.org/ml/gcc-patches/2011-06/msg01593.html and
https://gcc.gnu.org/ml/gcc-patches/2011-07/msg00133.html) is used only
in arc, bfin, c6x, and xtensa.  Certainly some other platforms may have
additional loop reorg steps in target-specific part (e.q. pru), but not
all of them.  And that reorg is actually needed independently, whether
SMS is on or off.

Actually, the question was: what goes wrong if you remove that
"!flag_modulo_sched" condition from three new patterns?  I had actually
made one step forward, removed that "!flag_modulo_sched" parts in your
patch, and made the following simplest testing for such modified patch. 
I've build and then compared regtest results of two ARM cross-compilers:
first was built from clean trunk, second with patch.  Both compilers
were configured -with-march=armv8.1-m.main and had modified common.opt
to enable -fmodulo-sched and -fmodulo-sched-allow-regmoves by default. 
Regtest results are identical.
> Second version of the patch here addressing comments.

Thank you, now I see in second patch that aspect was solved.

> SMS is disabled in tests not to break them when SMS does loop versioning.

And I'm not really sure about this.  First of all, there are a lot of
scan-assembler-times tests which fail when modulo-scheduler is enabled,
probably the same happens when some unrolling parameters are not
default.  It seems that any non-default optimization which creates more
instruction copies can break scan-assembler-times check.  IMHO, it is
not necessary to workaround this in few particular tests.  Second, I'm
not sure how dg-skip-if directive works.  When one enables SMS setting
"Init(1)" directly into common.opt this won't be catched, would it?

Roman

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Roman Zhuykov]

11.02.2020 14:00, Richard Earnshaw (lists) wrote:
> +(define_insn "*doloop_end"
> +  [(parallel [(set (pc)
> +                   (if_then_else
> +                       (ne (reg:SI LR_REGNUM) (const_int 1))
> +                     (label_ref (match_operand 0 "" ""))
> +                     (pc)))
> +              (set (reg:SI LR_REGNUM)
> +                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
> +  "TARGET_32BIT && TARGET_HAVE_LOB && !flag_modulo_sched"
> +  "le\tlr, %l0")
>
> Is it deliberate that this pattern name has a '*' prefix?  doloop_end
> is a named expansion pattern according to md.texi.
>
> R.

21.02.2020 18:30, Kyrill Tkachov wrote:
> +;; Originally expanded by 'doloop_end'.
> +(define_insn "doloop_end_internal"
>
> We usually prefer to name these patterns with a '*' in front to
> prevent the gen* machinery from generating gen_* unneeded expanders
> for them if they're not used.
>

It seems you and Richard asking Andrea to do the opposite things.
:) LOL.patch

Roman

PS. I don't have an idea what approach is correct.

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Kyrill Tkachov]

Hi Roman,

On 2/21/20 3:49 PM, Roman Zhuykov wrote:
> 11.02.2020 14:00, Richard Earnshaw (lists) wrote:
>> +(define_insn "*doloop_end"
>> +  [(parallel [(set (pc)
>> +                   (if_then_else
>> +                       (ne (reg:SI LR_REGNUM) (const_int 1))
>> +                     (label_ref (match_operand 0 "" ""))
>> +                     (pc)))
>> +              (set (reg:SI LR_REGNUM)
>> +                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
>> +  "TARGET_32BIT && TARGET_HAVE_LOB && !flag_modulo_sched"
>> +  "le\tlr, %l0")
>>
>> Is it deliberate that this pattern name has a '*' prefix?  doloop_end
>> is a named expansion pattern according to md.texi.
>>
>> R.
> 21.02.2020 18:30, Kyrill Tkachov wrote:
>> +;; Originally expanded by 'doloop_end'.
>> +(define_insn "doloop_end_internal"
>>
>> We usually prefer to name these patterns with a '*' in front to
>> prevent the gen* machinery from generating gen_* unneeded expanders
>> for them if they're not used.
>>
> It seems you and Richard asking Andrea to do the opposite things.
> :) LOL.patch


Almost, but not exactly incompatible things ;)

doloop_end is a standard name and if we wanted to use it directly it 
cannot have a '*', which Richard is right to point out.

Once "doloop_end" is moved to its own expander and the define_insn is 
doloop_end_internal, there is no reason for it to not have a '*' as its 
gen_* form is never called.

Thanks,

Kyrill


> Roman
>
> PS. I don't have an idea what approach is correct.

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Andrea Corallo]

Hi Roman,

Roman Zhuykov <zhroma@ispras.ru> writes:

>> SMS is disabled in tests not to break them when SMS does loop versioning.
>
> And I'm not really sure about this.  First of all, there are a lot of
> scan-assembler-times tests which fail when modulo-scheduler is enabled,
> probably the same happens when some unrolling parameters are not
> default.  It seems that any non-default optimization which creates more
> instruction copies can break scan-assembler-times check.  IMHO, it is
> not necessary to workaround this in few particular tests.  Second, I'm
> not sure how dg-skip-if directive works.  When one enables SMS setting
> "Init(1)" directly into common.opt this won't be catched, would it?

Agree on everything.  Also enabling SMS from common.opt apparently makes
dg-skip-if not effective.

Thanks for commenting I'm updating the patch.

  Andrea

Re: [PATCH] [arm] Implement Armv8.1-M low overhead loops

[Andrea Corallo]

[-- Attachment #1: Type: text/plain, Size: 1941 bytes --]

Hi all,

Third version of the patch here addressing comments.

This patch enables the Armv8.1-M Mainline LOB (low overhead branch) extension
low overhead loops (LOL) feature by using the 'loop-doloop' pass.

Given the following function:

void
loop (int *a)
{
  for (int i = 0; i < 1000; i++)
    a[i] = i;
}

'doloop_begin' and 'doloop_end' patterns translates into 'dls' and 'le'
giving:

 loop:
         movw    r2, #10000
         movs    r3, #0
         subs    r0, r0, #4
         push    {lr}
         dls     lr, r2
 .L2:
         str     r3, [r0, #4]!
         adds    r3, r3, #1
         le      lr, .L2
         ldr     pc, [sp], #4

bootstrapped arm-none-linux-gnueabihf, do not introduce testsuite regressions.

Andrea

gcc/ChangeLog:

2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
            Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
            Iain Apreotesei  <iain.apreotesei@arm.com>

        * config/arm/arm.c (TARGET_INVALID_WITHIN_DOLOOP):
        (arm_invalid_within_doloop): Implement invalid_within_doloop hook.
        * config/arm/arm.h (TARGET_HAVE_LOB): Add new macro.
        * config/arm/thumb2.md (*doloop_end, doloop_begin, dls_insn):
        Add new patterns.
        * config/arm/unspecs.md: Add new unspec.
        * doc/sourcebuild.texi (arm_v8_1_lob_ok): Document new target
	supports option.

gcc/testsuite/ChangeLog:

2020-??-??  Andrea Corallo  <andrea.corallo@arm.com>
            Mihail-Calin Ionescu  <mihail.ionescu@arm.com>
            Iain Apreotesei  <iain.apreotesei@arm.com>

        * gcc.target/arm/lob.h: New header.
        * gcc.target/arm/lob1.c: New testcase.
        * gcc.target/arm/lob2.c: Likewise.
        * gcc.target/arm/lob3.c: Likewise.
        * gcc.target/arm/lob4.c: Likewise.
        * gcc.target/arm/lob5.c: Likewise.
        * gcc.target/arm/lob6.c: Likewise.
        * lib/target-supports.exp (check_effective_target_arm_v8_1_lob_ok):
        New proc.


[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: lol.patch --]
[-- Type: text/x-diff, Size: 14270 bytes --]

diff --git a/gcc/config/arm/arm.h b/gcc/config/arm/arm.h
index e07cf03538c5..1269f40bd77c 100644
--- a/gcc/config/arm/arm.h
+++ b/gcc/config/arm/arm.h
@@ -586,6 +586,9 @@ extern int arm_arch_bf16;
 \f
 /* Target machine storage Layout.  */
 
+/* Nonzero if this chip provides Armv8.1-M Mainline
+   LOB (low overhead branch features) extension instructions.  */
+#define TARGET_HAVE_LOB (arm_arch8_1m_main)
 
 /* Define this macro if it is advisable to hold scalars in registers
    in a wider mode than that declared by the program.  In such cases,
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index 9cc7bc0e5621..7c2a7b7e9e97 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -833,6 +833,9 @@ static const struct attribute_spec arm_attribute_table[] =
 #undef TARGET_CONSTANT_ALIGNMENT
 #define TARGET_CONSTANT_ALIGNMENT arm_constant_alignment
 
+#undef TARGET_INVALID_WITHIN_DOLOOP
+#define TARGET_INVALID_WITHIN_DOLOOP arm_invalid_within_doloop
+
 #undef TARGET_MD_ASM_ADJUST
 #define TARGET_MD_ASM_ADJUST arm_md_asm_adjust
 \f
@@ -32937,6 +32940,27 @@ arm_ge_bits_access (void)
   return true;
 }
 
+/* NULL if INSN insn is valid within a low-overhead loop.
+   Otherwise return why doloop cannot be applied.  */
+
+static const char *
+arm_invalid_within_doloop (const rtx_insn *insn)
+{
+  if (!TARGET_HAVE_LOB)
+    return default_invalid_within_doloop (insn);
+
+  if (CALL_P (insn))
+    return "Function call in the loop.";
+
+  if (tablejump_p (insn, NULL, NULL) || computed_jump_p (insn))
+    return "Computed branch in the loop.";
+
+  if (reg_mentioned_p (gen_rtx_REG (SImode, LR_REGNUM), insn))
+    return "LR is used inside loop.";
+
+  return NULL;
+}
+
 #if CHECKING_P
 namespace selftest {
 
diff --git a/gcc/config/arm/thumb2.md b/gcc/config/arm/thumb2.md
index b0d3bd1cf1c4..fab993a8079f 100644
--- a/gcc/config/arm/thumb2.md
+++ b/gcc/config/arm/thumb2.md
@@ -1555,8 +1555,11 @@
       using a certain 'count' register and (2) the loop count can be
       adjusted by modifying this register prior to the loop.
       ??? The possible introduction of a new block to initialize the
-      new IV can potentially affect branch optimizations.  */
-   if (optimize > 0 && flag_modulo_sched)
+      new IV can potentially affect branch optimizations.
+
+      Also used to implement the low over head loops feature, which is part of
+      the Armv8.1-M Mainline Low Overhead Branch (LOB) extension.  */
+   if (optimize > 0 && (flag_modulo_sched || TARGET_HAVE_LOB))
    {
      rtx s0;
      rtx bcomp;
@@ -1569,6 +1572,11 @@
        FAIL;
 
      s0 = operands [0];
+
+     /* Low over head loop instructions require the first operand to be LR.  */
+     if (TARGET_HAVE_LOB)
+       s0 = gen_rtx_REG (SImode, LR_REGNUM);
+
      if (TARGET_THUMB2)
        insn = emit_insn (gen_thumb2_addsi3_compare0 (s0, s0, GEN_INT (-1)));
      else
@@ -1650,3 +1658,30 @@
   "TARGET_HAVE_MVE"
   "lsrl%?\\t%Q0, %R0, %1"
   [(set_attr "predicable" "yes")])
+
+;; Originally expanded by 'doloop_end'.
+(define_insn "*doloop_end_internal"
+  [(parallel [(set (pc)
+                   (if_then_else
+                       (ne (reg:SI LR_REGNUM) (const_int 1))
+                     (label_ref (match_operand 0 "" ""))
+                     (pc)))
+              (set (reg:SI LR_REGNUM)
+                   (plus:SI (reg:SI LR_REGNUM) (const_int -1)))])]
+  "TARGET_32BIT && TARGET_HAVE_LOB"
+  "le\t%|lr, %l0")
+
+(define_expand "doloop_begin"
+  [(match_operand 0 "" "")
+   (match_operand 1 "" "")]
+  "TARGET_32BIT && TARGET_HAVE_LOB"
+  {
+    emit_insn (gen_dls_insn (operands[0]));
+    DONE;
+  })
+
+(define_insn "dls_insn"
+  [(set (reg:SI LR_REGNUM)
+        (unspec:SI [(match_operand:SI 0 "s_register_operand" "r")] UNSPEC_DLS))]
+  "TARGET_32BIT && TARGET_HAVE_LOB"
+  "dls\t%|lr, %0")
diff --git a/gcc/config/arm/unspecs.md b/gcc/config/arm/unspecs.md
index 8f4a705f43ef..df5ecb731925 100644
--- a/gcc/config/arm/unspecs.md
+++ b/gcc/config/arm/unspecs.md
@@ -154,6 +154,7 @@
   UNSPEC_SMUADX		; Represent the SMUADX operation.
   UNSPEC_SSAT16		; Represent the SSAT16 operation.
   UNSPEC_USAT16		; Represent the USAT16 operation.
+  UNSPEC_DLS		; Used for DLS (Do Loop Start), Armv8.1-M Mainline instruction
 ])
 
 
diff --git a/gcc/doc/sourcebuild.texi b/gcc/doc/sourcebuild.texi
index 1f412ded2bb7..5b9e0399ebc1 100644
--- a/gcc/doc/sourcebuild.texi
+++ b/gcc/doc/sourcebuild.texi
@@ -1945,6 +1945,12 @@ ARM Target supports options suitable for accessing the Q-bit manipulation
 intrinsics from @code{arm_acle.h}.
 Some multilibs may be incompatible with these options.
 
+@item arm_v8_1_lob_ok
+@anchor{arm_v8_1_lob_ok}
+ARM Target supports executing the Armv8.1-M Mainline Low Overhead Loop
+instructions @code{DLS} and @code{LE}.
+Some multilibs may be incompatible with these options.
+
 @end table
 
 @subsubsection AArch64-specific attributes
diff --git a/gcc/testsuite/gcc.target/arm/lob.h b/gcc/testsuite/gcc.target/arm/lob.h
new file mode 100644
index 000000000000..feaae7cc8995
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob.h
@@ -0,0 +1,15 @@
+#include <string.h>
+
+/* Common code for lob tests.  */
+
+#define NO_LOB asm volatile ("@ clobber lr" : : : "lr" )
+
+#define N 10000
+
+static void
+reset_data (int *a, int *b, int *c)
+{
+  memset (a, -1, N * sizeof (*a));
+  memset (b, -1, N * sizeof (*b));
+  memset (c, -1, N * sizeof (*c));
+}
diff --git a/gcc/testsuite/gcc.target/arm/lob1.c b/gcc/testsuite/gcc.target/arm/lob1.c
new file mode 100644
index 000000000000..b92dc551d50b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob1.c
@@ -0,0 +1,85 @@
+/* Check that GCC generates Armv8.1-M low over head loop instructions
+   for some simple loops.  */
+/* { dg-do run } */
+/* { dg-require-effective-target arm_v8_1_lob_ok } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int
+foo (int a, int b)
+{
+  return a + b;
+}
+
+void __attribute__((noinline))
+loop1 (int *a, int *b, int *c)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = a[i] + b[i];
+    }
+}
+
+void __attribute__((noinline))
+loop2 (int *a, int *b, int *c)
+{
+  int i = 0;
+  while (i < N)
+    {
+      a[i] = i - 2;
+      b[i] = i * 5;
+      c[i] = a[i] + b[i];
+      i++;
+    }
+}
+
+void __attribute__((noinline))
+loop3 (int *a, int *b, int *c)
+{
+  int i = 0;
+  do
+    {
+      a[i] = i - 4;
+      b[i] = i * 3;
+      c[i] = a[i] + b[i];
+      i++;
+    } while (i < N);
+}
+
+void
+check (int *a, int *b, int *c)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (c[i] != a[i] + b[i])
+	abort ();
+    }
+}
+
+int
+main (void)
+{
+  reset_data (a, b, c);
+  loop1 (a, b ,c);
+  check (a, b ,c);
+  reset_data (a, b, c);
+  loop2 (a, b ,c);
+  check (a, b ,c);
+  reset_data (a, b, c);
+  loop3 (a, b ,c);
+  check (a, b ,c);
+
+  return 0;
+}
+
+/* { dg-final { scan-assembler-times {dls\s\S*,\s\S*} 3 } } */
+/* { dg-final { scan-assembler-times {le\slr,\s\S*} 3 } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob2.c b/gcc/testsuite/gcc.target/arm/lob2.c
new file mode 100644
index 000000000000..1fe9a9d82bb9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob2.c
@@ -0,0 +1,32 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if a non-inlineable function call takes place inside the loop.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int __attribute__ ((noinline))
+foo (int a, int b)
+{
+  return a + b;
+}
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = foo (a[i], b[i]);
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob3.c b/gcc/testsuite/gcc.target/arm/lob3.c
new file mode 100644
index 000000000000..17cba007ccb6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob3.c
@@ -0,0 +1,27 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if causes VFP emulation library calls to happen inside the loop.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps -mfloat-abi=soft" } */
+/* { dg-require-effective-target arm_softfloat } */
+#include <stdlib.h>
+#include "lob.h"
+
+double a[N];
+double b[N];
+double c[N];
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = a[i] + b[i];
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob4.c b/gcc/testsuite/gcc.target/arm/lob4.c
new file mode 100644
index 000000000000..444a2c7b4bfd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob4.c
@@ -0,0 +1,34 @@
+/* Check that GCC does not generate Armv8.1-M low over head loop instructions
+   if LR is modified within the loop.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps -mfloat-abi=soft" } */
+/* { dg-require-effective-target arm_softfloat } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+static __attribute__ ((always_inline)) inline int
+foo (int a, int b)
+{
+  NO_LOB;
+  return a + b;
+}
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+      c[i] = foo(a[i], b[i]);
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob5.c b/gcc/testsuite/gcc.target/arm/lob5.c
new file mode 100644
index 000000000000..c4f46e41532b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob5.c
@@ -0,0 +1,35 @@
+/* Check that GCC does not generates Armv8.1-M low over head loop
+   instructions.  Innermost loop has no fixed number of iterations
+   therefore is not optimizable.  Outer loops are not optimized.  */
+/* { dg-do compile } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+int a[N];
+int b[N];
+int c[N];
+
+int
+main (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      a[i] = i;
+      b[i] = i * 2;
+
+      int k = b[i];
+      while (k != 0)
+	{
+	  if (k % 2 == 0)
+	    c[i - 1] = k % 2;
+	  k /= 2;
+	}
+      c[i] = a[i] - b[i];
+    }
+
+  return 0;
+}
+/* { dg-final { scan-assembler-not {dls\s\S*,\s\S*} } } */
+/* { dg-final { scan-assembler-not {le\slr,\s\S*} } } */
diff --git a/gcc/testsuite/gcc.target/arm/lob6.c b/gcc/testsuite/gcc.target/arm/lob6.c
new file mode 100644
index 000000000000..95db2f47efe9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/lob6.c
@@ -0,0 +1,97 @@
+/* Check that GCC generates Armv8.1-M low over head loop instructions
+   with some less trivial loops and the result is correct.  */
+/* { dg-do run } */
+/* { dg-require-effective-target arm_v8_1_lob_ok } */
+/* { dg-skip-if "avoid conflicting multilib options" { *-*-* } { "-marm" "-mcpu=*" } } */
+/* { dg-options "-march=armv8.1-m.main -O3 --save-temps" } */
+#include <stdlib.h>
+#include "lob.h"
+
+#define TEST_CODE1				\
+  {						\
+    for (int i = 0; i < N; i++)			\
+      {						\
+	a[i] = i;				\
+	b[i] = i * 2;				\
+						\
+	for (int k = 0; k < N; k++)		\
+	  {					\
+	    MAYBE_LOB;				\
+	    c[k] = k / 2;			\
+	  }					\
+	c[i] = a[i] - b[i];			\
+      }						\
+  }
+
+#define TEST_CODE2				\
+  {						\
+    for (int i = 0; i < N / 2; i++)		\
+      {						\
+	MAYBE_LOB;				\
+	if (c[i] % 2 == 0)			\
+	  break;				\
+	a[i]++;					\
+	b[i]++;					\
+      }						\
+  }
+
+int a1[N];
+int b1[N];
+int c1[N];
+
+int a2[N];
+int b2[N];
+int c2[N];
+
+#define MAYBE_LOB
+void __attribute__((noinline))
+loop1 (int *a, int *b, int *c)
+  TEST_CODE1;
+
+void __attribute__((noinline))
+loop2 (int *a, int *b, int *c)
+  TEST_CODE2;
+
+#undef MAYBE_LOB
+#define MAYBE_LOB NO_LOB
+
+void
+ref1 (int *a, int *b, int *c)
+  TEST_CODE1;
+
+void
+ref2 (int *a, int *b, int *c)
+  TEST_CODE2;
+
+void
+check (void)
+{
+  for (int i = 0; i < N; i++)
+    {
+      NO_LOB;
+      if (a1[i] != a2[i]
+	  && b1[i] != b2[i]
+	  && c1[i] != c2[i])
+	abort ();
+    }
+}
+
+int
+main (void)
+{
+  reset_data (a1, b1, c1);
+  reset_data (a2, b2, c2);
+  loop1 (a1, b1, c1);
+  ref1 (a2, b2, c2);
+  check ();
+
+  reset_data (a1, b1, c1);
+  reset_data (a2, b2, c2);
+  loop2 (a1, b1, c1);
+  ref2 (a2, b2, c2);
+  check ();
+
+  return 0;
+}
+/* { dg-final { scan-assembler-times {dls\s\S*,\s\S*} 2 } } */
+/* { dg-final { scan-assembler-times {le\slr,\s\S*} 2 } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index d3b2798df3e8..51669aac1327 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -9807,6 +9807,28 @@ proc check_effective_target_arm_v8_3a_bkey_directive { } {
 	}]
 }
 
+# Return 1 if the target supports executing the Armv8.1-M Mainline Low
+# Overhead Loop, 0 otherwise.  The test is valid for ARM.
+
+proc check_effective_target_arm_v8_1_lob_ok { } {
+    if { ![istarget arm*-*-*] } {
+        return 0;
+    } else {
+	return [check_runtime arm_v8_1_lob_hw_available {
+		int
+		main (void)
+	        { int i = 0;
+		  asm  ("movw r3, #10\n\t" /* movs? */
+			"dls lr, r3" : : : "r3", "lr");
+		 loop:
+		  i++;
+		  asm goto ("le lr, %l0" : : : "lr" : loop);
+		  return i != 10;
+		}
+	} "-march=armv8.1-m.main" ]
+    }
+}
+
 # Returns 1 if the target is using glibc, 0 otherwise.
 
 proc check_effective_target_glibc { } {