diff mbox series

middle-end: inspect all exits for additional annotations for loop.

Message ID patch-18267-tamar@arm.com
State New
Headers show
Series middle-end: inspect all exits for additional annotations for loop. | expand

Commit Message

Tamar Christina Feb. 14, 2024, 1:09 p.m. UTC 
Hi All,

Attaching a pragma to a loop which has a complex condition often gets the pragma
dropped. e.g.

#pragma GCC novector
  while (i < N && parse_tables_n--)

before lowering this is represented as:

 if (ANNOTATE_EXPR <i <= 305 && parse_tables_n--  != 0, no-vector>) ...

But after lowering the condition is broken appart and attached to the final
component of the expression:

  if (parse_tables_n.2_2 != 0) goto <D.4456>; else goto <D.4453>;
  <D.4456>:
    iftmp.1D.4452 = 1;
    goto <D.4454>;
  <D.4453>:
    iftmp.1D.4452 = 0;
  <D.4454>:
    D.4451 = .ANNOTATE (iftmp.1D.4452, 2, 0);
    if (D.4451 != 0) goto <D.4442>; else goto <D.4440>;
  <D.4440>:

and it's never heard from again because during replace_loop_annotate we only
inspect the loop header and latch for annotations.

Since annotations were supposed to apply to the loop as a whole this fixes it
by also checking the loop exit src blocks for annotations.

Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.

Ok for master?

Thanks,
Tamar

gcc/ChangeLog:

	* tree-cfg.cc (replace_loop_annotate): Inspect loop edges for annotations.

gcc/testsuite/ChangeLog:

	* gcc.dg/vect/vect-novect_gcond.c: New test.

--- inline copy of patch -- 
diff --git a/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
new file mode 100644
index 0000000000000000000000000000000000000000..01e69cbef9d51b234c08a400c78dc078d53252f1




--
diff --git a/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
new file mode 100644
index 0000000000000000000000000000000000000000..01e69cbef9d51b234c08a400c78dc078d53252f1
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
@@ -0,0 +1,39 @@
+/* { dg-add-options vect_early_break } */
+/* { dg-require-effective-target vect_early_break_hw } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-O3" } */
+
+/* { dg-final { scan-tree-dump-not "LOOP VECTORIZED" "vect" } } */
+
+#include "tree-vect.h"
+
+#define N 306
+#define NEEDLE 136
+
+int table[N];
+
+__attribute__ ((noipa))
+int foo (int i, unsigned short parse_tables_n)
+{
+  parse_tables_n >>= 9;
+  parse_tables_n += 11;
+#pragma GCC novector
+  while (i < N && parse_tables_n--)
+    table[i++] = 0;
+
+  return table[NEEDLE];
+}
+
+int main ()
+{
+  check_vect ();
+
+#pragma GCC novector
+  for (int j = 0; j < N; j++)
+    table[j] = -1;
+
+  if (foo (0, 0xFFFF) != 0)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/tree-cfg.cc b/gcc/tree-cfg.cc
index cdd439fe7506e7bc33654ffa027b493f23d278ac..a29681bffb902d2d05e3f18764ab519aacb3c5bc 100644
--- a/gcc/tree-cfg.cc
+++ b/gcc/tree-cfg.cc
@@ -327,6 +327,10 @@ replace_loop_annotate (void)
       if (loop->latch)
 	replace_loop_annotate_in_block (loop->latch, loop);
 
+      /* Then also check all other exits.  */
+      for (auto e : get_loop_exit_edges (loop))
+	replace_loop_annotate_in_block (e->src, loop);
+
       /* Push the global flag_finite_loops state down to individual loops.  */
       loop->finite_p = flag_finite_loops;
     }

Comments

Richard Biener Feb. 14, 2024, 1:41 p.m. UTC | #1 
On Wed, 14 Feb 2024, Tamar Christina wrote:

> Hi All,
> 
> Attaching a pragma to a loop which has a complex condition often gets the pragma
> dropped. e.g.
> 
> #pragma GCC novector
>   while (i < N && parse_tables_n--)
> 
> before lowering this is represented as:
> 
>  if (ANNOTATE_EXPR <i <= 305 && parse_tables_n--  != 0, no-vector>) ...
> 
> But after lowering the condition is broken appart and attached to the final
> component of the expression:
> 
>   if (parse_tables_n.2_2 != 0) goto <D.4456>; else goto <D.4453>;
>   <D.4456>:
>     iftmp.1D.4452 = 1;
>     goto <D.4454>;
>   <D.4453>:
>     iftmp.1D.4452 = 0;
>   <D.4454>:
>     D.4451 = .ANNOTATE (iftmp.1D.4452, 2, 0);
>     if (D.4451 != 0) goto <D.4442>; else goto <D.4440>;
>   <D.4440>:
> 
> and it's never heard from again because during replace_loop_annotate we only
> inspect the loop header and latch for annotations.
> 
> Since annotations were supposed to apply to the loop as a whole this fixes it
> by also checking the loop exit src blocks for annotations.
> 
> Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
> 
> Ok for master?

I think this isn't entirely good.  For simple cases for
do {} while the condition ends up in the latch while for while () {}
loops it ends up in the header.  In your case the latch isn't empty
so it doesn't end up with the conditional.

I think your patch is OK to the point of looking at all loop exit
sources but you should elide the special-casing of header and
latch since it's really only exit conditionals that matter.

Richard.


> Thanks,
> Tamar
> 
> gcc/ChangeLog:
> 
> 	* tree-cfg.cc (replace_loop_annotate): Inspect loop edges for annotations.
> 
> gcc/testsuite/ChangeLog:
> 
> 	* gcc.dg/vect/vect-novect_gcond.c: New test.
> 
> --- inline copy of patch -- 
> diff --git a/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
> new file mode 100644
> index 0000000000000000000000000000000000000000..01e69cbef9d51b234c08a400c78dc078d53252f1
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
> @@ -0,0 +1,39 @@
> +/* { dg-add-options vect_early_break } */
> +/* { dg-require-effective-target vect_early_break_hw } */
> +/* { dg-require-effective-target vect_int } */
> +/* { dg-additional-options "-O3" } */
> +
> +/* { dg-final { scan-tree-dump-not "LOOP VECTORIZED" "vect" } } */
> +
> +#include "tree-vect.h"
> +
> +#define N 306
> +#define NEEDLE 136
> +
> +int table[N];
> +
> +__attribute__ ((noipa))
> +int foo (int i, unsigned short parse_tables_n)
> +{
> +  parse_tables_n >>= 9;
> +  parse_tables_n += 11;
> +#pragma GCC novector
> +  while (i < N && parse_tables_n--)
> +    table[i++] = 0;
> +
> +  return table[NEEDLE];
> +}
> +
> +int main ()
> +{
> +  check_vect ();
> +
> +#pragma GCC novector
> +  for (int j = 0; j < N; j++)
> +    table[j] = -1;
> +
> +  if (foo (0, 0xFFFF) != 0)
> +    __builtin_abort ();
> +
> +  return 0;
> +}
> diff --git a/gcc/tree-cfg.cc b/gcc/tree-cfg.cc
> index cdd439fe7506e7bc33654ffa027b493f23d278ac..a29681bffb902d2d05e3f18764ab519aacb3c5bc 100644
> --- a/gcc/tree-cfg.cc
> +++ b/gcc/tree-cfg.cc
> @@ -327,6 +327,10 @@ replace_loop_annotate (void)
>        if (loop->latch)
>  	replace_loop_annotate_in_block (loop->latch, loop);
>  
> +      /* Then also check all other exits.  */
> +      for (auto e : get_loop_exit_edges (loop))
> +	replace_loop_annotate_in_block (e->src, loop);
> +
>        /* Push the global flag_finite_loops state down to individual loops.  */
>        loop->finite_p = flag_finite_loops;
>      }
> 
> 
> 
> 
>
Tamar Christina Feb. 14, 2024, 3:15 p.m. UTC | #2 
> 
> I think this isn't entirely good.  For simple cases for
> do {} while the condition ends up in the latch while for while () {}
> loops it ends up in the header.  In your case the latch isn't empty
> so it doesn't end up with the conditional.
> 
> I think your patch is OK to the point of looking at all loop exit
> sources but you should elide the special-casing of header and
> latch since it's really only exit conditionals that matter.
> 

That makes sense, since in both cases the edges are in the respective
blocks.  Should have thought about it more.

So how about this one.

Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.

Ok for master?

Thanks,
Tamar

gcc/ChangeLog:

	* tree-cfg.cc (replace_loop_annotate): Inspect loop edges for annotations.

gcc/testsuite/ChangeLog:

	* gcc.dg/vect/vect-novect_gcond.c: New test.

--- inline copy of patch ---

diff --git a/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
new file mode 100644
index 0000000000000000000000000000000000000000..01e69cbef9d51b234c08a400c78dc078d53252f1
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
@@ -0,0 +1,39 @@
+/* { dg-add-options vect_early_break } */
+/* { dg-require-effective-target vect_early_break_hw } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-O3" } */
+
+/* { dg-final { scan-tree-dump-not "LOOP VECTORIZED" "vect" } } */
+
+#include "tree-vect.h"
+
+#define N 306
+#define NEEDLE 136
+
+int table[N];
+
+__attribute__ ((noipa))
+int foo (int i, unsigned short parse_tables_n)
+{
+  parse_tables_n >>= 9;
+  parse_tables_n += 11;
+#pragma GCC novector
+  while (i < N && parse_tables_n--)
+    table[i++] = 0;
+
+  return table[NEEDLE];
+}
+
+int main ()
+{
+  check_vect ();
+
+#pragma GCC novector
+  for (int j = 0; j < N; j++)
+    table[j] = -1;
+
+  if (foo (0, 0xFFFF) != 0)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/tree-cfg.cc b/gcc/tree-cfg.cc
index cdd439fe7506e7bc33654ffa027b493f23d278ac..bdffc3b4ed277724e81b7dd67fe7966e8ece0c13 100644
--- a/gcc/tree-cfg.cc
+++ b/gcc/tree-cfg.cc
@@ -320,12 +320,9 @@ replace_loop_annotate (void)
 
   for (auto loop : loops_list (cfun, 0))
     {
-      /* First look into the header.  */
-      replace_loop_annotate_in_block (loop->header, loop);
-
-      /* Then look into the latch, if any.  */
-      if (loop->latch)
-	replace_loop_annotate_in_block (loop->latch, loop);
+      /* Check all exit source blocks for annotations.  */
+      for (auto e : get_loop_exit_edges (loop))
+	replace_loop_annotate_in_block (e->src, loop);
 
       /* Push the global flag_finite_loops state down to individual loops.  */
       loop->finite_p = flag_finite_loops;
Richard Biener Feb. 14, 2024, 3:18 p.m. UTC | #3 
> Am 14.02.2024 um 16:16 schrieb Tamar Christina <tamar.christina@arm.com>:
> 
> 
>> 
>> 
>> I think this isn't entirely good.  For simple cases for
>> do {} while the condition ends up in the latch while for while () {}
>> loops it ends up in the header.  In your case the latch isn't empty
>> so it doesn't end up with the conditional.
>> 
>> I think your patch is OK to the point of looking at all loop exit
>> sources but you should elide the special-casing of header and
>> latch since it's really only exit conditionals that matter.
>> 
> 
> That makes sense, since in both cases the edges are in the respective
> blocks.  Should have thought about it more.
> 
> So how about this one.
> 
> Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
> 
> Ok for master?

Ok

Richard 

> Thanks,
> Tamar
> 
> gcc/ChangeLog:
> 
>    * tree-cfg.cc (replace_loop_annotate): Inspect loop edges for annotations.
> 
> gcc/testsuite/ChangeLog:
> 
>    * gcc.dg/vect/vect-novect_gcond.c: New test.
> 
> --- inline copy of patch ---
> 
> diff --git a/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
> new file mode 100644
> index 0000000000000000000000000000000000000000..01e69cbef9d51b234c08a400c78dc078d53252f1
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
> @@ -0,0 +1,39 @@
> +/* { dg-add-options vect_early_break } */
> +/* { dg-require-effective-target vect_early_break_hw } */
> +/* { dg-require-effective-target vect_int } */
> +/* { dg-additional-options "-O3" } */
> +
> +/* { dg-final { scan-tree-dump-not "LOOP VECTORIZED" "vect" } } */
> +
> +#include "tree-vect.h"
> +
> +#define N 306
> +#define NEEDLE 136
> +
> +int table[N];
> +
> +__attribute__ ((noipa))
> +int foo (int i, unsigned short parse_tables_n)
> +{
> +  parse_tables_n >>= 9;
> +  parse_tables_n += 11;
> +#pragma GCC novector
> +  while (i < N && parse_tables_n--)
> +    table[i++] = 0;
> +
> +  return table[NEEDLE];
> +}
> +
> +int main ()
> +{
> +  check_vect ();
> +
> +#pragma GCC novector
> +  for (int j = 0; j < N; j++)
> +    table[j] = -1;
> +
> +  if (foo (0, 0xFFFF) != 0)
> +    __builtin_abort ();
> +
> +  return 0;
> +}
> diff --git a/gcc/tree-cfg.cc b/gcc/tree-cfg.cc
> index cdd439fe7506e7bc33654ffa027b493f23d278ac..bdffc3b4ed277724e81b7dd67fe7966e8ece0c13 100644
> --- a/gcc/tree-cfg.cc
> +++ b/gcc/tree-cfg.cc
> @@ -320,12 +320,9 @@ replace_loop_annotate (void)
> 
>   for (auto loop : loops_list (cfun, 0))
>     {
> -      /* First look into the header.  */
> -      replace_loop_annotate_in_block (loop->header, loop);
> -
> -      /* Then look into the latch, if any.  */
> -      if (loop->latch)
> -    replace_loop_annotate_in_block (loop->latch, loop);
> +      /* Check all exit source blocks for annotations.  */
> +      for (auto e : get_loop_exit_edges (loop))
> +    replace_loop_annotate_in_block (e->src, loop);
> 
>       /* Push the global flag_finite_loops state down to individual loops.  */
>       loop->finite_p = flag_finite_loops;
> <rb18267.patch>
diff mbox series

Patch

--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/vect-novect_gcond.c
@@ -0,0 +1,39 @@ 
+/* { dg-add-options vect_early_break } */
+/* { dg-require-effective-target vect_early_break_hw } */
+/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-O3" } */
+
+/* { dg-final { scan-tree-dump-not "LOOP VECTORIZED" "vect" } } */
+
+#include "tree-vect.h"
+
+#define N 306
+#define NEEDLE 136
+
+int table[N];
+
+__attribute__ ((noipa))
+int foo (int i, unsigned short parse_tables_n)
+{
+  parse_tables_n >>= 9;
+  parse_tables_n += 11;
+#pragma GCC novector
+  while (i < N && parse_tables_n--)
+    table[i++] = 0;
+
+  return table[NEEDLE];
+}
+
+int main ()
+{
+  check_vect ();
+
+#pragma GCC novector
+  for (int j = 0; j < N; j++)
+    table[j] = -1;
+
+  if (foo (0, 0xFFFF) != 0)
+    __builtin_abort ();
+
+  return 0;
+}
diff --git a/gcc/tree-cfg.cc b/gcc/tree-cfg.cc
index cdd439fe7506e7bc33654ffa027b493f23d278ac..a29681bffb902d2d05e3f18764ab519aacb3c5bc 100644
--- a/gcc/tree-cfg.cc
+++ b/gcc/tree-cfg.cc
@@ -327,6 +327,10 @@  replace_loop_annotate (void)
       if (loop->latch)
 	replace_loop_annotate_in_block (loop->latch, loop);
 
+      /* Then also check all other exits.  */
+      for (auto e : get_loop_exit_edges (loop))
+	replace_loop_annotate_in_block (e->src, loop);
+
       /* Push the global flag_finite_loops state down to individual loops.  */
       loop->finite_p = flag_finite_loops;
     }