Patchwork Relax the requirement of reduction pattern in GCC vectorizer.

login
register
mail settings
Submitter Cong Hou
Date Sept. 28, 2013, 1:28 a.m.
Message ID <CAK=A3=1Sao0Cwxsj6LCQ0R6oLTc3zOZyFdJHribxjymnJSYUcw@mail.gmail.com>
Download mbox | patch
Permalink /patch/278699/
State New
Headers show

Comments

Cong Hou - Sept. 28, 2013, 1:28 a.m.
The current GCC vectorizer requires the following pattern as a simple
reduction computation:

   loop_header:
     a1 = phi < a0, a2 >
     a3 = ...
     a2 = operation (a3, a1)

But a3 can also be defined outside of the loop. For example, the
following loop can benefit from vectorization but the GCC vectorizer
fails to vectorize it:


int foo(int v)
{
  int s = 1;
  ++v;
  for (int i = 0; i < 100000; ++i)
    s *= v;
  return s;
}


This patch relaxes the original requirement by also considering the
following pattern:


   a3 = ...
   loop_header:
     a1 = phi < a0, a2 >
     a2 = operation (a3, a1)


A test case is also added. The patch is tested on x86-64.


thanks,
Cong
Xinliang David Li - Sept. 28, 2013, 4:34 p.m.
You can also add a test case of this form:

int foo( int t, int n, int *dst)
{
   int j = 0;
   int s = 1;
   t++;
   for (j = 0; j < n; j++)
     {
         dst[j] = t;
         s *= t;
     }

   return s;
}

where without the fix the loop vectorization is missed.

David

On Fri, Sep 27, 2013 at 6:28 PM, Cong Hou <congh@google.com> wrote:
> The current GCC vectorizer requires the following pattern as a simple
> reduction computation:
>
>    loop_header:
>      a1 = phi < a0, a2 >
>      a3 = ...
>      a2 = operation (a3, a1)
>
> But a3 can also be defined outside of the loop. For example, the
> following loop can benefit from vectorization but the GCC vectorizer
> fails to vectorize it:
>
>
> int foo(int v)
> {
>   int s = 1;
>   ++v;
>   for (int i = 0; i < 100000; ++i)
>     s *= v;
>   return s;
> }
>
>
> This patch relaxes the original requirement by also considering the
> following pattern:
>
>
>    a3 = ...
>    loop_header:
>      a1 = phi < a0, a2 >
>      a2 = operation (a3, a1)
>
>
> A test case is also added. The patch is tested on x86-64.
>
>
> thanks,
> Cong
>
> ================================
>
> diff --git a/gcc/ChangeLog b/gcc/ChangeLog
> index 39c786e..45c1667 100644
> --- a/gcc/ChangeLog
> +++ b/gcc/ChangeLog
> @@ -1,3 +1,9 @@
> +2013-09-27  Cong Hou  <congh@google.com>
> +
> + * tree-vect-loop.c: Relax the requirement of the reduction
> + pattern so that one operand of the reduction operation can
> + come from outside of the loop.
> +
>  2013-09-25  Tom Tromey  <tromey@redhat.com>
>
>   * Makefile.in (PARTITION_H, LTO_SYMTAB_H, COMMON_TARGET_DEF_H)
> diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
> index 09644d2..90496a2 100644
> --- a/gcc/testsuite/ChangeLog
> +++ b/gcc/testsuite/ChangeLog
> @@ -1,3 +1,7 @@
> +2013-09-27  Cong Hou  <congh@google.com>
> +
> + * gcc.dg/vect/vect-reduc-pattern-3.c: New test.
> +
>  2013-09-25  Marek Polacek  <polacek@redhat.com>
>
>   PR sanitizer/58413
> diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
> index 2871ba1..3c51c3b 100644
> --- a/gcc/tree-vect-loop.c
> +++ b/gcc/tree-vect-loop.c
> @@ -2091,6 +2091,13 @@ vect_is_slp_reduction (loop_vec_info loop_info,
> gimple phi, gimple first_stmt)
>       a3 = ...
>       a2 = operation (a3, a1)
>
> +   or
> +
> +   a3 = ...
> +   loop_header:
> +     a1 = phi < a0, a2 >
> +     a2 = operation (a3, a1)
> +
>     such that:
>     1. operation is commutative and associative and it is safe to
>        change the order of the computation (if CHECK_REDUCTION is true)
> @@ -2451,6 +2458,7 @@ vect_is_simple_reduction_1 (loop_vec_info
> loop_info, gimple phi,
>    if (def2 && def2 == phi
>        && (code == COND_EXPR
>    || !def1 || gimple_nop_p (def1)
> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def1))
>            || (def1 && flow_bb_inside_loop_p (loop, gimple_bb (def1))
>                && (is_gimple_assign (def1)
>    || is_gimple_call (def1)
> @@ -2469,6 +2477,7 @@ vect_is_simple_reduction_1 (loop_vec_info
> loop_info, gimple phi,
>    if (def1 && def1 == phi
>        && (code == COND_EXPR
>    || !def2 || gimple_nop_p (def2)
> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def2))
>            || (def2 && flow_bb_inside_loop_p (loop, gimple_bb (def2))
>        && (is_gimple_assign (def2)
>    || is_gimple_call (def2)
> diff --git gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
> gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
> new file mode 100644
> index 0000000..06a9416
> --- /dev/null
> +++ gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
> @@ -0,0 +1,41 @@
> +/* { dg-require-effective-target vect_int } */
> +
> +#include <stdarg.h>
> +#include "tree-vect.h"
> +
> +#define N 10
> +#define RES 1024
> +
> +/* A reduction pattern in which there is no data ref in
> +   the loop and one operand is defined outside of the loop.  */
> +
> +__attribute__ ((noinline)) int
> +foo (int v)
> +{
> +  int i;
> +  int result = 1;
> +
> +  ++v;
> +  for (i = 0; i < N; i++)
> +    result *= v;
> +
> +  return result;
> +}
> +
> +int
> +main (void)
> +{
> +  int res;
> +
> +  check_vect ();
> +
> +  res = foo (1);
> +  if (res != RES)
> +    abort ();
> +
> +  return 0;
> +}
> +
> +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
> +/* { dg-final { cleanup-tree-dump "vect" } } */
> +
Cong Hou - Oct. 2, 2013, 6:18 p.m.
Ping..  Any comment on this patch?


thanks,
Cong


On Sat, Sep 28, 2013 at 9:34 AM, Xinliang David Li <davidxl@google.com> wrote:
> You can also add a test case of this form:
>
> int foo( int t, int n, int *dst)
> {
>    int j = 0;
>    int s = 1;
>    t++;
>    for (j = 0; j < n; j++)
>      {
>          dst[j] = t;
>          s *= t;
>      }
>
>    return s;
> }
>
> where without the fix the loop vectorization is missed.
>
> David
>
> On Fri, Sep 27, 2013 at 6:28 PM, Cong Hou <congh@google.com> wrote:
>> The current GCC vectorizer requires the following pattern as a simple
>> reduction computation:
>>
>>    loop_header:
>>      a1 = phi < a0, a2 >
>>      a3 = ...
>>      a2 = operation (a3, a1)
>>
>> But a3 can also be defined outside of the loop. For example, the
>> following loop can benefit from vectorization but the GCC vectorizer
>> fails to vectorize it:
>>
>>
>> int foo(int v)
>> {
>>   int s = 1;
>>   ++v;
>>   for (int i = 0; i < 100000; ++i)
>>     s *= v;
>>   return s;
>> }
>>
>>
>> This patch relaxes the original requirement by also considering the
>> following pattern:
>>
>>
>>    a3 = ...
>>    loop_header:
>>      a1 = phi < a0, a2 >
>>      a2 = operation (a3, a1)
>>
>>
>> A test case is also added. The patch is tested on x86-64.
>>
>>
>> thanks,
>> Cong
>>
>> ================================
>>
>> diff --git a/gcc/ChangeLog b/gcc/ChangeLog
>> index 39c786e..45c1667 100644
>> --- a/gcc/ChangeLog
>> +++ b/gcc/ChangeLog
>> @@ -1,3 +1,9 @@
>> +2013-09-27  Cong Hou  <congh@google.com>
>> +
>> + * tree-vect-loop.c: Relax the requirement of the reduction
>> + pattern so that one operand of the reduction operation can
>> + come from outside of the loop.
>> +
>>  2013-09-25  Tom Tromey  <tromey@redhat.com>
>>
>>   * Makefile.in (PARTITION_H, LTO_SYMTAB_H, COMMON_TARGET_DEF_H)
>> diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
>> index 09644d2..90496a2 100644
>> --- a/gcc/testsuite/ChangeLog
>> +++ b/gcc/testsuite/ChangeLog
>> @@ -1,3 +1,7 @@
>> +2013-09-27  Cong Hou  <congh@google.com>
>> +
>> + * gcc.dg/vect/vect-reduc-pattern-3.c: New test.
>> +
>>  2013-09-25  Marek Polacek  <polacek@redhat.com>
>>
>>   PR sanitizer/58413
>> diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
>> index 2871ba1..3c51c3b 100644
>> --- a/gcc/tree-vect-loop.c
>> +++ b/gcc/tree-vect-loop.c
>> @@ -2091,6 +2091,13 @@ vect_is_slp_reduction (loop_vec_info loop_info,
>> gimple phi, gimple first_stmt)
>>       a3 = ...
>>       a2 = operation (a3, a1)
>>
>> +   or
>> +
>> +   a3 = ...
>> +   loop_header:
>> +     a1 = phi < a0, a2 >
>> +     a2 = operation (a3, a1)
>> +
>>     such that:
>>     1. operation is commutative and associative and it is safe to
>>        change the order of the computation (if CHECK_REDUCTION is true)
>> @@ -2451,6 +2458,7 @@ vect_is_simple_reduction_1 (loop_vec_info
>> loop_info, gimple phi,
>>    if (def2 && def2 == phi
>>        && (code == COND_EXPR
>>    || !def1 || gimple_nop_p (def1)
>> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def1))
>>            || (def1 && flow_bb_inside_loop_p (loop, gimple_bb (def1))
>>                && (is_gimple_assign (def1)
>>    || is_gimple_call (def1)
>> @@ -2469,6 +2477,7 @@ vect_is_simple_reduction_1 (loop_vec_info
>> loop_info, gimple phi,
>>    if (def1 && def1 == phi
>>        && (code == COND_EXPR
>>    || !def2 || gimple_nop_p (def2)
>> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def2))
>>            || (def2 && flow_bb_inside_loop_p (loop, gimple_bb (def2))
>>        && (is_gimple_assign (def2)
>>    || is_gimple_call (def2)
>> diff --git gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
>> gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
>> new file mode 100644
>> index 0000000..06a9416
>> --- /dev/null
>> +++ gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
>> @@ -0,0 +1,41 @@
>> +/* { dg-require-effective-target vect_int } */
>> +
>> +#include <stdarg.h>
>> +#include "tree-vect.h"
>> +
>> +#define N 10
>> +#define RES 1024
>> +
>> +/* A reduction pattern in which there is no data ref in
>> +   the loop and one operand is defined outside of the loop.  */
>> +
>> +__attribute__ ((noinline)) int
>> +foo (int v)
>> +{
>> +  int i;
>> +  int result = 1;
>> +
>> +  ++v;
>> +  for (i = 0; i < N; i++)
>> +    result *= v;
>> +
>> +  return result;
>> +}
>> +
>> +int
>> +main (void)
>> +{
>> +  int res;
>> +
>> +  check_vect ();
>> +
>> +  res = foo (1);
>> +  if (res != RES)
>> +    abort ();
>> +
>> +  return 0;
>> +}
>> +
>> +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
>> +/* { dg-final { cleanup-tree-dump "vect" } } */
>> +
Cong Hou - Oct. 15, 2013, 12:20 a.m.
Ping...


thanks,
Cong


On Wed, Oct 2, 2013 at 11:18 AM, Cong Hou <congh@google.com> wrote:
> Ping..  Any comment on this patch?
>
>
> thanks,
> Cong
>
>
> On Sat, Sep 28, 2013 at 9:34 AM, Xinliang David Li <davidxl@google.com> wrote:
>> You can also add a test case of this form:
>>
>> int foo( int t, int n, int *dst)
>> {
>>    int j = 0;
>>    int s = 1;
>>    t++;
>>    for (j = 0; j < n; j++)
>>      {
>>          dst[j] = t;
>>          s *= t;
>>      }
>>
>>    return s;
>> }
>>
>> where without the fix the loop vectorization is missed.
>>
>> David
>>
>> On Fri, Sep 27, 2013 at 6:28 PM, Cong Hou <congh@google.com> wrote:
>>> The current GCC vectorizer requires the following pattern as a simple
>>> reduction computation:
>>>
>>>    loop_header:
>>>      a1 = phi < a0, a2 >
>>>      a3 = ...
>>>      a2 = operation (a3, a1)
>>>
>>> But a3 can also be defined outside of the loop. For example, the
>>> following loop can benefit from vectorization but the GCC vectorizer
>>> fails to vectorize it:
>>>
>>>
>>> int foo(int v)
>>> {
>>>   int s = 1;
>>>   ++v;
>>>   for (int i = 0; i < 100000; ++i)
>>>     s *= v;
>>>   return s;
>>> }
>>>
>>>
>>> This patch relaxes the original requirement by also considering the
>>> following pattern:
>>>
>>>
>>>    a3 = ...
>>>    loop_header:
>>>      a1 = phi < a0, a2 >
>>>      a2 = operation (a3, a1)
>>>
>>>
>>> A test case is also added. The patch is tested on x86-64.
>>>
>>>
>>> thanks,
>>> Cong
>>>
>>> ================================
>>>
>>> diff --git a/gcc/ChangeLog b/gcc/ChangeLog
>>> index 39c786e..45c1667 100644
>>> --- a/gcc/ChangeLog
>>> +++ b/gcc/ChangeLog
>>> @@ -1,3 +1,9 @@
>>> +2013-09-27  Cong Hou  <congh@google.com>
>>> +
>>> + * tree-vect-loop.c: Relax the requirement of the reduction
>>> + pattern so that one operand of the reduction operation can
>>> + come from outside of the loop.
>>> +
>>>  2013-09-25  Tom Tromey  <tromey@redhat.com>
>>>
>>>   * Makefile.in (PARTITION_H, LTO_SYMTAB_H, COMMON_TARGET_DEF_H)
>>> diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
>>> index 09644d2..90496a2 100644
>>> --- a/gcc/testsuite/ChangeLog
>>> +++ b/gcc/testsuite/ChangeLog
>>> @@ -1,3 +1,7 @@
>>> +2013-09-27  Cong Hou  <congh@google.com>
>>> +
>>> + * gcc.dg/vect/vect-reduc-pattern-3.c: New test.
>>> +
>>>  2013-09-25  Marek Polacek  <polacek@redhat.com>
>>>
>>>   PR sanitizer/58413
>>> diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
>>> index 2871ba1..3c51c3b 100644
>>> --- a/gcc/tree-vect-loop.c
>>> +++ b/gcc/tree-vect-loop.c
>>> @@ -2091,6 +2091,13 @@ vect_is_slp_reduction (loop_vec_info loop_info,
>>> gimple phi, gimple first_stmt)
>>>       a3 = ...
>>>       a2 = operation (a3, a1)
>>>
>>> +   or
>>> +
>>> +   a3 = ...
>>> +   loop_header:
>>> +     a1 = phi < a0, a2 >
>>> +     a2 = operation (a3, a1)
>>> +
>>>     such that:
>>>     1. operation is commutative and associative and it is safe to
>>>        change the order of the computation (if CHECK_REDUCTION is true)
>>> @@ -2451,6 +2458,7 @@ vect_is_simple_reduction_1 (loop_vec_info
>>> loop_info, gimple phi,
>>>    if (def2 && def2 == phi
>>>        && (code == COND_EXPR
>>>    || !def1 || gimple_nop_p (def1)
>>> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def1))
>>>            || (def1 && flow_bb_inside_loop_p (loop, gimple_bb (def1))
>>>                && (is_gimple_assign (def1)
>>>    || is_gimple_call (def1)
>>> @@ -2469,6 +2477,7 @@ vect_is_simple_reduction_1 (loop_vec_info
>>> loop_info, gimple phi,
>>>    if (def1 && def1 == phi
>>>        && (code == COND_EXPR
>>>    || !def2 || gimple_nop_p (def2)
>>> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def2))
>>>            || (def2 && flow_bb_inside_loop_p (loop, gimple_bb (def2))
>>>        && (is_gimple_assign (def2)
>>>    || is_gimple_call (def2)
>>> diff --git gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
>>> gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
>>> new file mode 100644
>>> index 0000000..06a9416
>>> --- /dev/null
>>> +++ gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
>>> @@ -0,0 +1,41 @@
>>> +/* { dg-require-effective-target vect_int } */
>>> +
>>> +#include <stdarg.h>
>>> +#include "tree-vect.h"
>>> +
>>> +#define N 10
>>> +#define RES 1024
>>> +
>>> +/* A reduction pattern in which there is no data ref in
>>> +   the loop and one operand is defined outside of the loop.  */
>>> +
>>> +__attribute__ ((noinline)) int
>>> +foo (int v)
>>> +{
>>> +  int i;
>>> +  int result = 1;
>>> +
>>> +  ++v;
>>> +  for (i = 0; i < N; i++)
>>> +    result *= v;
>>> +
>>> +  return result;
>>> +}
>>> +
>>> +int
>>> +main (void)
>>> +{
>>> +  int res;
>>> +
>>> +  check_vect ();
>>> +
>>> +  res = foo (1);
>>> +  if (res != RES)
>>> +    abort ();
>>> +
>>> +  return 0;
>>> +}
>>> +
>>> +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
>>> +/* { dg-final { cleanup-tree-dump "vect" } } */
>>> +
Richard Guenther - Oct. 15, 2013, 1:38 p.m.
On Sat, Sep 28, 2013 at 3:28 AM, Cong Hou <congh@google.com> wrote:
> The current GCC vectorizer requires the following pattern as a simple
> reduction computation:
>
>    loop_header:
>      a1 = phi < a0, a2 >
>      a3 = ...
>      a2 = operation (a3, a1)
>
> But a3 can also be defined outside of the loop. For example, the
> following loop can benefit from vectorization but the GCC vectorizer
> fails to vectorize it:
>
>
> int foo(int v)
> {
>   int s = 1;
>   ++v;
>   for (int i = 0; i < 100000; ++i)
>     s *= v;
>   return s;
> }
>
>
> This patch relaxes the original requirement by also considering the
> following pattern:
>
>
>    a3 = ...
>    loop_header:
>      a1 = phi < a0, a2 >
>      a2 = operation (a3, a1)
>
>
> A test case is also added. The patch is tested on x86-64.
>
>
> thanks,
> Cong
>
> ================================
>
> diff --git a/gcc/ChangeLog b/gcc/ChangeLog
> index 39c786e..45c1667 100644
> --- a/gcc/ChangeLog
> +++ b/gcc/ChangeLog
> @@ -1,3 +1,9 @@
> +2013-09-27  Cong Hou  <congh@google.com>
> +
> + * tree-vect-loop.c: Relax the requirement of the reduction

ChangeLog format is

<tab>* tree-vect-loop.c (vect_is_simple_reduction_1): Relax the
<tab>requirement of the reduction.

Ok with that change.

Thanks,
Richard.

> + pattern so that one operand of the reduction operation can
> + come from outside of the loop.
> +
>  2013-09-25  Tom Tromey  <tromey@redhat.com>
>
>   * Makefile.in (PARTITION_H, LTO_SYMTAB_H, COMMON_TARGET_DEF_H)
> diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
> index 09644d2..90496a2 100644
> --- a/gcc/testsuite/ChangeLog
> +++ b/gcc/testsuite/ChangeLog
> @@ -1,3 +1,7 @@
> +2013-09-27  Cong Hou  <congh@google.com>
> +
> + * gcc.dg/vect/vect-reduc-pattern-3.c: New test.
> +
>  2013-09-25  Marek Polacek  <polacek@redhat.com>
>
>   PR sanitizer/58413
> diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
> index 2871ba1..3c51c3b 100644
> --- a/gcc/tree-vect-loop.c
> +++ b/gcc/tree-vect-loop.c
> @@ -2091,6 +2091,13 @@ vect_is_slp_reduction (loop_vec_info loop_info,
> gimple phi, gimple first_stmt)
>       a3 = ...
>       a2 = operation (a3, a1)
>
> +   or
> +
> +   a3 = ...
> +   loop_header:
> +     a1 = phi < a0, a2 >
> +     a2 = operation (a3, a1)
> +
>     such that:
>     1. operation is commutative and associative and it is safe to
>        change the order of the computation (if CHECK_REDUCTION is true)
> @@ -2451,6 +2458,7 @@ vect_is_simple_reduction_1 (loop_vec_info
> loop_info, gimple phi,
>    if (def2 && def2 == phi
>        && (code == COND_EXPR
>    || !def1 || gimple_nop_p (def1)
> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def1))
>            || (def1 && flow_bb_inside_loop_p (loop, gimple_bb (def1))
>                && (is_gimple_assign (def1)
>    || is_gimple_call (def1)
> @@ -2469,6 +2477,7 @@ vect_is_simple_reduction_1 (loop_vec_info
> loop_info, gimple phi,
>    if (def1 && def1 == phi
>        && (code == COND_EXPR
>    || !def2 || gimple_nop_p (def2)
> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def2))
>            || (def2 && flow_bb_inside_loop_p (loop, gimple_bb (def2))
>        && (is_gimple_assign (def2)
>    || is_gimple_call (def2)
> diff --git gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
> gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
> new file mode 100644
> index 0000000..06a9416
> --- /dev/null
> +++ gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
> @@ -0,0 +1,41 @@
> +/* { dg-require-effective-target vect_int } */
> +
> +#include <stdarg.h>
> +#include "tree-vect.h"
> +
> +#define N 10
> +#define RES 1024
> +
> +/* A reduction pattern in which there is no data ref in
> +   the loop and one operand is defined outside of the loop.  */
> +
> +__attribute__ ((noinline)) int
> +foo (int v)
> +{
> +  int i;
> +  int result = 1;
> +
> +  ++v;
> +  for (i = 0; i < N; i++)
> +    result *= v;
> +
> +  return result;
> +}
> +
> +int
> +main (void)
> +{
> +  int res;
> +
> +  check_vect ();
> +
> +  res = foo (1);
> +  if (res != RES)
> +    abort ();
> +
> +  return 0;
> +}
> +
> +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
> +/* { dg-final { cleanup-tree-dump "vect" } } */
> +
Cong Hou - Oct. 15, 2013, 5:19 p.m.
I have corrected the ChangeLog format, and committed this patch.

Thank you!


Cong


On Tue, Oct 15, 2013 at 6:38 AM, Richard Biener
<richard.guenther@gmail.com> wrote:
> On Sat, Sep 28, 2013 at 3:28 AM, Cong Hou <congh@google.com> wrote:
>> The current GCC vectorizer requires the following pattern as a simple
>> reduction computation:
>>
>>    loop_header:
>>      a1 = phi < a0, a2 >
>>      a3 = ...
>>      a2 = operation (a3, a1)
>>
>> But a3 can also be defined outside of the loop. For example, the
>> following loop can benefit from vectorization but the GCC vectorizer
>> fails to vectorize it:
>>
>>
>> int foo(int v)
>> {
>>   int s = 1;
>>   ++v;
>>   for (int i = 0; i < 100000; ++i)
>>     s *= v;
>>   return s;
>> }
>>
>>
>> This patch relaxes the original requirement by also considering the
>> following pattern:
>>
>>
>>    a3 = ...
>>    loop_header:
>>      a1 = phi < a0, a2 >
>>      a2 = operation (a3, a1)
>>
>>
>> A test case is also added. The patch is tested on x86-64.
>>
>>
>> thanks,
>> Cong
>>
>> ================================
>>
>> diff --git a/gcc/ChangeLog b/gcc/ChangeLog
>> index 39c786e..45c1667 100644
>> --- a/gcc/ChangeLog
>> +++ b/gcc/ChangeLog
>> @@ -1,3 +1,9 @@
>> +2013-09-27  Cong Hou  <congh@google.com>
>> +
>> + * tree-vect-loop.c: Relax the requirement of the reduction
>
> ChangeLog format is
>
> <tab>* tree-vect-loop.c (vect_is_simple_reduction_1): Relax the
> <tab>requirement of the reduction.
>
> Ok with that change.
>
> Thanks,
> Richard.
>
>> + pattern so that one operand of the reduction operation can
>> + come from outside of the loop.
>> +
>>  2013-09-25  Tom Tromey  <tromey@redhat.com>
>>
>>   * Makefile.in (PARTITION_H, LTO_SYMTAB_H, COMMON_TARGET_DEF_H)
>> diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
>> index 09644d2..90496a2 100644
>> --- a/gcc/testsuite/ChangeLog
>> +++ b/gcc/testsuite/ChangeLog
>> @@ -1,3 +1,7 @@
>> +2013-09-27  Cong Hou  <congh@google.com>
>> +
>> + * gcc.dg/vect/vect-reduc-pattern-3.c: New test.
>> +
>>  2013-09-25  Marek Polacek  <polacek@redhat.com>
>>
>>   PR sanitizer/58413
>> diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
>> index 2871ba1..3c51c3b 100644
>> --- a/gcc/tree-vect-loop.c
>> +++ b/gcc/tree-vect-loop.c
>> @@ -2091,6 +2091,13 @@ vect_is_slp_reduction (loop_vec_info loop_info,
>> gimple phi, gimple first_stmt)
>>       a3 = ...
>>       a2 = operation (a3, a1)
>>
>> +   or
>> +
>> +   a3 = ...
>> +   loop_header:
>> +     a1 = phi < a0, a2 >
>> +     a2 = operation (a3, a1)
>> +
>>     such that:
>>     1. operation is commutative and associative and it is safe to
>>        change the order of the computation (if CHECK_REDUCTION is true)
>> @@ -2451,6 +2458,7 @@ vect_is_simple_reduction_1 (loop_vec_info
>> loop_info, gimple phi,
>>    if (def2 && def2 == phi
>>        && (code == COND_EXPR
>>    || !def1 || gimple_nop_p (def1)
>> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def1))
>>            || (def1 && flow_bb_inside_loop_p (loop, gimple_bb (def1))
>>                && (is_gimple_assign (def1)
>>    || is_gimple_call (def1)
>> @@ -2469,6 +2477,7 @@ vect_is_simple_reduction_1 (loop_vec_info
>> loop_info, gimple phi,
>>    if (def1 && def1 == phi
>>        && (code == COND_EXPR
>>    || !def2 || gimple_nop_p (def2)
>> +  || !flow_bb_inside_loop_p (loop, gimple_bb (def2))
>>            || (def2 && flow_bb_inside_loop_p (loop, gimple_bb (def2))
>>        && (is_gimple_assign (def2)
>>    || is_gimple_call (def2)
>> diff --git gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
>> gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
>> new file mode 100644
>> index 0000000..06a9416
>> --- /dev/null
>> +++ gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
>> @@ -0,0 +1,41 @@
>> +/* { dg-require-effective-target vect_int } */
>> +
>> +#include <stdarg.h>
>> +#include "tree-vect.h"
>> +
>> +#define N 10
>> +#define RES 1024
>> +
>> +/* A reduction pattern in which there is no data ref in
>> +   the loop and one operand is defined outside of the loop.  */
>> +
>> +__attribute__ ((noinline)) int
>> +foo (int v)
>> +{
>> +  int i;
>> +  int result = 1;
>> +
>> +  ++v;
>> +  for (i = 0; i < N; i++)
>> +    result *= v;
>> +
>> +  return result;
>> +}
>> +
>> +int
>> +main (void)
>> +{
>> +  int res;
>> +
>> +  check_vect ();
>> +
>> +  res = foo (1);
>> +  if (res != RES)
>> +    abort ();
>> +
>> +  return 0;
>> +}
>> +
>> +/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
>> +/* { dg-final { cleanup-tree-dump "vect" } } */
>> +

Patch

================================

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 39c786e..45c1667 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@ 
+2013-09-27  Cong Hou  <congh@google.com>
+
+ * tree-vect-loop.c: Relax the requirement of the reduction
+ pattern so that one operand of the reduction operation can
+ come from outside of the loop.
+
 2013-09-25  Tom Tromey  <tromey@redhat.com>

  * Makefile.in (PARTITION_H, LTO_SYMTAB_H, COMMON_TARGET_DEF_H)
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 09644d2..90496a2 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@ 
+2013-09-27  Cong Hou  <congh@google.com>
+
+ * gcc.dg/vect/vect-reduc-pattern-3.c: New test.
+
 2013-09-25  Marek Polacek  <polacek@redhat.com>

  PR sanitizer/58413
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index 2871ba1..3c51c3b 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -2091,6 +2091,13 @@  vect_is_slp_reduction (loop_vec_info loop_info,
gimple phi, gimple first_stmt)
      a3 = ...
      a2 = operation (a3, a1)

+   or
+
+   a3 = ...
+   loop_header:
+     a1 = phi < a0, a2 >
+     a2 = operation (a3, a1)
+
    such that:
    1. operation is commutative and associative and it is safe to
       change the order of the computation (if CHECK_REDUCTION is true)
@@ -2451,6 +2458,7 @@  vect_is_simple_reduction_1 (loop_vec_info
loop_info, gimple phi,
   if (def2 && def2 == phi
       && (code == COND_EXPR
   || !def1 || gimple_nop_p (def1)
+  || !flow_bb_inside_loop_p (loop, gimple_bb (def1))
           || (def1 && flow_bb_inside_loop_p (loop, gimple_bb (def1))
               && (is_gimple_assign (def1)
   || is_gimple_call (def1)
@@ -2469,6 +2477,7 @@  vect_is_simple_reduction_1 (loop_vec_info
loop_info, gimple phi,
   if (def1 && def1 == phi
       && (code == COND_EXPR
   || !def2 || gimple_nop_p (def2)
+  || !flow_bb_inside_loop_p (loop, gimple_bb (def2))
           || (def2 && flow_bb_inside_loop_p (loop, gimple_bb (def2))
       && (is_gimple_assign (def2)
   || is_gimple_call (def2)
diff --git gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
new file mode 100644
index 0000000..06a9416
--- /dev/null
+++ gcc/testsuite/gcc.dg/vect/vect-reduc-pattern-3.c
@@ -0,0 +1,41 @@ 
+/* { dg-require-effective-target vect_int } */
+
+#include <stdarg.h>
+#include "tree-vect.h"
+
+#define N 10
+#define RES 1024
+
+/* A reduction pattern in which there is no data ref in
+   the loop and one operand is defined outside of the loop.  */
+
+__attribute__ ((noinline)) int
+foo (int v)
+{
+  int i;
+  int result = 1;
+
+  ++v;
+  for (i = 0; i < N; i++)
+    result *= v;
+
+  return result;
+}
+
+int
+main (void)
+{
+  int res;
+
+  check_vect ();
+
+  res = foo (1);
+  if (res != RES)
+    abort ();
+
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
+