Re: [PATCH] tree-optimization/110742 - fix latent issue with permuting existing vectors

Re: [PATCH] tree-optimization/110742 - fix latent issue with permuting existing vectors

[Richard Sandiford]

Richard Biener via Gcc-patches <gcc-patches@gcc.gnu.org> writes:
> When we materialize a layout we push edge permutes to constant/external
> defs without checking we can actually do so.  For externals defined
> by vector stmts rather than scalar components we can't.
>
> Bootstrapped and tested on x86_64-unknown-linux-gnu.
>
> OK?
>
> Thanks,
> Richard.
>
> 	PR tree-optimization/110742
> 	* tree-vect-slp.cc (vect_optimize_slp_pass::get_result_with_layout):
> 	Do not materialize an edge permutation in an external node with
> 	vector defs.
> 	(vect_slp_analyze_node_operations_1): Guard purely internal
> 	nodes better.
>
> 	* g++.dg/torture/pr110742.C: New testcase.
> ---
>  gcc/testsuite/g++.dg/torture/pr110742.C | 47 +++++++++++++++++++++++++
>  gcc/tree-vect-slp.cc                    |  8 +++--
>  2 files changed, 53 insertions(+), 2 deletions(-)
>  create mode 100644 gcc/testsuite/g++.dg/torture/pr110742.C
>
> diff --git a/gcc/testsuite/g++.dg/torture/pr110742.C b/gcc/testsuite/g++.dg/torture/pr110742.C
> new file mode 100644
> index 00000000000..d41ac0479d2
> --- /dev/null
> +++ b/gcc/testsuite/g++.dg/torture/pr110742.C
> @@ -0,0 +1,47 @@
> +// { dg-do compile }
> +
> +struct HARD_REG_SET {
> +  HARD_REG_SET operator~() const {
> +    HARD_REG_SET res;
> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
> +      res.elts[i] = ~elts[i];
> +    return res;
> +  }
> +  HARD_REG_SET operator&(const HARD_REG_SET &other) const {
> +    HARD_REG_SET res;
> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
> +      res.elts[i] = elts[i] & other.elts[i];
> +    return res;
> +  }
> +  unsigned long elts[4];
> +};
> +typedef const HARD_REG_SET &const_hard_reg_set;
> +inline bool hard_reg_set_subset_p(const_hard_reg_set x, const_hard_reg_set y) {
> +  unsigned long bad = 0;
> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
> +    bad |= (x.elts[i] & ~y.elts[i]);
> +  return bad == 0;
> +}
> +inline bool hard_reg_set_empty_p(const_hard_reg_set x) {
> +  unsigned long bad = 0;
> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
> +    bad |= x.elts[i];
> +  return bad == 0;
> +}
> +extern HARD_REG_SET rr[2];
> +extern int t[2];
> +extern HARD_REG_SET nn;
> +static HARD_REG_SET mm;
> +void setup_reg_class_relations(void) {
> +  HARD_REG_SET intersection_set, union_set, temp_set2;
> +  for (int cl2 = 0; cl2 < 2; cl2++) {
> +    temp_set2 = rr[cl2] & ~nn;
> +    if (hard_reg_set_empty_p(mm) && hard_reg_set_empty_p(temp_set2)) {
> +      mm = rr[0] & nn;
> +      if (hard_reg_set_subset_p(mm, intersection_set))
> +        if (!hard_reg_set_subset_p(mm, temp_set2) ||
> +            hard_reg_set_subset_p(rr[0], rr[t[cl2]]))
> +          t[cl2] = 0;
> +    }
> +  }
> +}
> diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
> index 693621ca990..1d79c77e8ce 100644
> --- a/gcc/tree-vect-slp.cc
> +++ b/gcc/tree-vect-slp.cc
> @@ -5198,7 +5198,10 @@ vect_optimize_slp_pass::get_result_with_layout (slp_tree node,
>      return result;
>  
>    if (SLP_TREE_DEF_TYPE (node) == vect_constant_def
> -      || SLP_TREE_DEF_TYPE (node) == vect_external_def)
> +      || (SLP_TREE_DEF_TYPE (node) == vect_external_def
> +	  && (to_layout_i == 0
> +	      /* We can't permute vector defs.  */
> +	      || SLP_TREE_VEC_DEFS (node).is_empty ())))

Guess it's personal preference, but IMO it's easier to follow without the
to_layout_i condition, so that it ties directly to the create_partitions
test.  (Would be nice to have a name for whatever a node matching the new
condition is, but I don't have any good ideas.)

LGTM otherwise FWIW.

Thanks,
Richard

>      {
>        /* If the vector is uniform or unchanged, there's nothing to do.  */
>        if (to_layout_i == 0 || vect_slp_tree_uniform_p (node))
> @@ -5944,7 +5947,8 @@ vect_slp_analyze_node_operations_1 (vec_info *vinfo, slp_tree node,
>       calculated by the recursive call).  Otherwise it is the number of
>       scalar elements in one scalar iteration (DR_GROUP_SIZE) multiplied by
>       VF divided by the number of elements in a vector.  */
> -  if (!STMT_VINFO_DATA_REF (stmt_info)
> +  if (SLP_TREE_CODE (node) != VEC_PERM_EXPR
> +      && !STMT_VINFO_DATA_REF (stmt_info)
>        && REDUC_GROUP_FIRST_ELEMENT (stmt_info))
>      {
>        for (unsigned i = 0; i < SLP_TREE_CHILDREN (node).length (); ++i)

Re: [PATCH] tree-optimization/110742 - fix latent issue with permuting existing vectors

[Richard Biener]

> Am 20.07.2023 um 16:09 schrieb Richard Sandiford <richard.sandiford@arm.com>:
> 
> Richard Biener via Gcc-patches <gcc-patches@gcc.gnu.org> writes:
>> When we materialize a layout we push edge permutes to constant/external
>> defs without checking we can actually do so.  For externals defined
>> by vector stmts rather than scalar components we can't.
>> 
>> Bootstrapped and tested on x86_64-unknown-linux-gnu.
>> 
>> OK?
>> 
>> Thanks,
>> Richard.
>> 
>>    PR tree-optimization/110742
>>    * tree-vect-slp.cc (vect_optimize_slp_pass::get_result_with_layout):
>>    Do not materialize an edge permutation in an external node with
>>    vector defs.
>>    (vect_slp_analyze_node_operations_1): Guard purely internal
>>    nodes better.
>> 
>>    * g++.dg/torture/pr110742.C: New testcase.
>> ---
>> gcc/testsuite/g++.dg/torture/pr110742.C | 47 +++++++++++++++++++++++++
>> gcc/tree-vect-slp.cc                    |  8 +++--
>> 2 files changed, 53 insertions(+), 2 deletions(-)
>> create mode 100644 gcc/testsuite/g++.dg/torture/pr110742.C
>> 
>> diff --git a/gcc/testsuite/g++.dg/torture/pr110742.C b/gcc/testsuite/g++.dg/torture/pr110742.C
>> new file mode 100644
>> index 00000000000..d41ac0479d2
>> --- /dev/null
>> +++ b/gcc/testsuite/g++.dg/torture/pr110742.C
>> @@ -0,0 +1,47 @@
>> +// { dg-do compile }
>> +
>> +struct HARD_REG_SET {
>> +  HARD_REG_SET operator~() const {
>> +    HARD_REG_SET res;
>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
>> +      res.elts[i] = ~elts[i];
>> +    return res;
>> +  }
>> +  HARD_REG_SET operator&(const HARD_REG_SET &other) const {
>> +    HARD_REG_SET res;
>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
>> +      res.elts[i] = elts[i] & other.elts[i];
>> +    return res;
>> +  }
>> +  unsigned long elts[4];
>> +};
>> +typedef const HARD_REG_SET &const_hard_reg_set;
>> +inline bool hard_reg_set_subset_p(const_hard_reg_set x, const_hard_reg_set y) {
>> +  unsigned long bad = 0;
>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
>> +    bad |= (x.elts[i] & ~y.elts[i]);
>> +  return bad == 0;
>> +}
>> +inline bool hard_reg_set_empty_p(const_hard_reg_set x) {
>> +  unsigned long bad = 0;
>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
>> +    bad |= x.elts[i];
>> +  return bad == 0;
>> +}
>> +extern HARD_REG_SET rr[2];
>> +extern int t[2];
>> +extern HARD_REG_SET nn;
>> +static HARD_REG_SET mm;
>> +void setup_reg_class_relations(void) {
>> +  HARD_REG_SET intersection_set, union_set, temp_set2;
>> +  for (int cl2 = 0; cl2 < 2; cl2++) {
>> +    temp_set2 = rr[cl2] & ~nn;
>> +    if (hard_reg_set_empty_p(mm) && hard_reg_set_empty_p(temp_set2)) {
>> +      mm = rr[0] & nn;
>> +      if (hard_reg_set_subset_p(mm, intersection_set))
>> +        if (!hard_reg_set_subset_p(mm, temp_set2) ||
>> +            hard_reg_set_subset_p(rr[0], rr[t[cl2]]))
>> +          t[cl2] = 0;
>> +    }
>> +  }
>> +}
>> diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
>> index 693621ca990..1d79c77e8ce 100644
>> --- a/gcc/tree-vect-slp.cc
>> +++ b/gcc/tree-vect-slp.cc
>> @@ -5198,7 +5198,10 @@ vect_optimize_slp_pass::get_result_with_layout (slp_tree node,
>>     return result;
>> 
>>   if (SLP_TREE_DEF_TYPE (node) == vect_constant_def
>> -      || SLP_TREE_DEF_TYPE (node) == vect_external_def)
>> +      || (SLP_TREE_DEF_TYPE (node) == vect_external_def
>> +      && (to_layout_i == 0
>> +          /* We can't permute vector defs.  */
>> +          || SLP_TREE_VEC_DEFS (node).is_empty ())))
> 
> Guess it's personal preference, but IMO it's easier to follow without the
> to_layout_i condition, so that it ties directly to the create_partitions
> test.

I don’t understand- in the code guarding this we seem to expect to_layout_i == 0 and that’s the case we can handle as noop.  I didn’t understand why the function doesn’t always just do nothing in this case though, so I must have missed something.

Richard 


>  (Would be nice to have a name for whatever a node matching the new
> condition is, but I don't have any good ideas.)
> 
> LGTM otherwise FWIW.
> 
> Thanks,
> Richard
> 
>>     {
>>       /* If the vector is uniform or unchanged, there's nothing to do.  */
>>       if (to_layout_i == 0 || vect_slp_tree_uniform_p (node))
>> @@ -5944,7 +5947,8 @@ vect_slp_analyze_node_operations_1 (vec_info *vinfo, slp_tree node,
>>      calculated by the recursive call).  Otherwise it is the number of
>>      scalar elements in one scalar iteration (DR_GROUP_SIZE) multiplied by
>>      VF divided by the number of elements in a vector.  */
>> -  if (!STMT_VINFO_DATA_REF (stmt_info)
>> +  if (SLP_TREE_CODE (node) != VEC_PERM_EXPR
>> +      && !STMT_VINFO_DATA_REF (stmt_info)
>>       && REDUC_GROUP_FIRST_ELEMENT (stmt_info))
>>     {
>>       for (unsigned i = 0; i < SLP_TREE_CHILDREN (node).length (); ++i)

Re: [PATCH] tree-optimization/110742 - fix latent issue with permuting existing vectors

[Richard Sandiford]

Richard Biener <rguenther@suse.de> writes:
>> Am 20.07.2023 um 16:09 schrieb Richard Sandiford <richard.sandiford@arm.com>:
>> 
>> Richard Biener via Gcc-patches <gcc-patches@gcc.gnu.org> writes:
>>> When we materialize a layout we push edge permutes to constant/external
>>> defs without checking we can actually do so.  For externals defined
>>> by vector stmts rather than scalar components we can't.
>>> 
>>> Bootstrapped and tested on x86_64-unknown-linux-gnu.
>>> 
>>> OK?
>>> 
>>> Thanks,
>>> Richard.
>>> 
>>>    PR tree-optimization/110742
>>>    * tree-vect-slp.cc (vect_optimize_slp_pass::get_result_with_layout):
>>>    Do not materialize an edge permutation in an external node with
>>>    vector defs.
>>>    (vect_slp_analyze_node_operations_1): Guard purely internal
>>>    nodes better.
>>> 
>>>    * g++.dg/torture/pr110742.C: New testcase.
>>> ---
>>> gcc/testsuite/g++.dg/torture/pr110742.C | 47 +++++++++++++++++++++++++
>>> gcc/tree-vect-slp.cc                    |  8 +++--
>>> 2 files changed, 53 insertions(+), 2 deletions(-)
>>> create mode 100644 gcc/testsuite/g++.dg/torture/pr110742.C
>>> 
>>> diff --git a/gcc/testsuite/g++.dg/torture/pr110742.C b/gcc/testsuite/g++.dg/torture/pr110742.C
>>> new file mode 100644
>>> index 00000000000..d41ac0479d2
>>> --- /dev/null
>>> +++ b/gcc/testsuite/g++.dg/torture/pr110742.C
>>> @@ -0,0 +1,47 @@
>>> +// { dg-do compile }
>>> +
>>> +struct HARD_REG_SET {
>>> +  HARD_REG_SET operator~() const {
>>> +    HARD_REG_SET res;
>>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
>>> +      res.elts[i] = ~elts[i];
>>> +    return res;
>>> +  }
>>> +  HARD_REG_SET operator&(const HARD_REG_SET &other) const {
>>> +    HARD_REG_SET res;
>>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
>>> +      res.elts[i] = elts[i] & other.elts[i];
>>> +    return res;
>>> +  }
>>> +  unsigned long elts[4];
>>> +};
>>> +typedef const HARD_REG_SET &const_hard_reg_set;
>>> +inline bool hard_reg_set_subset_p(const_hard_reg_set x, const_hard_reg_set y) {
>>> +  unsigned long bad = 0;
>>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
>>> +    bad |= (x.elts[i] & ~y.elts[i]);
>>> +  return bad == 0;
>>> +}
>>> +inline bool hard_reg_set_empty_p(const_hard_reg_set x) {
>>> +  unsigned long bad = 0;
>>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
>>> +    bad |= x.elts[i];
>>> +  return bad == 0;
>>> +}
>>> +extern HARD_REG_SET rr[2];
>>> +extern int t[2];
>>> +extern HARD_REG_SET nn;
>>> +static HARD_REG_SET mm;
>>> +void setup_reg_class_relations(void) {
>>> +  HARD_REG_SET intersection_set, union_set, temp_set2;
>>> +  for (int cl2 = 0; cl2 < 2; cl2++) {
>>> +    temp_set2 = rr[cl2] & ~nn;
>>> +    if (hard_reg_set_empty_p(mm) && hard_reg_set_empty_p(temp_set2)) {
>>> +      mm = rr[0] & nn;
>>> +      if (hard_reg_set_subset_p(mm, intersection_set))
>>> +        if (!hard_reg_set_subset_p(mm, temp_set2) ||
>>> +            hard_reg_set_subset_p(rr[0], rr[t[cl2]]))
>>> +          t[cl2] = 0;
>>> +    }
>>> +  }
>>> +}
>>> diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
>>> index 693621ca990..1d79c77e8ce 100644
>>> --- a/gcc/tree-vect-slp.cc
>>> +++ b/gcc/tree-vect-slp.cc
>>> @@ -5198,7 +5198,10 @@ vect_optimize_slp_pass::get_result_with_layout (slp_tree node,
>>>     return result;
>>> 
>>>   if (SLP_TREE_DEF_TYPE (node) == vect_constant_def
>>> -      || SLP_TREE_DEF_TYPE (node) == vect_external_def)
>>> +      || (SLP_TREE_DEF_TYPE (node) == vect_external_def
>>> +      && (to_layout_i == 0
>>> +          /* We can't permute vector defs.  */
>>> +          || SLP_TREE_VEC_DEFS (node).is_empty ())))
>> 
>> Guess it's personal preference, but IMO it's easier to follow without the
>> to_layout_i condition, so that it ties directly to the create_partitions
>> test.
>
> I don’t understand- in the code guarding this we seem to expect to_layout_i == 0 and that’s the case we can handle as noop.  I didn’t understand why the function doesn’t always just do nothing in this case though, so I must have missed something.

OK, so I guess that disproves that my way is easier to understand :)

I think logically, the code is doing the equivalent of:

  int partition_i = m_vertices[node->vertex].partition;
  if (partition < 0)
    {
      /* If the vector is uniform or unchanged, there's nothing to do.  */
      ...      
    }
  else
    {
      ... Return node if to_layout_i matches this partition's chosen layout...
    }

And I guess I should have written it that way.

So when there is no partition, we have a constant or external def
built from individual scalars.  We can use the node as-is if the
caller wants an unpermuted node or if all elements are equal
(so that the permutation doesn't matter).  Otherwise we need
to permute the scalars.

When there is a partition, we can use the node as-is if the caller
wants the layout that was chosen for that partition.  Otherwise we
need a new VEC_PERM_EXPR node.

In the particular case of external defs built from vectors, we're
guaranteed that the node's chosen layout is 0 (i.e. the original layout),
and so both ways work.  But in principle this case fits the "else" arm
better than the "then" arm, because we're dealing with a node that is in
a partition, and that is not built from scalars.

Thanks,
Richard

Re: [PATCH] tree-optimization/110742 - fix latent issue with permuting existing vectors

[Richard Biener]

> Am 20.07.2023 um 18:59 schrieb Richard Sandiford <richard.sandiford@arm.com>:
> 
> Richard Biener <rguenther@suse.de> writes:
>>>> Am 20.07.2023 um 16:09 schrieb Richard Sandiford <richard.sandiford@arm.com>:
>>> 
>>> Richard Biener via Gcc-patches <gcc-patches@gcc.gnu.org> writes:
>>>> When we materialize a layout we push edge permutes to constant/external
>>>> defs without checking we can actually do so.  For externals defined
>>>> by vector stmts rather than scalar components we can't.
>>>> 
>>>> Bootstrapped and tested on x86_64-unknown-linux-gnu.
>>>> 
>>>> OK?
>>>> 
>>>> Thanks,
>>>> Richard.
>>>> 
>>>>   PR tree-optimization/110742
>>>>   * tree-vect-slp.cc (vect_optimize_slp_pass::get_result_with_layout):
>>>>   Do not materialize an edge permutation in an external node with
>>>>   vector defs.
>>>>   (vect_slp_analyze_node_operations_1): Guard purely internal
>>>>   nodes better.
>>>> 
>>>>   * g++.dg/torture/pr110742.C: New testcase.
>>>> ---
>>>> gcc/testsuite/g++.dg/torture/pr110742.C | 47 +++++++++++++++++++++++++
>>>> gcc/tree-vect-slp.cc                    |  8 +++--
>>>> 2 files changed, 53 insertions(+), 2 deletions(-)
>>>> create mode 100644 gcc/testsuite/g++.dg/torture/pr110742.C
>>>> 
>>>> diff --git a/gcc/testsuite/g++.dg/torture/pr110742.C b/gcc/testsuite/g++.dg/torture/pr110742.C
>>>> new file mode 100644
>>>> index 00000000000..d41ac0479d2
>>>> --- /dev/null
>>>> +++ b/gcc/testsuite/g++.dg/torture/pr110742.C
>>>> @@ -0,0 +1,47 @@
>>>> +// { dg-do compile }
>>>> +
>>>> +struct HARD_REG_SET {
>>>> +  HARD_REG_SET operator~() const {
>>>> +    HARD_REG_SET res;
>>>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
>>>> +      res.elts[i] = ~elts[i];
>>>> +    return res;
>>>> +  }
>>>> +  HARD_REG_SET operator&(const HARD_REG_SET &other) const {
>>>> +    HARD_REG_SET res;
>>>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
>>>> +      res.elts[i] = elts[i] & other.elts[i];
>>>> +    return res;
>>>> +  }
>>>> +  unsigned long elts[4];
>>>> +};
>>>> +typedef const HARD_REG_SET &const_hard_reg_set;
>>>> +inline bool hard_reg_set_subset_p(const_hard_reg_set x, const_hard_reg_set y) {
>>>> +  unsigned long bad = 0;
>>>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
>>>> +    bad |= (x.elts[i] & ~y.elts[i]);
>>>> +  return bad == 0;
>>>> +}
>>>> +inline bool hard_reg_set_empty_p(const_hard_reg_set x) {
>>>> +  unsigned long bad = 0;
>>>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
>>>> +    bad |= x.elts[i];
>>>> +  return bad == 0;
>>>> +}
>>>> +extern HARD_REG_SET rr[2];
>>>> +extern int t[2];
>>>> +extern HARD_REG_SET nn;
>>>> +static HARD_REG_SET mm;
>>>> +void setup_reg_class_relations(void) {
>>>> +  HARD_REG_SET intersection_set, union_set, temp_set2;
>>>> +  for (int cl2 = 0; cl2 < 2; cl2++) {
>>>> +    temp_set2 = rr[cl2] & ~nn;
>>>> +    if (hard_reg_set_empty_p(mm) && hard_reg_set_empty_p(temp_set2)) {
>>>> +      mm = rr[0] & nn;
>>>> +      if (hard_reg_set_subset_p(mm, intersection_set))
>>>> +        if (!hard_reg_set_subset_p(mm, temp_set2) ||
>>>> +            hard_reg_set_subset_p(rr[0], rr[t[cl2]]))
>>>> +          t[cl2] = 0;
>>>> +    }
>>>> +  }
>>>> +}
>>>> diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
>>>> index 693621ca990..1d79c77e8ce 100644
>>>> --- a/gcc/tree-vect-slp.cc
>>>> +++ b/gcc/tree-vect-slp.cc
>>>> @@ -5198,7 +5198,10 @@ vect_optimize_slp_pass::get_result_with_layout (slp_tree node,
>>>>    return result;
>>>> 
>>>>  if (SLP_TREE_DEF_TYPE (node) == vect_constant_def
>>>> -      || SLP_TREE_DEF_TYPE (node) == vect_external_def)
>>>> +      || (SLP_TREE_DEF_TYPE (node) == vect_external_def
>>>> +      && (to_layout_i == 0
>>>> +          /* We can't permute vector defs.  */
>>>> +          || SLP_TREE_VEC_DEFS (node).is_empty ())))
>>> 
>>> Guess it's personal preference, but IMO it's easier to follow without the
>>> to_layout_i condition, so that it ties directly to the create_partitions
>>> test.
>> 
>> I don’t understand- in the code guarding this we seem to expect to_layout_i == 0 and that’s the case we can handle as noop.  I didn’t understand why the function doesn’t always just do nothing in this case though, so I must have missed something.
> 
> OK, so I guess that disproves that my way is easier to understand :)
> 
> I think logically, the code is doing the equivalent of:
> 
>  int partition_i = m_vertices[node->vertex].partition;
>  if (partition < 0)
>    {
>      /* If the vector is uniform or unchanged, there's nothing to do.  */
>      ...      
>    }
>  else
>    {
>      ... Return node if to_layout_i matches this partition's chosen layout...
>    }
> 
> And I guess I should have written it that way.
> 
> So when there is no partition, we have a constant or external def
> built from individual scalars.  We can use the node as-is if the
> caller wants an unpermuted node or if all elements are equal
> (so that the permutation doesn't matter).  Otherwise we need
> to permute the scalars.
> 
> When there is a partition, we can use the node as-is if the caller
> wants the layout that was chosen for that partition.  Otherwise we
> need a new VEC_PERM_EXPR node.
> 
> In the particular case of external defs built from vectors, we're
> guaranteed that the node's chosen layout is 0 (i.e. the original layout),
> and so both ways work.

Hmm, but I arrived here with that not being the case … (the chosen Lay-out not zero)


>  But in principle this case fits the "else" arm
> better than the "then" arm, because we're dealing with a node that is in
> a partition, and that is not built from scalars.
> 
> Thanks,
> Richard

Re: [PATCH] tree-optimization/110742 - fix latent issue with permuting existing vectors

[Richard Sandiford]

Richard Biener <rguenther@suse.de> writes:
>> Am 20.07.2023 um 18:59 schrieb Richard Sandiford <richard.sandiford@arm.com>:
>> 
>> Richard Biener <rguenther@suse.de> writes:
>>>>> Am 20.07.2023 um 16:09 schrieb Richard Sandiford <richard.sandiford@arm.com>:
>>>> 
>>>> Richard Biener via Gcc-patches <gcc-patches@gcc.gnu.org> writes:
>>>>> When we materialize a layout we push edge permutes to constant/external
>>>>> defs without checking we can actually do so.  For externals defined
>>>>> by vector stmts rather than scalar components we can't.
>>>>> 
>>>>> Bootstrapped and tested on x86_64-unknown-linux-gnu.
>>>>> 
>>>>> OK?
>>>>> 
>>>>> Thanks,
>>>>> Richard.
>>>>> 
>>>>>   PR tree-optimization/110742
>>>>>   * tree-vect-slp.cc (vect_optimize_slp_pass::get_result_with_layout):
>>>>>   Do not materialize an edge permutation in an external node with
>>>>>   vector defs.
>>>>>   (vect_slp_analyze_node_operations_1): Guard purely internal
>>>>>   nodes better.
>>>>> 
>>>>>   * g++.dg/torture/pr110742.C: New testcase.
>>>>> ---
>>>>> gcc/testsuite/g++.dg/torture/pr110742.C | 47 +++++++++++++++++++++++++
>>>>> gcc/tree-vect-slp.cc                    |  8 +++--
>>>>> 2 files changed, 53 insertions(+), 2 deletions(-)
>>>>> create mode 100644 gcc/testsuite/g++.dg/torture/pr110742.C
>>>>> 
>>>>> diff --git a/gcc/testsuite/g++.dg/torture/pr110742.C b/gcc/testsuite/g++.dg/torture/pr110742.C
>>>>> new file mode 100644
>>>>> index 00000000000..d41ac0479d2
>>>>> --- /dev/null
>>>>> +++ b/gcc/testsuite/g++.dg/torture/pr110742.C
>>>>> @@ -0,0 +1,47 @@
>>>>> +// { dg-do compile }
>>>>> +
>>>>> +struct HARD_REG_SET {
>>>>> +  HARD_REG_SET operator~() const {
>>>>> +    HARD_REG_SET res;
>>>>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
>>>>> +      res.elts[i] = ~elts[i];
>>>>> +    return res;
>>>>> +  }
>>>>> +  HARD_REG_SET operator&(const HARD_REG_SET &other) const {
>>>>> +    HARD_REG_SET res;
>>>>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
>>>>> +      res.elts[i] = elts[i] & other.elts[i];
>>>>> +    return res;
>>>>> +  }
>>>>> +  unsigned long elts[4];
>>>>> +};
>>>>> +typedef const HARD_REG_SET &const_hard_reg_set;
>>>>> +inline bool hard_reg_set_subset_p(const_hard_reg_set x, const_hard_reg_set y) {
>>>>> +  unsigned long bad = 0;
>>>>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
>>>>> +    bad |= (x.elts[i] & ~y.elts[i]);
>>>>> +  return bad == 0;
>>>>> +}
>>>>> +inline bool hard_reg_set_empty_p(const_hard_reg_set x) {
>>>>> +  unsigned long bad = 0;
>>>>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
>>>>> +    bad |= x.elts[i];
>>>>> +  return bad == 0;
>>>>> +}
>>>>> +extern HARD_REG_SET rr[2];
>>>>> +extern int t[2];
>>>>> +extern HARD_REG_SET nn;
>>>>> +static HARD_REG_SET mm;
>>>>> +void setup_reg_class_relations(void) {
>>>>> +  HARD_REG_SET intersection_set, union_set, temp_set2;
>>>>> +  for (int cl2 = 0; cl2 < 2; cl2++) {
>>>>> +    temp_set2 = rr[cl2] & ~nn;
>>>>> +    if (hard_reg_set_empty_p(mm) && hard_reg_set_empty_p(temp_set2)) {
>>>>> +      mm = rr[0] & nn;
>>>>> +      if (hard_reg_set_subset_p(mm, intersection_set))
>>>>> +        if (!hard_reg_set_subset_p(mm, temp_set2) ||
>>>>> +            hard_reg_set_subset_p(rr[0], rr[t[cl2]]))
>>>>> +          t[cl2] = 0;
>>>>> +    }
>>>>> +  }
>>>>> +}
>>>>> diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
>>>>> index 693621ca990..1d79c77e8ce 100644
>>>>> --- a/gcc/tree-vect-slp.cc
>>>>> +++ b/gcc/tree-vect-slp.cc
>>>>> @@ -5198,7 +5198,10 @@ vect_optimize_slp_pass::get_result_with_layout (slp_tree node,
>>>>>    return result;
>>>>> 
>>>>>  if (SLP_TREE_DEF_TYPE (node) == vect_constant_def
>>>>> -      || SLP_TREE_DEF_TYPE (node) == vect_external_def)
>>>>> +      || (SLP_TREE_DEF_TYPE (node) == vect_external_def
>>>>> +      && (to_layout_i == 0
>>>>> +          /* We can't permute vector defs.  */
>>>>> +          || SLP_TREE_VEC_DEFS (node).is_empty ())))
>>>> 
>>>> Guess it's personal preference, but IMO it's easier to follow without the
>>>> to_layout_i condition, so that it ties directly to the create_partitions
>>>> test.
>>> 
>>> I don’t understand- in the code guarding this we seem to expect to_layout_i == 0 and that’s the case we can handle as noop.  I didn’t understand why the function doesn’t always just do nothing in this case though, so I must have missed something.
>> 
>> OK, so I guess that disproves that my way is easier to understand :)
>> 
>> I think logically, the code is doing the equivalent of:
>> 
>>  int partition_i = m_vertices[node->vertex].partition;
>>  if (partition < 0)
>>    {
>>      /* If the vector is uniform or unchanged, there's nothing to do.  */
>>      ...      
>>    }
>>  else
>>    {
>>      ... Return node if to_layout_i matches this partition's chosen layout...
>>    }
>> 
>> And I guess I should have written it that way.
>> 
>> So when there is no partition, we have a constant or external def
>> built from individual scalars.  We can use the node as-is if the
>> caller wants an unpermuted node or if all elements are equal
>> (so that the permutation doesn't matter).  Otherwise we need
>> to permute the scalars.
>> 
>> When there is a partition, we can use the node as-is if the caller
>> wants the layout that was chosen for that partition.  Otherwise we
>> need a new VEC_PERM_EXPR node.
>> 
>> In the particular case of external defs built from vectors, we're
>> guaranteed that the node's chosen layout is 0 (i.e. the original layout),
>> and so both ways work.
>
> Hmm, but I arrived here with that not being the case … (the chosen Lay-out not zero)

By chosen layout for the partition, I meant:

      unsigned int from_layout_i = m_partitions[partition_i].layout;

That should be 0 for these external vector nodes due to the
start_choosing_layout code that you mentioned in the PR.  to_layout_i
(the layout that the caller wants for a use of the node) can be anything,
so yeah, to_layout_i != 0 has to go through the "else" arm and generate
a VEC_PERM_EXPR.  But because from_layout_i == 0 for these nodes,
the "else" arm should handle all cases correctly, not just the
to_layout_i != 0 case.

Thanks,
Richard

Re: [PATCH] tree-optimization/110742 - fix latent issue with permuting existing vectors

[Richard Biener]

[-- Attachment #1: Type: text/plain, Size: 6669 bytes --]

On Thu, 20 Jul 2023, Richard Sandiford wrote:

> Richard Biener <rguenther@suse.de> writes:
> >> Am 20.07.2023 um 18:59 schrieb Richard Sandiford <richard.sandiford@arm.com>:
> >> 
> >> Richard Biener <rguenther@suse.de> writes:
> >>>>> Am 20.07.2023 um 16:09 schrieb Richard Sandiford <richard.sandiford@arm.com>:
> >>>> 
> >>>> Richard Biener via Gcc-patches <gcc-patches@gcc.gnu.org> writes:
> >>>>> When we materialize a layout we push edge permutes to constant/external
> >>>>> defs without checking we can actually do so.  For externals defined
> >>>>> by vector stmts rather than scalar components we can't.
> >>>>> 
> >>>>> Bootstrapped and tested on x86_64-unknown-linux-gnu.
> >>>>> 
> >>>>> OK?
> >>>>> 
> >>>>> Thanks,
> >>>>> Richard.
> >>>>> 
> >>>>>   PR tree-optimization/110742
> >>>>>   * tree-vect-slp.cc (vect_optimize_slp_pass::get_result_with_layout):
> >>>>>   Do not materialize an edge permutation in an external node with
> >>>>>   vector defs.
> >>>>>   (vect_slp_analyze_node_operations_1): Guard purely internal
> >>>>>   nodes better.
> >>>>> 
> >>>>>   * g++.dg/torture/pr110742.C: New testcase.
> >>>>> ---
> >>>>> gcc/testsuite/g++.dg/torture/pr110742.C | 47 +++++++++++++++++++++++++
> >>>>> gcc/tree-vect-slp.cc                    |  8 +++--
> >>>>> 2 files changed, 53 insertions(+), 2 deletions(-)
> >>>>> create mode 100644 gcc/testsuite/g++.dg/torture/pr110742.C
> >>>>> 
> >>>>> diff --git a/gcc/testsuite/g++.dg/torture/pr110742.C b/gcc/testsuite/g++.dg/torture/pr110742.C
> >>>>> new file mode 100644
> >>>>> index 00000000000..d41ac0479d2
> >>>>> --- /dev/null
> >>>>> +++ b/gcc/testsuite/g++.dg/torture/pr110742.C
> >>>>> @@ -0,0 +1,47 @@
> >>>>> +// { dg-do compile }
> >>>>> +
> >>>>> +struct HARD_REG_SET {
> >>>>> +  HARD_REG_SET operator~() const {
> >>>>> +    HARD_REG_SET res;
> >>>>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
> >>>>> +      res.elts[i] = ~elts[i];
> >>>>> +    return res;
> >>>>> +  }
> >>>>> +  HARD_REG_SET operator&(const HARD_REG_SET &other) const {
> >>>>> +    HARD_REG_SET res;
> >>>>> +    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
> >>>>> +      res.elts[i] = elts[i] & other.elts[i];
> >>>>> +    return res;
> >>>>> +  }
> >>>>> +  unsigned long elts[4];
> >>>>> +};
> >>>>> +typedef const HARD_REG_SET &const_hard_reg_set;
> >>>>> +inline bool hard_reg_set_subset_p(const_hard_reg_set x, const_hard_reg_set y) {
> >>>>> +  unsigned long bad = 0;
> >>>>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
> >>>>> +    bad |= (x.elts[i] & ~y.elts[i]);
> >>>>> +  return bad == 0;
> >>>>> +}
> >>>>> +inline bool hard_reg_set_empty_p(const_hard_reg_set x) {
> >>>>> +  unsigned long bad = 0;
> >>>>> +  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
> >>>>> +    bad |= x.elts[i];
> >>>>> +  return bad == 0;
> >>>>> +}
> >>>>> +extern HARD_REG_SET rr[2];
> >>>>> +extern int t[2];
> >>>>> +extern HARD_REG_SET nn;
> >>>>> +static HARD_REG_SET mm;
> >>>>> +void setup_reg_class_relations(void) {
> >>>>> +  HARD_REG_SET intersection_set, union_set, temp_set2;
> >>>>> +  for (int cl2 = 0; cl2 < 2; cl2++) {
> >>>>> +    temp_set2 = rr[cl2] & ~nn;
> >>>>> +    if (hard_reg_set_empty_p(mm) && hard_reg_set_empty_p(temp_set2)) {
> >>>>> +      mm = rr[0] & nn;
> >>>>> +      if (hard_reg_set_subset_p(mm, intersection_set))
> >>>>> +        if (!hard_reg_set_subset_p(mm, temp_set2) ||
> >>>>> +            hard_reg_set_subset_p(rr[0], rr[t[cl2]]))
> >>>>> +          t[cl2] = 0;
> >>>>> +    }
> >>>>> +  }
> >>>>> +}
> >>>>> diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
> >>>>> index 693621ca990..1d79c77e8ce 100644
> >>>>> --- a/gcc/tree-vect-slp.cc
> >>>>> +++ b/gcc/tree-vect-slp.cc
> >>>>> @@ -5198,7 +5198,10 @@ vect_optimize_slp_pass::get_result_with_layout (slp_tree node,
> >>>>>    return result;
> >>>>> 
> >>>>>  if (SLP_TREE_DEF_TYPE (node) == vect_constant_def
> >>>>> -      || SLP_TREE_DEF_TYPE (node) == vect_external_def)
> >>>>> +      || (SLP_TREE_DEF_TYPE (node) == vect_external_def
> >>>>> +      && (to_layout_i == 0
> >>>>> +          /* We can't permute vector defs.  */
> >>>>> +          || SLP_TREE_VEC_DEFS (node).is_empty ())))
> >>>> 
> >>>> Guess it's personal preference, but IMO it's easier to follow without the
> >>>> to_layout_i condition, so that it ties directly to the create_partitions
> >>>> test.
> >>> 
> >>> I don?t understand- in the code guarding this we seem to expect to_layout_i == 0 and that?s the case we can handle as noop.  I didn?t understand why the function doesn?t always just do nothing in this case though, so I must have missed something.
> >> 
> >> OK, so I guess that disproves that my way is easier to understand :)
> >> 
> >> I think logically, the code is doing the equivalent of:
> >> 
> >>  int partition_i = m_vertices[node->vertex].partition;
> >>  if (partition < 0)
> >>    {
> >>      /* If the vector is uniform or unchanged, there's nothing to do.  */
> >>      ...      
> >>    }
> >>  else
> >>    {
> >>      ... Return node if to_layout_i matches this partition's chosen layout...
> >>    }
> >> 
> >> And I guess I should have written it that way.
> >> 
> >> So when there is no partition, we have a constant or external def
> >> built from individual scalars.  We can use the node as-is if the
> >> caller wants an unpermuted node or if all elements are equal
> >> (so that the permutation doesn't matter).  Otherwise we need
> >> to permute the scalars.
> >> 
> >> When there is a partition, we can use the node as-is if the caller
> >> wants the layout that was chosen for that partition.  Otherwise we
> >> need a new VEC_PERM_EXPR node.
> >> 
> >> In the particular case of external defs built from vectors, we're
> >> guaranteed that the node's chosen layout is 0 (i.e. the original layout),
> >> and so both ways work.
> >
> > Hmm, but I arrived here with that not being the case ? (the chosen Lay-out not zero)
> 
> By chosen layout for the partition, I meant:
> 
>       unsigned int from_layout_i = m_partitions[partition_i].layout;
> 
> That should be 0 for these external vector nodes due to the
> start_choosing_layout code that you mentioned in the PR.  to_layout_i
> (the layout that the caller wants for a use of the node) can be anything,
> so yeah, to_layout_i != 0 has to go through the "else" arm and generate
> a VEC_PERM_EXPR.  But because from_layout_i == 0 for these nodes,
> the "else" arm should handle all cases correctly, not just the
> to_layout_i != 0 case.

Ah, yes - of course.  I'll remove the extra test, re-test and push.

Thanks,
Richard.

Re: [PATCH] tree-optimization/110742 - fix latent issue with permuting existing vectors

[Jeff Law]

On 7/20/23 06:38, Richard Biener via Gcc-patches wrote:
> When we materialize a layout we push edge permutes to constant/external
> defs without checking we can actually do so.  For externals defined
> by vector stmts rather than scalar components we can't.
> 
> Bootstrapped and tested on x86_64-unknown-linux-gnu.
> 
> OK?
> 
> Thanks,
> Richard.
> 
> 	PR tree-optimization/110742
> 	* tree-vect-slp.cc (vect_optimize_slp_pass::get_result_with_layout):
> 	Do not materialize an edge permutation in an external node with
> 	vector defs.
> 	(vect_slp_analyze_node_operations_1): Guard purely internal
> 	nodes better.
> 
> 	* g++.dg/torture/pr110742.C: New testcase.
OK
jeff

[PATCH] tree-optimization/110742 - fix latent issue with permuting existing vectors

[Richard Biener]

When we materialize a layout we push edge permutes to constant/external
defs without checking we can actually do so.  For externals defined
by vector stmts rather than scalar components we can't.

Bootstrapped and tested on x86_64-unknown-linux-gnu.

OK?

Thanks,
Richard.

	PR tree-optimization/110742
	* tree-vect-slp.cc (vect_optimize_slp_pass::get_result_with_layout):
	Do not materialize an edge permutation in an external node with
	vector defs.
	(vect_slp_analyze_node_operations_1): Guard purely internal
	nodes better.

	* g++.dg/torture/pr110742.C: New testcase.
---
 gcc/testsuite/g++.dg/torture/pr110742.C | 47 +++++++++++++++++++++++++
 gcc/tree-vect-slp.cc                    |  8 +++--
 2 files changed, 53 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/g++.dg/torture/pr110742.C

diff --git a/gcc/testsuite/g++.dg/torture/pr110742.C b/gcc/testsuite/g++.dg/torture/pr110742.C
new file mode 100644
index 00000000000..d41ac0479d2
--- /dev/null
+++ b/gcc/testsuite/g++.dg/torture/pr110742.C
@@ -0,0 +1,47 @@
+// { dg-do compile }
+
+struct HARD_REG_SET {
+  HARD_REG_SET operator~() const {
+    HARD_REG_SET res;
+    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
+      res.elts[i] = ~elts[i];
+    return res;
+  }
+  HARD_REG_SET operator&(const HARD_REG_SET &other) const {
+    HARD_REG_SET res;
+    for (unsigned int i = 0; i < (sizeof(elts) / sizeof((elts)[0])); ++i)
+      res.elts[i] = elts[i] & other.elts[i];
+    return res;
+  }
+  unsigned long elts[4];
+};
+typedef const HARD_REG_SET &const_hard_reg_set;
+inline bool hard_reg_set_subset_p(const_hard_reg_set x, const_hard_reg_set y) {
+  unsigned long bad = 0;
+  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
+    bad |= (x.elts[i] & ~y.elts[i]);
+  return bad == 0;
+}
+inline bool hard_reg_set_empty_p(const_hard_reg_set x) {
+  unsigned long bad = 0;
+  for (unsigned int i = 0; i < (sizeof(x.elts) / sizeof((x.elts)[0])); ++i)
+    bad |= x.elts[i];
+  return bad == 0;
+}
+extern HARD_REG_SET rr[2];
+extern int t[2];
+extern HARD_REG_SET nn;
+static HARD_REG_SET mm;
+void setup_reg_class_relations(void) {
+  HARD_REG_SET intersection_set, union_set, temp_set2;
+  for (int cl2 = 0; cl2 < 2; cl2++) {
+    temp_set2 = rr[cl2] & ~nn;
+    if (hard_reg_set_empty_p(mm) && hard_reg_set_empty_p(temp_set2)) {
+      mm = rr[0] & nn;
+      if (hard_reg_set_subset_p(mm, intersection_set))
+        if (!hard_reg_set_subset_p(mm, temp_set2) ||
+            hard_reg_set_subset_p(rr[0], rr[t[cl2]]))
+          t[cl2] = 0;
+    }
+  }
+}
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 693621ca990..1d79c77e8ce 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -5198,7 +5198,10 @@ vect_optimize_slp_pass::get_result_with_layout (slp_tree node,
     return result;
 
   if (SLP_TREE_DEF_TYPE (node) == vect_constant_def
-      || SLP_TREE_DEF_TYPE (node) == vect_external_def)
+      || (SLP_TREE_DEF_TYPE (node) == vect_external_def
+	  && (to_layout_i == 0
+	      /* We can't permute vector defs.  */
+	      || SLP_TREE_VEC_DEFS (node).is_empty ())))
     {
       /* If the vector is uniform or unchanged, there's nothing to do.  */
       if (to_layout_i == 0 || vect_slp_tree_uniform_p (node))
@@ -5944,7 +5947,8 @@ vect_slp_analyze_node_operations_1 (vec_info *vinfo, slp_tree node,
      calculated by the recursive call).  Otherwise it is the number of
      scalar elements in one scalar iteration (DR_GROUP_SIZE) multiplied by
      VF divided by the number of elements in a vector.  */
-  if (!STMT_VINFO_DATA_REF (stmt_info)
+  if (SLP_TREE_CODE (node) != VEC_PERM_EXPR
+      && !STMT_VINFO_DATA_REF (stmt_info)
       && REDUC_GROUP_FIRST_ELEMENT (stmt_info))
     {
       for (unsigned i = 0; i < SLP_TREE_CHILDREN (node).length (); ++i)
-- 
2.35.3