[gcc(refs/vendors/vrull/heads/slp-improvements)] match.pd: Look through view_convert when folding vec_perms

[gcc(refs/vendors/vrull/heads/slp-improvements)] match.pd: Look through view_convert when folding vec_perms

[Philipp Tomsich]

https://gcc.gnu.org/g:e9bbe3d12c929449053eadb485bcfa5586d311e0

commit e9bbe3d12c929449053eadb485bcfa5586d311e0
Author: Manolis Tsamis <manolis.tsamis@vrull.eu>
Date:   Wed Nov 1 12:27:28 2023 +0100

    match.pd: Look through view_convert when folding vec_perms
    
    The match.pd patterns to merge two vector permutes into one fail to
    match when a (potentially no-op) view convert expressions is
    separating the two permutes.  This is observable in the SLP tree for
    the first loop of x264's satd and inhibits optimization.
    
    This change adds a check whether a view_convert will be a no-op
    (comparing the element precision) and rewrites the permute sequence
    for those cases.
    
    Ref #343

Diff:
---
 gcc/match.pd | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/gcc/match.pd b/gcc/match.pd
index b30de36e836..c41e1f8796b 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -9818,7 +9818,7 @@ and,
      d = VEC_PERM_EXPR <a, b, NEW_VCST>;  */
 
 (simplify
- (vec_perm (vec_perm@0 @1 @2 VECTOR_CST@3) @0 VECTOR_CST@4)
+ (vec_perm (view_convert?@0 (vec_perm @1 @2 VECTOR_CST@3)) @0 VECTOR_CST@4)
  (if (TYPE_VECTOR_SUBPARTS (type).is_constant ())
   (with
    {
@@ -9830,7 +9830,8 @@ and,
      vec_perm_builder builder2 (nelts, nelts, 1);
    }
    (if (tree_to_vec_perm_builder (&builder0, @3)
-	&& tree_to_vec_perm_builder (&builder1, @4))
+	&& tree_to_vec_perm_builder (&builder1, @4)
+	&& element_precision (type) == element_precision (TREE_TYPE (@0)))
     (with
      {
        vec_perm_indices sel0 (builder0, 2, nelts);
@@ -9855,7 +9856,7 @@ and,
 	 op0 = vec_perm_indices_to_tree (TREE_TYPE (@4), sel2);
      }
      (if (op0)
-      (vec_perm @1 @2 { op0; })))))))
+      (view_convert (vec_perm @1 @2 { op0; }))))))))
 
 /* Merge
      c = VEC_PERM_EXPR <a, b, VCST0>;

[gcc(refs/vendors/vrull/heads/slp-improvements)] match.pd: Look through view_convert when folding vec_perms

[Philipp Tomsich]

https://gcc.gnu.org/g:89a6e3d55d5b4422f6be334cfd8ea4127917068f

commit 89a6e3d55d5b4422f6be334cfd8ea4127917068f
Author: Manolis Tsamis <manolis.tsamis@vrull.eu>
Date:   Wed Nov 1 12:27:28 2023 +0100

    match.pd: Look through view_convert when folding vec_perms
    
    The match.pd patterns to merge two vector permutes into one fail to
    match when a (potentially no-op) view convert expressions is
    separating the two permutes.  This is observable in the SLP tree for
    the first loop of x264's satd and inhibits optimization.
    
    This change adds a check whether a view_convert will be a no-op
    (comparing the element precision) and rewrites the permute sequence
    for those cases.
    
    Ref #343

Diff:
---
 gcc/match.pd | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/gcc/match.pd b/gcc/match.pd
index 7b4b15acc41..59a664293ea 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -9929,7 +9929,7 @@ and,
      d = VEC_PERM_EXPR <a, b, NEW_VCST>;  */
 
 (simplify
- (vec_perm (vec_perm@0 @1 @2 VECTOR_CST@3) @0 VECTOR_CST@4)
+ (vec_perm (view_convert?@0 (vec_perm @1 @2 VECTOR_CST@3)) @0 VECTOR_CST@4)
  (if (TYPE_VECTOR_SUBPARTS (type).is_constant ())
   (with
    {
@@ -9941,7 +9941,8 @@ and,
      vec_perm_builder builder2 (nelts, nelts, 1);
    }
    (if (tree_to_vec_perm_builder (&builder0, @3)
-	&& tree_to_vec_perm_builder (&builder1, @4))
+	&& tree_to_vec_perm_builder (&builder1, @4)
+	&& element_precision (type) == element_precision (TREE_TYPE (@0)))
     (with
      {
        vec_perm_indices sel0 (builder0, 2, nelts);
@@ -9966,7 +9967,7 @@ and,
 	 op0 = vec_perm_indices_to_tree (TREE_TYPE (@4), sel2);
      }
      (if (op0)
-      (vec_perm @1 @2 { op0; })))))))
+      (view_convert (vec_perm @1 @2 { op0; }))))))))
 
 /* Merge
      c = VEC_PERM_EXPR <a, b, VCST0>;

[gcc(refs/vendors/vrull/heads/slp-improvements)] match.pd: Look through view_convert when folding vec_perms

[Philipp Tomsich]

https://gcc.gnu.org/g:b896c82f141211437b5b5b83a3537d6bd2d243dc

commit b896c82f141211437b5b5b83a3537d6bd2d243dc
Author: Manolis Tsamis <manolis.tsamis@vrull.eu>
Date:   Wed Nov 1 12:27:28 2023 +0100

    match.pd: Look through view_convert when folding vec_perms
    
    The match.pd patterns to merge two vector permutes into one fail to
    match when a (potentially no-op) view convert expressions is
    separating the two permutes.  This is observable in the SLP tree for
    the first loop of x264's satd and inhibits optimization.
    
    This change adds a check whether a view_convert will be a no-op
    (comparing the element precision) and rewrites the permute sequence
    for those cases.
    
    Ref #343

Diff:
---
 gcc/match.pd | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/gcc/match.pd b/gcc/match.pd
index e42ecaf9ec7..be623d9773c 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -9965,7 +9965,7 @@ and,
      d = VEC_PERM_EXPR <a, b, NEW_VCST>;  */
 
 (simplify
- (vec_perm (vec_perm@0 @1 @2 VECTOR_CST@3) @0 VECTOR_CST@4)
+ (vec_perm (view_convert?@0 (vec_perm @1 @2 VECTOR_CST@3)) @0 VECTOR_CST@4)
  (if (TYPE_VECTOR_SUBPARTS (type).is_constant ())
   (with
    {
@@ -9977,7 +9977,8 @@ and,
      vec_perm_builder builder2 (nelts, nelts, 1);
    }
    (if (tree_to_vec_perm_builder (&builder0, @3)
-	&& tree_to_vec_perm_builder (&builder1, @4))
+	&& tree_to_vec_perm_builder (&builder1, @4)
+	&& element_precision (type) == element_precision (TREE_TYPE (@0)))
     (with
      {
        vec_perm_indices sel0 (builder0, 2, nelts);
@@ -10002,7 +10003,7 @@ and,
 	 op0 = vec_perm_indices_to_tree (TREE_TYPE (@4), sel2);
      }
      (if (op0)
-      (vec_perm @1 @2 { op0; })))))))
+      (view_convert (vec_perm @1 @2 { op0; }))))))))
 
 /* Merge
      c = VEC_PERM_EXPR <a, b, VCST0>;

Re: [gcc(refs/vendors/vrull/heads/slp-improvements)] match.pd: Look through view_convert when folding vec_perms

[Andrew Pinski]

On Tue, Jan 23, 2024 at 12:57 PM Philipp Tomsich via Gcc-cvs
<gcc-cvs@gcc.gnu.org> wrote:
>
> https://gcc.gnu.org/g:b896c82f141211437b5b5b83a3537d6bd2d243dc
>
> commit b896c82f141211437b5b5b83a3537d6bd2d243dc
> Author: Manolis Tsamis <manolis.tsamis@vrull.eu>
> Date:   Wed Nov 1 12:27:28 2023 +0100
>
>     match.pd: Look through view_convert when folding vec_perms
>
>     The match.pd patterns to merge two vector permutes into one fail to
>     match when a (potentially no-op) view convert expressions is
>     separating the two permutes.  This is observable in the SLP tree for
>     the first loop of x264's satd and inhibits optimization.
>
>     This change adds a check whether a view_convert will be a no-op
>     (comparing the element precision) and rewrites the permute sequence
>     for those cases.

My suggestion is just use nop_convert instead and which does the
correct thing for a vector conversion between signed and unsigned
types.
Or  do you need one between integer and floating point types too?

Thanks,
Andrew

>
>     Ref #343
>
> Diff:
> ---
>  gcc/match.pd | 7 ++++---
>  1 file changed, 4 insertions(+), 3 deletions(-)
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index e42ecaf9ec7..be623d9773c 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -9965,7 +9965,7 @@ and,
>       d = VEC_PERM_EXPR <a, b, NEW_VCST>;  */
>
>  (simplify
> - (vec_perm (vec_perm@0 @1 @2 VECTOR_CST@3) @0 VECTOR_CST@4)
> + (vec_perm (view_convert?@0 (vec_perm @1 @2 VECTOR_CST@3)) @0 VECTOR_CST@4)
>   (if (TYPE_VECTOR_SUBPARTS (type).is_constant ())
>    (with
>     {
> @@ -9977,7 +9977,8 @@ and,
>       vec_perm_builder builder2 (nelts, nelts, 1);
>     }
>     (if (tree_to_vec_perm_builder (&builder0, @3)
> -       && tree_to_vec_perm_builder (&builder1, @4))
> +       && tree_to_vec_perm_builder (&builder1, @4)
> +       && element_precision (type) == element_precision (TREE_TYPE (@0)))
>      (with
>       {
>         vec_perm_indices sel0 (builder0, 2, nelts);
> @@ -10002,7 +10003,7 @@ and,
>          op0 = vec_perm_indices_to_tree (TREE_TYPE (@4), sel2);
>       }
>       (if (op0)
> -      (vec_perm @1 @2 { op0; })))))))
> +      (view_convert (vec_perm @1 @2 { op0; }))))))))
>
>  /* Merge
>       c = VEC_PERM_EXPR <a, b, VCST0>;

[gcc(refs/vendors/vrull/heads/slp-improvements)] match.pd: Look through view_convert when folding vec_perms

[Philipp Tomsich]

https://gcc.gnu.org/g:e8a30f2e241d213a9761a473eb63f1c32e2c182e

commit e8a30f2e241d213a9761a473eb63f1c32e2c182e
Author: Manolis Tsamis <manolis.tsamis@vrull.eu>
Date:   Wed Nov 1 12:27:28 2023 +0100

    match.pd: Look through view_convert when folding vec_perms
    
    The match.pd patterns to merge two vector permutes into one fail to
    match when a (potentially no-op) view convert expressions is
    separating the two permutes.  This is observable in the SLP tree for
    the first loop of x264's satd and inhibits optimization.
    
    This change adds a check whether a view_convert will be a no-op
    (comparing the element precision) and rewrites the permute sequence
    for those cases.
    
    Ref #343

Diff:
---
 gcc/match.pd                       | 14 ++++++++------
 gcc/testsuite/gcc.dg/fold-perm-2.c | 16 ++++++++++++++++
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/gcc/match.pd b/gcc/match.pd
index f3fffd8dec2..ae8c981b306 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -9978,19 +9978,21 @@ and,
      d = VEC_PERM_EXPR <a, b, NEW_VCST>;  */
 
 (simplify
- (vec_perm (vec_perm@0 @1 @2 VECTOR_CST@3) @0 VECTOR_CST@4)
+ (vec_perm (view_convert?@0 (vec_perm@1 @2 @3 VECTOR_CST@4)) @0 VECTOR_CST@5)
  (if (TYPE_VECTOR_SUBPARTS (type).is_constant ())
   (with
    {
      machine_mode result_mode = TYPE_MODE (type);
-     machine_mode op_mode = TYPE_MODE (TREE_TYPE (@1));
+     machine_mode op_mode = TYPE_MODE (TREE_TYPE (@2));
      int nelts = TYPE_VECTOR_SUBPARTS (type).to_constant ();
      vec_perm_builder builder0;
      vec_perm_builder builder1;
      vec_perm_builder builder2 (nelts, nelts, 1);
    }
-   (if (tree_to_vec_perm_builder (&builder0, @3)
-	&& tree_to_vec_perm_builder (&builder1, @4))
+   (if (tree_to_vec_perm_builder (&builder0, @4)
+	&& tree_to_vec_perm_builder (&builder1, @5)
+	&& element_precision (TREE_TYPE (@0))
+	   == element_precision (TREE_TYPE (@1)))
     (with
      {
        vec_perm_indices sel0 (builder0, 2, nelts);
@@ -10012,10 +10014,10 @@ and,
 	       ? (!can_vec_perm_const_p (result_mode, op_mode, sel0, false)
 		  || !can_vec_perm_const_p (result_mode, op_mode, sel1, false))
 	       : !can_vec_perm_const_p (result_mode, op_mode, sel1, false)))
-	 op0 = vec_perm_indices_to_tree (TREE_TYPE (@4), sel2);
+	 op0 = vec_perm_indices_to_tree (TREE_TYPE (@5), sel2);
      }
      (if (op0)
-      (vec_perm @1 @2 { op0; })))))))
+      (view_convert (vec_perm @2 @3 { op0; }))))))))
 
 /* Merge
      c = VEC_PERM_EXPR <a, b, VCST0>;
diff --git a/gcc/testsuite/gcc.dg/fold-perm-2.c b/gcc/testsuite/gcc.dg/fold-perm-2.c
new file mode 100644
index 00000000000..1a4ab4065de
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/fold-perm-2.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-O -fdump-tree-fre1" } */
+
+typedef int veci __attribute__ ((vector_size (4 * sizeof (int))));
+typedef unsigned int vecu __attribute__ ((vector_size (4 * sizeof (unsigned int))));
+
+void fun (veci *a, veci *b, veci *c)
+{
+  veci r1 = __builtin_shufflevector (*a, *b, 0, 5, 2, 7);
+  vecu r2 = __builtin_convertvector (r1, vecu);
+  vecu r3 = __builtin_shufflevector (r2, r2, 2, 3, 1, 0);
+  *c = __builtin_convertvector (r3, veci);
+}
+
+/* { dg-final { scan-tree-dump "VEC_PERM_EXPR.*{ 2, 7, 5, 0 }" "fre1" } } */
+/* { dg-final { scan-tree-dump-times "VEC_PERM_EXPR" 1 "fre1" } } */