[gcc r14-4764] vect: Fix vect_get_smallest_scalar_type for simd clones

[gcc r14-4764] vect: Fix vect_get_smallest_scalar_type for simd clones

[Andre Simoes Dias Vieira]

https://gcc.gnu.org/g:c9ce846763c3d220c754ac0a327e275ac00a83e1

commit r14-4764-gc9ce846763c3d220c754ac0a327e275ac00a83e1
Author: Andre Vieira <andre.simoesdiasvieira@arm.com>
Date:   Thu Oct 19 18:30:15 2023 +0100

    vect: Fix vect_get_smallest_scalar_type for simd clones
    
    The vect_get_smallest_scalar_type helper function was using any argument to a
    simd clone call when trying to determine the smallest scalar type that would be
    vectorized.  This included the function pointer type in a MASK_CALL for
    instance, and would result in the wrong type being selected.  Instead this
    patch special cases simd_clone_call's and uses only scalar types of the
    original function that get transformed into vector types.
    
    gcc/ChangeLog:
    
            * tree-vect-data-refs.cc (vect_get_smallest_scalar_type): Special case
            simd clone calls and only use types that are mapped to vectors.
            (simd_clone_call_p): New helper function.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.dg/vect/vect-simd-clone-16f.c: Remove unnecessary differentation
            between targets with different pointer sizes.
            * gcc.dg/vect/vect-simd-clone-17f.c: Likewise.
            * gcc.dg/vect/vect-simd-clone-18f.c: Likewise.

Diff:
---
 gcc/testsuite/gcc.dg/vect/vect-simd-clone-16f.c |  5 ++-
 gcc/testsuite/gcc.dg/vect/vect-simd-clone-17f.c |  5 ++-
 gcc/testsuite/gcc.dg/vect/vect-simd-clone-18f.c |  5 ++-
 gcc/tree-vect-data-refs.cc                      | 45 +++++++++++++++++++++++++
 4 files changed, 51 insertions(+), 9 deletions(-)

diff --git a/gcc/testsuite/gcc.dg/vect/vect-simd-clone-16f.c b/gcc/testsuite/gcc.dg/vect/vect-simd-clone-16f.c
index 574698d3e133..7cd29e894d05 100644
--- a/gcc/testsuite/gcc.dg/vect/vect-simd-clone-16f.c
+++ b/gcc/testsuite/gcc.dg/vect/vect-simd-clone-16f.c
@@ -7,9 +7,8 @@
 #include "vect-simd-clone-16.c"
 
 /* Ensure the the in-branch simd clones are used on targets that support them.
-   Some targets use pairs of vectors and do twice the calls.  */
-/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 2 "vect" { target { ! { { i?86-*-* x86_64-*-* } && { ! lp64 } } } } } } */
-/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 4 "vect" { target { { i?86*-*-* x86_64-*-* } && { ! lp64 } } } } } */
+ */
+/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 2 "vect" } } */
 
 /* The LTO test produces two dump files and we scan the wrong one.  */
 /* { dg-skip-if "" { *-*-* } { "-flto" } { "" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/vect-simd-clone-17f.c b/gcc/testsuite/gcc.dg/vect/vect-simd-clone-17f.c
index 8bb6d19301a6..177521dc4453 100644
--- a/gcc/testsuite/gcc.dg/vect/vect-simd-clone-17f.c
+++ b/gcc/testsuite/gcc.dg/vect/vect-simd-clone-17f.c
@@ -7,9 +7,8 @@
 #include "vect-simd-clone-17.c"
 
 /* Ensure the the in-branch simd clones are used on targets that support them.
-   Some targets use pairs of vectors and do twice the calls.  */
-/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 2 "vect" { target { ! { { i?86-*-* x86_64-*-* } && { ! lp64 } } } } } } */
-/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 4 "vect" { target { { i?86*-*-* x86_64-*-* } && { ! lp64 } } } } } */
+ */
+/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 2 "vect" } } */
 
 /* The LTO test produces two dump files and we scan the wrong one.  */
 /* { dg-skip-if "" { *-*-* } { "-flto" } { "" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/vect-simd-clone-18f.c b/gcc/testsuite/gcc.dg/vect/vect-simd-clone-18f.c
index d34f23f4db8e..4dd51381d73c 100644
--- a/gcc/testsuite/gcc.dg/vect/vect-simd-clone-18f.c
+++ b/gcc/testsuite/gcc.dg/vect/vect-simd-clone-18f.c
@@ -7,9 +7,8 @@
 #include "vect-simd-clone-18.c"
 
 /* Ensure the the in-branch simd clones are used on targets that support them.
-   Some targets use pairs of vectors and do twice the calls.  */
-/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 2 "vect" { target { ! { { i?86-*-* x86_64-*-* } && { ! lp64 } } } } } } */
-/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 4 "vect" { target { { i?86*-*-* x86_64-*-* } && { ! lp64 } } } } } */
+ */
+/* { dg-final { scan-tree-dump-times {[\n\r] [^\n]* = foo\.simdclone} 2 "vect" } } */
 
 /* The LTO test produces two dump files and we scan the wrong one.  */
 /* { dg-skip-if "" { *-*-* } { "-flto" } { "" } } */
diff --git a/gcc/tree-vect-data-refs.cc b/gcc/tree-vect-data-refs.cc
index 9607a9fb25da..d5c9c4a11c2e 100644
--- a/gcc/tree-vect-data-refs.cc
+++ b/gcc/tree-vect-data-refs.cc
@@ -97,6 +97,34 @@ vect_lanes_optab_supported_p (const char *name, convert_optab optab,
   return true;
 }
 
+/* Helper function to identify a simd clone call.  If this is a call to a
+   function with simd clones then return the corresponding cgraph_node,
+   otherwise return NULL.  */
+
+static cgraph_node*
+simd_clone_call_p (gimple *stmt)
+{
+  gcall *call = dyn_cast <gcall *> (stmt);
+  if (!call)
+    return NULL;
+
+  tree fndecl = NULL_TREE;
+  if (gimple_call_internal_p (call, IFN_MASK_CALL))
+    fndecl = TREE_OPERAND (gimple_call_arg (stmt, 0), 0);
+  else
+    fndecl = gimple_call_fndecl (stmt);
+
+  if (fndecl == NULL_TREE)
+    return NULL;
+
+  cgraph_node *node = cgraph_node::get (fndecl);
+  if (node && node->simd_clones != NULL)
+    return node;
+
+  return NULL;
+}
+
+
 
 /* Return the smallest scalar part of STMT_INFO.
    This is used to determine the vectype of the stmt.  We generally set the
@@ -145,6 +173,23 @@ vect_get_smallest_scalar_type (stmt_vec_info stmt_info, tree scalar_type)
 	    scalar_type = rhs_type;
 	}
     }
+  else if (cgraph_node *node = simd_clone_call_p (stmt_info->stmt))
+    {
+      auto clone = node->simd_clones->simdclone;
+      for (unsigned int i = 0; i < clone->nargs; ++i)
+	{
+	  if (clone->args[i].arg_type == SIMD_CLONE_ARG_TYPE_VECTOR)
+	    {
+	      tree arg_scalar_type = TREE_TYPE (clone->args[i].vector_type);
+	      rhs = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (arg_scalar_type));
+	      if (rhs < lhs)
+		{
+		  scalar_type = arg_scalar_type;
+		  lhs = rhs;
+		}
+	    }
+	}
+    }
   else if (gcall *call = dyn_cast <gcall *> (stmt_info->stmt))
     {
       unsigned int i = 0;