Made it a local function and changed prototype according to comments.
Is this OK?
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.
On 30/08/2023 13:54, Richard Biener wrote:
On Wed, 30 Aug 2023, Andre Vieira (lists) wrote:
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.
Looks sensible.
+bool
+simd_clone_call_p (gimple *stmt, cgraph_node **out_node)
you could return the cgraph_node * or NULL here. Are you going to
use the function elsewhere? Otherwise put it in the same TU as
the only use please and avoid exporting it.
Richard.
gcc/ChangeLog:
* tree-vect-data-refs.cci (vect_get_smallest_scalar_type): Special
case
simd clone calls and only use types that are mapped to vectors.
* tree-vect-stmts.cc (simd_clone_call_p): New helper function.
* tree-vectorizer.h (simd_clone_call_p): Declare new 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 --git a/gcc/testsuite/gcc.dg/vect/vect-simd-clone-16f.c
b/gcc/testsuite/gcc.dg/vect/vect-simd-clone-16f.c
index
574698d3e133ecb8700e698fa42a6b05dd6b8a18..7cd29e894d0502a59fadfe67db2db383133022d3
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
8bb6d19301a67a3eebce522daaf7d54d88f708d7..177521dc44531479fca1f1a1a0f2010f30fa3fb5
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
d34f23f4db8e9c237558cc22fe66b7e02b9e6c20..4dd51381d73c0c7c8ec812f24e5054df038059c5
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
40ab568fe355964b878d770010aa9eeaef63eeac..106d46e68910df94e806433e1cd841894a86d062
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;
