Hi,

For function with different target attributes, current logic rejects to
inline the callee when any arch or tune is mismatched. Relax the
condition to honor just prefer_vecotr_width_type and other flags that
may cause safety issue so caller can get more optimization opportunity.

Bootstrapped/regtested on x86_64-pc-linux-gnu{-m32,}

Ok for trunk?

gcc/ChangeLog:

        * config/i386/i386.cc (ix86_can_inline_p): Do not check arch or
        tune directly, just check prefer_vector_width_type and make sure
        not to inline if they mismatch.

gcc/testsuite/ChangeLog:

        * gcc.target/i386/inline-target-attr.c: New test.
---
 gcc/config/i386/i386.cc                       | 11 +++++----
 .../gcc.target/i386/inline-target-attr.c      | 24 +++++++++++++++++++
 2 files changed, 30 insertions(+), 5 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/inline-target-attr.c

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 0761965344b..1d86384ac06 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -605,11 +605,12 @@ ix86_can_inline_p (tree caller, tree callee)
               != (callee_opts->x_target_flags & ~always_inline_safe_mask))
     ret = false;
 
-  /* See if arch, tune, etc. are the same.  */
-  else if (caller_opts->arch != callee_opts->arch)
-    ret = false;
-
-  else if (!always_inline && caller_opts->tune != callee_opts->tune)
+  /* Do not inline when specified perfer-vector-width mismatched between
+     callee and caller.  */
+  else if ((callee_opts->x_prefer_vector_width_type != PVW_NONE
+          && caller_opts->x_prefer_vector_width_type != PVW_NONE)
+          && callee_opts->x_prefer_vector_width_type
+             != caller_opts->x_prefer_vector_width_type)
     ret = false;
 
   else if (caller_opts->x_ix86_fpmath != callee_opts->x_ix86_fpmath
diff --git a/gcc/testsuite/gcc.target/i386/inline-target-attr.c 
b/gcc/testsuite/gcc.target/i386/inline-target-attr.c
new file mode 100644
index 00000000000..995502165f0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/inline-target-attr.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+/* { dg-final { scan-assembler-not "call\[ \t\]callee" } } */
+
+__attribute__((target("arch=skylake")))
+int callee (int n)
+{
+  int sum = 0;
+  for (int i = 0; i < n; i++)
+    {
+      if (i % 2 == 0)
+       sum +=i;
+      else
+       sum += (i - 1);
+    }
+  return sum + n;
+}
+
+__attribute__((target("arch=icelake-server")))
+int caller (int n)
+{
+  return callee (n) + n;
+}
+
-- 
2.31.1

Reply via email to