i386: Inline function with default arch/tune to caller

For function with different target attributes, current logic rejects to
inline the callee when any arch or tune is mismatched. Relax the
condition to allow callee with default arch/tune to be inlined.

gcc/ChangeLog:

	* config/i386/i386.cc (ix86_can_inline_p): If callee has
	default arch=x86-64 and tune=generic, do not block the
	inlining to its caller. Also allow callee with different
	arch= to be inlined if it has always_inline attribute and
	it's ISA is subset of caller's.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/inline_attr_arch.c: New test.
	* gcc.target/i386/inline_target_clones.c: Ditto.

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 0cc4b329b9966ba4fb1ccdd3687fc361bcb569ac..f0d6167e667f85de7e3673144bc5c5c9b1797778 100644 (file)
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -605,13 +605,6 @@ 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)
-    ret = false;
-
   else if (caller_opts->x_ix86_fpmath != callee_opts->x_ix86_fpmath
           /* If the calle doesn't use FP expressions differences in
              ix86_fpmath can be ignored.  We are called from FEs
@@ -622,6 +615,23 @@ ix86_can_inline_p (tree caller, tree callee)
               || ipa_fn_summaries->get (callee_node)->fp_expressions))
     ret = false;
 
+  /* At this point we cannot identify whether arch or tune setting
+     comes from target attribute or not. So the most conservative way
+     is to allow the callee that uses default arch and tune string to
+     be inlined.  */
+  else if (!strcmp (callee_opts->x_ix86_arch_string, "x86-64")
+          && !strcmp (callee_opts->x_ix86_tune_string, "generic"))
+    ret = true;
+
+  /* See if arch, tune, etc. are the same. As previous ISA flags already
+     checks if callee's ISA is subset of caller's, do not block
+     always_inline attribute for callee even it has different arch. */
+  else if (!always_inline && caller_opts->arch != callee_opts->arch)
+    ret = false;
+
+  else if (!always_inline && caller_opts->tune != callee_opts->tune)
+    ret = false;
+
   else if (!always_inline
           && caller_opts->branch_cost != callee_opts->branch_cost)
     ret = false;

diff --git a/gcc/testsuite/gcc.target/i386/inline_attr_arch.c b/gcc/testsuite/gcc.target/i386/inline_attr_arch.c
new file mode 100644 (file)
index 0000000..1fab485
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/inline_attr_arch.c
@@ -0,0 +1,25 @@
+/* { dg-do compile } */
+/* { dg-require-ifunc "" } */
+/* { dg-options "-O3 -march=x86-64" } */
+/* { dg-final { scan-assembler-not "call\[ \t\]+callee" } } */
+
+__attribute__((always_inline,target("arch=haswell")))
+inline float callee (float a, float b, float c, float d,
+             float e, float f, float g, float h)
+{
+  return a * b + c * d + e * f + g + h + a * c + b * c
+    + a * d + b * e + a * f + c * h + 
+    b * (a - 0.4f) * (c + h) * (b + e * d) - a / f * h;
+}
+
+__attribute__((target("arch=icelake-server")))
+void caller (int n, float *a,
+            float c1, float c2, float c3,
+            float c4, float c5, float c6,
+            float c7)
+{
+  for (int i = 0; i < n; i++)
+    {
+      a[i] = callee (a[i], c1, c2, c3, c4, c5, c6, c7);
+    }
+}

diff --git a/gcc/testsuite/gcc.target/i386/inline_target_clones.c b/gcc/testsuite/gcc.target/i386/inline_target_clones.c
new file mode 100644 (file)
index 0000000..53db160
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/inline_target_clones.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-require-ifunc "" } */
+/* { dg-options "-O3 -march=x86-64" } */
+/* { dg-final { scan-assembler-not "call\[ \t\]+callee" } } */
+
+float callee (float a, float b, float c, float d,
+             float e, float f, float g, float h)
+{
+  return a * b + c * d + e * f + g + h + a * c + b * c
+    + a * d + b * e + a * f + c * h + 
+    b * (a - 0.4f) * (c + h) * (b + e * d) - a / f * h;
+}
+
+__attribute__((target_clones("default","arch=icelake-server")))
+void caller (int n, float *a,
+            float c1, float c2, float c3,
+            float c4, float c5, float c6,
+            float c7)
+{
+  for (int i = 0; i < n; i++)
+    {
+      a[i] = callee (a[i], c1, c2, c3, c4, c5, c6, c7);
+    }
+}