i386: Sync tune_string with arch_string for target attribute arch=*

For function with target attribute arch=*, current logic will set its
tune to -mtune from command line so all target_clones will get same
tuning flags which would affect the performance for each clone. Override
tune with arch if tune was not explicitly specified to get proper tuning
flags for target_clones.

gcc/ChangeLog:

	* config/i386/i386-options.cc (ix86_valid_target_attribute_tree):
	Override tune_string with arch_string if tune_string is not
	explicitly specified.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/mvc17.c: New test.

diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index 2cb0bddcd35e1caf30c268483cb19543d84219a1..7f593cebe76529955a2b8b7ddff2be0a7136815d 100644 (file)
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -1400,7 +1400,11 @@ ix86_valid_target_attribute_tree (tree fndecl, tree args,
       if (option_strings[IX86_FUNCTION_SPECIFIC_TUNE])
        opts->x_ix86_tune_string
          = ggc_strdup (option_strings[IX86_FUNCTION_SPECIFIC_TUNE]);
-      else if (orig_tune_defaulted)
+      /* If we have explicit arch string and no tune string specified, set
+        tune_string to NULL and later it will be overriden by arch_string
+        so target clones can get proper optimization.  */
+      else if (option_strings[IX86_FUNCTION_SPECIFIC_ARCH]
+              || orig_tune_defaulted)
        opts->x_ix86_tune_string = NULL;
 
       /* If fpmath= is not set, and we now have sse2 on 32-bit, use it.  */

diff --git a/gcc/testsuite/gcc.target/i386/mvc17.c b/gcc/testsuite/gcc.target/i386/mvc17.c
new file mode 100644 (file)
index 0000000..2c7cc2f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/mvc17.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-require-ifunc "" } */
+/* { dg-options "-O2" } */
+/* { dg-final { scan-assembler-times "rep mov" 1 } } */
+
+__attribute__((target_clones("default","arch=icelake-server")))
+void
+foo (char *a, char *b, int size)
+{
+  __builtin_memcpy (a, b, size & 0x7F);
+}