Hi,

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.

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

Ok for trunk and backport to active release branches?

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.
---
 gcc/config/i386/i386-options.cc       |  6 +++++-
 gcc/testsuite/gcc.target/i386/mvc17.c | 11 +++++++++++
 2 files changed, 16 insertions(+), 1 deletion(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/mvc17.c

diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index 2cb0bddcd35..7f593cebe76 100644
--- 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
index 00000000000..2c7cc2fdace
--- /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);
+}
-- 
2.31.1

Reply via email to