Hi.
The patch was supposed to be a next stage1 material, but then PR94271
was reported. The patch for it includes the hunk and one more that
leaves unique_name and resolution for the "default" clone. That will
align the symbol with other target clones and it's name will become
privatized eventually in LTO.
Patch can bootstrap on x86_64-linux-gnu and survives regression tests.
Ready to be installed?
Thanks,
Martin
>From 1431a34f70128bdce59c94dad1d10f91673f63eb Mon Sep 17 00:00:00 2001
From: Martin Liska <mli...@suse.cz>
Date: Thu, 16 Jan 2020 10:38:41 +0100
Subject: [PATCH] Make target_clones resolver fn static if possible.
gcc/ChangeLog:
2020-03-17 Martin Liska <mli...@suse.cz>
PR target/93274
PR ipa/94271
* config/i386/i386-features.c (make_resolver_func): Drop
public flag for resolver.
* config/rs6000/rs6000.c (make_resolver_func): Add comdat
group for resolver and drop public flag if possible.
* multiple_target.c (create_dispatcher_calls): Drop unique_name
and resolution as we want to enable LTO privatization of the default
symbol.
gcc/testsuite/ChangeLog:
2020-03-17 Martin Liska <mli...@suse.cz>
PR target/93274 PR lto/94271
* gcc.target/i386/pr81213-2.c: New test.
* gcc.target/i386/pr81213.c: Add additional source.
* gcc.dg/lto/pr94271_0.c: New test.
* gcc.dg/lto/pr94271_1.c: New test.
---
gcc/config/i386/i386-features.c | 3 +++
gcc/config/rs6000/rs6000.c | 12 ++++++++++++
gcc/multiple_target.c | 4 ----
gcc/testsuite/gcc.dg/lto/pr94271_0.c | 13 +++++++++++++
gcc/testsuite/gcc.dg/lto/pr94271_1.c | 17 +++++++++++++++++
gcc/testsuite/gcc.target/i386/pr81213-2.c | 11 +++++++++++
gcc/testsuite/gcc.target/i386/pr81213.c | 7 +++++--
7 files changed, 61 insertions(+), 6 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/lto/pr94271_0.c
create mode 100644 gcc/testsuite/gcc.dg/lto/pr94271_1.c
create mode 100644 gcc/testsuite/gcc.target/i386/pr81213-2.c
diff --git a/gcc/config/i386/i386-features.c b/gcc/config/i386/i386-features.c
index 6528832487e..3c70279dc7c 100644
--- a/gcc/config/i386/i386-features.c
+++ b/gcc/config/i386/i386-features.c
@@ -2777,6 +2777,9 @@ make_resolver_func (const tree default_decl,
DECL_COMDAT (decl) = 1;
make_decl_one_only (decl, DECL_ASSEMBLER_NAME (decl));
}
+ else
+ TREE_PUBLIC (ifunc_alias_decl) = 0;
+
/* Build result decl and add to function_decl. */
t = build_decl (UNKNOWN_LOCATION, RESULT_DECL, NULL_TREE, ptr_type_node);
DECL_CONTEXT (t) = decl;
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 07f7cf516ba..7505a0e1e8e 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -23894,6 +23894,18 @@ make_resolver_func (const tree default_decl,
DECL_INITIAL (decl) = make_node (BLOCK);
DECL_STATIC_CONSTRUCTOR (decl) = 0;
+ if (DECL_COMDAT_GROUP (default_decl)
+ || TREE_PUBLIC (default_decl))
+ {
+ /* In this case, each translation unit with a call to this
+ versioned function will put out a resolver. Ensure it
+ is comdat to keep just one copy. */
+ DECL_COMDAT (decl) = 1;
+ make_decl_one_only (decl, DECL_ASSEMBLER_NAME (decl));
+ }
+ else
+ TREE_PUBLIC (dispatch_decl) = 0;
+
/* Build result decl and add to function_decl. */
tree t = build_decl (UNKNOWN_LOCATION, RESULT_DECL, NULL_TREE, ptr_type_node);
DECL_CONTEXT (t) = decl;
diff --git a/gcc/multiple_target.c b/gcc/multiple_target.c
index cccfd2774db..c1cfe8ff978 100644
--- a/gcc/multiple_target.c
+++ b/gcc/multiple_target.c
@@ -178,10 +178,6 @@ create_dispatcher_calls (struct cgraph_node *node)
node->externally_visible = false;
node->forced_by_abi = false;
node->set_section (NULL);
- node->unique_name = ((node->resolution == LDPR_PREVAILING_DEF_IRONLY
- || node->resolution == LDPR_PREVAILING_DEF_IRONLY_EXP)
- && !flag_incremental_link);
- node->resolution = LDPR_PREVAILING_DEF_IRONLY;
DECL_ARTIFICIAL (node->decl) = 1;
node->force_output = true;
diff --git a/gcc/testsuite/gcc.dg/lto/pr94271_0.c b/gcc/testsuite/gcc.dg/lto/pr94271_0.c
new file mode 100644
index 00000000000..2ce7d65411a
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/lto/pr94271_0.c
@@ -0,0 +1,13 @@
+/* PR lto/94271 */
+/* { dg-lto-do link } */
+
+int a;
+
+static int __attribute__ ((target_clones ("default", "avx512f"))) fast_clamp ()
+{}
+
+void
+c ()
+{
+ a = fast_clamp ();
+}
diff --git a/gcc/testsuite/gcc.dg/lto/pr94271_1.c b/gcc/testsuite/gcc.dg/lto/pr94271_1.c
new file mode 100644
index 00000000000..db9bc9df6db
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/lto/pr94271_1.c
@@ -0,0 +1,17 @@
+int aa;
+
+static inline int __attribute__ ((target_clones ("default", "avx512f")))
+fast_clamp ()
+{}
+
+void
+b ()
+{
+ aa = fast_clamp ();
+}
+
+int
+main ()
+{
+ return 0;
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr81213-2.c b/gcc/testsuite/gcc.target/i386/pr81213-2.c
new file mode 100644
index 00000000000..a80622cb184
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr81213-2.c
@@ -0,0 +1,11 @@
+__attribute__((target_clones("avx","arch=slm","arch=core-avx2","default")))
+static int
+foo ()
+{
+ return 2;
+}
+
+int bar()
+{
+ return foo();
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr81213.c b/gcc/testsuite/gcc.target/i386/pr81213.c
index 89c47529861..334838631d0 100644
--- a/gcc/testsuite/gcc.target/i386/pr81213.c
+++ b/gcc/testsuite/gcc.target/i386/pr81213.c
@@ -1,6 +1,9 @@
/* PR ipa/81214. */
-/* { dg-do compile } */
+/* { dg-do run } */
/* { dg-require-ifunc "" } */
+/* { dg-additional-sources "pr81213-2.c" } */
+
+int bar();
__attribute__((target_clones("avx","arch=slm","arch=core-avx2","default")))
static int
@@ -11,7 +14,7 @@ foo ()
int main()
{
- return foo();
+ return foo() + bar();
}
/* { dg-final { scan-assembler "\t.globl\tfoo" } } */
--
2.25.1
