[gcc r14-4571] x86: set spincount 1 for x86 hybrid platform

[gcc r14-4571] x86: set spincount 1 for x86 hybrid platform

[hongtao Liu]

https://gcc.gnu.org/g:e1e127de18dbee47b88fa0ce74a1c7f4d658dc68

commit r14-4571-ge1e127de18dbee47b88fa0ce74a1c7f4d658dc68
Author: Zhang, Jun <jun.zhang@intel.com>
Date:   Fri Sep 22 23:56:37 2023 +0800

    x86: set spincount 1 for x86 hybrid platform
    
    By test, we find in hybrid platform spincount 1 is better.
    
    Use '-march=native -Ofast -funroll-loops -flto',
    results as follows:
    
    spec2017 speed   RPL     ADL
    657.xz_s         0.00%   0.50%
    603.bwaves_s     10.90%  26.20%
    607.cactuBSSN_s  5.50%   72.50%
    619.lbm_s        2.40%   2.50%
    621.wrf_s        -7.70%  2.40%
    627.cam4_s       0.50%   0.70%
    628.pop2_s       48.20%  153.00%
    638.imagick_s    -0.10%  0.20%
    644.nab_s        2.30%   1.40%
    649.fotonik3d_s  8.00%   13.80%
    654.roms_s       1.20%   1.10%
    Geomean-int      0.00%   0.50%
    Geomean-fp       6.30%   21.10%
    Geomean-all      5.70%   19.10%
    
    omp2012          RPL     ADL
    350.md           -1.81%  -1.75%
    351.bwaves       7.72%   12.50%
    352.nab          14.63%  19.71%
    357.bt331        -0.20%  1.77%
    358.botsalgn     0.00%   0.00%
    359.botsspar     0.00%   0.65%
    360.ilbdc        0.00%   0.25%
    362.fma3d        2.66%   -0.51%
    363.swim         10.44%  0.00%
    367.imagick      0.00%   0.12%
    370.mgrid331     2.49%   25.56%
    371.applu331     1.06%   4.22%
    372.smithwa      0.74%   3.34%
    376.kdtree       10.67%  16.03%
    GEOMEAN          3.34%   5.53%
    
    include/ChangeLog:
    
            PR target/109812
            * spincount.h: New file.
    
    libgomp/ChangeLog:
    
            * env.c (initialize_env): Use do_adjust_default_spincount.
            * config/linux/x86/spincount.h: New file.

Diff:
---
 include/spincount.h                  | 33 ++++++++++++++++++++++++
 libgomp/config/linux/x86/spincount.h | 49 ++++++++++++++++++++++++++++++++++++
 libgomp/env.c                        |  6 ++++-
 3 files changed, 87 insertions(+), 1 deletion(-)

diff --git a/include/spincount.h b/include/spincount.h
new file mode 100644
index 00000000000..9eecfff198d
--- /dev/null
+++ b/include/spincount.h
@@ -0,0 +1,33 @@
+/* Copyright (C) 2023-2023 Free Software Foundation, Inc.
+   Contributed by Jun Zhang <jun.zhang@intel.com>.
+
+   This file is part of the GNU Offloading and Multi Processing Library
+   (libgomp).
+
+   Libgomp is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 3, or (at your option)
+   any later version.
+
+   Libgomp is distributed in the hope that it will be useful, but WITHOUT ANY
+   WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+   FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+   more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#ifndef GOMP_SPINCOUNT_H
+#define GOMP_SPINCOUNT_H 1
+
+static inline void do_adjust_default_spincount (void)
+{
+}
+
+#endif /* GOMP_SPINCOUNT_H */
diff --git a/libgomp/config/linux/x86/spincount.h b/libgomp/config/linux/x86/spincount.h
new file mode 100644
index 00000000000..9d2624fd457
--- /dev/null
+++ b/libgomp/config/linux/x86/spincount.h
@@ -0,0 +1,49 @@
+/* Copyright (C) 2023-2023 Free Software Foundation, Inc.
+   Contributed by Jun Zhang <jun.zhang@intel.com>.
+
+   This file is part of the GNU Offloading and Multi Processing Library
+   (libgomp).
+
+   Libgomp is free software; you can redistribute it and/or modify it
+   under the terms of the GNU General Public License as published by
+   the Free Software Foundation; either version 3, or (at your option)
+   any later version.
+
+   Libgomp is distributed in the hope that it will be useful, but WITHOUT ANY
+   WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+   FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+   more details.
+
+   Under Section 7 of GPL version 3, you are granted additional
+   permissions described in the GCC Runtime Library Exception, version
+   3.1, as published by the Free Software Foundation.
+
+   You should have received a copy of the GNU General Public License and
+   a copy of the GCC Runtime Library Exception along with this program;
+   see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
+   <http://www.gnu.org/licenses/>.  */
+
+#ifndef GOMP_SPINCOUNT_H
+#define GOMP_SPINCOUNT_H 1
+
+#ifdef __x86_64__
+#include "cpuid.h"
+#include "libgomp.h"
+
+/* Only for x86 hybrid platform  */
+static inline void do_adjust_default_spincount (void)
+{
+  unsigned int eax, ebx, ecx, edx;
+  if (__get_cpuid_count (7, 0, &eax, &ebx, &ecx, &edx)
+      /* CPUID.07H.0H:EDX[15] Hybrid.  */
+      && ((edx >> 15) & 1))
+    gomp_spin_count_var = 1LL;
+}
+#else
+
+static inline void do_adjust_default_spincount (void)
+{
+}
+#endif
+
+#endif /* GOMP_SPINCOUNT_H */
diff --git a/libgomp/env.c b/libgomp/env.c
index a21adb3fd4b..d058043b06c 100644
--- a/libgomp/env.c
+++ b/libgomp/env.c
@@ -61,6 +61,7 @@
 
 #include "secure_getenv.h"
 #include "environ.h"
+#include "spincount.h"
 
 /* Default values of ICVs according to the OpenMP standard,
    except for default-device-var.  */
@@ -2431,7 +2432,10 @@ initialize_env (void)
       if (wait_policy > 0)
 	gomp_spin_count_var = 30000000000LL;
       else if (wait_policy < 0)
-	gomp_spin_count_var = 300000LL;
+	{
+	  gomp_spin_count_var = 300000LL;
+	  do_adjust_default_spincount ();
+	}
     }
   /* gomp_throttled_spin_count_var is used when there are more libgomp
      managed threads than available CPUs.  Use very short spinning.  */