[glibc] x86-64: Compile branred.c with -mprefer-vector-width=128 [BZ #24603]

[glibc] x86-64: Compile branred.c with -mprefer-vector-width=128 [BZ #24603]

[H.J.Lu]

https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=7e681561a3aea7aa8f21fb031a7c778147dfdf5b

commit 7e681561a3aea7aa8f21fb031a7c778147dfdf5b
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Wed Jul 24 14:48:33 2019 -0700

    x86-64: Compile branred.c with -mprefer-vector-width=128 [BZ #24603]
    
    When compiled with -O3 and AVX, GCC 8 and 9 optimize some loops in
    sysdeps/ieee754/dbl-64/branred.c with 256-bit vector instructions,
    which leads to store forward stall:
    
    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90579
    
    There is no easy fix in compiler.  This patch limits vector width to
    128 bits to work around this issue.  It improves performance of sin
    and cos by more than 40% on Skylake compiled with -O3 -march=skylake.
    
    Tested with GCC 7/8/9 on x86-64.
    
    	[BZ #24603]
    	* sysdeps/x86_64/configure.ac: Check if -mprefer-vector-width=128
    	works.
    	* sysdeps/x86_64/configure: Regenerated.
    	* sysdeps/x86_64/fpu/Makefile (CFLAGS-branred.c): New.  Set
    	to -mprefer-vector-width=128 if supported.

Diff:
---
 ChangeLog                   |  9 +++++++++
 sysdeps/x86_64/configure    | 22 ++++++++++++++++++++++
 sysdeps/x86_64/configure.ac |  9 +++++++++
 sysdeps/x86_64/fpu/Makefile | 12 ++++++++++++
 4 files changed, 52 insertions(+)

diff --git a/ChangeLog b/ChangeLog
index 88108d1..31a6b38 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,12 @@
+2019-07-24  H.J. Lu  <hongjiu.lu@intel.com>
+
+	[BZ #24603]
+	* sysdeps/x86_64/configure.ac: Check if -mprefer-vector-width=128
+	works.
+	* sysdeps/x86_64/configure: Regenerated.
+	* sysdeps/x86_64/fpu/Makefile (CFLAGS-branred.c): New.  Set
+	to -mprefer-vector-width=128 if supported.
+
 2019-07-24  Florian Weimer  <fweimer@redhat.com>
 
 	* scripts/build-many-glibcs.py (Context.checkout): Default to
diff --git a/sysdeps/x86_64/configure b/sysdeps/x86_64/configure
index 8674d14..84f82c2 100644
--- a/sysdeps/x86_64/configure
+++ b/sysdeps/x86_64/configure
@@ -54,6 +54,28 @@ fi
 config_vars="$config_vars
 config-cflags-avx512 = $libc_cv_cc_avx512"
 
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking -mprefer-vector-width=128" >&5
+$as_echo_n "checking -mprefer-vector-width=128... " >&6; }
+if ${libc_cv_cc_mprefer_vector_width+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if { ac_try='${CC-cc} -mprefer-vector-width=128 -xc /dev/null -S -o /dev/null'
+  { { eval echo "\"\$as_me\":${as_lineno-$LINENO}: \"$ac_try\""; } >&5
+  (eval $ac_try) 2>&5
+  ac_status=$?
+  $as_echo "$as_me:${as_lineno-$LINENO}: \$? = $ac_status" >&5
+  test $ac_status = 0; }; }; then :
+  libc_cv_cc_mprefer_vector_width=yes
+else
+  libc_cv_cc_mprefer_vector_width=no
+fi
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $libc_cv_cc_mprefer_vector_width" >&5
+$as_echo "$libc_cv_cc_mprefer_vector_width" >&6; }
+config_vars="$config_vars
+config-cflags-mprefer-vector-width = $libc_cv_cc_mprefer_vector_width"
+
 { $as_echo "$as_me:${as_lineno-$LINENO}: checking for Intel MPX support" >&5
 $as_echo_n "checking for Intel MPX support... " >&6; }
 if ${libc_cv_asm_mpx+:} false; then :
diff --git a/sysdeps/x86_64/configure.ac b/sysdeps/x86_64/configure.ac
index b7d2c01..cdaba0c 100644
--- a/sysdeps/x86_64/configure.ac
+++ b/sysdeps/x86_64/configure.ac
@@ -25,6 +25,15 @@ if test $libc_cv_cc_avx512 = yes; then
 fi
 LIBC_CONFIG_VAR([config-cflags-avx512], [$libc_cv_cc_avx512])
 
+dnl Check if -mprefer-vector-width=128 works.
+AC_CACHE_CHECK(-mprefer-vector-width=128, libc_cv_cc_mprefer_vector_width, [dnl
+LIBC_TRY_CC_OPTION([-mprefer-vector-width=128],
+		   [libc_cv_cc_mprefer_vector_width=yes],
+		   [libc_cv_cc_mprefer_vector_width=no])
+])
+LIBC_CONFIG_VAR([config-cflags-mprefer-vector-width],
+		[$libc_cv_cc_mprefer_vector_width])
+
 dnl Check whether asm supports Intel MPX
 AC_CACHE_CHECK(for Intel MPX support, libc_cv_asm_mpx, [dnl
 cat > conftest.s <<\EOF
diff --git a/sysdeps/x86_64/fpu/Makefile b/sysdeps/x86_64/fpu/Makefile
index 2b7d69b..74b14ba 100644
--- a/sysdeps/x86_64/fpu/Makefile
+++ b/sysdeps/x86_64/fpu/Makefile
@@ -237,3 +237,15 @@ CFLAGS-test-float-libmvec-sincosf-avx512.c = -DREQUIRE_AVX512F
 CFLAGS-test-float-libmvec-sincosf-avx512-main.c = $(libmvec-sincos-cflags) $(float-vlen16-arch-ext-cflags)
 endif
 endif
+
+ifeq ($(subdir)$(config-cflags-mprefer-vector-width),mathyes)
+# When compiled with -O3 -march=skylake, GCC 8 and 9 optimize some loops
+# in branred.c with 256-bit vector instructions, which leads to store
+# forward stall:
+#
+# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90579
+#
+# Limit vector width to 128 bits to work around this issue.  It improves
+# performance of sin and cos by more than 40% on Skylake.
+CFLAGS-branred.c = -mprefer-vector-width=128
+endif