summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMike Pagano <mpagano@gentoo.org>2016-06-30 20:31:10 -0400
committerMike Pagano <mpagano@gentoo.org>2016-06-30 20:31:10 -0400
commitfd28e3ad763ea79a262ca9d96d6d812817ec60fe (patch)
tree4180eabb72e81ad14ccbd3bd533ff83ad72ff9f4
parentLinux patch 4.6.3 (diff)
downloadlinux-patches-fd28e3ad.tar.gz
linux-patches-fd28e3ad.tar.bz2
linux-patches-fd28e3ad.zip
Update gcc 4.9+ optimization patch. Bug #587578
-rw-r--r--5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch90
1 files changed, 57 insertions, 33 deletions
diff --git a/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch b/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch
index 418201d9..d9729b23 100644
--- a/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch
+++ b/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch
@@ -21,11 +21,12 @@ bug report to see if I'm right: https://bugzilla.kernel.org/show_bug.cgi?id=7746
This patch will expand the number of microarchitectures to include newer
processors including: AMD K10-family, AMD Family 10h (Barcelona), AMD Family
14h (Bobcat), AMD Family 15h (Bulldozer), AMD Family 15h (Piledriver), AMD
-Family 16h (Jaguar), Intel 1st Gen Core i3/i5/i7 (Nehalem), Intel 1.5 Gen Core
-i3/i5/i7 (Westmere), Intel 2nd Gen Core i3/i5/i7 (Sandybridge), Intel 3rd Gen
-Core i3/i5/i7 (Ivybridge), Intel 4th Gen Core i3/i5/i7 (Haswell), Intel 5th
-Gen Core i3/i5/i7 (Broadwell), and the low power Silvermont series of Atom
-processors (Silvermont). It also offers the compiler the 'native' flag.
+Family 15h (Steamroller), Family 16h (Jaguar), Intel 1st Gen Core i3/i5/i7
+(Nehalem), Intel 1.5 Gen Core i3/i5/i7 (Westmere), Intel 2nd Gen Core i3/i5/i7
+(Sandybridge), Intel 3rd Gen Core i3/i5/i7 (Ivybridge), Intel 4th Gen Core
+i3/i5/i7 (Haswell), Intel 5th Gen Core i3/i5/i7 (Broadwell), and the low power
+Silvermont series of Atom processors (Silvermont). It also offers the compiler
+the 'native' flag.
Small but real speed increases are measurable using a make endpoint comparing
a generic kernel to one built with one of the respective microarchs.
@@ -37,9 +38,9 @@ REQUIREMENTS
linux version >=3.15
gcc version >=4.9
---- a/arch/x86/include/asm/module.h 2014-06-16 16:44:27.000000000 -0400
-+++ b/arch/x86/include/asm/module.h 2015-03-07 03:27:32.556672424 -0500
-@@ -15,6 +15,22 @@
+--- a/arch/x86/include/asm/module.h 2015-08-30 14:34:09.000000000 -0400
++++ b/arch/x86/include/asm/module.h 2015-11-06 14:18:24.234941036 -0500
+@@ -15,6 +15,24 @@
#define MODULE_PROC_FAMILY "586MMX "
#elif defined CONFIG_MCORE2
#define MODULE_PROC_FAMILY "CORE2 "
@@ -59,10 +60,12 @@ gcc version >=4.9
+#define MODULE_PROC_FAMILY "HASWELL "
+#elif defined CONFIG_MBROADWELL
+#define MODULE_PROC_FAMILY "BROADWELL "
++#elif defined CONFIG_MSKYLAKE
++#define MODULE_PROC_FAMILY "SKYLAKE "
#elif defined CONFIG_MATOM
#define MODULE_PROC_FAMILY "ATOM "
#elif defined CONFIG_M686
-@@ -33,6 +49,20 @@
+@@ -33,6 +51,22 @@
#define MODULE_PROC_FAMILY "K7 "
#elif defined CONFIG_MK8
#define MODULE_PROC_FAMILY "K8 "
@@ -77,14 +80,16 @@ gcc version >=4.9
+#elif defined CONFIG_MBULLDOZER
+#define MODULE_PROC_FAMILY "BULLDOZER "
+#elif defined CONFIG_MPILEDRIVER
++#define MODULE_PROC_FAMILY "STEAMROLLER "
++#elif defined CONFIG_MSTEAMROLLER
+#define MODULE_PROC_FAMILY "PILEDRIVER "
+#elif defined CONFIG_MJAGUAR
+#define MODULE_PROC_FAMILY "JAGUAR "
#elif defined CONFIG_MELAN
#define MODULE_PROC_FAMILY "ELAN "
#elif defined CONFIG_MCRUSOE
---- a/arch/x86/Kconfig.cpu 2014-06-16 16:44:27.000000000 -0400
-+++ b/arch/x86/Kconfig.cpu 2015-03-07 03:32:14.337713226 -0500
+--- a/arch/x86/Kconfig.cpu 2015-08-30 14:34:09.000000000 -0400
++++ b/arch/x86/Kconfig.cpu 2015-11-06 14:20:14.948369244 -0500
@@ -137,9 +137,8 @@ config MPENTIUM4
-Paxville
-Dempsey
@@ -105,7 +110,7 @@ gcc version >=4.9
depends on X86_32
---help---
Select this for an AMD Athlon K7-family processor. Enables use of
-@@ -155,12 +154,62 @@ config MK7
+@@ -155,12 +154,69 @@ config MK7
flags to GCC.
config MK8
@@ -159,6 +164,13 @@ gcc version >=4.9
+
+ Enables -march=bdver2
+
++config MSTEAMROLLER
++ bool "AMD Steamroller"
++ ---help---
++ Select this for AMD Steamroller processors.
++
++ Enables -march=bdver3
++
+config MJAGUAR
+ bool "AMD Jaguar"
+ ---help---
@@ -169,7 +181,7 @@ gcc version >=4.9
config MCRUSOE
bool "Crusoe"
depends on X86_32
-@@ -251,8 +300,17 @@ config MPSC
+@@ -251,8 +307,17 @@ config MPSC
using the cpu family field
in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
@@ -188,7 +200,7 @@ gcc version >=4.9
---help---
Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
-@@ -260,14 +318,63 @@ config MCORE2
+@@ -260,14 +325,71 @@ config MCORE2
family in /proc/cpuinfo. Newer ones have 6 and older ones 15
(not a typo)
@@ -255,10 +267,18 @@ gcc version >=4.9
+ Select this for 5th Gen Core processors in the Broadwell family.
+
+ Enables -march=broadwell
++
++config MSKYLAKE
++ bool "Intel Skylake"
++ ---help---
++
++ Select this for 6th Gen Core processors in the Skylake family.
++
++ Enables -march=skylake
config GENERIC_CPU
bool "Generic-x86-64"
-@@ -276,6 +383,19 @@ config GENERIC_CPU
+@@ -276,6 +398,19 @@ config GENERIC_CPU
Generic x86-64 CPU.
Run equally well on all x86-64 CPUs.
@@ -278,54 +298,54 @@ gcc version >=4.9
endchoice
config X86_GENERIC
-@@ -300,7 +420,7 @@ config X86_INTERNODE_CACHE_SHIFT
+@@ -300,7 +435,7 @@ config X86_INTERNODE_CACHE_SHIFT
config X86_L1_CACHE_SHIFT
int
default "7" if MPENTIUM4 || MPSC
- default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
-+ default "6" if MK7 || MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MPENTIUMM || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MNATIVE || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
++ default "6" if MK7 || MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MJAGUAR || MPENTIUMM || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MNATIVE || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
default "4" if MELAN || M486 || MGEODEGX1
default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
-@@ -331,11 +451,11 @@ config X86_ALIGNMENT_16
+@@ -331,11 +466,11 @@ config X86_ALIGNMENT_16
config X86_INTEL_USERCOPY
def_bool y
- depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
-+ depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK8SSE3 || MK7 || MEFFICEON || MCORE2 || MK10 || MBARCELONA || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MNATIVE
++ depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK8SSE3 || MK7 || MEFFICEON || MCORE2 || MK10 || MBARCELONA || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MNATIVE
config X86_USE_PPRO_CHECKSUM
def_bool y
- depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
-+ depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MK10 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MATOM || MNATIVE
++ depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MK10 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MATOM || MNATIVE
config X86_USE_3DNOW
def_bool y
-@@ -359,17 +479,17 @@ config X86_P6_NOP
+@@ -359,17 +494,17 @@ config X86_P6_NOP
config X86_TSC
def_bool y
- depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64
-+ depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MNATIVE || MATOM) || X86_64
++ depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MK8SSE3 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MNATIVE || MATOM) || X86_64
config X86_CMPXCHG64
def_bool y
- depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM
-+ depends on X86_PAE || X86_64 || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM || MNATIVE
++ depends on X86_PAE || X86_64 || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM || MNATIVE
# this should be set for all -march=.. options where the compiler
# generates cmov.
config X86_CMOV
def_bool y
- depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX)
-+ depends on (MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MK7 || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MNATIVE || MATOM || MGEODE_LX)
++ depends on (MK8 || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MJAGUAR || MK7 || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MNATIVE || MATOM || MGEODE_LX)
config X86_MINIMUM_CPU_FAMILY
int
---- a/arch/x86/Makefile 2014-06-16 16:44:27.000000000 -0400
-+++ b/arch/x86/Makefile 2015-03-07 03:33:27.650843211 -0500
-@@ -92,13 +92,35 @@ else
- KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
+--- a/arch/x86/Makefile 2015-08-30 14:34:09.000000000 -0400
++++ b/arch/x86/Makefile 2015-11-06 14:21:05.708983344 -0500
+@@ -94,13 +94,38 @@ else
+ KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
+ cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native)
@@ -336,6 +356,7 @@ gcc version >=4.9
+ cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1)
+ cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1)
+ cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2)
++ cflags-$(CONFIG_MSTEAMROLLER) += $(call cc-option,-march=bdver3)
+ cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2)
cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
@@ -358,14 +379,16 @@ gcc version >=4.9
+ $(call cc-option,-march=haswell,$(call cc-option,-mtune=haswell))
+ cflags-$(CONFIG_MBROADWELL) += \
+ $(call cc-option,-march=broadwell,$(call cc-option,-mtune=broadwell))
++ cflags-$(CONFIG_MSKYLAKE) += \
++ $(call cc-option,-march=skylake,$(call cc-option,-mtune=skylake))
+ cflags-$(CONFIG_MATOM) += $(call cc-option,-march=bonnell) \
+ $(call cc-option,-mtune=bonnell,$(call cc-option,-mtune=generic))
cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
KBUILD_CFLAGS += $(cflags-y)
---- a/arch/x86/Makefile_32.cpu 2014-06-16 16:44:27.000000000 -0400
-+++ b/arch/x86/Makefile_32.cpu 2015-03-07 03:34:15.203586024 -0500
-@@ -23,7 +23,15 @@ cflags-$(CONFIG_MK6) += -march=k6
+--- a/arch/x86/Makefile_32.cpu 2015-08-30 14:34:09.000000000 -0400
++++ b/arch/x86/Makefile_32.cpu 2015-11-06 14:21:43.604429077 -0500
+@@ -23,7 +23,16 @@ cflags-$(CONFIG_MK6) += -march=k6
# Please note, that patches that add -march=athlon-xp and friends are pointless.
# They make zero difference whatsosever to performance at this time.
cflags-$(CONFIG_MK7) += -march=athlon
@@ -377,11 +400,12 @@ gcc version >=4.9
+cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1,-march=athlon)
+cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1,-march=athlon)
+cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2,-march=athlon)
++cflags-$(CONFIG_MSTEAMROLLER) += $(call cc-option,-march=bdver3,-march=athlon)
+cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2,-march=athlon)
cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586)
-@@ -32,8 +40,15 @@ cflags-$(CONFIG_MCYRIXIII) += $(call cc-
+@@ -32,8 +41,16 @@ cflags-$(CONFIG_MCYRIXIII) += $(call cc-
cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686)
cflags-$(CONFIG_MVIAC7) += -march=i686
cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2)
@@ -394,9 +418,9 @@ gcc version >=4.9
+cflags-$(CONFIG_MIVYBRIDGE) += -march=i686 $(call tune,ivybridge)
+cflags-$(CONFIG_MHASWELL) += -march=i686 $(call tune,haswell)
+cflags-$(CONFIG_MBROADWELL) += -march=i686 $(call tune,broadwell)
++cflags-$(CONFIG_MSKYLAKE) += -march=i686 $(call tune,skylake)
+cflags-$(CONFIG_MATOM) += $(call cc-option,-march=bonnell,$(call cc-option,-march=core2,-march=i686)) \
+ $(call cc-option,-mtune=bonnell,$(call cc-option,-mtune=generic))
# AMD Elan support
cflags-$(CONFIG_MELAN) += -march=i486
-