diff options
Diffstat (limited to '5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch')
| -rw-r--r-- | 5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch | 402 |
1 files changed, 0 insertions, 402 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 deleted file mode 100644 index c4efd06a..00000000 --- a/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch +++ /dev/null @@ -1,402 +0,0 @@ -WARNING - this version of the patch works with version 4.9+ of gcc and with -kernel version 3.15.x+ and should NOT be applied when compiling on older -versions due to name changes of the flags with the 4.9 release of gcc. -Use the older version of this patch hosted on the same github for older -versions of gcc. For example: - -corei7 --> nehalem -corei7-avx --> sandybridge -core-avx-i --> ivybridge -core-avx2 --> haswell - -For more, see: https://gcc.gnu.org/gcc-4.9/changes.html - -It also changes 'atom' to 'bonnell' in accordance with the gcc v4.9 changes. -Note that upstream is using the deprecated 'match=atom' flags when I believe it -should use the newer 'march=bonnell' flag for atom processors. - -I have made that change to this patch set as well. See the following kernel -bug report to see if I'm right: https://bugzilla.kernel.org/show_bug.cgi?id=77461 - -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. - -Small but real speed increases are measurable using a make endpoint comparing -a generic kernel to one built with one of the respective microarchs. - -See the following experimental evidence supporting this statement: -https://github.com/graysky2/kernel_gcc_patch - -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 @@ - #define MODULE_PROC_FAMILY "586MMX " - #elif defined CONFIG_MCORE2 - #define MODULE_PROC_FAMILY "CORE2 " -+#elif defined CONFIG_MNATIVE -+#define MODULE_PROC_FAMILY "NATIVE " -+#elif defined CONFIG_MNEHALEM -+#define MODULE_PROC_FAMILY "NEHALEM " -+#elif defined CONFIG_MWESTMERE -+#define MODULE_PROC_FAMILY "WESTMERE " -+#elif defined CONFIG_MSILVERMONT -+#define MODULE_PROC_FAMILY "SILVERMONT " -+#elif defined CONFIG_MSANDYBRIDGE -+#define MODULE_PROC_FAMILY "SANDYBRIDGE " -+#elif defined CONFIG_MIVYBRIDGE -+#define MODULE_PROC_FAMILY "IVYBRIDGE " -+#elif defined CONFIG_MHASWELL -+#define MODULE_PROC_FAMILY "HASWELL " -+#elif defined CONFIG_MBROADWELL -+#define MODULE_PROC_FAMILY "BROADWELL " - #elif defined CONFIG_MATOM - #define MODULE_PROC_FAMILY "ATOM " - #elif defined CONFIG_M686 -@@ -33,6 +49,20 @@ - #define MODULE_PROC_FAMILY "K7 " - #elif defined CONFIG_MK8 - #define MODULE_PROC_FAMILY "K8 " -+#elif defined CONFIG_MK8SSE3 -+#define MODULE_PROC_FAMILY "K8SSE3 " -+#elif defined CONFIG_MK10 -+#define MODULE_PROC_FAMILY "K10 " -+#elif defined CONFIG_MBARCELONA -+#define MODULE_PROC_FAMILY "BARCELONA " -+#elif defined CONFIG_MBOBCAT -+#define MODULE_PROC_FAMILY "BOBCAT " -+#elif defined CONFIG_MBULLDOZER -+#define MODULE_PROC_FAMILY "BULLDOZER " -+#elif defined CONFIG_MPILEDRIVER -+#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 -@@ -137,9 +137,8 @@ config MPENTIUM4 - -Paxville - -Dempsey - -- - config MK6 -- bool "K6/K6-II/K6-III" -+ bool "AMD K6/K6-II/K6-III" - depends on X86_32 - ---help--- - Select this for an AMD K6-family processor. Enables use of -@@ -147,7 +146,7 @@ config MK6 - flags to GCC. - - config MK7 -- bool "Athlon/Duron/K7" -+ bool "AMD Athlon/Duron/K7" - depends on X86_32 - ---help--- - Select this for an AMD Athlon K7-family processor. Enables use of -@@ -155,12 +154,62 @@ config MK7 - flags to GCC. - - config MK8 -- bool "Opteron/Athlon64/Hammer/K8" -+ bool "AMD Opteron/Athlon64/Hammer/K8" - ---help--- - Select this for an AMD Opteron or Athlon64 Hammer-family processor. - Enables use of some extended instructions, and passes appropriate - optimization flags to GCC. - -+config MK8SSE3 -+ bool "AMD Opteron/Athlon64/Hammer/K8 with SSE3" -+ ---help--- -+ Select this for improved AMD Opteron or Athlon64 Hammer-family processors. -+ Enables use of some extended instructions, and passes appropriate -+ optimization flags to GCC. -+ -+config MK10 -+ bool "AMD 61xx/7x50/PhenomX3/X4/II/K10" -+ ---help--- -+ Select this for an AMD 61xx Eight-Core Magny-Cours, Athlon X2 7x50, -+ Phenom X3/X4/II, Athlon II X2/X3/X4, or Turion II-family processor. -+ Enables use of some extended instructions, and passes appropriate -+ optimization flags to GCC. -+ -+config MBARCELONA -+ bool "AMD Barcelona" -+ ---help--- -+ Select this for AMD Barcelona and newer processors. -+ -+ Enables -march=barcelona -+ -+config MBOBCAT -+ bool "AMD Bobcat" -+ ---help--- -+ Select this for AMD Bobcat processors. -+ -+ Enables -march=btver1 -+ -+config MBULLDOZER -+ bool "AMD Bulldozer" -+ ---help--- -+ Select this for AMD Bulldozer processors. -+ -+ Enables -march=bdver1 -+ -+config MPILEDRIVER -+ bool "AMD Piledriver" -+ ---help--- -+ Select this for AMD Piledriver processors. -+ -+ Enables -march=bdver2 -+ -+config MJAGUAR -+ bool "AMD Jaguar" -+ ---help--- -+ Select this for AMD Jaguar processors. -+ -+ Enables -march=btver2 -+ - config MCRUSOE - bool "Crusoe" - depends on X86_32 -@@ -251,8 +300,17 @@ config MPSC - using the cpu family field - in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one. - -+config MATOM -+ bool "Intel Atom" -+ ---help--- -+ -+ Select this for the Intel Atom platform. Intel Atom CPUs have an -+ in-order pipelining architecture and thus can benefit from -+ accordingly optimized code. Use a recent GCC with specific Atom -+ support in order to fully benefit from selecting this option. -+ - config MCORE2 -- bool "Core 2/newer Xeon" -+ bool "Intel Core 2" - ---help--- - - Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and -@@ -260,14 +318,63 @@ config MCORE2 - family in /proc/cpuinfo. Newer ones have 6 and older ones 15 - (not a typo) - --config MATOM -- bool "Intel Atom" -+ Enables -march=core2 -+ -+config MNEHALEM -+ bool "Intel Nehalem" - ---help--- - -- Select this for the Intel Atom platform. Intel Atom CPUs have an -- in-order pipelining architecture and thus can benefit from -- accordingly optimized code. Use a recent GCC with specific Atom -- support in order to fully benefit from selecting this option. -+ Select this for 1st Gen Core processors in the Nehalem family. -+ -+ Enables -march=nehalem -+ -+config MWESTMERE -+ bool "Intel Westmere" -+ ---help--- -+ -+ Select this for the Intel Westmere formerly Nehalem-C family. -+ -+ Enables -march=westmere -+ -+config MSILVERMONT -+ bool "Intel Silvermont" -+ ---help--- -+ -+ Select this for the Intel Silvermont platform. -+ -+ Enables -march=silvermont -+ -+config MSANDYBRIDGE -+ bool "Intel Sandy Bridge" -+ ---help--- -+ -+ Select this for 2nd Gen Core processors in the Sandy Bridge family. -+ -+ Enables -march=sandybridge -+ -+config MIVYBRIDGE -+ bool "Intel Ivy Bridge" -+ ---help--- -+ -+ Select this for 3rd Gen Core processors in the Ivy Bridge family. -+ -+ Enables -march=ivybridge -+ -+config MHASWELL -+ bool "Intel Haswell" -+ ---help--- -+ -+ Select this for 4th Gen Core processors in the Haswell family. -+ -+ Enables -march=haswell -+ -+config MBROADWELL -+ bool "Intel Broadwell" -+ ---help--- -+ -+ Select this for 5th Gen Core processors in the Broadwell family. -+ -+ Enables -march=broadwell - - config GENERIC_CPU - bool "Generic-x86-64" -@@ -276,6 +383,19 @@ config GENERIC_CPU - Generic x86-64 CPU. - Run equally well on all x86-64 CPUs. - -+config MNATIVE -+ bool "Native optimizations autodetected by GCC" -+ ---help--- -+ -+ GCC 4.2 and above support -march=native, which automatically detects -+ the optimum settings to use based on your processor. -march=native -+ also detects and applies additional settings beyond -march specific -+ to your CPU, (eg. -msse4). Unless you have a specific reason not to -+ (e.g. distcc cross-compiling), you should probably be using -+ -march=native rather than anything listed below. -+ -+ Enables -march=native -+ - endchoice - - config X86_GENERIC -@@ -300,7 +420,7 @@ 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 || BROADWELL || 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 - - 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 - - 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 - - config X86_USE_3DNOW - def_bool y -@@ -359,17 +479,17 @@ 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 - - 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 - - # 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) - - 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 += $(call cc-option,-mpreferred-stack-boundary=3) - - # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) -+ cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) - cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) -+ cflags-$(CONFIG_MK8SSE3) += $(call cc-option,-march=k8-sse3,-mtune=k8) -+ cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10) -+ cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona) -+ cflags-$(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_MJAGUAR) += $(call cc-option,-march=btver2) - cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) - - cflags-$(CONFIG_MCORE2) += \ -- $(call cc-option,-march=core2,$(call cc-option,-mtune=generic)) -- cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \ -- $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) -+ $(call cc-option,-march=core2,$(call cc-option,-mtune=core2)) -+ cflags-$(CONFIG_MNEHALEM) += \ -+ $(call cc-option,-march=nehalem,$(call cc-option,-mtune=nehalem)) -+ cflags-$(CONFIG_MWESTMERE) += \ -+ $(call cc-option,-march=westmere,$(call cc-option,-mtune=westmere)) -+ cflags-$(CONFIG_MSILVERMONT) += \ -+ $(call cc-option,-march=silvermont,$(call cc-option,-mtune=silvermont)) -+ cflags-$(CONFIG_MSANDYBRIDGE) += \ -+ $(call cc-option,-march=sandybridge,$(call cc-option,-mtune=sandybridge)) -+ cflags-$(CONFIG_MIVYBRIDGE) += \ -+ $(call cc-option,-march=ivybridge,$(call cc-option,-mtune=ivybridge)) -+ cflags-$(CONFIG_MHASWELL) += \ -+ $(call cc-option,-march=haswell,$(call cc-option,-mtune=haswell)) -+ cflags-$(CONFIG_MBROADWELL) += \ -+ $(call cc-option,-march=broadwell,$(call cc-option,-mtune=broadwell)) -+ cflags-$(CONFIG_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 - # Please note, that patches that add -march=athlon-xp and friends are pointless. - # They make zero difference whatsosever to performance at this time. - cflags-$(CONFIG_MK7) += -march=athlon -+cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native) - cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon) -+cflags-$(CONFIG_MK8SSE3) += $(call cc-option,-march=k8-sse3,-march=athlon) -+cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10,-march=athlon) -+cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona,-march=athlon) -+cflags-$(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_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) += $(call cc- - cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) - cflags-$(CONFIG_MVIAC7) += -march=i686 - cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) --cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \ -- $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) -+cflags-$(CONFIG_MNEHALEM) += -march=i686 $(call tune,nehalem) -+cflags-$(CONFIG_MWESTMERE) += -march=i686 $(call tune,westmere) -+cflags-$(CONFIG_MSILVERMONT) += -march=i686 $(call tune,silvermont) -+cflags-$(CONFIG_MSANDYBRIDGE) += -march=i686 $(call tune,sandybridge) -+cflags-$(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_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 - |