diff options
| -rw-r--r-- | 5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch | 67 |
1 files changed, 41 insertions, 26 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 f931f75f..c4efd06a 100644 --- a/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch +++ b/5010_enable-additional-cpu-optimizations-for-gcc-4.9.patch @@ -18,13 +18,14 @@ 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 new +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), and Intel 5th -Gen Core i3/i5/i7 (Broadwell). It also offers the compiler the 'native' flag. +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. @@ -36,9 +37,9 @@ REQUIREMENTS linux version >=3.15 gcc version >=4.9 ---- a/arch/x86/include/asm/module.h 2014-08-03 18:25:02.000000000 -0400 -+++ b/arch/x86/include/asm/module.h 2014-09-13 09:37:16.721385247 -0400 -@@ -15,6 +15,20 @@ +--- 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 " @@ -48,6 +49,8 @@ gcc version >=4.9 +#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 @@ -59,7 +62,7 @@ gcc version >=4.9 #elif defined CONFIG_MATOM #define MODULE_PROC_FAMILY "ATOM " #elif defined CONFIG_M686 -@@ -33,6 +47,20 @@ +@@ -33,6 +49,20 @@ #define MODULE_PROC_FAMILY "K7 " #elif defined CONFIG_MK8 #define MODULE_PROC_FAMILY "K8 " @@ -80,8 +83,8 @@ gcc version >=4.9 #elif defined CONFIG_MELAN #define MODULE_PROC_FAMILY "ELAN " #elif defined CONFIG_MCRUSOE ---- a/arch/x86/Kconfig.cpu 2014-08-03 18:25:02.000000000 -0400 -+++ b/arch/x86/Kconfig.cpu 2014-09-13 09:37:16.721385247 -0400 +--- 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 @@ -185,7 +188,7 @@ gcc version >=4.9 ---help--- Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and -@@ -260,14 +318,55 @@ config MCORE2 +@@ -260,14 +318,63 @@ config MCORE2 family in /proc/cpuinfo. Newer ones have 6 and older ones 15 (not a typo) @@ -213,6 +216,14 @@ gcc version >=4.9 + + 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--- @@ -247,7 +258,7 @@ gcc version >=4.9 config GENERIC_CPU bool "Generic-x86-64" -@@ -276,6 +375,19 @@ config GENERIC_CPU +@@ -276,6 +383,19 @@ config GENERIC_CPU Generic x86-64 CPU. Run equally well on all x86-64 CPUs. @@ -267,53 +278,53 @@ gcc version >=4.9 endchoice config X86_GENERIC -@@ -300,7 +412,7 @@ config X86_INTERNODE_CACHE_SHIFT +@@ -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 || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || BROADWELL || MNATIVE || 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 +443,11 @@ config X86_ALIGNMENT_16 +@@ -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 || 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 || 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 || 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 || MATOM || MNATIVE config X86_USE_3DNOW def_bool y -@@ -359,17 +471,17 @@ config X86_P6_NOP +@@ -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 || 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 || 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 || 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 || 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 || 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 || 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 2014-08-03 18:25:02.000000000 -0400 -+++ b/arch/x86/Makefile 2014-09-13 09:37:16.721385247 -0400 -@@ -92,13 +92,33 @@ else +--- 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) @@ -337,6 +348,8 @@ gcc version >=4.9 + $(call cc-option,-march=nehalem,$(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-$(CONFIG_MIVYBRIDGE) += \ @@ -350,8 +363,8 @@ gcc version >=4.9 cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic) KBUILD_CFLAGS += $(cflags-y) ---- a/arch/x86/Makefile_32.cpu 2014-08-03 18:25:02.000000000 -0400 -+++ b/arch/x86/Makefile_32.cpu 2014-09-13 09:37:16.721385247 -0400 +--- a/arch/x86/Makefile_32.cpu 2014-06-16 16:44:27.000000000 -0400 ++++ b/arch/x86/Makefile_32.cpu 2015-03-07 03:34:15.203586024 -0500 @@ -23,7 +23,15 @@ cflags-$(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. @@ -368,7 +381,7 @@ gcc version >=4.9 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) += $(call cc-option,-march=winchip-c6,-march=i586) -@@ -32,8 +40,14 @@ cflags-$(CONFIG_MCYRIXIII) += $(call cc- +@@ -32,8 +40,15 @@ cflags-$(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) @@ -376,6 +389,7 @@ gcc version >=4.9 - $(call cc-option,-mtune=atom,$(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 $(call tune,haswell) @@ -385,3 +399,4 @@ gcc version >=4.9 # AMD Elan support cflags-$(CONFIG_MELAN) += -march=i486 + |