path: root/5000_enable-additional-cpu-optimizations-for-gcc.patch

This patch has been tested on and known to work with kernel versions from 3.2
up to the latest git version (pulled on 12/14/2013).

This patch will expand the number of microarchitectures to include new
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 2nd Gen Core
i3/i5/i7 (Sandybridge), Intel 3rd Gen Core i3/i5/i7 (Ivybridge), and Intel 4th
Gen Core i3/i5/i7 (Haswell). 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

---
diff -uprN a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
--- a/arch/x86/include/asm/module.h	2013-11-03 18:41:51.000000000 -0500
+++ b/arch/x86/include/asm/module.h	2013-12-15 06:21:24.351122516 -0500
@@ -15,6 +15,16 @@
 #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_MCOREI7
+#define MODULE_PROC_FAMILY "COREI7 "
+#elif defined CONFIG_MCOREI7AVX
+#define MODULE_PROC_FAMILY "COREI7AVX "
+#elif defined CONFIG_MCOREAVXI
+#define MODULE_PROC_FAMILY "COREAVXI "
+#elif defined CONFIG_MCOREAVX2
+#define MODULE_PROC_FAMILY "COREAVX2 "
 #elif defined CONFIG_MATOM
 #define MODULE_PROC_FAMILY "ATOM "
 #elif defined CONFIG_M686
@@ -33,6 +43,18 @@
 #define MODULE_PROC_FAMILY "K7 "
 #elif defined CONFIG_MK8
 #define MODULE_PROC_FAMILY "K8 "
+#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
diff -uprN a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
--- a/arch/x86/Kconfig.cpu	2013-11-03 18:41:51.000000000 -0500
+++ b/arch/x86/Kconfig.cpu	2013-12-15 06:21:24.351122516 -0500
@@ -139,7 +139,7 @@ config MPENTIUM4
 
 
 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 +147,7 @@ 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 +155,55 @@ 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 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 +294,17 @@ 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 +312,40 @@ 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 MCOREI7
+	bool "Intel Core i7"
 	---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 the Intel Nehalem platform. Intel Nehalem proecessors
+	  include Core i3, i5, i7, Xeon: 34xx, 35xx, 55xx, 56xx, 75xx processors.
+
+	  Enables -march=corei7
+
+config MCOREI7AVX
+	bool "Intel Core 2nd Gen AVX"
+	---help---
+
+	  Select this for 2nd Gen Core processors including Sandy Bridge.
+
+	  Enables -march=corei7-avx
+
+config MCOREAVXI
+	bool "Intel Core 3rd Gen AVX"
+	---help---
+
+	  Select this for 3rd Gen Core processors including Ivy Bridge.
+
+	  Enables -march=core-avx-i
+
+config MCOREAVX2
+	bool "Intel Core AVX2"
+	---help---
+
+	  Select this for AVX2 enabled processors including Haswell.
+
+	  Enables -march=core-avx2
 
 config GENERIC_CPU
 	bool "Generic-x86-64"
@@ -276,6 +354,19 @@ 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 +391,7 @@ 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 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MPENTIUMM || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MATOM || MVIAC7 || X86_GENERIC || MNATIVE || 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 +422,11 @@ 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 || MNATIVE || X86_GENERIC || MK8 || MK7 || MK10 || MBARCELONA || MEFFICEON || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2
 
 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 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MATOM || MNATIVE
 
 config X86_USE_3DNOW
 	def_bool y
@@ -363,17 +454,17 @@ 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_NUMAQ) || X86_64
+	depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MCOREI7 || MCOREI7-AVX || MATOM) && !X86_NUMAQ) || X86_64 || MNATIVE
 
 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 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || 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 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MK7 || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MNATIVE || MATOM || MGEODE_LX)
 
 config X86_MINIMUM_CPU_FAMILY
 	int
diff -uprN a/arch/x86/Makefile b/arch/x86/Makefile
--- a/arch/x86/Makefile	2013-11-03 18:41:51.000000000 -0500
+++ b/arch/x86/Makefile	2013-12-15 06:21:24.354455723 -0500
@@ -61,11 +61,26 @@ else
 	KBUILD_CFLAGS += $(call cc-option,-mno-sse -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_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))
+                $(call cc-option,-march=core2,$(call cc-option,-mtune=core2))
+        cflags-$(CONFIG_MCOREI7) += \
+                $(call cc-option,-march=corei7,$(call cc-option,-mtune=corei7))
+        cflags-$(CONFIG_MCOREI7AVX) += \
+                $(call cc-option,-march=corei7-avx,$(call cc-option,-mtune=corei7-avx))
+        cflags-$(CONFIG_MCOREAVXI) += \
+                $(call cc-option,-march=core-avx-i,$(call cc-option,-mtune=core-avx-i))
+        cflags-$(CONFIG_MCOREAVX2) += \
+                $(call cc-option,-march=core-avx2,$(call cc-option,-mtune=core-avx2))
 	cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \
 		$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
         cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
diff -uprN a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
--- a/arch/x86/Makefile_32.cpu	2013-11-03 18:41:51.000000000 -0500
+++ b/arch/x86/Makefile_32.cpu	2013-12-15 06:21:24.354455723 -0500
@@ -23,7 +23,14 @@ cflags-$(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_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)	+= $(call cc-option,-march=winchip-c6,-march=i586)
@@ -32,6 +39,10 @@ cflags-$(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_MCOREI7)	+= -march=i686 $(call tune,corei7)
+cflags-$(CONFIG_MCOREI7AVX)	+= -march=i686 $(call tune,corei7-avx)
+cflags-$(CONFIG_MCOREAVXI)	+= -march=i686 $(call tune,core-avx-i)
+cflags-$(CONFIG_MCOREAVX2)	+= -march=i686 $(call tune,core-avx2)
 cflags-$(CONFIG_MATOM)		+= $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \
 	$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))