path: root/5010_enable-additional-cpu-optimizations-for-gcc.patch

WARNING
This patch works with gcc versions 4.9+ and with kernel version 4.13+ and should
NOT be applied when compiling on older versions of gcc due to key name changes
of the march flags introduced with the version 4.9 release of gcc.[1]

Use the older version of this patch hosted on the same github for older
versions of gcc.

FEATURES
This patch adds additional CPU options to the Linux kernel accessible under:
 Processor type and features  --->
  Processor family --->

The expanded microarchitectures include:
* AMD Improved K8-family
* AMD K10-family
* AMD Family 10h (Barcelona)
* AMD Family 14h (Bobcat)
* AMD Family 16h (Jaguar)
* AMD Family 15h (Bulldozer)
* AMD Family 15h (Piledriver)
* AMD Family 15h (Steamroller)
* AMD Family 15h (Excavator)
* AMD Family 17h (Zen)
* Intel Silvermont low-power processors
* 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)
* Intel 6th Gen Core i3/i5/i7 (Skylake)
* Intel 6th Gen Core i7/i9 (Skylake X)

It also offers to compile passing the 'native' option which, "selects the CPU
to generate code for at compilation time by determining the processor type of
the compiling machine. Using -march=native enables all instruction subsets
supported by the local machine and will produce code optimized for the local
machine under the constraints of the selected instruction set."[3]

MINOR NOTES
This patch 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.[2]

It is not recommended to compile on Atom-CPUs with the 'native' option.[4] The
recommendation is to use the 'atom' option instead.

BENEFITS
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 >=4.13
gcc version >=4.9

ACKNOWLEDGMENTS
This patch builds on the seminal work by Jeroen.[5]

REFERENCES
1. https://gcc.gnu.org/gcc-4.9/changes.html
2. https://bugzilla.kernel.org/show_bug.cgi?id=77461
3. https://gcc.gnu.org/onlinedocs/gcc/x86-Options.html
4. https://github.com/graysky2/kernel_gcc_patch/issues/15
5. http://www.linuxforge.net/docs/linux/linux-gcc.php

--- a/arch/x86/include/asm/module.h	2018-01-28 16:20:33.000000000 -0500
+++ b/arch/x86/include/asm/module.h	2018-03-10 06:42:38.688317317 -0500
@@ -25,6 +25,26 @@ struct mod_arch_specific {
 #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_MSKYLAKE
+#define MODULE_PROC_FAMILY "SKYLAKE "
+#elif defined CONFIG_MSKYLAKEX
+#define MODULE_PROC_FAMILY "SKYLAKEX "
 #elif defined CONFIG_MATOM
 #define MODULE_PROC_FAMILY "ATOM "
 #elif defined CONFIG_M686
@@ -43,6 +63,26 @@ struct mod_arch_specific {
 #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_MSTEAMROLLER
+#define MODULE_PROC_FAMILY "STEAMROLLER "
+#elif defined CONFIG_MJAGUAR
+#define MODULE_PROC_FAMILY "JAGUAR "
+#elif defined CONFIG_MEXCAVATOR
+#define MODULE_PROC_FAMILY "EXCAVATOR "
+#elif defined CONFIG_MZEN
+#define MODULE_PROC_FAMILY "ZEN "
 #elif defined CONFIG_MELAN
 #define MODULE_PROC_FAMILY "ELAN "
 #elif defined CONFIG_MCRUSOE
--- a/arch/x86/Kconfig.cpu	2018-01-28 16:20:33.000000000 -0500
+++ b/arch/x86/Kconfig.cpu	2018-03-10 06:45:50.244371799 -0500
@@ -116,6 +116,7 @@ config MPENTIUMM
 config MPENTIUM4
 	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
 	depends on X86_32
+	select X86_P6_NOP
 	---help---
 	  Select this for Intel Pentium 4 chips.  This includes the
 	  Pentium 4, Pentium D, P4-based Celeron and Xeon, and
@@ -148,9 +149,8 @@ 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
@@ -158,7 +158,7 @@ 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
@@ -166,12 +166,83 @@ 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 Family 10h Barcelona processors.
+
+	  Enables -march=barcelona
+
+config MBOBCAT
+	bool "AMD Bobcat"
+	---help---
+	  Select this for AMD Family 14h Bobcat processors.
+
+	  Enables -march=btver1
+
+config MJAGUAR
+	bool "AMD Jaguar"
+	---help---
+	  Select this for AMD Family 16h Jaguar processors.
+
+	  Enables -march=btver2
+
+config MBULLDOZER
+	bool "AMD Bulldozer"
+	---help---
+	  Select this for AMD Family 15h Bulldozer processors.
+
+	  Enables -march=bdver1
+
+config MPILEDRIVER
+	bool "AMD Piledriver"
+	---help---
+	  Select this for AMD Family 15h Piledriver processors.
+
+	  Enables -march=bdver2
+
+config MSTEAMROLLER
+	bool "AMD Steamroller"
+	---help---
+	  Select this for AMD Family 15h Steamroller processors.
+
+	  Enables -march=bdver3
+
+config MEXCAVATOR
+	bool "AMD Excavator"
+	---help---
+	  Select this for AMD Family 15h Excavator processors.
+
+	  Enables -march=bdver4
+
+config MZEN
+	bool "AMD Zen"
+	---help---
+	  Select this for AMD Family 17h Zen processors.
+
+	  Enables -march=znver1
+
 config MCRUSOE
 	bool "Crusoe"
 	depends on X86_32
@@ -253,6 +324,7 @@ config MVIAC7
 
 config MPSC
 	bool "Intel P4 / older Netburst based Xeon"
+	select X86_P6_NOP
 	depends on X86_64
 	---help---
 	  Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
@@ -262,8 +334,19 @@ 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"
+	select X86_P6_NOP
+	---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"
+	select X86_P6_NOP
 	---help---
 
 	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
@@ -271,14 +354,88 @@ 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"
+	select X86_P6_NOP
 	---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"
+	select X86_P6_NOP
+	---help---
+
+	  Select this for the Intel Westmere formerly Nehalem-C family.
+
+	  Enables -march=westmere
+
+config MSILVERMONT
+	bool "Intel Silvermont"
+	select X86_P6_NOP
+	---help---
+
+	  Select this for the Intel Silvermont platform.
+
+	  Enables -march=silvermont
+
+config MSANDYBRIDGE
+	bool "Intel Sandy Bridge"
+	select X86_P6_NOP
+	---help---
+
+	  Select this for 2nd Gen Core processors in the Sandy Bridge family.
+
+	  Enables -march=sandybridge
+
+config MIVYBRIDGE
+	bool "Intel Ivy Bridge"
+	select X86_P6_NOP
+	---help---
+
+	  Select this for 3rd Gen Core processors in the Ivy Bridge family.
+
+	  Enables -march=ivybridge
+
+config MHASWELL
+	bool "Intel Haswell"
+	select X86_P6_NOP
+	---help---
+
+	  Select this for 4th Gen Core processors in the Haswell family.
+
+	  Enables -march=haswell
+
+config MBROADWELL
+	bool "Intel Broadwell"
+	select X86_P6_NOP
+	---help---
+
+	  Select this for 5th Gen Core processors in the Broadwell family.
+
+	  Enables -march=broadwell
+
+config MSKYLAKE
+	bool "Intel Skylake"
+	select X86_P6_NOP
+	---help---
+
+	  Select this for 6th Gen Core processors in the Skylake family.
+
+	  Enables -march=skylake
+
+config MSKYLAKEX
+	bool "Intel Skylake X"
+	select X86_P6_NOP
+	---help---
+
+	  Select this for 6th Gen Core processors in the Skylake X family.
+
+	  Enables -march=skylake-avx512
 
 config GENERIC_CPU
 	bool "Generic-x86-64"
@@ -287,6 +444,19 @@ 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
@@ -311,7 +481,7 @@ 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 || MSTEAMROLLER || MEXCAVATOR || MZEN || MJAGUAR || MPENTIUMM || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || 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
 
@@ -342,35 +512,36 @@ 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 || MSKYLAKE || MSKYLAKEX || 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 || MSKYLAKE || MSKYLAKEX || MATOM || MNATIVE
 
 config X86_USE_3DNOW
 	def_bool y
 	depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
 
-#
-# P6_NOPs are a relatively minor optimization that require a family >=
-# 6 processor, except that it is broken on certain VIA chips.
-# Furthermore, AMD chips prefer a totally different sequence of NOPs
-# (which work on all CPUs).  In addition, it looks like Virtual PC
-# does not understand them.
-#
-# As a result, disallow these if we're not compiling for X86_64 (these
-# NOPs do work on all x86-64 capable chips); the list of processors in
-# the right-hand clause are the cores that benefit from this optimization.
-#
 config X86_P6_NOP
-	def_bool y
-	depends on X86_64
-	depends on (MCORE2 || MPENTIUM4 || MPSC)
+	default n
+	bool "Support for P6_NOPs on Intel chips"
+	depends on (MCORE2 || MPENTIUM4 || MPSC || MATOM || MNEHALEM || MWESTMERE || MSILVERMONT  || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MNATIVE)
+	---help---
+	P6_NOPs are a relatively minor optimization that require a family >=
+	6 processor, except that it is broken on certain VIA chips.
+	Furthermore, AMD chips prefer a totally different sequence of NOPs
+	(which work on all CPUs).  In addition, it looks like Virtual PC
+	does not understand them.
+
+	As a result, disallow these if we're not compiling for X86_64 (these
+	NOPs do work on all x86-64 capable chips); the list of processors in
+	the right-hand clause are the cores that benefit from this optimization.
+
+	Say Y if you have Intel CPU newer than Pentium Pro, N otherwise.
 
 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 || MSKYLAKE || MSKYLAKEX || MNATIVE || MATOM) || X86_64
 
 config X86_CMPXCHG64
 	def_bool y
@@ -380,7 +551,7 @@ config X86_CMPXCHG64
 # 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 || MSTEAMROLLER || MEXCAVATOR || MZEN || MJAGUAR || MK7 || MCORE2 || MNEHALEM || MWESTMERE || MSILVERMONT || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || 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	2018-01-28 16:20:33.000000000 -0500
+++ b/arch/x86/Makefile	2018-03-10 06:47:00.284240139 -0500
@@ -124,13 +124,42 @@ else
 	KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
 
         # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
+        cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native)
         cflags-$(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_MJAGUAR) += $(call cc-option,-march=btver2)
+        cflags-$(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_MEXCAVATOR) += $(call cc-option,-march=bdver4)
+        cflags-$(CONFIG_MZEN) += $(call cc-option,-march=znver1)
         cflags-$(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_MSKYLAKE) += \
+                $(call cc-option,-march=skylake,$(call cc-option,-mtune=skylake))
+        cflags-$(CONFIG_MSKYLAKEX) += \
+                $(call cc-option,-march=skylake-avx512,$(call cc-option,-mtune=skylake-avx512))
+        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	2018-01-28 16:20:33.000000000 -0500
+++ b/arch/x86/Makefile_32.cpu	2018-03-10 06:47:46.025992644 -0500
@@ -23,7 +23,18 @@ 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_MJAGUAR)	+= $(call cc-option,-march=btver2,-march=athlon)
+cflags-$(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_MEXCAVATOR)	+= $(call cc-option,-march=bdver4,-march=athlon)
+cflags-$(CONFIG_MZEN)	+= $(call cc-option,-march=znver1,-march=athlon)
 cflags-$(CONFIG_MCRUSOE)	+= -march=i686 -falign-functions=0 -falign-jumps=0 -falign-loops=0
 cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) -falign-functions=0 -falign-jumps=0 -falign-loops=0
 cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
@@ -32,8 +43,17 @@ cflags-$(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_MSKYLAKE)	+= -march=i686 $(call tune,skylake)
+cflags-$(CONFIG_MSKYLAKEX)	+= -march=i686 $(call tune,skylake-avx512)
+cflags-$(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