lkml.org 
[lkml]   [2009]   [May]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
SubjectRe: Specific support for Intel Atom architecture
Date
Hi,

thanks for your comments. Fixed some of your remarks and attached a new patch.

Am Montag, 4. Mai 2009 09:22:46 schrieb Andi Kleen:
> This is wrong, There are Atom CPUs which support 64bit code too.
Fixed.

> > config X86_XADD
> > def_bool y
> > @@ -355,11 +364,11 @@ 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 || MK7 || MEFFICEON || MCORE2 || MATOM
>
> I don't think that's necessarily a good idea. You would need benchmarks
> showing that intel user copy performs better on Atom than the original one.
> Do you have some?
You're right here. I made some quick benchmarks of
__copy_user[_intel[_nocache]]() and __copy_zeroing[_intel[_nocache]]() in
userspace and the generic ones indeed were about 15% faster.

> > config X86_USE_PPRO_CHECKSUM
> > def_bool y
> > - depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 ||
> > MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 ||
> > MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2 + depends on MWINCHIP3D ||
> > MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM ||
> > MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON ||
> > MGEODE_LX || MCORE2 || MATOM
>
> Similar here. Atom is quite different from PPro/K8.
Made some benchmarks of csum_partial() and csum_partial_copy_generic() as
well. Here the PPro version of csum_partial() performed 10-15% better
(depending on buffer len) while both implementations of
csum_partial_copy_generic() performed equal.


> > diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
> > index 80177ec..07a11b0 100644
> > --- a/arch/x86/Makefile_32.cpu
> > +++ b/arch/x86/Makefile_32.cpu
> > @@ -33,6 +33,7 @@ cflags-$(CONFIG_MCYRIXIII) += $(call
> > cc-option,-march=c3,-march=i486) $(align)-f cflags-$(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) += -march=atom $(call tune,atom)
> >
> > # AMD Elan support
> > cflags-$(CONFIG_X86_ELAN) += -march=i486
>
> That needs to be in the 64bit version too.
Fixed as well. Also included changes to call cc-option as recommended by hpa.

> > diff --git a/arch/x86/include/asm/module.h
> > b/arch/x86/include/asm/module.h index 47d6274..e959c4a 100644
> > --- a/arch/x86/include/asm/module.h
> > +++ b/arch/x86/include/asm/module.h
> > @@ -28,6 +28,8 @@ struct mod_arch_specific {};
> > #define MODULE_PROC_FAMILY "586MMX "
> > #elif defined CONFIG_MCORE2
> > #define MODULE_PROC_FAMILY "CORE2 "
> > +#elif defined CONFIG_MATOM
> > +#define MODULE_PROC_FAMILY "ATOM "
>
> This should be obsolete anyways, you can just uses CORE2. They have
> compatible ISAs.
So you would recommend writing

#elif defined CONFIG_MCORE2 || defined CONFIG_ATOM
#define MODULE_PROC_FAMILY "CORE2 "

?

Regards,

Tobias
From bd9378b21f86a783dc17a741d2167e7158070d97 Mon Sep 17 00:00:00 2001
From: Tobias Doerffel <tobias.doerffel@gmail.com>
Date: Mon, 11 May 2009 23:20:54 +0200
Subject: [PATCH] x86: add specific support for Intel Atom architecture

This adds another option when selecting CPU family so the kernel can
be optimized for Intel Atom CPUs. If GCC supports tuning options for
Intel Atom they will be used.
---
arch/x86/Kconfig.cpu | 17 +++++++++++++----
arch/x86/Makefile | 2 ++
arch/x86/Makefile_32.cpu | 1 +
arch/x86/include/asm/module.h | 2 ++
4 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 8130334..f88a7f6 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -262,6 +262,15 @@ config MCORE2
family in /proc/cpuinfo. Newer ones have 6 and older ones 15
(not a typo)

+config MATOM
+ bool "Intel Atom"
+ ---help---
+
+ Select this for Intel Atom platform. Intel Atom CPUs have an in-order
+ pipelining architecture and thus can benefit from in-order optimized
+ code. Use a recent GCC with specific Intel Atom support in order to
+ fully benefit from selecting this option.
+
config GENERIC_CPU
bool "Generic-x86-64"
depends on X86_64
@@ -310,7 +319,7 @@ config X86_L1_CACHE_SHIFT
default "7" if MPENTIUM4 || MPSC
default "4" if X86_ELAN || M486 || M386 || MGEODEGX1
default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
- default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7 || X86_GENERIC || GENERIC_CPU
+ default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU

config X86_XADD
def_bool y
@@ -359,7 +368,7 @@ config X86_INTEL_USERCOPY

config X86_USE_PPRO_CHECKSUM
def_bool y
- depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2
+ depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM

config X86_USE_3DNOW
def_bool y
@@ -387,7 +396,7 @@ 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) && !X86_NUMAQ) || X86_64
+ 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

config X86_CMPXCHG64
def_bool y
@@ -397,7 +406,7 @@ 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)
+ depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM)

config X86_MINIMUM_CPU_FAMILY
int
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8c86b72..3cfbd74 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -57,6 +57,8 @@ else

cflags-$(CONFIG_MCORE2) += \
$(call cc-option,-march=core2,$(call cc-option,-mtune=generic))
+ cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \
+ $(call cc-option,-mtune=atom)
cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
KBUILD_CFLAGS += $(cflags-y)

diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 80177ec..4470fa0 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -33,6 +33,7 @@ cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-f
cflags-$(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,-march=core2) $(call cc-option,-mtune=atom)

# AMD Elan support
cflags-$(CONFIG_X86_ELAN) += -march=i486
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 47d6274..e959c4a 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -28,6 +28,8 @@ struct mod_arch_specific {};
#define MODULE_PROC_FAMILY "586MMX "
#elif defined CONFIG_MCORE2
#define MODULE_PROC_FAMILY "CORE2 "
+#elif defined CONFIG_MATOM
+#define MODULE_PROC_FAMILY "ATOM "
#elif defined CONFIG_M686
#define MODULE_PROC_FAMILY "686 "
#elif defined CONFIG_MPENTIUMII
--
1.6.2.4
[unhandled content-type:application/pgp-signature]
\
 
 \ /
  Last update: 2009-05-11 23:33    [W:0.101 / U:0.020 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site