Specific support for Intel Atom architecture
Hi,
as some of you already might know, work is going on to make GCC fully support Intel Atom architecture specifics, i.e. make -mtune=atom generate code optimized for in-order architectures like Intel Atom [1].
I therefore started to make up a small patch which adds Intel Atom as a new processor family which can be selected upon configuration. It's nothing special and also requires a patched GCC. I'd just like to get some feedback on it, i.e. is X86_L1_CACHE_SHIFT=6 ok for Atom CPUs (I was not able to find any information on Atom's cacheline size)? Any chance to include this patch once the Atom patch went into GCC mainline (probably in GCC 4.5)? Any other objections?
Please Cc me, I'm not on the list.
Regards,
Tobias
[1] http://gcc.gnu.org/viewcvs/branches/ix86/atom/
From 6aa86b4431619d38849d469c70904afe1e5a8ca0 Mon Sep 17 00:00:00 2001
From: Tobias Doerffel <[email protected]>
Date: Thu, 30 Apr 2009 12:36:46 +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. This patch requires a GCC with a patch applied which adds specific Intel Atom support.
--- arch/x86/Kconfig.cpu | 19 ++++++++++++++----- arch/x86/Makefile_32.cpu | 1 + arch/x86/include/asm/module.h | 2 ++ 3 files changed, 17 insertions(+), 5 deletions(-)
arch/x86/Kconfig.cpu +14 -5
@@ -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" + depends on X86_32 + ---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 (requires Intel Atom patch in GCC). + 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
@@ -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 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
arch/x86/Makefile_32.cpu +1 -0
@@ -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
arch/x86/include/asm/module.h +2 -0
@@ -28,6 +28,8 @@ struct mod_arch_specific {};#define MODULE_PROC_FAMILY "586MMX "#elif definedCONFIG_MCORE2 #define MODULE_PROC_FAMILY "CORE2 " +#elif definedCONFIG_MATOM +#define MODULE_PROC_FAMILY "ATOM "#elif definedCONFIG_M686 #define MODULE_PROC_FAMILY "686 "#elif definedCONFIG_MPENTIUMII
Signature · 1 line
1.6.2.4
Quoted 118 lines · Tobias Doerffel
Hi,
as some of you already might know, work is going on to make GCC fully support Intel Atom architecture specifics, i.e. make -mtune=atom generate code optimized for in-order architectures like Intel Atom [1].
I therefore started to make up a small patch which adds Intel Atom as a new processor family which can be selected upon configuration. It's nothing special and also requires a patched GCC. I'd just like to get some feedback on it, i.e. is X86_L1_CACHE_SHIFT=6 ok for Atom CPUs (I was not able to find any information on Atom's cacheline size)? Any chance to include this patch once the Atom patch went into GCC mainline (probably in GCC 4.5)? Any other objections?
Please Cc me, I'm not on the list.
Regards,
Tobias
[1] http://gcc.gnu.org/viewcvs/branches/ix86/atom/
From
6aa86b4431619d38849d469c70904afe1e5a8ca0Mon Sep 17 00:00:00 2001
From: Tobias Doerffel <[email protected]>
Date: Thu, 30 Apr 2009 12:36:46 +0200
Subject: [PATCH] x86: add specific support for Intel Atom architectureThis adds another option when selecting CPU family so the kernel can be optimized for Intel Atom CPUs. This patch requires a GCC with a patch applied which adds specific Intel Atom support.
--- arch/x86/Kconfig.cpu | 19 ++++++++++++++----- arch/x86/Makefile_32.cpu | 1 + arch/x86/include/asm/module.h | 2 ++ 3 files changed, 17 insertions(+), 5 deletions(-)arch/x86/Kconfig.cpu +14
-5@@ -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" + depends on X86_32 + ---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 (requires Intel Atom patch in GCC). + 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@@ -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 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 intarch/x86/Makefile_32.cpu +1
-0@@ -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=i486arch/x86/include/asm/module.h +0
-0
arch/x86/include/asm/module.h struct mod_arch_specific {}; · line 35
Quoted 8 lines
arch/x86/include/asm/module.h +2
-0@@ -28,6 +28,8 @@ struct mod_arch_specific {};#define MODULE_PROC_FAMILY "586MMX "#elif definedCONFIG_MCORE2 #define MODULE_PROC_FAMILY "CORE2 " +#elif definedCONFIG_MATOM +#define MODULE_PROC_FAMILY "ATOM "#elif definedCONFIG_M686 #define MODULE_PROC_FAMILY "686 "#elif definedCONFIG_MPENTIUMII
Makes sense. One question would be X86_L1_CACHE_SHIFT - you set it to 2^6 == 64 - that's correct i think, most Atoms come with 64 byte L2 cache AFAIK.
I've Cc:-ed Intel folks - is this assumption about 64 bytes correct?
Ingo
H. Peter Anvin
reviewerQuoted 7 lines · Ingo Molnar
Makes sense. One question would be
X86_L1_CACHE_SHIFT- you set it to 2^6 == 64 - that's correct i think, most Atoms come with 64 byte L2 cache AFAIK.I've Cc:-ed Intel folks - is this assumption about 64 bytes correct?
Seems to be. At least that's what CPUID reports.
-hpa
Signature · 2 lines
H. Peter Anvin, Intel Open Source Technology Center I work for Intel. I don't speak on their behalf.
H. Peter Anvin
reviewerQuoted 10 lines · Ingo Molnar
arch/x86/Makefile_32.cpu cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-f · line 37
Quoted 10 lines
arch/x86/Makefile_32.cpu +1
-0@@ -33,6 +33,7 @@ cflags-$(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)
There should be a fallback option used here rather than requiring a new gcc, e.g. something like:
$(call cc-option,-march=atom,-march=i686)
-hpa
Signature · 2 lines
H. Peter Anvin, Intel Open Source Technology Center I work for Intel. I don't speak on their behalf.
Quoted 15 lines · H. Peter Anvin
Quoted 10 lines · Ingo Molnar
arch/x86/Makefile_32.cpu cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-f · line 37
Quoted 10 lines
arch/x86/Makefile_32.cpu +1
-0@@ -33,6 +33,7 @@ cflags-$(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)There should be a fallback option used here rather than requiring a new gcc, e.g. something like:
Quoted 1 line
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
Willy
H. Peter Anvin
reviewerQuoted 6 lines · Willy Tarreau
Quoted 2 lines
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
Possibly. It would be worth measuring.
-hpa
Signature · 2 lines
H. Peter Anvin, Intel Open Source Technology Center I work for Intel. I don't speak on their behalf.
Am Sonntag, 3. Mai 2009 08:48:54 schrieb H. Peter Anvin:
Quoted 7 lines
Quoted 4 lines · Willy Tarreau
Quoted 1 line
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
Possibly. It would be worth measuring.
How would one do that (never benchmarked kernel stuff before)?
Regards,
Tobias
Quoted 18 lines · On Sun, 3 May 2009 07:38:23 +0200 Willy Tarreau <[email protected]> wrote:
Quoted 17 lines · H. Peter Anvin
Quoted 4 lines · Ingo Molnar
Quoted 4 lines
arch/x86/Makefile_32.cpu +0
-0Quoted 8 lines
Quoted 8 lines
arch/x86/Makefile_32.cpu +0
-0@@ -33,6 +33,7 @@ cflags-$(CONFIG_MCYRIXIII) += $(callcc-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)There should be a fallback option used here rather than requiring a new gcc, e.g. something like:
Quoted 4 lines
Quoted 1 line
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
-march isn't about tuning, it's about supported instructions. The right line is
$(call cc-option,-march=atom,-march=core2)
For tuning, our experience is that currently -mtune=generic works best. Not sure about the gcc's that have complete atom tuning support yet.
Please don't do something like "oh it's in order, so was the Pentium, so lets use that"; it actually gives really really bad results.
Signature · 3 lines
Arjan van de Ven Intel Open Source Technology Centre For development, discussion and tips for power savings, visit http://www.lesswatts.org
Quoted 21 lines · Arjan van de Ven
Quoted 18 lines · On Sun, 3 May 2009 07:38:23 +0200 Willy Tarreau <[email protected]> wrote:
Quoted 17 lines · H. Peter Anvin
Quoted 4 lines · Ingo Molnar
Quoted 4 lines
arch/x86/Makefile_32.cpu +0
-0Quoted 8 lines
Quoted 8 lines
arch/x86/Makefile_32.cpu +0
-0@@ -33,6 +33,7 @@ cflags-$(CONFIG_MCYRIXIII) += $(callcc-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)There should be a fallback option used here rather than requiring a new gcc, e.g. something like:
Quoted 6 lines
Quoted 4 lines
Quoted 1 line
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
-march isn't about tuning, it's about supported instructions.
agreed, but unless specified otherwise using -mtune, -march also sets default tuning for the indicated CPU. At least in my experience.
Quoted 2 lines
The right line is
$(call cc-option,-march=atom,-march=core2)
OK thanks.
Quoted 1 line
For tuning, our experience is that currently -mtune=generic works best.
OK.
Quoted 4 lines
Not sure about the gcc's that have complete atom tuning support yet.
Please don't do something like "oh it's in order, so was the Pentium, so lets use that"; it actually gives really really bad results.
I know, I was not thinking about tuning for an "advanced" CPU such as the pentium, but rather for something generic, hence my proposal of i486 or i386. I did not know about the "generic" target. In my experience, tuning for i386/i486 often shows best overall performance on recent CPUs such as core2. I should try "generic" to compare.
Regards,
Willy
H. Peter Anvin
reviewerQuoted 11 lines · Willy Tarreau
Quoted 5 lines
Quoted 4 lines
Quoted 2 lines
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
-march isn't about tuning, it's about supported instructions.
agreed, but unless specified otherwise using -mtune, -march also sets default tuning for the indicated CPU. At least in my experience.
Quoted 2 lines
The right line is
$(call cc-option,-march=atom,-march=core2)
For really old gcc's (we support all the way back to gcc 3.2 still) -march=core2 might not work either.
-hpa
Signature · 2 lines
H. Peter Anvin, Intel Open Source Technology Center I work for Intel. I don't speak on their behalf.
Quoted 7 lines · H. Peter Anvin
Quoted 6 lines · Willy Tarreau
Quoted 5 lines
Quoted 4 lines
Quoted 2 lines
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
-march isn't about tuning, it's about supported instructions.
Quoted 8 lines
Quoted 5 lines
agreed, but unless specified otherwise using -mtune, -march also sets default tuning for the indicated CPU. At least in my experience.
Quoted 2 lines
The right line is
$(call cc-option,-march=atom,-march=core2)For really old gcc's (we support all the way back to gcc 3.2 still) -march=core2 might not work either.
-march=core2 support was added in gcc 4.3.
Signature · 2 lines
Måns Rullgård [email protected]
Quoted 11 lines · Tobias Doerffel
Hi,
as some of you already might know, work is going on to make GCC fully support Intel Atom architecture specifics, i.e. make -mtune=atom generate code optimized for in-order architectures like Intel Atom [1].
I therefore started to make up a small patch which adds Intel Atom as a new processor family which can be selected upon configuration. It's nothing special and also requires a patched GCC. I'd just like to get some feedback on it, i.e. is X86_L1_CACHE_SHIFT=6 ok for Atom CPUs (I was not able to find any information on Atom's cacheline size)?
64bytes.
Quoted 2 lines
Any chance to include this patch once
the Atom patch went into GCC mainline (probably in GCC 4.5)? Any other
atom support already went into gcc mainline.
Quoted 3 lines
objections?
Please Cc me, I'm not on the list.
FWIW I have a similar patch, but I haven't submitted it yet due to lack of benchmark numbers.
Some comments on yours.
arch/x86/Kconfig.cpu config MCORE2 · line 267
Quoted 11 lines
arch/x86/Kconfig.cpu +3
-0@@ -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" + depends on X86_32
This is wrong, There are Atom CPUs which support 64bit code too.
Quoted 14 lines
arch/x86/Kconfig.cpu +2
-1+ 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
arch/x86/Kconfig.cpu config X86_ALIGNMENT_16 · line 367
Quoted 5 lines
arch/x86/Kconfig.cpu +1
-1@@ -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?
arch/x86/Kconfig.cpu config X86_ALIGNMENT_16 · line 371
Quoted 5 lines
arch/x86/Kconfig.cpu +1
-1config 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.
Quoted 9 lines
arch/x86/Kconfig.cpu +0
-0config X86_USE_3DNOW config X86_MINIMUM_CPU_FAMILY intarch/x86/Makefile_32.cpu +0
-0
arch/x86/Makefile_32.cpu cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-f · line 39
Quoted 7 lines
arch/x86/Makefile_32.cpu +1
-0@@ -33,6 +33,7 @@ cflags-$(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.
arch/x86/include/asm/module.h struct mod_arch_specific {}; · line 32
Quoted 10 lines
arch/x86/include/asm/module.h +2
-0@@ -28,6 +28,8 @@ struct mod_arch_specific {};#define MODULE_PROC_FAMILY "586MMX "#elif definedCONFIG_MCORE2 #define MODULE_PROC_FAMILY "CORE2 " +#elif definedCONFIG_MATOM +#define MODULE_PROC_FAMILY "ATOM "
This should be obsolete anyways, you can just uses CORE2. They have compatible ISAs.
-Andi
Signature · 1 line
[email protected] -- Speaking for myself only.
Quoted 10 lines · Tobias Doerffel
Am Sonntag, 3. Mai 2009 08:48:54 schrieb H. Peter Anvin:
Quoted 7 lines
Quoted 4 lines · Willy Tarreau
Quoted 1 line
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
Possibly. It would be worth measuring.
How would one do that (never benchmarked kernel stuff before)?
A standard method is to run lmbench and compare the results - lmbench has a built-in 'report comparison between two runs' feature.
Ingo
Quoted 10 lines · On Mon, 4 May 2009 15:14:57 +0200 Ingo Molnar <[email protected]> wrote:
Quoted 7 lines · Tobias Doerffel
Am Sonntag, 3. Mai 2009 08:48:54 schrieb H. Peter Anvin:
Quoted 6 lines
Quoted 4 lines · Willy Tarreau
Quoted 1 line
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
Quoted 6 lines
Quoted 3 lines
Quoted 1 line
Possibly. It would be worth measuring.
How would one do that (never benchmarked kernel stuff before)?
A standard method is to run lmbench and compare the results - lmbench has a built-in 'report comparison between two runs' feature.
well... you're normally REALLY hard pressed to measure compiler differences this way.....
normally compiler options get benchmarked using speccpu and the like....
Signature · 3 lines
Arjan van de Ven Intel Open Source Technology Centre For development, discussion and tips for power savings, visit http://www.lesswatts.org
Quoted 21 lines · Arjan van de Ven
Quoted 10 lines · On Mon, 4 May 2009 15:14:57 +0200 Ingo Molnar <[email protected]> wrote:
Quoted 7 lines · Tobias Doerffel
Am Sonntag, 3. Mai 2009 08:48:54 schrieb H. Peter Anvin:
Quoted 6 lines
Quoted 4 lines · Willy Tarreau
Quoted 1 line
$(call cc-option,-march=atom,-march=i686)
if it's an in-order architecture, wouldn't it be better to tune for i386 or i486 instead ?
Quoted 7 lines
Quoted 3 lines
Quoted 1 line
Possibly. It would be worth measuring.
How would one do that (never benchmarked kernel stuff before)?
A standard method is to run lmbench and compare the results - lmbench has a built-in 'report comparison between two runs' feature.
Quoted 5 lines
well... you're normally REALLY hard pressed to measure compiler differences this way.....
normally compiler options get benchmarked using speccpu and the like....
Well, if there's no measurable difference in lmbench at all then the options probably dont matter that much. If some workload is found where compiler options show a difference then that matters. Speccpu only matters if those compiler options also help the kernel, in a measurable way.
Ingo
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:
Quoted 1 line
This is wrong, There are Atom CPUs which support 64bit code too.
Fixed.
Quoted 4 lines
Quoted 4 lines
config
X86_XADD(quoted diff) +0
-0def_bool y@@ -355,11 +364,11 @@ config X86_ALIGNMENT_16
Quoted 10 lines
Quoted 6 lines
(quoted diff) +0
-1config 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 || MATOMI 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.
Quoted 10 lines
Quoted 8 lines
config
X86_USE_PPRO_CHECKSUM(quoted diff) +0
-1def_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 || MATOMSimilar 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.
Quoted 11 lines
Quoted 11 lines
arch/x86/Makefile_32.cpu +0
-0@@ -33,6 +33,7 @@ cflags-$(CONFIG_MCYRIXIII) += $(callcc-option,-march=c3,-march=i486) $(align)-f cflags-$(CONFIG_MVIAC3_2) +=
$(call cc-option,-march=c3-2,-march=i686) cflags-$(CONFIG_MVIAC7) +=arch/x86/Makefile_32.cpu +1
-1-march=i686 cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) +cflags-$(CONFIG_MATOM) += -march=atom $(call tune,atom)
Quoted 4 lines
Quoted 2 lines
# AMD Elan support
cflags-$(CONFIG_X86_ELAN) += -march=i486That needs to be in the 64bit version too.
Fixed as well. Also included changes to call cc-option as recommended by hpa.
Quoted 5 lines
Quoted 5 lines
(quoted diff) +0
-0
b/arch/x86/include/asm/module.hindex 47d6274..e959c4a 100644arch/x86/include/asm/module.h +0
-0@@ -28,6 +28,8 @@ struct mod_arch_specific {};
Quoted 8 lines
arch/x86/include/asm/module.h struct mod_arch_specific {}; · line 32
Quoted 5 lines
arch/x86/include/asm/module.h +2
-0#define MODULE_PROC_FAMILY "586MMX "#elif definedCONFIG_MCORE2 #define MODULE_PROC_FAMILY "CORE2 " +#elif definedCONFIG_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 <[email protected]>
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(-)
arch/x86/Kconfig.cpu +13 -4
@@ -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
arch/x86/Makefile +2 -0
@@ -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 += $(cflags-y)
arch/x86/Makefile_32.cpu +1 -0
@@ -33,6 +33,7 @@ cflags-$(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
arch/x86/include/asm/module.h +2 -0
@@ -28,6 +28,8 @@ struct mod_arch_specific {};#define MODULE_PROC_FAMILY "586MMX "#elif definedCONFIG_MCORE2 #define MODULE_PROC_FAMILY "CORE2 " +#elif definedCONFIG_MATOM +#define MODULE_PROC_FAMILY "ATOM "#elif definedCONFIG_M686 #define MODULE_PROC_FAMILY "686 "#elif definedCONFIG_MPENTIUMII
Signature · 1 line
1.6.2.4
Quoted 13 lines · Tobias Doerffel
Quoted 5 lines
Quoted 5 lines
(quoted diff) +0
-0
b/arch/x86/include/asm/module.hindex 47d6274..e959c4a 100644arch/x86/include/asm/module.h +0
-0@@ -28,6 +28,8 @@ struct mod_arch_specific {};Quoted 8 lines
arch/x86/include/asm/module.h struct mod_arch_specific {}; · line 32
Quoted 5 lines
arch/x86/include/asm/module.h +2
-0#define MODULE_PROC_FAMILY "586MMX "#elif definedCONFIG_MCORE2 #define MODULE_PROC_FAMILY "CORE2 " +#elif definedCONFIG_MATOM +#define MODULE_PROC_FAMILY "ATOM "This should be obsolete anyways, you can just uses CORE2. They have compatible ISAs.
Quoted 6 lines
So you would recommend writing
#elif defined
CONFIG_MCORE2|| definedCONFIG_ATOM#defineMODULE_PROC_FAMILY"CORE2 "?
Yes. Or maybe you can find a better name.
-Andi
Signature · 1 line
[email protected] -- Speaking for myself only.
Quoted 1 line · Andi Kleen
This should be obsolete anyways, you can just uses CORE2. They have compatible ISAs.
Only correct if you don't plan to use the movbe instruction. The kernel would be the one place where I can imagine this to make sense.
Quoted 5 lines · Ulrich Drepper
Quoted 1 line · Andi Kleen
This should be obsolete anyways, you can just uses CORE2. They have compatible ISAs.
Only correct if you don't plan to use the movbe instruction. The kernel would be the one place where I can imagine this to make sense.
The problem is that you can't express the situations where movbe is better than bswap (you need both and the old and the new value) in inline assembler in a way that gcc decides automatically.
I also doubt there are many (any?) situations in the kernel where the destruction of the old register is a problem in the kernel; e.g. the network stack normally doesn't care.
My understanding is that movbe is really mainly useful for some special situations where you run a emulator/jit for a BE ISA, but that's not something the kernel does.
-Andi
Signature · 1 line
[email protected] -- Speaking for myself only.
Quoted 3 lines · Andi Kleen
The problem is that you can't express the situations where movbe is better than bswap (you need both and the old and the new value) in inline assembler in a way that gcc decides automatically.
True. But I was mostly thinking about loads from memory. A quick search for ntoh*/hton* shows code like
u_int16_t queue_num = ntohs(nfmsg->res_id);
If there would be a ntohs_load() macro movbe could be used.
Quoted 11 lines · Ulrich Drepper
Quoted 3 lines · Andi Kleen
The problem is that you can't express the situations where movbe is better than bswap (you need both and the old and the new value) in inline assembler in a way that gcc decides automatically.
True. But I was mostly thinking about loads from memory. A quick search for ntoh*/hton* shows code like
u_int16_t queue_num = ntohs(nfmsg->res_id);If there would be a
ntohs_load()macro movbe could be used.
It wouldn't surprise me if
movbe memory,%reg
generates the same uops sequence internally as
mov memory,%reg
bswap %reg
I doubt there's any dedicated hardware for this in Atom (but I don't know for sure)
So unless you're really decoding constrained it would only save a few bytes of code size. Probably not worth having incompatible modules for or adding special code to the source.
-Andi
Signature · 1 line
[email protected] -- Speaking for myself only.
Quoted 11 lines · Ulrich Drepper
Quoted 3 lines · Andi Kleen
The problem is that you can't express the situations where movbe is better than bswap (you need both and the old and the new value) in inline assembler in a way that gcc decides automatically.
True. But I was mostly thinking about loads from memory. A quick search for ntoh*/hton* shows code like
u_int16_t queue_num = ntohs(nfmsg->res_id);If there would be a
ntohs_load()macro movbe could be used.
It's called be16_to_cpup, or on x86, swab16p()
Cheers,
Harvey
Quoted 1 line · Harvey Harrison
It's called
be16_to_cpup, or on x86,swab16p()
Indeed. If now somebody with an Atom could test whether using movbe has an advantage (my guess is that there is a slight advantage) then one could define a special version of the __beXX_to_cpup and __cpu_to_beXXp functions for Atom and start using these functions more rigorously in the tree.
Quoted 6 lines · Ulrich Drepper
Quoted 1 line · Harvey Harrison
It's called
be16_to_cpup, or on x86,swab16p()Indeed. If now somebody with an Atom could test whether using movbe has an advantage (my guess is that there is a slight advantage) then
How would you test that?
-Andi
Signature · 1 line
[email protected] -- Speaking for myself only.
Quoted 1 line · Andi Kleen
How would you test that?
Compare runtimes with mov+bswap for some simple code which uses the value after the conversion (e.g., just add to something).
Or in your case: get the Atom designers to comment.
Quoted 7 lines · Ulrich Drepper
Quoted 1 line · Andi Kleen
How would you test that?
Compare runtimes with mov+bswap for some simple code which uses the value after the conversion (e.g., just add to something).
Or in your case: get the Atom designers to comment.
Don't really need Atom designers; you can prove or disprove my theory (that they generate the same uops sequence) by checking the uops performance counter for a micro benchmark.
However even if that was not the case I have some doubts the kernel is doing enough endian conversions that it really matters.
For example the network stack is doing maybe 4-5 endian conversions (very conservative estimate) per packet and processing a packet takes tens of thousands of cycles. But at best you could save 1-2 cycles this way, so even if you save a few cycles this way it will be very likely in the noise.
-Andi
Signature · 1 line
[email protected] -- Speaking for myself only.