Re: About mtune=atom

2011-01-25 Thread Ian Pilcher
On 01/24/2011 10:07 AM, Kevin Kofler wrote: > Because everything that's not an Atom should be using x86_64 these days > (unless it's ancient, in which case you can't be aiming at performance that > much or you'd have already bought a newer, much faster CPU ;-) ). I can't wait to try that on my bra

Re: About mtune=atom

2011-01-25 Thread Matthew Miller
On Tue, Jan 25, 2011 at 08:02:35AM +0100, Kevin Kofler wrote: > > Although, pedantically, I have to point out that the 1%s you list are not > > all synonymous. > Indeed, a 1% reduction in CPU time per process is a 1.0101…% increase in > processes/hr. ;-) But that's being very pedantic. ;-) Yeah t

Re: About mtune=atom

2011-01-24 Thread Adam Williamson
On Mon, 2011-01-24 at 09:25 -0800, John Reiser wrote: > On 01/24/2011 07:43 AM, drago01 wrote: > > On Mon, Jan 24, 2011 at 3:32 PM, Sergio Belkin wrote: > >> Hi, > >> > >> I've read on > >> http://fedoraproject.org/wiki/Packaging:RPMMacros#Build_flags_macros_and_variables > >> that mtune=atom. Ju

Re: About mtune=atom

2011-01-24 Thread Kevin Kofler
Bill Nottingham wrote: > Am I missing something, or would this [*] also be binary-incompatible? If > so, that's very very very much not worth the effort. +1 I don't think having another Fedora build for x86_64 machines is worth the effort. (And it definitely doesn't make sense to replace the tru

Re: About mtune=atom

2011-01-24 Thread Kevin Kofler
Matthew Miller wrote: > Although, pedantically, I have to point out that the 1%s you list are not > all synonymous. Indeed, a 1% reduction in CPU time per process is a 1.0101…% increase in processes/hr. ;-) But that's being very pedantic. ;-) Kevin Kofler -- devel mailing list devel@li

Re: About mtune=atom

2011-01-24 Thread Gilboa Davara
On Mon, 2011-01-24 at 17:07 +0100, Kevin Kofler wrote: > Sergio Belkin wrote: > > I've read on > > http://fedoraproject.org/wiki/Packaging:RPMMacros#Build_flags_macros_and_variables > > that mtune=atom. Just because I'm curious, why? :) > > Because everything that's not an Atom should be using x8

Re: About mtune=atom

2011-01-24 Thread Matthew Miller
On Mon, Jan 24, 2011 at 05:30:49PM -0800, John Reiser wrote: > > On Mon, Jan 24, 2011 at 04:43:47PM -0800, John Reiser wrote: > >>> This seems like it might be useful in many virtual machine setups. Can you > >>> quantify "measurable"? > >> "Measurable" means 1% or more. Obviously this depends on

Re: About mtune=atom

2011-01-24 Thread John Reiser
On 01/24/2011 05:11 PM, Matthew Miller wrote: > On Mon, Jan 24, 2011 at 04:43:47PM -0800, John Reiser wrote: >>> This seems like it might be useful in many virtual machine setups. Can you >>> quantify "measurable"? > >> "Measurable" means 1% or more. Obviously this depends on the workload. > > 1

Re: About mtune=atom

2011-01-24 Thread Matthew Miller
On Mon, Jan 24, 2011 at 04:43:47PM -0800, John Reiser wrote: > > This seems like it might be useful in many virtual machine setups. Can you > > quantify "measurable"? > "Measurable" means 1% or more. Obviously this depends on the workload. 1% or more _what_? Performance gain? -- Matthew Mil

Re: About mtune=atom

2011-01-24 Thread John Reiser
On 01/24/2011 03:53 PM, Matthew Miller wrote: > This seems like it might be useful in many virtual machine setups. Can you > quantify "measurable"? "Measurable" means 1% or more. Obviously this depends on the workload. All code gets 16 general registers and the first six integer/pointer arguments

Re: About mtune=atom

2011-01-24 Thread Matthew Miller
On Mon, Jan 24, 2011 at 09:25:45AM -0800, John Reiser wrote: > Actually many of them should be using the new x86_32 software architecture, > which is the 64-bit instruction set (thus 16 "general" registers, SSE, ...) > but with integers, longs, and pointers all 32 bits. The upper 32 bits > of any

Re: About mtune=atom

2011-01-24 Thread Xose Vazquez Perez
Bill Nottingham wrote: > Am I missing something, or would this also be binary-incompatible? If so, > that's very very very much not worth the effort. - X32 System V Application Binary Interface: A new 32bit psABI for x86-64 with 32bit pointer size. https://sites.google.com/site/x32abi/ -- d

Re: About mtune=atom

2011-01-24 Thread Jakub Jelinek
On Mon, Jan 24, 2011 at 12:55:59PM -0500, Bill Nottingham wrote: > Jakub Jelinek (ja...@redhat.com) said: > > On Mon, Jan 24, 2011 at 09:25:45AM -0800, John Reiser wrote: > > > Actually many of them should be using the new x86_32 software > > > architecture, > > > which is the 64-bit instruction

Re: About mtune=atom

2011-01-24 Thread Peter Robinson
On Mon, Jan 24, 2011 at 5:45 PM, Richard W.M. Jones wrote: > On Mon, Jan 24, 2011 at 09:25:45AM -0800, John Reiser wrote: >> On 01/24/2011 07:43 AM, drago01 wrote: >> > It is the only 32bit only CPU still being sold, >> >> There are plenty of machines with 32-bit only CPUs (such as early Celeron,

Re: About mtune=atom

2011-01-24 Thread Bill Nottingham
Jakub Jelinek (ja...@redhat.com) said: > On Mon, Jan 24, 2011 at 09:25:45AM -0800, John Reiser wrote: > > Actually many of them should be using the new x86_32 software architecture, > > which is the 64-bit instruction set (thus 16 "general" registers, SSE, ...) > > but with integers, longs, and po

Re: About mtune=atom

2011-01-24 Thread Jakub Jelinek
On Mon, Jan 24, 2011 at 09:25:45AM -0800, John Reiser wrote: > Actually many of them should be using the new x86_32 software architecture, > which is the 64-bit instruction set (thus 16 "general" registers, SSE, ...) > but with integers, longs, and pointers all 32 bits. The upper 32 bits > of any

Re: About mtune=atom

2011-01-24 Thread Richard W.M. Jones
On Mon, Jan 24, 2011 at 09:25:45AM -0800, John Reiser wrote: > On 01/24/2011 07:43 AM, drago01 wrote: > > It is the only 32bit only CPU still being sold, > > There are plenty of machines with 32-bit only CPUs (such as early Celeron, > Pentium socket 478, even some Core Duos [Apple Mini]) which ru

Re: About mtune=atom

2011-01-24 Thread Przemek Klosowski
On 01/24/2011 12:25 PM, John Reiser wrote: > On 01/24/2011 07:43 AM, drago01 wrote: >> On Mon, Jan 24, 2011 at 3:32 PM, Sergio Belkin wrote: >>> Hi, >>> >>> I've read on >>> http://fedoraproject.org/wiki/Packaging:RPMMacros#Build_flags_macros_and_variables >>> that mtune=atom. Just because I'm cu

Re: About mtune=atom

2011-01-24 Thread drago01
On Mon, Jan 24, 2011 at 6:25 PM, John Reiser wrote: > On 01/24/2011 07:43 AM, drago01 wrote: >> On Mon, Jan 24, 2011 at 3:32 PM, Sergio Belkin wrote: >>> Hi, >>> >>> I've read on >>> http://fedoraproject.org/wiki/Packaging:RPMMacros#Build_flags_macros_and_variables >>> that mtune=atom. Just beca

Re: About mtune=atom

2011-01-24 Thread John Reiser
On 01/24/2011 07:43 AM, drago01 wrote: > On Mon, Jan 24, 2011 at 3:32 PM, Sergio Belkin wrote: >> Hi, >> >> I've read on >> http://fedoraproject.org/wiki/Packaging:RPMMacros#Build_flags_macros_and_variables >> that mtune=atom. Just because I'm curious, why? :) > > Why not? > > It is the only 3

Re: About mtune=atom

2011-01-24 Thread Kevin Kofler
Sergio Belkin wrote: > I've read on > http://fedoraproject.org/wiki/Packaging:RPMMacros#Build_flags_macros_and_variables > that mtune=atom. Just because I'm curious, why? :) Because everything that's not an Atom should be using x86_64 these days (unless it's ancient, in which case you can't be ai

Re: About mtune=atom

2011-01-24 Thread drago01
On Mon, Jan 24, 2011 at 3:32 PM, Sergio Belkin wrote: > Hi, > > I've read on > http://fedoraproject.org/wiki/Packaging:RPMMacros#Build_flags_macros_and_variables > that mtune=atom. Just because I'm curious, why?  :) Why not? It is the only 32bit only CPU still being sold, and it does not seem t