Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ATLAS.spkg: add Altivec errata support for Linux PPC #3791

Closed
sagetrac-mabshoff mannequin opened this issue Aug 8, 2008 · 6 comments
Closed

ATLAS.spkg: add Altivec errata support for Linux PPC #3791

sagetrac-mabshoff mannequin opened this issue Aug 8, 2008 · 6 comments

Comments

@sagetrac-mabshoff
Copy link
Mannequin

sagetrac-mabshoff mannequin commented Aug 8, 2008

I was told that this line means that altivec was not detected.
For atlas on linux ppc with altivec, we should use the options
--cflags='-mregnames' -D c -DATL_AVgcc
for configure ( http://math-atlas.sourceforge.net/errata.html#G4gcc ).

With these options, I had "Vector ISA Extension configured as  AltiVec (1,2)".

Best regards,
Bin 

CC: @kiwifb @jpflori

Component: build

Issue created by migration from https://trac.sagemath.org/ticket/3791

@sagetrac-mabshoff sagetrac-mabshoff mannequin added this to the sage-3.2 milestone Aug 8, 2008
@sagetrac-mabshoff sagetrac-mabshoff mannequin self-assigned this Aug 8, 2008
@sagetrac-mabshoff sagetrac-mabshoff mannequin modified the milestones: sage-3.2, sage-3.1.3 Sep 30, 2008
@jdemeyer jdemeyer modified the milestones: sage-5.11, sage-5.12 Aug 13, 2013
@sagetrac-vbraun-spam sagetrac-vbraun-spam mannequin modified the milestones: sage-6.1, sage-6.2 Jan 30, 2014
@sagetrac-vbraun-spam sagetrac-vbraun-spam mannequin modified the milestones: sage-6.2, sage-6.3 May 6, 2014
@sagetrac-vbraun-spam sagetrac-vbraun-spam mannequin modified the milestones: sage-6.3, sage-6.4 Aug 10, 2014
@kcrisman
Copy link
Member

kcrisman commented Jan 5, 2015

comment:7

What do you guys think - is this still valid?

@jpflori
Copy link

jpflori commented Jan 5, 2015

comment:8

Frankly, I'd say we don't care about such systems...
And from the ticket description it just seems that ATLAS won't be optimized on such systems but would still build.

@kiwifb
Copy link
Member

kiwifb commented Jan 5, 2015

comment:9

My own experience is that you need to let ATLAS set its own flags on power7 and probably other ppc(64) arch. It detects and adds altivec/vsx flags appropriately. If you touch CFLAGS you have to make sure to include flags that activate altivec (appropriate -mcpu and -mtune does the trick the CPPFLAGS should be included automatically and failure to include the right flags will result in a compilation failure at some point).

Is this for your project of building a last tiger ppc binary?

@kcrisman
Copy link
Member

kcrisman commented Jan 5, 2015

comment:10

Is this for your project of building a last tiger ppc binary?

No, although that is going fine. This is just me seeing random tickets that possibly could be closed as wontfix/invalid... I can't say whether it would but if you both agree then I say you should do so :)

@kiwifb
Copy link
Member

kiwifb commented Jan 5, 2015

comment:12

I am putting it as "invalid".

@vbraun
Copy link
Member

vbraun commented Jan 13, 2015

comment:13

You are supposed to change the milestone to "duplicate/invalid/wontfix" then...

@vbraun vbraun closed this as completed Jan 13, 2015
@vbraun vbraun removed this from the sage-6.4 milestone Jan 13, 2015
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

5 participants