JiscMail Logo
Email discussion lists for the UK Education and Research communities

Help for COMP-FORTRAN-90 Archives


COMP-FORTRAN-90 Archives

COMP-FORTRAN-90 Archives


COMP-FORTRAN-90@JISCMAIL.AC.UK


View:

Message:

[

First

|

Previous

|

Next

|

Last

]

By Topic:

[

First

|

Previous

|

Next

|

Last

]

By Author:

[

First

|

Previous

|

Next

|

Last

]

Font:

Proportional Font

LISTSERV Archives

LISTSERV Archives

COMP-FORTRAN-90 Home

COMP-FORTRAN-90 Home

COMP-FORTRAN-90  September 2015

COMP-FORTRAN-90 September 2015

Options

Subscribe or Unsubscribe

Subscribe or Unsubscribe

Log In

Log In

Get Password

Get Password

Subject:

Re: atomic: 2 compilers - 2 results

From:

Bill Long <[log in to unmask]>

Reply-To:

Fortran 90 List <[log in to unmask]>

Date:

Sat, 19 Sep 2015 16:23:46 +0000

Content-Type:

text/plain

Parts/Attachments:

Parts/Attachments

text/plain (86 lines)

On Sep 18, 2015, at 4:00 AM, Anton Shterenlikht <[log in to unmask]> wrote:

> I think this program is conforming:
> 
> program mumu
> use, intrinsic :: iso_fortran_env
> implicit none
> integer( atomic_int_kind ) :: z[*]
> integer :: p, q, var
> p = 1
> q = num_images()
> z = 0
> if ( this_image() .eq. p .or. this_image() .eq. q ) &
>  write (*,*) "before: img:", this_image(), "z:", z
> if ( this_image() .eq. p ) call atomic_define( z[q], 1 )
> if ( this_image() .eq. q ) then
>  do
>    call atomic_ref( var, z )
>    if ( var .eq. 1 ) exit
>  end do
>  write (*,*) "got it, img:", this_image(), "var:", var, "z:", z
> end if
> if ( this_image() .eq. p .or. this_image() .eq. q ) &
>  write (*,*) "after: img:", this_image(), "z:", z
> end program mumu
> 
> This is adapted from example in MFE, p. 416.
> Coarray z is defined on P and referenced on Q in
> unordered segments (there is only a single segment
> on each image, therefore unordered).
> 
> I think 8.5.2 par 3 makes this code conforming:
> 
> *quote*
> A coarray may be referenced or defined by execution
> of an atomic subroutine during the execution of a segment
> that is unordered relative to the execution of a segment
> in which the coarray is referenced or defined by execution
> of an atomic subroutine.
> *end quote*


This exemption applies to atomic reference and defines only.  The text following “Otherwise…” disallows a non-atomic reference of a variable defined by a different image in an unordered segment.  As you correctly point out, there is only segment on each of the two relevant images, and those segments are unordered.  In the segment executing on image q, there is a non-atomic reference to z in the write statement 

write (*,*) "got it, img:", this_image(), "var:", var, "z:", z

which, I believe, technically makes the code not conforming. 

If you insert a SYNC MEMORY statement (as suggested by Harvey)  just before this statement, you create a new segment, and the interaction of the atomic defines and references should provide sufficient ordering to get what you expect as the “correct” output.

Cheers,
Bill

> 
> If the code is conforming, then what should be the
> correct answer?
> 
> One compiler gives this on 16 images:
> 
> before: img:           1 z:           0
> before: img:          16 z:           0
> after: img:           1 z:           0
> got it, img:          16 var:           1 z:           1
> after: img:          16 z:           1
> 
> which is correct, I think.
> 
> Another compiler gives this on 24 images:
> 
> before: img: 24 z: 0
> before: img: 1 z: 0
> got it, img: 24 var: 1 z: 0
> after: img: 24 z: 0
> after: img: 1 z: 0
> 
> which is wrong, I think. On image 24 var must
> be of the same value as z.
> 
> Please comment
> 
> Anton

Bill Long                                                                       [log in to unmask]
Fortran Technical Support  &                                  voice:  651-605-9024
Bioinformatics Software Development                     fax:  651-605-9142
Cray Inc./ Cray Plaza, Suite 210/ 380 Jackson St./ St. Paul, MN 55101

Top of Message | Previous Page | Permalink

JiscMail Tools


RSS Feeds and Sharing


Advanced Options


Archives

September 2018
August 2018
July 2018
May 2018
April 2018
March 2018
February 2018
January 2018
December 2017
November 2017
October 2017
September 2017
August 2017
July 2017
June 2017
May 2017
April 2017
March 2017
January 2017
December 2016
November 2016
October 2016
September 2016
August 2016
July 2016
June 2016
May 2016
April 2016
March 2016
February 2016
December 2015
November 2015
October 2015
September 2015
August 2015
June 2015
April 2015
March 2015
January 2015
December 2014
November 2014
October 2014
August 2014
July 2014
May 2014
April 2014
March 2014
February 2014
January 2014
December 2013
November 2013
July 2013
June 2013
May 2013
April 2013
February 2013
January 2013
December 2012
November 2012
October 2012
September 2012
August 2012
July 2012
June 2012
April 2012
March 2012
February 2012
January 2012
December 2011
November 2011
October 2011
September 2011
August 2011
July 2011
June 2011
May 2011
April 2011
March 2011
February 2011
January 2011
December 2010
November 2010
October 2010
August 2010
July 2010
June 2010
March 2010
February 2010
January 2010
December 2009
October 2009
August 2009
July 2009
June 2009
March 2009
February 2009
January 2009
December 2008
November 2008
October 2008
September 2008
August 2008
July 2008
June 2008
May 2008
April 2008
March 2008
February 2008
December 2007
November 2007
October 2007
September 2007
August 2007
July 2007
June 2007
May 2007
April 2007
March 2007
January 2007
2006
2005
2004
2003
2002
2001
2000
1999
1998
1997


JiscMail is a Jisc service.

View our service policies at https://www.jiscmail.ac.uk/policyandsecurity/ and Jisc's privacy policy at https://www.jisc.ac.uk/website/privacy-notice

Secured by F-Secure Anti-Virus CataList Email List Search Powered by the LISTSERV Email List Manager