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

Help for TB-SUPPORT Archives


TB-SUPPORT Archives

TB-SUPPORT Archives


TB-SUPPORT@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

TB-SUPPORT Home

TB-SUPPORT Home

TB-SUPPORT  April 2019

TB-SUPPORT April 2019

Options

Subscribe or Unsubscribe

Subscribe or Unsubscribe

Log In

Log In

Get Password

Get Password

Subject:

Re: HS06 results

From:

Alessandra Forti <[log in to unmask]>

Reply-To:

Testbed Support for GridPP member institutes <[log in to unmask]>

Date:

Tue, 2 Apr 2019 14:53:42 +0100

Content-Type:

text/plain

Parts/Attachments:

Parts/Attachments

text/plain (368 lines)

Hi,

I still have 1.1 but 32bit still fails for me even with these changes.

cheers
alessandra



On 28/03/2019 10:16, Daniel Traynor wrote:
> As Simon says adding
>
> -include cstddef" to your CXXPORTABILITY
>
> enables 64bit compilation
>
> Also installing (as stated in https://www.gridpp.ac.uk/wiki/Benchmarking_procedure)
> glibc-devel.i686
> compat-libstdc++-33.i686
> libstdc++.i686
> libstdc++-devel.i686
>
> Seems to be enough to get 32 bit compilation up and running (note compat-libstdc++-296.i686 is not available in cenots7)
>
> for comparison
>
> for Intel Xeon gold 5118 (Dell R440 bios option set to performance per watt OS)
> 32 bit SL6 = ~575
> 32 bit centos7 = ~590
> 64 bit cenots7 = ~660
>
> * Dr Daniel Traynor, Grid cluster system manager
> * Tel +44(0)20 7882 6560, Particle Physics,QMUL
>
> ________________________________________
> From: Testbed Support for GridPP member institutes <[log in to unmask]> on behalf of Martin Bly - UKRI STFC <[log in to unmask]>
> Sent: 26 March 2019 22:20
> To: [log in to unmask]
> Subject: Re: HS06 results
>
>
> SPEC CPU2006 v1.2 is *required* for SL/CentOS7 - it fixes all the compile problems with v1.1.
>
>          Martin.
> --
> Martin Bly
> RAL Tier1 Fabric Manager
>
>> -----Original Message-----
>> From: Testbed Support for GridPP member institutes [mailto:TB-
>> [log in to unmask]] On Behalf Of Simon Fayer
>> Sent: Tuesday, March 26, 2019 7:02 PM
>> To: [log in to unmask]
>> Subject: Re: HS06 results
>>
>> Hi Dan,
>>
>> Yes, I think this is almost certainly fixed in the newer spec version
>> (although I can't find any mention of it in the changelog). As a workaround
>> you could try adding "-include cstddef" to your CXXPORTABILITY, which I
>> think is the right header for the ptrdiff_t type.
>>
>> Regards,
>> Simon
>>
>>
>> On Tue, Mar 26, 2019 at 04:58:41PM +0000, Daniel Traynor wrote:
>>> For me i'm unable to compile dealII package. error below on centos7.6.1810.
>> it's the same with 32 or 64 bit
>>> my config file has
>>>
>>> 447.dealII=default=default=default:
>>> CXXPORTABILITY= -DSPEC_CPU_LINUX -include cstdlib -include cstring
>>>
>>>
>>> ./runspec.sh.new -a 64 -d "64 bit CentOS7 " -w -f $OUTPUT_DIR
>>>
>>> I note I'm using SPEC2006_v11.tar.bz2, but if i can get hold of an updated
>> version I can give it a try
>>> dan
>>>
>>> ....
>>> g++ -c -o block_vector.o -DSPEC_CPU -DNDEBUG  -Iinclude -
>> DBOOST_DISABLE_THREADS -Ddeal_II_dimension=3  -O2 -fPIC -pthread   -
>> DSPEC_CPU_LP64 -DSPEC_CPU_LINUX -include cstdlib -include cstring
>> block_vector.cc
>>> In file included from include/lac/block_vector.templates.h:19:0,
>>>                   from block_vector.cc:14:
>>> include/lac/block_vector.h:227:17: error: 'ptrdiff_t' does not name a type
>>>           typedef ptrdiff_t                                     difference_type;
>>>                   ^
>>> include/lac/block_vector.h:333:38: error: 'difference_type' does not name a
>> type
>>>           reference operator [] (const difference_type d) const;
>>>                                        ^
>>> include/lac/block_vector.h:333:38: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:333:54: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>           reference operator [] (const difference_type d) const;
>>>                                                        ^
>>> include/lac/block_vector.h:469:9: error: 'difference_type' does not name a
>> type
>>>           difference_type operator - (const Iterator &i) const;
>>>           ^
>>> include/lac/block_vector.h:469:9: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:475:9: error: 'difference_type' does not name a
>> type
>>>           difference_type operator - (const InverseConstnessIterator &i) const;
>>>           ^
>>> include/lac/block_vector.h:475:9: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:482:36: error: 'difference_type' does not name a
>> type
>>>           Iterator operator + (const difference_type &d) const;
>>>                                      ^
>>> include/lac/block_vector.h:482:36: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:482:53: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>           Iterator operator + (const difference_type &d) const;
>>>                                                       ^
>>> include/lac/block_vector.h:489:36: error: 'difference_type' does not name a
>> type
>>>           Iterator operator - (const difference_type &d) const;
>>>                                      ^
>>> include/lac/block_vector.h:489:36: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:489:53: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>           Iterator operator - (const difference_type &d) const;
>>>                                                       ^
>>> include/lac/block_vector.h:496:39: error: 'difference_type' does not name a
>> type
>>>           Iterator & operator += (const difference_type &d);
>>>                                         ^
>>> include/lac/block_vector.h:496:39: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:496:56: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>           Iterator & operator += (const difference_type &d);
>>>                                                          ^
>>> include/lac/block_vector.h:503:39: error: 'difference_type' does not name a
>> type
>>>           Iterator & operator -= (const difference_type &d);
>>>                                         ^
>>> include/lac/block_vector.h:503:39: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:503:56: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>           Iterator & operator -= (const difference_type &d);
>>>                                                          ^
>>> include/lac/block_vector.h:1494:52: error: 'difference_type' does not name a
>> type
>>>       Iterator<number,constness>::operator [] (const difference_type d) const
>>>                                                      ^
>>> include/lac/block_vector.h:1494:52: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:1494:68: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>       Iterator<number,constness>::operator [] (const difference_type d) const
>>>                                                                      ^
>>> include/lac/block_vector.h:1727:5: error: prototype for 'typename
>> internal::BlockVectorIterators::Iterator<number, constness>::difference_type
>> internal::BlockVectorIterators::Iterator<number, constness>::operator-(const
>> internal::BlockVectorIterators::Iterator<number, constness>&) const' does not
>> match any in class 'internal::BlockVectorIterators::Iterator<number, constness>'
>>>       Iterator<number,constness>::
>>>       ^
>>> include/lac/block_vector.h:489:18: error: candidate is:
>> internal::BlockVectorIterators::Iterator<number, constness>
>> internal::BlockVectorIterators::Iterator<number, constness>::operator-(const
>> int&) const
>>>           Iterator operator - (const difference_type &d) const;
>>>                    ^
>>> include/lac/block_vector.h:1741:5: error: prototype for 'typename
>> internal::BlockVectorIterators::Iterator<number, constness>::difference_type
>> internal::BlockVectorIterators::Iterator<number, constness>::operator-(const
>> InverseConstnessIterator&) const' does not match any in class
>> 'internal::BlockVectorIterators::Iterator<number, constness>'
>>>       Iterator<number,constness>::
>>>       ^
>>> include/lac/block_vector.h:489:18: error: candidate is:
>> internal::BlockVectorIterators::Iterator<number, constness>
>> internal::BlockVectorIterators::Iterator<number, constness>::operator-(const
>> int&) const
>>>           Iterator operator - (const difference_type &d) const;
>>>                    ^
>>> include/lac/block_vector.h:1756:23: error: 'difference_type' does not name a
>> type
>>>       operator + (const difference_type &d) const
>>>                         ^
>>> include/lac/block_vector.h:1756:23: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:1756:40: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>       operator + (const difference_type &d) const
>>>                                          ^
>>> include/lac/block_vector.h:1781:23: error: 'difference_type' does not name a
>> type
>>>       operator - (const difference_type &d) const
>>>                         ^
>>> include/lac/block_vector.h:1781:23: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:1781:40: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>       operator - (const difference_type &d) const
>>>                                          ^
>>> include/lac/block_vector.h:1806:24: error: 'difference_type' does not name a
>> type
>>>       operator += (const difference_type &d)
>>>                          ^
>>> include/lac/block_vector.h:1806:24: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:1806:41: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>       operator += (const difference_type &d)
>>>                                           ^
>>> include/lac/block_vector.h:1834:24: error: 'difference_type' does not name a
>> type
>>>       operator -= (const difference_type &d)
>>>                          ^
>>> include/lac/block_vector.h:1834:24: note: (perhaps 'typename
>> std::iterator<std::random_access_iterator_tag, typename
>> internal::BlockVectorIterators::Types<number,
>> constness>::NumberType>::difference_type' was intended)
>>> include/lac/block_vector.h:1834:41: error: ISO C++ forbids declaration of 'd'
>> with no type [-fpermissive]
>>>       operator -= (const difference_type &d)
>>>                                           ^
>>> specmake: *** [block_vector.o] Error 1
>>> Error with make 'specmake build': check file
>> '/scratch/tmp/hepspec/SPEC2006_v11/benchspec/CPU2006/447.dealII/run/buil
>> d_base_x64_gcc_cern.0000/make.err'
>>>    Error with make!
>>> *** Error building 447.dealII
>>>
>>>
>>>
>>> * Dr Daniel Traynor, Grid cluster system manager
>>> * Tel +44(0)20 7882 6560, Particle Physics,QMUL
>>>
>>> ________________________________________
>>> From: Testbed Support for GridPP member institutes <TB-
>> [log in to unmask]> on behalf of Simon Fayer
>> <[log in to unmask]>
>>> Sent: 26 March 2019 16:30
>>> To: [log in to unmask]
>>> Subject: Re: HS06 results
>>>
>>> Hi,
>>>
>>> I ran HS06 (using SPEC06 v1.2 as the base) 32-bit on CentOS 7.6.1810
>>> recently without any problems: What are the exact issues/error messages you
>>> are seeing?
>>>
>>> Regards,
>>> Simon
>>>
>>>
>>> On Mon, Mar 25, 2019 at 02:41:25PM +0000, Daniel Traynor wrote:
>>>> yes I've been having problems
>>>>
>>>> I can compile the dealII package.
>>>>
>>>> Also as CentOs7.6 is our first release with our new deployment system going
>> back to an old release is difficult
>>>> dan
>>>>
>>>> * Dr Daniel Traynor, Grid cluster system manager
>>>> * Tel +44(0)20 7882 6560, Particle Physics,QMUL
>>>>
>>>> ________________________________________
>>>> From: Testbed Support for GridPP member institutes <TB-
>> [log in to unmask]> on behalf of Alastair Dewhurst
>> <[log in to unmask]>
>>>> Sent: 25 March 2019 13:46
>>>> To: [log in to unmask]
>>>> Subject: HS06 results
>>>>
>>>> Hi All
>>>>
>>>> We are currently performing our HS06 benchmarking for the new WN at the
>> Tier-1.  The hardware was the same as last year, so I wasn’t expecting any
>> surprises….  The work was being done by our very talented apprentice (Dominic)
>> and he found he was unable to run the the test using the latest versions of SL7
>> that we run.  This was because various 32 bit packages no longer get bundled.
>> He ‘solved' the problem by changing the flag in the test to 64 bit which gave us a
>> HS06 about 100 higher per box than before (~900 rather than ~800).  In order to
>> get a HS06 score using the 32 bit packages we have had to roll back to an older
>> version of SL7, which seems to be a bit silly.
>>>> Has anybody else run into this or a similar problem?  It might be a relatively
>> minor problem for us this year, but this is only going to get worse.  Do we need
>> to push (again) for an updated benchmark?   I know it is HEPiX this week, so if
>> there is anybody in San Diego in the benchmarking WG, it might be a good time
>> to mention this again.
>>>> Thanks
>>>>
>>>> Alastair
>>>>
>>>>
>> #################################################################
>> #######
>>>> To unsubscribe from the TB-SUPPORT list, click the following link:
>>>> https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=TB-SUPPORT&A=1
>>>>
>>>>
>> #################################################################
>> #######
>>>> To unsubscribe from the TB-SUPPORT list, click the following link:
>>>> https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=TB-SUPPORT&A=1
>>>
>> #################################################################
>> #######
>>> To unsubscribe from the TB-SUPPORT list, click the following link:
>>> https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=TB-SUPPORT&A=1
>>>
>>>
>> #################################################################
>> #######
>>> To unsubscribe from the TB-SUPPORT list, click the following link:
>>> https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=TB-SUPPORT&A=1
>> #################################################################
>> #######
>>
>> To unsubscribe from the TB-SUPPORT list, click the following link:
>> https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=TB-SUPPORT&A=1
> ########################################################################
>
> To unsubscribe from the TB-SUPPORT list, click the following link:
> https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=TB-SUPPORT&A=1
>
> ########################################################################
>
> To unsubscribe from the TB-SUPPORT list, click the following link:
> https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=TB-SUPPORT&A=1

-- 
Respect is a rational process. \\//
For Ur-Fascism, disagreement is treason. (U. Eco)

########################################################################

To unsubscribe from the TB-SUPPORT list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=TB-SUPPORT&A=1

Top of Message | Previous Page | Permalink

JiscMail Tools


RSS Feeds and Sharing


Advanced Options


Archives

April 2019
March 2019
February 2019
January 2019
December 2018
November 2018
October 2018
September 2018
August 2018
July 2018
June 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
February 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
January 2016
December 2015
November 2015
October 2015
September 2015
August 2015
July 2015
June 2015
May 2015
April 2015
March 2015
February 2015
January 2015
December 2014
November 2014
October 2014
September 2014
August 2014
July 2014
June 2014
May 2014
April 2014
March 2014
February 2014
January 2014
December 2013
November 2013
October 2013
September 2013
August 2013
July 2013
June 2013
May 2013
April 2013
March 2013
February 2013
January 2013
December 2012
November 2012
October 2012
September 2012
August 2012
July 2012
June 2012
May 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
September 2010
August 2010
July 2010
June 2010
May 2010
April 2010
March 2010
February 2010
January 2010
December 2009
November 2009
October 2009
September 2009
August 2009
July 2009
June 2009
May 2009
April 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
January 2008
December 2007
November 2007
October 2007
September 2007
August 2007
July 2007
June 2007
May 2007
April 2007
March 2007
February 2007
January 2007
December 2006
November 2006
October 2006
September 2006
August 2006
July 2006
June 2006
May 2006
April 2006
March 2006
February 2006
January 2006
December 2005
November 2005
October 2005
September 2005
August 2005
July 2005
June 2005
May 2005
April 2005
March 2005
February 2005
January 2005
December 2004
November 2004
October 2004
September 2004
August 2004
July 2004
June 2004
May 2004
April 2004
March 2004
February 2004
January 2004
December 2003
November 2003
October 2003
September 2003
August 2003
July 2003
June 2003
May 2003
April 2003
March 2003
February 2003
January 2003
December 2002
November 2002
October 2002
September 2002
August 2002
July 2002
June 2002
May 2002
April 2002
March 2002
February 2002
January 2002


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