Re: [Rd] as.character.Date() strips names in R 4.3.2 beta, bug?

[Andrew Piskorski]

On Tue, Oct 24, 2023 at 10:53:10AM +0200, Martin Maechler wrote:

> Yes, this change has been *very* intentional:  as.character() for
> these objects since 4.3.0 (April 2023) finally behaves as other
> as.character() methods and *does* drop attributes.
[...]

Thank you for the detailed explanation and pointers to the old info
I'd missed, Martin.  The as.character.Date tip in particular was very
helpful in adapting my code to work with this change.

-- 
Andrew Piskorski 

__
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel

Re: [Rd] About FlexiBLAS in the R-admin docs

[Tomas Kalibera]

On 10/11/23 23:12, George Ostrouchov wrote:

I agree that the "R Installation and Administration" guide statement about 
FlexiBLAS needs an update. Standard R in CentOS Stream 9, which is now downstream from 
Fedora, gives the following result for Matrix products in sessionInfo():


sessionInfo()

R version 4.3.1 (2023-06-16)
Platform: x86_64-redhat-linux-gnu (64-bit)
Running under: CentOS Stream 9

Matrix products: default
BLAS/LAPACK: FlexiBLAS OPENBLAS-OPENMP;  LAPACK version 3.9.0
…

So OpenBLAS compiled with OpenMP is the default. FlexiBLAS (via the flexiblas 
package) is my favorite way to manage core use in multithreaded BLAS 
computations. It is also the default in the EasyBuild foss compiler toolchain 
for HPC clusters: https://docs.easybuild.io/common-toolchains/


The output of session info is based on that flexiblas is used and on 
what flexiblas tells R is the backend it uses. R does not attempt to 
check that optimized LAPACK functions from the backend really end up 
called via flexiblas, and I don't think it could be realistically checked.


But I've checked one case manually in Fedora 38 using Linux perf tool. 
The following code:


S <- toeplitz((10:1)/10)
repeat { R <- rWishart(10, 20, S) }

uses dpotrf from LAPACK, which is optimized in OpenBLAS and ATLAS and 
the corresponding optimized implementations really appeared on the 
sampling profile for me from the backend libraries.


The comment from R Admin has been removed now and if anyone runs into 
the problem (that an optimized LAPACK function is not called from a 
backend that provides it), it would be best to report it with sufficient 
detail to flexiblas.


Best
Tomas


What would be a good way to suggest or construct an update?

Best regards,
George



Date: Wed, 27 Sep 2023 15:14:43 +0200
From: =?UTF-8?Q?I=C3=B1aki_Ucar?= 
To: "r-devel@r-project.org" 
Subject: [Rd] About FlexiBLAS in the R-admin docs
Message-ID:

Content-Type: text/plain; charset="utf-8"

Hi,

Not sure if this is the right place for this. The "R Installation and
Administration" guide states:


Apparently undocumented: FlexiBLAS on Fedora provides a complete LAPACK, but 
not the enhanced routines from ATLAS or OpenBLAS.

I'm not sure what this means. FlexiBLAS does provide 100% of BLAS and
LAPACK, and if the active backend (say, OpenBLAS) implements an
enhanced LAPACK routine, then the call is redirected to the backend.
If the user switches to another backend and that routine is not
available there, then the original LAPACK routine is dispatched
instead.

Best,
--
Iñaki Úcar



[[alternative HTML version deleted]]

__
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel


__
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel

Re: [Rd] as.character.Date() strips names in R 4.3.2 beta, bug?

[Martin Maechler]

> Andrew Piskorski 
> on Tue, 24 Oct 2023 00:01:58 -0400 writes:

> In previous versions of R, 

Not in R 4.3.0 or 4.3.1   {you are a bit late with updating ..}.

> as.character.Date() retained any names on
> its input vector.  In R 4.3.2 beta, it removes names.  Is this change
> intentional, or a bug?  (For what it's worth, I greatly dislike this
> change, and hope it gets changed back.)

Yes, this change has been *very* intentional:  as.character() for
these objects since 4.3.0 (April 2023) finally behaves as other
as.character() methods and *does* drop attributes.

The NEWS entry
(visible since more than a year if you'd follows NEWS.Rd tweats/.. etc)  
is

   • ‘as.character()’ now behaves more in line with the
 methods for atomic vectors such as numbers, and is no longer
 influenced by ‘options()’.  Ditto for
 ‘as.character()’.  The ‘as.character()’ method gets
 arguments ‘digits’ and ‘OutDec’ with defaults _not_
 depending on ‘options()’.  Use of ‘as.character(*, format = .)’
 now warns.

At the time (Sep 2022!) there was quite some traffic on R-devel
about this, IIRC.

Often it's most convenient for people to use  format() instead
of as.character() if they want to keep names, notably here,
because before the fix, the as.character() method for Date and POSIXt
*was* identical to format()  --- contrary to all other methods
for "simple" vectors.

There's more about this if just simply at  ?as.character.Date

Best regards,
Martin

--
Martin Maechler
ETH Zurich  and  R Core team

__
R-devel@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-devel