Karl,
I point your attention to this :
http://www.iue.tuwien.ac.at/cse/index.php/gsoc/2011/ideas-2011/104-viennacl-mpi-layer-for-linear-algebra-with-large-matrices-new.html
has this ever been incorporated into ViennaCL?
Thanks and Regards Sumit
--
and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar ; viennacl-devel
Sent: Tuesday, March 1, 2016 7:24 PM
Subject: Re: [ViennaCL-devel] Examples of importing raw buffers
Hi Sumit,
sorry, I overlooked this email in my mailers threaded view.
> I have a question here:
Hey KarlI have a question here:a.) Suppose I have three raw buffers (let us
assume float); I would like to do something like this:v = (I- a) / (W-a+EPS),
where I, W and a are the three buffers and EPS is a scalar to prevent a
division by 0 operation.
b.) I know I can wrap these buffers to Eigen
@Ok and @KRGreat! This would be an ideal scenario. Thanks for initiating this
process. Regards Sumit
From: Karl Rupp
To: Oswin Krause ;
viennacl-devel@lists.sourceforge.net
Sent: Friday, October 30, 2015 7:14 PM
Subject: Re: [ViennaCL-devel] Help in Interfacing another BLAS library?
I am not getting you wrong. My first (and only logical) attempt was that only.
I tried doing that and I got loads of compilation errors. Let me send them to
you in a different mail (I will need to rebuild my code again) Thanks and
Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent: Wednesday, August 5, 2015 7:38 PM
Subject: Re: [ViennaCL-devel] ViennaCL fast_copy() matrices
Hi,
> I have a dense matrix (2048 x 2048) on the GPU and I want to copy it
> back to a host matrix on the CPU (20
Hah ! I will need to learn Group Theory first !! (though it sounds interesting)
Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent: Wednesday, August 5, 2015 7:47 PM
Subject: Re: [ViennaCL-devel] ViennaCL reductions
http://arxiv.org/pdf/math/0307321v2.pdfCan this be implemented? I am not aware
of Group theory :) Apparently, this has a complexity of O(n^2) ! Thanks and
Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent: Monday, August 3, 20
prod(vcl_A, vcl_B); // Copy the matrix back to the host
matrix viennacl::copy(vcl_C, (*result));
Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent: Monday, August 3, 2015 1:23 AM
Subject: Re: [ViennaCL-devel]
Hi KarlI have a dense matrix (2048 x 2048) on the GPU and I want to copy it
back to a host matrix on the CPU (2048 x 2048). Is there any example of using
fast_copy() ? 2048 is a multiple of 128. Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-
think the correct way to do this would be:a.)
Not do any matrix multiplication if all elements are zeros b.) If done, then it
should fill up the matrix with zeros and return it without throwing an
assertion. Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-
alignment
order. Suppose I have a Row-major Sparse Eigen matrix, then I can copy it to a
(Row-Major ?) VCL compressed matrix. What about a column-major sparse Eigen
matrix? Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sparse matrix with a
VCL dense matrix? Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent: Friday, July 31, 2015 6:20 PM
Subject: Re: [ViennaCL-devel] ViennaCL reductions
Hi Sumit,
> I know that we can copy a dense
KarlI know that we can copy a dense eigen matrix to a dense VCL matrix and the
same thing for sparse matrices also.Is it possible to copy a sparse eigen
matrix to a dense eigen matrix? and vice-versa ? Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-
g the Zero padded
data. What this would mean for regular matrices is that some of the
sub-matrices would become Dense matrix matrix products while others may become
sparse matrix/dense matrix products. Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "vien
s sparse matrix multiplication routine (of course with a
sufficiently large base size) - With my GPU I can reduce the size to at least
8192 x 8192
Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent: Tuesday, July 28,
Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent: Tuesday, July 28, 2015 2:06 AM
Subject: Re: [ViennaCL-devel] ViennaCL reductions
Hi,
> That's why I explicitly stated in my previous mail "Optional&
go element_wise multiplication ?b.) A
unary operation on a matrix that has been transferred to the GPU? Thanks and
Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent: Monday, July 27, 2015 9:13 PM
Subject: Re: [ViennaCL-devel] ViennaC
CharlesIndeed, you should try to reduce row/column wise reductions to simple
matrix multiplications. I had posed a similar question earlier and reworked my
problem. Thanks and Regards
Sumit
From: Karl Rupp
To: viennacl-devel@lists.sourceforge.net
Sent: Monday, July 27, 2015 8:27 PM
Su
context selection etc
can be avoided?c.) Of course, this would be purely optional and only available
if the user wants to pre-select the device before writing any VCL code! Thanks
and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Se
discrete // GPU. viennacl::ocl::setup_context(0,
devices[1]); } else { devices = pf.devices(CL_DEVICE_TYPE_CPU);
viennacl::ocl::setup_context(0, devices[0]); } Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent
picking up b.) whereas I want to pick up
c.)Can anyone share an example of how to go about doing this? Thanks and Regards
Sumit
From: Karl Rupp
To: Sumit Kumar
Cc: "viennacl-devel@lists.sourceforge.net"
Sent: Sunday, July 26, 2015 11:37 PM
Subject: Re: [ViennaCL-devel
ateContext(0, cl_uint(device_id_array.size()),
&(device_id_array[0]), NULL, NULL, &err);
and this made it work. However, is there a cleaner way of doing this? This code
snippet is from "custom-context.cpp". If i tried &(device_id_array[1]), the
program crashes !
Thanks and
KarlI have the following reduction that I can do in Eigen. Is there something
similar that I can do in ViennaCL? RMMatrix_Float v =
(prod.block(0,0,rows,cols).rowwise() -
aVector.transpose());RMSparseMatrix_Float v1 =
v.unaryExpr(std::ptr_fun(clip_lower)).sparseView();
Essentially, I am subtrac
If I were to use an Eigen Matrix, I can potentially access its raw data using
the Matrix.data() function. Is there anything similar in ViennaCL also?
Thanks and Regards
Sumit--
HPCC Systems Open Source Big Data Platform
25 matches
Mail list logo
