mirror of
https://github.com/sfilippone/psblas3.git
synced 2026-10-19 04:12:09 +00:00
Update docs
This commit is contained in:
Salvatore Filippone
+152
-1
@@ -31,9 +31,19 @@ routine in the library is built according to the following principles:
|
||||
In this way, data items are put on the {GPU} memory ``on demand'' and
|
||||
remain there as long as ``normal'' computations are carried out.
|
||||
As an example, the following call to a matrix-vector product
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true,bgcolor=bg,fontsize=\small]{fortran}
|
||||
call psb_spmm(alpha,a,x,beta,y,desc_a,info)
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
call psb_spmm(alpha,a,x,beta,y,desc_a,info)
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
will transparently and automatically be performed on the {GPU} whenever
|
||||
all three data inputs \fortinline|a|, \fortinline|x| and
|
||||
\fortinline|y| are {GPU}-enabled. If a program makes many such calls
|
||||
@@ -81,9 +91,19 @@ and \fortinline|beta|, and the return code \fortinline|info|.
|
||||
environment}
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_init}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
call psb_cuda_init(ctxt [, device])
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
call psb_cuda_init(ctxt [, device])
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
This subroutine initializes the PSBLAS-CUDA environment.
|
||||
\begin{description}
|
||||
@@ -109,9 +129,19 @@ available on the current node.
|
||||
environment}
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_exit}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
call psb_cuda_exit(ctxt)
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
call psb_cuda_exit(ctxt)
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
This subroutine exits from the PSBLAS CUDA context.
|
||||
\begin{description}
|
||||
@@ -131,9 +161,19 @@ Specified as: an integer variable.
|
||||
\subsection*{psb\_cuda\_DeviceSync --- Synchronize CUDA device}
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_DeviceSync}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
call psb_cuda_DeviceSync()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
call psb_cuda_DeviceSync()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
This subroutine ensures that all previosly invoked kernels, i.e. all
|
||||
invocation of CUDA-side code, have completed.
|
||||
@@ -142,45 +182,96 @@ invocation of CUDA-side code, have completed.
|
||||
\subsection*{psb\_cuda\_getDeviceCount }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_getDeviceCount}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
ngpus = psb_cuda_getDeviceCount()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
ngpus = psb_cuda_getDeviceCount()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Get number of devices available on current computing node.
|
||||
|
||||
\subsection*{psb\_cuda\_getDevice }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_getDevice}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
ngpus = psb_cuda_getDevice()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
ngpus = psb_cuda_getDevice()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Get device in use by current process.
|
||||
|
||||
\subsection*{psb\_cuda\_setDevice }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_setDevice}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
info = psb_cuda_setDevice(dev)
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
info = psb_cuda_setDevice(dev)
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Set device to be used by current process.
|
||||
|
||||
\subsection*{psb\_cuda\_DeviceHasUVA }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_DeviceHasUVA}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
hasUva = psb_cuda_DeviceHasUVA()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
hasUva = psb_cuda_DeviceHasUVA()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Returns true if device currently in use supports UVA (Unified Virtual Addressing).
|
||||
Returns true if device currently in use supports UVA
|
||||
(Unified Virtual Addressing).
|
||||
|
||||
\subsection*{psb\_cuda\_WarpSize }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_WarpSize}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
nw = psb_cuda_WarpSize()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
nw = psb_cuda_WarpSize()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Returns the warp size.
|
||||
|
||||
@@ -188,18 +279,38 @@ Returns the warp size.
|
||||
\subsection*{psb\_cuda\_MultiProcessors }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_MultiProcessors}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
nmp = psb_cuda_MultiProcessors()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
nmp = psb_cuda_MultiProcessors()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Returns the number of multiprocessors in the CUDA device.
|
||||
|
||||
\subsection*{psb\_cuda\_MaxThreadsPerMP }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_MaxThreadsPerMP}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
nt = psb_cuda_MaxThreadsPerMP()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
nt = psb_cuda_MaxThreadsPerMP()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Returns the maximum number of threads per multiprocessor.
|
||||
|
||||
@@ -207,9 +318,19 @@ Returns the maximum number of threads per multiprocessor.
|
||||
\subsection*{psb\_cuda\_MaxRegistersPerBlock }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_MaxRegisterPerBlock}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
nr = psb_cuda_MaxRegistersPerBlock()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
nr = psb_cuda_MaxRegistersPerBlock()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Returns the maximum number of register per thread block.
|
||||
|
||||
@@ -217,27 +338,57 @@ Returns the maximum number of register per thread block.
|
||||
\subsection*{psb\_cuda\_MemoryClockRate }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_MemoryClockRate}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
cl = psb_cuda_MemoryClockRate()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
cl = psb_cuda_MemoryClockRate()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Returns the memory clock rate in KHz, as an integer.
|
||||
|
||||
\subsection*{psb\_cuda\_MemoryBusWidth }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_MemoryBusWidth}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
nb = psb_cuda_MemoryBusWidth()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
nb = psb_cuda_MemoryBusWidth()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
Returns the memory bus width in bits.
|
||||
|
||||
\subsection*{psb\_cuda\_MemoryPeakBandwidth }
|
||||
\addcontentsline{toc}{subsection}{psb\_cuda\_MemoryPeakBandwidth}
|
||||
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true]{fortran}
|
||||
bw = psb_cuda_MemoryPeakBandwidth()
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
bw = psb_cuda_MemoryPeakBandwidth()
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
Returns the peak memory bandwidth in MB/s (real double precision).
|
||||
|
||||
|
||||
|
||||
+192
-6
@@ -32,6 +32,7 @@ following steps:
|
||||
Suppose you want to use the CUDA-enabled ELLPACK data structure; you
|
||||
would use a piece of code like this (and don't forget, you need
|
||||
CUDA-side vectors along with the matrices):
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true,bgcolor=bg,fontsize=\small]{fortran}
|
||||
program my_cuda_test
|
||||
use psb_base_mod
|
||||
@@ -80,6 +81,61 @@ program my_cuda_test
|
||||
stop
|
||||
end program my_cuda_test
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
program my_cuda_test
|
||||
use psb_base_mod
|
||||
use psb_util_mod
|
||||
use psb_ext_mod
|
||||
use psb_cuda_mod
|
||||
type(psb_dspmat_type) :: a, agpu
|
||||
type(psb_d_vect_type) :: x, xg, bg
|
||||
|
||||
real(psb_dpk_), allocatable :: xtmp(:)
|
||||
type(psb_d_vect_cuda) :: vmold
|
||||
type(psb_d_elg_sparse_mat) :: aelg
|
||||
type(psb_ctxt_type) :: ctxt
|
||||
integer :: iam, np
|
||||
|
||||
|
||||
call psb_init(ctxt)
|
||||
call psb_info(ctxt,iam,np)
|
||||
call psb_cuda_init(ctxt, iam)
|
||||
|
||||
|
||||
! My own home-grown matrix generator
|
||||
call gen_matrix(ctxt,idim,desc_a,a,x,info)
|
||||
if (info /= 0) goto 9999
|
||||
|
||||
call a%cscnv(agpu,info,mold=aelg)
|
||||
if (info /= 0) goto 9999
|
||||
xtmp = x%get_vect()
|
||||
call xg%bld(xtmp,mold=vmold)
|
||||
call bg%bld(size(xtmp),mold=vmold)
|
||||
|
||||
! Do sparse MV
|
||||
call psb_spmm(done,agpu,xg,dzero,bg,desc_a,info)
|
||||
|
||||
|
||||
9999 continue
|
||||
if (info == 0) then
|
||||
write(*,*) '42'
|
||||
else
|
||||
write(*,*) 'Something went wrong ',info
|
||||
end if
|
||||
|
||||
|
||||
call psb_cuda_exit()
|
||||
call psb_exit(ctxt)
|
||||
stop
|
||||
end program my_cuda_test
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
A full example of this strategy can be seen in the
|
||||
\texttt{test/ext/kernel} and \texttt{test/\-cuda/\-kernel} subdirectories,
|
||||
where we provide sample programs
|
||||
@@ -132,7 +188,11 @@ OFFSET & Offset for diagonals \\
|
||||
\begin{figure}[ht]
|
||||
\centering
|
||||
% \includegraphics[width=5.2cm]{figures/mat.eps}
|
||||
\includegraphics[width=5.2cm]{figures/mat.pdf}
|
||||
\ifcase\pdfoutput
|
||||
\includegraphics[width=5.2cm]{mat.png}
|
||||
\or
|
||||
\includegraphics[width=5.2cm]{figures/mat.pdf}
|
||||
\fi
|
||||
\caption{Example of sparse matrix}
|
||||
\label{fig:dense}
|
||||
\end{figure}
|
||||
@@ -155,7 +215,11 @@ indices, e.g. the last valid one found in the same row.
|
||||
\begin{figure}[ht]
|
||||
\centering
|
||||
% \includegraphics[width=8.2cm]{figures/ell.eps}
|
||||
\includegraphics[width=8.2cm]{figures/ell.pdf}
|
||||
\ifcase\pdfoutput
|
||||
\includegraphics[width=8.2cm]{ell.png}
|
||||
\or
|
||||
\includegraphics[width=8.2cm]{figures/ell.pdf}
|
||||
\fi
|
||||
\caption{ELLPACK compression of matrix in Figure~\ref{fig:dense}}
|
||||
\label{fig:ell}
|
||||
\end{figure}
|
||||
@@ -199,6 +263,7 @@ computing days; in modern CPUs it is not quite as popular, but it
|
||||
is the basis for many GPU formats.
|
||||
|
||||
The relevant data type is \verb|psb_T_ell_sparse_mat|:
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true,bgcolor=bg,fontsize=\small]{fortran}
|
||||
type, extends(psb_d_base_sparse_mat) :: psb_d_ell_sparse_mat
|
||||
!
|
||||
@@ -212,6 +277,25 @@ The relevant data type is \verb|psb_T_ell_sparse_mat|:
|
||||
....
|
||||
end type psb_d_ell_sparse_mat
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
type, extends(psb_d_base_sparse_mat) :: psb_d_ell_sparse_mat
|
||||
!
|
||||
! ITPACK/ELL format, extended.
|
||||
!
|
||||
|
||||
integer(psb_ipk_), allocatable :: irn(:), ja(:,:), idiag(:)
|
||||
real(psb_dpk_), allocatable :: val(:,:)
|
||||
|
||||
contains
|
||||
....
|
||||
end type psb_d_ell_sparse_mat
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
|
||||
\subsubsection*{Hacked ELLPACK}
|
||||
@@ -251,13 +335,18 @@ submatrix inside the stacked \textit{cM}/\textit{rP} buffers, plus an
|
||||
additional element pointing past the end of the last block, where the
|
||||
next one would begin.
|
||||
We thus have the property that
|
||||
the elements of the $k$-th \textit{hack} are stored between \verb|hackOffsets[k]| and
|
||||
the elements of the $k$-th \textit{hack} are stored between
|
||||
\verb|hackOffsets[k]| and
|
||||
\verb|hackOffsets[k+1]|, similarly to what happens in the CSR format.
|
||||
|
||||
\begin{figure}[ht]
|
||||
\centering
|
||||
% \includegraphics[width=8.2cm]{../figures/hll.eps}
|
||||
\includegraphics[width=.72\textwidth]{../figures/hll.pdf}
|
||||
\ifcase\pdfoutput
|
||||
\includegraphics[width=.72\textwidth]{hll.png}
|
||||
\or
|
||||
\includegraphics[width=.72\textwidth]{../figures/hll.pdf}
|
||||
\fi
|
||||
\caption{Hacked ELLPACK compression of matrix in Figure~\ref{fig:dense}}
|
||||
\label{fig:hll}
|
||||
\end{figure}
|
||||
@@ -267,6 +356,7 @@ therefore the additional memory is limited to the hack in which the
|
||||
row appears.
|
||||
|
||||
The relevant data type is \verb|psb_T_hll_sparse_mat|:
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true,bgcolor=bg,fontsize=\small]{fortran}
|
||||
type, extends(psb_d_base_sparse_mat) :: psb_d_hll_sparse_mat
|
||||
!
|
||||
@@ -280,6 +370,25 @@ The relevant data type is \verb|psb_T_hll_sparse_mat|:
|
||||
....
|
||||
end type
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
type, extends(psb_d_base_sparse_mat) :: psb_d_hll_sparse_mat
|
||||
!
|
||||
! HLL format. (Hacked ELL)
|
||||
!
|
||||
integer(psb_ipk_) :: hksz
|
||||
integer(psb_ipk_), allocatable :: irn(:), ja(:), idiag(:), hkoffs(:)
|
||||
real(psb_dpk_), allocatable :: val(:)
|
||||
|
||||
contains
|
||||
....
|
||||
end type
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
\subsubsection*{Diagonal storage}
|
||||
|
||||
@@ -300,13 +409,18 @@ addressing is required.
|
||||
\begin{figure}[ht]
|
||||
\centering
|
||||
% \includegraphics[width=8.2cm]{figures/dia.eps}
|
||||
\includegraphics[width=.72\textwidth]{figures/dia.pdf}
|
||||
\ifcase\pdfoutput
|
||||
\includegraphics[width=.72\textwidth]{dia.png}
|
||||
\or
|
||||
\includegraphics[width=.72\textwidth]{figures/dia.pdf}
|
||||
\fi
|
||||
\caption{DIA compression of matrix in Figure~\ref{fig:dense}}
|
||||
\label{fig:dia}
|
||||
\end{figure}
|
||||
|
||||
|
||||
\begin{algorithm}
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true,bgcolor=bg,fontsize=\small]{fortran}
|
||||
do j=1,ndiag
|
||||
if (offset(j) > 0) then
|
||||
@@ -319,11 +433,30 @@ addressing is required.
|
||||
end do
|
||||
end do
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
do j=1,ndiag
|
||||
if (offset(j) > 0) then
|
||||
ir1 = 1; ir2 = m - offset(j);
|
||||
else
|
||||
ir1 = 1 - offset(j); ir2 = m;
|
||||
end if
|
||||
do i=ir1,ir2
|
||||
y(i) = y(i) + alpha*as(i,j)*x(i+offset(j))
|
||||
end do
|
||||
end do
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
\caption{\label{alg:dia} Matrix-Vector product in DIA format}
|
||||
\end{algorithm}
|
||||
|
||||
|
||||
The relevant data type is \verb|psb_T_dia_sparse_mat|:
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true,bgcolor=bg,fontsize=\small]{fortran}
|
||||
type, extends(psb_d_base_sparse_mat) :: psb_d_dia_sparse_mat
|
||||
!
|
||||
@@ -336,6 +469,24 @@ The relevant data type is \verb|psb_T_dia_sparse_mat|:
|
||||
|
||||
end type
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
type, extends(psb_d_base_sparse_mat) :: psb_d_dia_sparse_mat
|
||||
!
|
||||
! DIA format, extended.
|
||||
!
|
||||
|
||||
integer(psb_ipk_), allocatable :: offset(:)
|
||||
integer(psb_ipk_) :: nzeros
|
||||
real(psb_dpk_), allocatable :: data(:,:)
|
||||
|
||||
end type
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
|
||||
|
||||
@@ -378,12 +529,17 @@ the number of diagonals of the $k$-th \textit{hack} is given by
|
||||
\begin{figure}[ht]
|
||||
\centering
|
||||
% \includegraphics[width=8.2cm]{../figures/hdia.eps}
|
||||
\includegraphics[width=.72\textwidth]{../figures/hdia.pdf}
|
||||
\ifcase\pdfoutput
|
||||
\includegraphics[width=.72\textwidth]{hdia.png}
|
||||
\or
|
||||
\includegraphics[width=.72\textwidth]{../figures/hdia.pdf}
|
||||
\fi
|
||||
\caption{Hacked DIA compression of matrix in Figure~\ref{fig:dense}}
|
||||
\label{fig:hdia}
|
||||
\end{figure}
|
||||
|
||||
The relevant data type is \verb|psb_T_hdia_sparse_mat|:
|
||||
\ifpdf
|
||||
\begin{minted}[breaklines=true,bgcolor=bg,fontsize=\small]{fortran}
|
||||
type pm
|
||||
real(psb_dpk_), allocatable :: data(:,:)
|
||||
@@ -408,5 +564,35 @@ The relevant data type is \verb|psb_T_hdia_sparse_mat|:
|
||||
....
|
||||
end type
|
||||
\end{minted}
|
||||
\else
|
||||
\begin{center}
|
||||
\begin{minipage}[tl]{0.9\textwidth}
|
||||
\begin{verbatim}
|
||||
type pm
|
||||
real(psb_dpk_), allocatable :: data(:,:)
|
||||
end type pm
|
||||
|
||||
type po
|
||||
integer(psb_ipk_), allocatable :: off(:)
|
||||
end type po
|
||||
|
||||
type, extends(psb_d_base_sparse_mat) :: psb_d_hdia_sparse_mat
|
||||
!
|
||||
! HDIA format, extended.
|
||||
!
|
||||
|
||||
type(pm), allocatable :: hdia(:)
|
||||
type(po), allocatable :: offset(:)
|
||||
integer(psb_ipk_) :: nblocks, nzeros
|
||||
integer(psb_ipk_) :: hack = 64
|
||||
integer(psb_long_int_k_) :: dim=0
|
||||
|
||||
contains
|
||||
....
|
||||
end type
|
||||
\end{verbatim}
|
||||
\end{minipage}
|
||||
\end{center}
|
||||
\fi
|
||||
|
||||
|
||||
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 50 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 52 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 58 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 61 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 90 KiB |
@@ -18,8 +18,6 @@
|
||||
\newtheorem{corollary}{Corollary}
|
||||
\usepackage{listings}
|
||||
\usepackage{algorithm2e}
|
||||
\usepackage{minted}
|
||||
\usemintedstyle{friendly}
|
||||
\usepackage{microtype}
|
||||
\ifpdf
|
||||
\newmintinline[fortinline]{fortran}{}
|
||||
|
||||
Reference in New Issue
Block a user