amgcl

amgcl copied to clipboard

cuda compute error

2

hi ddemidov I met an issue when using cuda as backend to compute a topology optimization, with grid size 200x100, the code is below. The calculation results of the previous...

ripplesding

Compilation AMGCL problem on AMD architectur with scotch library

2

Hello, I try to compile AMGCL with scotch but I have problems with the examples: ``` [ 43% ] Linking CXX executable mpi_solver /lus/home/pelyakime/AMGCL/scotch-v7.0.3/build/install/lib/libptscotch.a(library_dgraph_map.c.o): In function `SCOTCH_st ratDgraphMapBuild': library_dgraph_map.c:(.text+0x1a3): undefined...

pelyakim

input GPU data directly into CUDA solver

2

Hi, How can I use my matrix data(I, J, N, val) on CUDA memory to the AMGCL CUDA solver? Currently, I copy those data from CUDA memory to main mamory...

MakotoChiba

Not divisible block size with nullspace vectors

5

Hi @ddemidov , I am using AMGCL to solve a 2D linear elasticity problem. It has a 2 $\times$ 2 block structure and works fine without nullspace vectors. But when...

njsyw1997

Errors Compiling Examples with CUDA Backend (Nvidia Geforce GTX 2080 Ti, Cuda 12.0)

6

Hi Demidov, Thanks for this awesome repo, I was trying to build the examples with Cuda backend, in the root directory with command ``` cmake -DCMAKE_BUILD_TYPE=Release -DAMGCL_BUILD_TESTS=ON -DAMGCL_BUILD_EXAMPLES=ON make ```...

AXIHIXA

Difference between using make_shared on distributed matrix vs. solver

1

I see that there are different options proposed to solve a linear system with a distributed matrix in different examples. Option 1 is described in this example: https://github.com/ddemidov/amgcl/blob/master/examples/mpi/mpi_solver.cpp 1. Reading...

allaffa

Use of Matrix Market routines to distributed matrix reading across MPI processes

1

Hello, I am trying to read a matrix from a file with Matrix Market (MM) format within a distributed computing framework using MPI. I familiarized with the methodology explained in...

allaffa

Matrix Assembly

1

I'm recently saw this amazing lib for AMG. Tried the examples and they perform very well so I wanted to use the lib for my own FE implementation as solver...

karabelaselias

how to implement matrix addition calculation

2

Hi Professor, I have a simple question When I use amgcl to solve the problem, I have used mpi to read the two matrices A and B. How to realize...

hoseaaaa

How to deal with multiple right hand sides.

8

Hi Professor, I have a basic question. If I have vectors `rhss` and `xs` as arguments to solver operator `()` as `(rhss,xs)`, which are multiple right hand sides (continusly stored)...

g873249824