AMGX
AMGX copied to clipboard
NVIDIA
Distributed multigrid linear solver library on GPU
We have been experimenting with the GMRES solver with ILU(0) preconditioner. We would like to know how a non-symmetric matrix is re-ordered before computing the ILU(0) preconditioner? Could someone point...
**Describe the issue** Using a matrix loaded with the `AMGX_matrix_upload_distributed` function, I obtain the following message on each MPI rank : ``` Caught amgx exception: Vector size too small: not...
sparse matrix A.mtx %%MatrixMarket matrix coordinate real general 1010022 1010022 41237996 1 1 11523.7737219475 1 2 1061.67578610102 1 3 2409.74830683316 1 4 -1580.26693723716 1 5 -1111.24700614505 1 6 594.409310481413 1...
I wonder if there is a newer reference for APIs. I notice that there is a reference in /doc. However, this version is 2017 and a lot APIs have changed...
Hi, I want to use AMGX to build a module in Fortran to solve the Poisson equation. How can I use AMGX in Fortran? Is there any example for reference?
**Describe the issue** I see no gain using MPI_Direct during solve except during setup. **Environment information:** - OS: Linux - CUDA runtime: All - MPI version (if applicable):All - AMGX...
Hello.. could I please get an example partition vector file for the distributed example https://github.com/NVIDIA/AMGX/blob/main/examples/amgx_mpi_capi.c
My workstation has Quadro RTX 5000 GPU with 16 GB memory, running NVIDIA Driver 470.103.01, and supporting CUDA 11.4. The output of nvcc --version nvcc: NVIDIA (R) Cuda compiler driver...
Hi, I have notives that the following pairs of files found at src/configs/ [PCG_CLASSICAL_W_JACOBI.json](https://github.com/NVIDIA/AMGX/blob/main/src/configs/PCG_CLASSICAL_W_JACOBI.json), [PCG_W.json](https://github.com/NVIDIA/AMGX/blob/main/src/configs/PCG_W.json) [PCG_CLASSICAL_F_JACOBI.json](https://github.com/NVIDIA/AMGX/blob/main/src/configs/PCG_CLASSICAL_F_JACOBI.json), [PCG_F.json](https://github.com/NVIDIA/AMGX/blob/main/src/configs/PCG_F.json) corresponds to exactly the same parameters. On the other hand: [PCG_CLASSICAL_V_JACOBI.json](https://github.com/NVIDIA/AMGX/blob/main/src/configs/PCG_CLASSICAL_V_JACOBI.json) has a...
Given the recent work on lower precision floating point being done by the PyTorch community, (See here: https://pytorch.org/blog/training-using-float8-fsdp2/?utm_content=317436495&utm_medium=social&utm_source=linkedin&hss_channel=lcp-78618366) has there been any thoughts on if AMGX will follow suite and...
