-
When xnack mode is enabled (on supported hardware i.e. MI100, MI200 series), using hypre will result in:
```plaintext
:0:rocdevice.cpp :2647: 531282443361 us: 2170233: [tid:0x7fa7feccf7…
-
As shown in paper, CUTLASS library is used for speedup. But I did not find codes rely on these settlement.How should I verify SparseGPT is faster than dense models when doing inference? Even with end-…
-
**Describe the bug**
Multiplication of either CSC or CSR sparse matrices is prohibitively slow.
**To reproduce**
The Minimal Working Example (MWE) for this bug:
```julia
using CUDA
using…
mashu updated
11 months ago
-
Environment:
[runDocker.txt](https://github.com/nicknytko/numml/files/12908070/runDocker.txt)
Docker Image nvcr.io/nvidia/pytorch:23.09-py3
Driver Version: 525.125.06 CUDA Version: 12.0…
-
Hi, I'm having the same problem with #174.
I have two large adjacency matrices, the details are as follows
adj_l
SparseTensor(row=tensor([ 0, 0, 0, ..., 736388, 736388, 736388], devi…
-
https://github.com/SparseBLAS/spblas-reference/blob/093068008c1f3e031fb43133d1a66051aa04b80a/notes/spmv.hpp#L10-L24
I like this idea of having an info type that is directly associated with some mat…
-
Hi,
I followed the build instructions for kokkos-kernels with OpenMP support with perf_tests enabled and ran ./sparse_spgemm in kokkos-kernels/build/perf_test/sparse. For smaller datasets, such as…
-
@william76
Currently two similar yet different calls can be made to obtain distance 2 coloring: `d2_graph_color` and `graph_color_d2`.
This is a little confusing and it also makes it hard for an ap…
lucbv updated
5 years ago
-
Hi,
My name is David and I am working with hypre libraries on some 3D supernova code written in FORTRAN. I've worked with hypre prior and been successful in building the necessary libraries for thi…
ghost updated
3 years ago
-
As in, we need to and the data (see previous tpetra-developers discussion) shows it.
@mhoemmen @jhux2 @jjellio