-
I used the following code to multiply two sparse matrices A and B using SpGEMM, following the [sample code](https://github.com/NVIDIA/CUDALibrarySamples/tree/master/cuSPARSE/spgemm).
```
#include …
-
@seheracer @lucbv
The "all scalars" build on Jenkins is finishing now, but there are some sparse test failures for float and complex_float. Just seems to be precision related, so maybe just a high…
-
### 🐛 Describe the bug
```
>>> import torch
>>> a = torch.randn(2000, 2000, device='cuda:3').to_sparse()
>>> a @ a
Traceback (most recent call last):
File "", line 1, in
RuntimeError: CUDA e…
-
## 論文URL
https://arxiv.org/abs/2302.01107
## 著者
Bohan Zhuang, Jing Liu, Zizheng Pan, Haoyu He, Yuetian Weng, Chunhua Shen
## 会議
IJCAI 2023 survey track
## 背景
最近のTransformerは大きな計算リ…
-
Test failures with the sparse_cuda, graph_cuda, wiki_spgemm began with cuda/11.2 builds on Power9+Volta70 with cusparse and cublas tpls enabled, some likely related to merge of #1618
**Test failur…
-
```julia
a = rand(100,100)
b = rand(100,100)
a*b == (b' * a')'
```
```Shell
true
```
```julia
using SparseArrays
a = sprand(100,100,0.1)
b = rand(100,100)
a*b == (b' * a')'
```
```Shel…
-
I'm trying to write CUTLASS code to multiply a sparse matrix A that is in row major layout with a dense matrix B that is in column major layout, and then to add some bias. All these tensors are of ha…
-
Hi Francisco Muñoz-Martínez,
Can we train an algorithm on STONNE? If not, can you guide me through the ways on (any documentation) to change the simulator to accelerate training?
-
### Description
Take summary, we try to do human segmentation on a social media video using an unsupervised deep CNN. The processing extract each video frame (using OpenCV). The video frame is segmen…
-
### What is the expected behavior
All tests pass with xnack enabled on supported GPUs.
### What actually happens
There are test failures with xnack.
Excerpt from test failures
```console
>…