-
**Describe the bug**
Pkg.test("CUDA") cublas errors
**To reproduce**
```julia
Pkg.add("CUDA")
using CUDA
Pkg.test("CUDA")
```
Manifest.toml
```
# This file is machine-genera…
-
The following program fails with "misaligned address" if either M or K is odd, while cuBLAS allows such inputs:
``` c++
#include
#include
#include
#include
#include
#include
#inc…
-
**Describe the bug**
When I run `] test CUDA` in an environment with CUDA 1.0.2 installed and nothing else, all but 1 tests succeed, but I also get a `Got exception outside of a @test` error. The f…
tsela updated
4 years ago
-
```
(@v1.5) pkg> test CUDA
Testing CUDA
Status `C:\Users\gzhang\AppData\Local\Temp\jl_GYVHeQ\Project.toml`
[621f4979] AbstractFFTs v0.5.0
[79e6a3ab] Adapt v2.3.0
[ab4f0b2a] BFloat16s v…
-
I'm using Julia v1.5 with CUDA Toolkit V10.2.89 on Ubuntu 18.04 and GeForce GT 730 with Driver Version: 440.100.
```
julia> CUDA.versioninfo()
CUDA toolkit 10.2.89, local installation
CUDA driver…
-
nvprof runs without error and CUDA.jl gives expected behavior, but nvprof cannot see anything.
Julia environment:
```
(@v1.4) pkg> status
Status `~/.julia/environments/v1.4/Project.toml`
[c52…
-
```
julia> using CUDA
julia> CUDA.versioninfo()
CUDA toolkit 11.0.3, artifact installation
CUDA driver 11.1.0
NVIDIA driver 456.43.0
Libraries:
- CUBLAS: 11.2.0
- CURAND: 10.2.1
- CUFFT:…
-
Tensor Core is a defining feature of the NVIDIA new Volta and Turing GPU Architecture, which gives a massive boost for matrix multiplication and convolution. Tensor Cores enable us to use mixed-precis…
-
I wrote a function using cutlass to test the performance of cutlass calculation (int8, int8 to int), but I have now found a problem. M, N, and K in my parameters cannot be selected at random, where N …