Scalar Indexing error when performing mul!(A, B, C) with A a view of a Matrix

Specific Domains GPU
, ,
1

Hello,

I paste also here the issue raised here.

Describe the bug

The in-place multiplication mul!(A, B, C) fails when A is a vector view of a matrix.

To reproduce

The Minimal Working Example (MWE) for this bug:

using LinearAlgebra
using CUDA
CUDA.allowscalar(false)

# Working case
prova1 = CUDA.rand(Int, 100) # Vector
prova2 = CUDA.rand(Int, 200, 200) # Matrix
prova3 = CUDA.rand(Int, 200) # Vector
mul!(@view(prova1[1:10]), transpose(@view(prova2[1:10, 1:10])), @view(prova3[1:10]))

# Not working case
prova1 = CUDA.rand(Int, 100, 100) # Matrix
prova2 = CUDA.rand(Int, 200, 200) # Matrix
prova3 = CUDA.rand(Int, 200) # Vector
mul!(@view(prova1[1, 1:10]), transpose(@view(prova2[1:10, 1:10])), @view(prova3[1:10]))

Surprisingly, it works for matrix views of matrices

# Working case
prova1 = CUDA.rand(Int, 100) # Vector
prova2 = CUDA.rand(Int, 200, 200) # Matrix
prova3 = CUDA.rand(Int, 200, 200) # Matrix
mul!(@view(prova1[1:10]), transpose(@view(prova2[1:10, 1:10])), @view(prova3[1, 1:10]))
1 Like
2

I don’t think it’s particularly useful to cross-post issues from a bug tracker. Unless there’s something you want to discuss that couldn’t happen over there?

3

Ok, I don’t know which place is most suitable for discussing about this issue.

4

I would suggest the issue itself.