Scalar indexing with CuArray * ReshapedArray{SubArray{CuArray}}}

[vpuri3]

MWE:

julia> CUDA.allowscalar(false)                                                                                                                                                                          [0/1467]
                                                                                                                                                                                                                
julia> CUDA.ones(5, 4) * reshape(view(CUDA.ones(10, 10, 10), 1:4, :, :), 4, 100)                                                                                                                                
ERROR: Scalar indexing is disallowed.                                                                                                                                                                           
Invocation of getindex resulted in scalar indexing of a GPU array.                                                                                                                                              
This is typically caused by calling an iterating implementation of a method.                                                                                                                                    
Such implementations *do not* execute on the GPU, but very slowly on the CPU,                                                                                                                                   
and therefore are only permitted from the REPL for prototyping purposes.                                                                                                                                        
If you did intend to index this array, annotate the caller with @allowscalar.                                                                                                                                   
Stacktrace:                                                                                                                                                                                                     
  [1] error(s::String)                                                                                                                                                                                          
    @ Base ./error.jl:35                                                                                                                                                                                        
  [2] assertscalar(op::String)                                                                                                                                                                                  
    @ GPUArraysCore ~/.julia/packages/GPUArraysCore/uOYfN/src/GPUArraysCore.jl:103                                                                                                                              
  [3] getindex(::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, ::Int64, ::Int64)                                                                                                                                  
    @ GPUArrays ~/.julia/packages/GPUArrays/5XhED/src/host/indexing.jl:9     
  [4] _generic_matmatmul!(C::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, tA::Char, tB::Char, A::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, B::Base.ReshapedArray{Float32, 2, SubArray{Float32, 3, CuArray{Float
32, 3, CUDA.Mem.DeviceBuffer}, Tuple{UnitRange{Int64}, Base.Slice{Base.OneTo{Int64}}, Base.Slice{Base.OneTo{Int64}}}, false}, Tuple{Base.MultiplicativeInverses.SignedMultiplicativeInverse{Int64}, Base.Multipl
icativeInverses.SignedMultiplicativeInverse{Int64}}}, _add::LinearAlgebra.MulAddMul{true, true, Bool, Bool})                                                                                                    
    @ LinearAlgebra ~/.julia/juliaup/julia-1.9.2+0.x64.linux.gnu/share/julia/stdlib/v1.9/LinearAlgebra/src/matmul.jl:876
  [5] generic_matmatmul!(C::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, tA::Char, tB::Char, A::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, B::Base.ReshapedArray{Float32, 2, SubArray{Float32, 3, CuArray{Float3
2, 3, CUDA.Mem.DeviceBuffer}, Tuple{UnitRange{Int64}, Base.Slice{Base.OneTo{Int64}}, Base.Slice{Base.OneTo{Int64}}}, false}, Tuple{Base.MultiplicativeInverses.SignedMultiplicativeInverse{Int64}, Base.Multipli
cativeInverses.SignedMultiplicativeInverse{Int64}}}, _add::LinearAlgebra.MulAddMul{true, true, Bool, Bool})
    @ LinearAlgebra ~/.julia/juliaup/julia-1.9.2+0.x64.linux.gnu/share/julia/stdlib/v1.9/LinearAlgebra/src/matmul.jl:844
  [6] mul!                                                                                              
    @ ~/.julia/juliaup/julia-1.9.2+0.x64.linux.gnu/share/julia/stdlib/v1.9/LinearAlgebra/src/matmul.jl:303 [inlined]                                                                                            
  [7] mul!                                                                                                                                                                                                      
    @ ~/.julia/juliaup/julia-1.9.2+0.x64.linux.gnu/share/julia/stdlib/v1.9/LinearAlgebra/src/matmul.jl:276 [inlined]
  [8] *(A::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, B::Base.ReshapedArray{Float32, 2, SubArray{Float32, 3, CuArray{Float32, 3, CUDA.Mem.DeviceBuffer}, Tuple{UnitRange{Int64}, Base.Slice{Base.OneTo{Int64}},
 Base.Slice{Base.OneTo{Int64}}}, false}, Tuple{Base.MultiplicativeInverses.SignedMultiplicativeInverse{Int64}, Base.MultiplicativeInverses.SignedMultiplicativeInverse{Int64}}})
    @ LinearAlgebra ~/.julia/juliaup/julia-1.9.2+0.x64.linux.gnu/share/julia/stdlib/v1.9/LinearAlgebra/src/matmul.jl:141
  [9] top-level scope
    @ REPL[8]:1
 [10] top-level scope
    @ ~/.julia/packages/CUDA/tVtYo/src/initialization.jl:185

[maleadt]

That's "expected"; multiple layers of array wrappers are not supported, as it would require an exponential amount of method definitions. See JuliaGPU/Adapt.jl#21. Would require support in Base to fix this using traits, e.g., JuliaLang/julia#31563.