You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Mar 12, 2021. It is now read-only.
julia> a =ones(2,2)
2×2 Array{Float64,2}:1.01.01.01.0
julia> da =CuArray(a)
2×2 CuArray{Float64,2}:1.01.01.01.0
julia> a = Base.mapreduce(identity, +, a, dims=2)
2×1 Array{Float64,2}:2.02.0
julia> da = Base.mapreduce(identity, +, da, dims=2)
blk =1
thr =2
f = identity
op =+
R = [0.0; 0.0]
A = [1.01.0; 1.01.0]
range = (nothing, Base.OneTo(2))
R = [0.0; 0.0]
2×1 CuArray{Float64,2}:0.00.0
Adding the following side effect-free statement (expanded from (I...)[1]) to the kernel "fixes" the issue:
--- a/src/mapreduce.jl+++ b/src/mapreduce.jl@@ -3,6 +3,7 @@ using CuArrays: @cuindex, cudims
function mapreducedim_kernel_serial(f, op, R, A, range)
I = @cuindex R
newrange = map((r, i) -> r === nothing ? i : r, range, I)
+ @inbounds ((Tuple(CartesianIndices(R)[(blockIdx().x-1) * blockDim().x + threadIdx().x]))...)[1]
for I′ in CartesianIndices(newrange)
@inbounds R[I...] = op(R[I...], f(A[I′]))
end
This makes me sad.
Adding the following side effect-free statement (expanded from
(I...)[1]
) to the kernel "fixes" the issue:IR is minimally different:
The text was updated successfully, but these errors were encountered: