merge

Author: GiggleLiu

src/cuda.jl

@@ -24,3 +24,22 @@ for TT in [:(Tropical{<:NativeTypes}), :TropicalTypes]
    end
 end
 
+<<<<<<< HEAD
+=======
+using .CUDA: @cartesianidx, AbstractGPUArray, gpu_call
+
+@inline @generated function map_index(dest, src, I, perm::NTuple{N,T}) where {N,T}
+    Expr(:(=), Expr(:ref, :dest, [:(@inbounds I[perm[$i]]) for i in 1:N]...), Expr(:ref, :src, :I))
+end
+function LinearAlgebra.permutedims!(dest::AbstractGPUArray, src::AbstractGPUArray,
+                                    perm::NTuple)
+    Base.checkdims_perm(dest, src, perm)
+    function permutedims_kernel(ctx, dest, src, perm)
+        I = @cartesianidx src
+        map_index(dest, src, I, perm)
+        return
+    end
+    gpu_call(permutedims_kernel, dest, src, perm)
+    return dest
+end
+>>>>>>> 22e8c5179a33a94ddc43baa995933d109050d502