Hand-crafted copyto! specialization

Author: lkdvos

src/auxiliary/auxiliary.jl

@@ -55,3 +55,27 @@ _interleave(::Tuple{}, ::Tuple{}) = ()
 function _interleave(a::NTuple{N}, b::NTuple{N}) where {N}
     return (a[1], b[1], _interleave(tail(a), tail(b))...)
 end
+
+# Low-overhead implementation of `copyto!` for specific case of `stride(B, 1) < stride(B, 2)`
+# used in indexmanipulations: avoids the overhead of Strided.jl
+function _copyto!(A::StridedView{<:Any,1}, B::StridedView{<:Any,2})
+    length(A) == length(B) || throw(DimensionMismatch())
+
+    Adata = parent(A)
+    Astr = stride(A, 1)
+    IA = A.offset
+
+    Bdata = parent(B)
+    Bstr = strides(B)
+
+    IB_1 = B.offset
+    @inbounds for _ in axes(B, 2)
+        IB = IB_1
+        for _ in axes(B, 1)
+            Adata[IA += Astr] = Bdata[IB += Bstr[1]]
+        end
+        IB_1 += Bstr[2]
+    end
+
+    return A
+end

src/tensors/indexmanipulations.jl

@@ -650,7 +650,7 @@ function _add_transform_multi!(tdst, tsrc, p,
     buffer_src = StridedView(buffer2, (blocksize, cols), (1, blocksize), 0)
     for (i, struct_src) in enumerate(structs_src)
         subblock_src = sreshape(StridedView(tsrc.data, sz_src, struct_src...), matsize)
-        copyto!(buffer_src[:, i], subblock_src)
+        _copyto!(buffer_src[:, i], subblock_src)
     end
 
     # Resummation into a second buffer using BLAS