Fix performance regression in broadcasting with CartesianIndices (#39333

) * Fix performance regression in broadcasting with CartesianIndices This avoids the boundary check due to a change in the implementation of iteration using `CartecianIndices` in PR #37829. This is a workaround on the caller side and does not change the iteration mechanism itself. Co-authored-by: Matt Bauman <[email protected]> Co-authored-by: thofma <[email protected]>
JuliaLang · Jan 21, 2021 · a4cd68c · a4cd68c
1 parent 9af1877
commit a4cd68c
Showing 1 changed file with 4 additions and 2 deletions.
diff --git a/base/broadcast.jl b/base/broadcast.jl
@@ -977,8 +977,10 @@ preprocess_args(dest, args::Tuple{}) = ()
         end
     end
     bc′ = preprocess(dest, bc)
-    @simd for I in eachindex(bc′)
-        @inbounds dest[I] = bc′[I]
+    # Performance may vary depending on whether `@inbounds` is placed outside the
+    # for loop or not. (cf. https://github.com/JuliaLang/julia/issues/38086)
+    @inbounds @simd for I in eachindex(bc′)
+        dest[I] = bc′[I]
     end
     return dest
 end