From 76f5291131608062f715b5457430c122ad10aa61 Mon Sep 17 00:00:00 2001
From: Magnus Ulimoen <magnus@ulimoen.dev>
Date: Thu, 25 Mar 2021 17:23:01 +0100
Subject: [PATCH] Elide bounds check in diffxi

array_windows.skip did not elide bounds checks as it should. If
the slice is instead offset by the skipped amount, we have the
same behavour, but aids the compiler enough.
The two changed lines allows SIMD optimisations, giving an
impressive reduction in instructions by two thirds in the
benchmark.
---
 sbp/src/operators/algos.rs | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sbp/src/operators/algos.rs b/sbp/src/operators/algos.rs
index 5d0896e..d9c5870 100644
--- a/sbp/src/operators/algos.rs
+++ b/sbp/src/operators/algos.rs
@@ -142,9 +142,8 @@ pub(crate) fn diff_op_1d_slice<const M: usize, const N: usize, const D: usize>(
     // based on the block size
     let window_elems_to_skip = M - ((D - 1) / 2);
 
-    for (window, f) in prev
+    for (window, f) in prev[window_elems_to_skip..]
         .array_windows::<D>()
-        .skip(window_elems_to_skip)
         .zip(fut.array_chunks_mut::<1>())
     {
         let fut = ColVector::<_, 1>::map_to_col_mut(f);