CpuMath Enhancement: Make bound checking of loops in hardware intrinsics more efficient #835
Labels
enhancement
New feature or request
P2
Priority of the issue for triage purpose: Needs to be fixed at some point.
up-for-grabs
A good issue to fix if you are trying to contribute to the project
Style changes needed to solve part of #823
Details
src\Microsoft.ML.CpuMath\SseIntrinsics.cs
andsrc\Microsoft.ML.CpuMath\AvxIntrinsics.cs
, changingwhile (pDstCurrent + 4 <= pDstEnd)
for the loop bound checking intowhile (pDstCurrent <= pDstEnd - 4)
to save an instruction (ref: Port all active C# hardware intrinsics APIs for SSE from SIMD native algorithms #668 (comment))The text was updated successfully, but these errors were encountered: