You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
(from Intel partners) In the original code of src\Microsoft.ML.CpuMath\SseIntrinsics.cs, even though VectorSum is inlined, the codegen is not optimized due to register spill and reload. It seems JIT has optimization opportunity over there. Do you mind opening an issue to discuss about it on CoreCLR github repo?
cc: @tannergooding since you might already have addressed this issue.
The text was updated successfully, but these errors were encountered:
briancylui
changed the title
Optimize codegen of inlining in hardware intrinsics APIs
CpuMath Enhancement: Optimize codegen of inlining in hardware intrinsics APIs
Sep 6, 2018
Style changes needed to solve part of #823
Details
src\Microsoft.ML.CpuMath\SseIntrinsics.cs
, even thoughVectorSum
is inlined, the codegen is not optimized due to register spill and reload. It seems JIT has optimization opportunity over there. Do you mind opening an issue to discuss about it on CoreCLR github repo?cc: @tannergooding since you might already have addressed this issue.
The text was updated successfully, but these errors were encountered: