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
{{ message }}
This repository has been archived by the owner on Jan 26, 2022. It is now read-only.
It looks reasonable that the upcoming Float64x2 type should have member functions Float64x2.load1 and Float64x2.store1. Please consider adding these in the spec for phase 2.
The text was updated successfully, but these errors were encountered:
We currently only have the load123/store123 functions for x4 types, and don't have them for x8 or x16 either. What is the use case for load1 which can't be accomplished by a simple TypedArray read and SIMD constructor call? I don't understand the difference in efficiency for implementations; IIRC the claimed advantage of load3 was that less bounds checking is needed, which would be hard to prove otherwise.
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
It looks reasonable that the upcoming
Float64x2
type should have member functionsFloat64x2.load1
andFloat64x2.store1
. Please consider adding these in the spec for phase 2.The text was updated successfully, but these errors were encountered: