Skip to content

arm64: filmgrain16: Use sqrdmulh for the scaling*grain multiplication

Martin Storsjö requested to merge mstorsjo/dav1d:arm64-fgy-scale-16bit into master
Before:               Cortex A53      A72      A73  Apple M1
fgy_32x32xn_16bpc_neon:  10396.8   8150.8   8718.3  19.5
After:
fgy_32x32xn_16bpc_neon:   9665.1   7558.8   7652.8  19.5

Merge request reports

Loading