On Sat, Oct 13, 2018 at 3:10 AM Finn Thain wrote:
> Unroll the raw_outsb() loop using the optimized assembler code from
> raw_outsw(). That code is copied and pasted, with movew changed to moveb.
>
> This improves the performance of sequential write transfers using mac_esp
> in PIO mode by 5% or
Unroll the raw_outsb() loop using the optimized assembler code from
raw_outsw(). That code is copied and pasted, with movew changed to moveb.
This improves the performance of sequential write transfers using mac_esp
in PIO mode by 5% or 10%. (The DMA controller on the 840av/660av models is
still