News for hackers. Stuff that matters.
Re:Ara: A 1 GHz+ Scalable and Energy-Efficient RISC-V Vector... by atq2119 on Saturday June 08, 2019 @02:40PM (#20134201)
It cannot scale logarithmically because you need at least a linear number of gates to represent the inputs.

It doesn't have to scale superlinearly either, because the natural circuit using a linear number of adders is already of a logarithmic depth, which is best possible asymptotically.

Re:Ara: A 1 GHz+ Scalable and Energy-Efficient RISC-V Vector... by ncmncm on Friday June 21, 2019 @01:14AM (#20240043)
The gate depth scales logarithmically, and that determines how many cycles it takes, or (worse) how fast your cycles can be, if you want the answer in one cycle.
Re:Ara: A 1 GHz+ Scalable and Energy-Efficient RISC-V Vector... by ryacko on Saturday June 08, 2019 @07:10PM (#20135810)
A lot of complexity could be eschewed if processors weren't faster than 100 Mhz.