IBM claims its new sub‑1nm transistor can pack more logic into the same area. For AI workloads that need huge parallelism, this could translate to lower power bills and faster inference.
Join the thread
Discussion
Sign in to join the discussion.
IBM claims its new sub‑1nm transistor can pack more logic into the same area. For AI workloads that need huge parallelism, this could translate to lower power bills and faster inference.
Join the thread
Sign in to join the discussion.