BendMlTensorArray.split_pick: def of bend-ml-tensor-array@0.1.19.0
Import: import bend-ml-tensor-array@0.1.19.0/main.bend as BendMlTensorArray
Lines 1185-1198 of bend-ml-tensor-array@0.1.19.0/main.bend: https://jend.leeeet.dev/read.txt?path=bend-ml-tensor-array@0.1.19.0/main.bend&start_line=1185&end_line=1198

import Base

# ---- the split depth of a product (0.1.11.0): par is an upper bound, and a product too small to gain splits 0 times ----
#
# A product of n x k by k x m splits into 2^par blocks only when it does at least 2^23 multiply-adds and each cell of C
# sums at least 64 of them; otherwise it runs sequentially. Measured on 16 threads (2026-10-16, 18 shapes): below 2^23 the
# split costs more than it saves, and with a short inner dimension (a weight gradient over a few tokens) every split
# was 2-3.6x slower, because each block hands its rows of C back as a list that is then written into C, a cost per cell
# of C that k multiply-adds per cell do not pay for. The result does not depend on the depth: the same bits at every
# depth (tests/t8.bend, tests/acc.bend, tests/split.bend).
def split_pick(big: Bool, d: Nat) -> Nat:
  match big:
    case True{}:
      d
    case False{}:
      0n

Uses (2):
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Bool
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Nat