KernelTile.update: def of stelliferous@0.0.2.0
Import: import stelliferous@0.0.2.0/kernel_tile.bend as KernelTile
Lines 45-51 of stelliferous@0.0.2.0/kernel_tile.bend: https://jend.leeeet.dev/read.txt?path=stelliferous@0.0.2.0/kernel_tile.bend&start_line=45&end_line=51

import Base
import stelliferous@0.0.2.0/math_fp32.bend as Fp32

# One ordered multiply-add per lane: eight output positions, one weight.
def update(accumulator: Tile8,input: Tile8,weight: F32) -> Tile8:
  Tile{a,b,c,d,e,f,g,h} = accumulator
  Tile{x0,x1,x2,x3,x4,x5,x6,x7} = input
  +weight = weight
  Tile{Fp32.multiply_add(a,x0,weight),Fp32.multiply_add(b,x1,weight),Fp32.multiply_add(c,x2,weight),Fp32.multiply_add(d,x3,weight),
    Fp32.multiply_add(e,x4,weight),Fp32.multiply_add(f,x5,weight),Fp32.multiply_add(g,x6,weight),Fp32.multiply_add(h,x7,weight)}

Uses (3):
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32
  https://jend.leeeet.dev/definition.txt?path=stelliferous@0.0.2.0/kernel_tile.bend&name=Tile8
  https://jend.leeeet.dev/definition.txt?path=stelliferous@0.0.2.0/math_fp32.bend&name=multiply_add