BendtorchGpu.tdot: def of bendtorch-gpu@1.3.0.0
Import: import bendtorch-gpu@1.3.0.0/main.bend as BendtorchGpu
Lines 658-663 of bendtorch-gpu@1.3.0.0/main.bend: https://jend.leeeet.dev/read.txt?path=bendtorch-gpu@1.3.0.0/main.bend&start_line=658&end_line=663

import Base
import bendtorch@1.3.0.0/main.bend as T

# acc + a[ia]·b[ib] + .. down column j of a head's packed triangle (row i + 1's cell is i + 1 after row i's) and b's
# rows (sb apart), from row i on: dot0's sum, but with the step in a growing by one a row
def tdot(k: Nat, +ia: U32, +ib: U32, +i: U32, +sb: U32, acc: F32, ra: Array<F32> & F32, rb: Array<F32> & F32) -> T.D2:
  match k ra rb:
    case 0n Tuple{a, x} Tuple{b, y}: T.D2{a, b, acc}
    case 1n+p Tuple{a, +x} Tuple{b, +y}: tdot(p, (ia + (i + 1 : U32) : U32), (ib + sb : U32), (i + 1 : U32), sb, (acc + (x * y : F32) : F32), Array.get(F32, a, (ia + (i + 1 : U32) : U32)), Array.get(F32, b, (ib + sb : U32)))

Uses (11):
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Array
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Array.get
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32.add
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32.mul
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Nat
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Pair
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Sigma
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=U32
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=U32.add
  https://jend.leeeet.dev/definition.txt?path=bendtorch@1.3.0.0/main.bend&name=D2