type E
import bend-ml-tensor-gpu@0.1.5.1/main.bend as BendMlTensorGpuimport Base
32# the sizes and strides of one product: C[i][j] = sum_p A[oa + i*arow + p*sa] * B[ob + p*sb + j*bcol], n x m, k steps
33# (oa, ob: 0 except for matmul_precise's blocks)
34type E is Data:
35 E{n: U32, m: U32, k: U32, tcols: U32, tiles: U32, arow: U32, sa: U32, sb: U32, bcol: U32, kg: Nat, rot: Nat, rem: U32, ac: Bool, oa: U32, ob: U32}