This is how the schedule looks like ones lowered:
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {C: Buffer(C_2: Pointer(int8), int8, [1, 1, 1, 8], []),
B: Buffer(B_2: Pointer(int8), int8, [1, 1, 8, 8], []),
A: Buffer(A_2: Pointer(int8), int8, [1, 1, 1, 8], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
for (ci: int32, 0, 8) {
C_2[ci] = 0i8
for (ki: int32, 0, 8) {
C_2[ci] = ((int8*)C_2[ci] + ((int8*)A_2[ki]*(int8*)B_2[((ci*8) + ki)]))
}
}
}