pub fn emit_wmma_i8_program(m: usize, k: usize, n: usize) -> StringExpand description
Full self-contained WMMA int8 program for M×K×N: kernel + host main that fills A/B deterministically
(same fill as the tiled program, so the SAME scalar oracle applies), launches
gemm_wmma_i8<<<(N/16, M/16), 32>>> (one warp per 16×16 tile), and prints int32 C row-major.