Skip to main content

emit_cutlass_i8_gemm_bench

Function emit_cutlass_i8_gemm_bench 

Source
pub fn emit_cutlass_i8_gemm_bench(
    cfg: &CutlassI8Gemm,
    m: usize,
    k: usize,
    n: usize,
) -> String
Expand description

Full head-to-head parity program: our compiler-emitted CUTLASS kernel vs cublasGemmEx, same process, interleaved best-of-100, varied-fill oracle-checked. Prints PARITY <pct> OURS <gops> CUBLAS <gops>.