Skip to main content

emit_mma_tn_k64_kernel

logicaffeine_compile::codegen_cuda::gemm_tile

Function emit_mma_tn_k64_kernel 

Source 
pub fn emit_mma_tn_k64_kernel(
    bm: usize,
    bn: usize,
    warps_m: usize,
    warps_n: usize,
    stages: usize,
) -> String
Expand description

Emit JUST the BK=64 champion kernel (no host main) — for the head-to-head cuBLAS parity harness and SASS analysis. Renames the entry to the given symbol so it can be linked beside cublas in one program.