inline __device__ Smem_tile_row_b()

in candle-flash-attn-v1/kernels/fmha/smem_tile.h [777:810]

• 20 lines of code
• 4 McCabe index (conditional complexity)

    inline __device__ Smem_tile_row_b(void *smem, int tidx) : Base(smem, tidx) {

        // The number of warps.
        const int WARPS_M = Cta_tile::WARPS_M;
        const int WARPS_N = Cta_tile::WARPS_N;
        const int WARPS_K = Cta_tile::WARPS_K;
        static_assert(WARPS_K == 1);
        static_assert(WARPS_M == 4 || WARPS_M == 8);
        static_assert(WARPS_N == 1);

        // The masks to select the warps.
        const int WARP_MASK_N = Warp_masks<WARPS_M, WARPS_N, WARPS_K>::N;
        const int WARP_MASK_K = Warp_masks<WARPS_M, WARPS_N, WARPS_K>::K;

        // The divisor for the warps.
        const int WARP_DIV_N = WARPS_M *       1 * Cta_tile::THREADS_PER_WARP;
        const int WARP_DIV_K = WARPS_M * WARPS_N * Cta_tile::THREADS_PER_WARP;


        static_assert(USE_LDSMT);
        static_assert(Base::ROWS_PER_XOR_PATTERN == 2 || Base::ROWS_PER_XOR_PATTERN == 4 || Base::ROWS_PER_XOR_PATTERN == 8);

        // The row/col read by the thread.
        int smem_read_row = (tidx & WARP_MASK_K) / WARP_DIV_K * Mma_tile::MMAS_K * 16 +
                            (tidx & 0x07) + (tidx & 0x08);
        constexpr int ROWS_PER_PACKING = Base::BYTES_PER_ROW / Base::BYTES_PER_ROW_BEFORE_PACKING;
        int smem_read_col = ((smem_read_row / ROWS_PER_PACKING) % Base::ROWS_PER_XOR_PATTERN) * Base::COLS_PER_XOR_PATTERN;
        smem_read_col ^= (tidx & WARP_MASK_N) / WARP_DIV_N * 2 + (tidx & 0x10) / 16;

        // The shared memory offset.
        this->smem_read_offset_ = smem_read_row*Base::BYTES_PER_ROW_BEFORE_PACKING + smem_read_col*BYTES_PER_LDS;

        // Fill zeroes for group conv
    }