TENANCY-BEFORE: []
##BARE acc_n=16
ninja: no work to do.
blocks=256 iters=4000 acc_n=16: 0.818 ms  656.7 TOPS
    dram__throughput.avg.pct_of_peak_sustained_elapsed                                        %         0.00
    gpu__time_duration.sum                                                                   us       921.22
    launch__occupancy_limit_registers                                                     block            6
    launch__occupancy_limit_shared_mem                                                    block           32
    launch__registers_per_thread                                                register/thread           75
    sm__inst_executed_pipe_lsu.avg.pct_of_peak_sustained_active                               %         0.78
    sm__pipe_alu_cycles_active.avg.pct_of_peak_sustained_active                               %         1.18
    sm__pipe_tensor_op_imma_cycles_active.avg.pct_of_peak_sustained_active                    %        99.65
    sm__warps_active.avg.pct_of_peak_sustained_active                                         %        16.66
    smsp__average_warp_latency_per_inst_issued.ratio                                      cycle        26.99
    smsp__average_warps_issue_stalled_barrier_per_issue_active.ratio                       inst            0
    smsp__average_warps_issue_stalled_math_pipe_throttle_per_issue_active.ratio            inst        18.78
    smsp__average_warps_issue_stalled_not_selected_per_issue_active.ratio                  inst         0.80
    smsp__average_warps_issue_stalled_wait_per_issue_active.ratio                          inst         6.10
##BARE acc_n=32
ninja: no work to do.
blocks=256 iters=4000 acc_n=32: 1.638 ms  655.6 TOPS
    dram__throughput.avg.pct_of_peak_sustained_elapsed                                        %         0.00
    gpu__time_duration.sum                                                                   ms         1.84
    launch__occupancy_limit_registers                                                     block            3
    launch__occupancy_limit_shared_mem                                                    block            8
    launch__registers_per_thread                                                register/thread          140
    sm__inst_executed_pipe_lsu.avg.pct_of_peak_sustained_active                               %         0.39
    sm__pipe_alu_cycles_active.avg.pct_of_peak_sustained_active                               %         0.59
    sm__pipe_tensor_op_imma_cycles_active.avg.pct_of_peak_sustained_active                    %        99.82
    sm__warps_active.avg.pct_of_peak_sustained_active                                         %        16.66
    smsp__average_warp_latency_per_inst_issued.ratio                                      cycle        29.25
    smsp__average_warps_issue_stalled_barrier_per_issue_active.ratio                       inst            0
    smsp__average_warps_issue_stalled_math_pipe_throttle_per_issue_active.ratio            inst        20.69
    smsp__average_warps_issue_stalled_not_selected_per_issue_active.ratio                  inst         0.89
    smsp__average_warps_issue_stalled_wait_per_issue_active.ratio                          inst         6.50
TENANCY-AFTER: []

[exited with code 0]
