==PROF== Connected to process 38811 (/home/hoo2/Work/AUTH/PDS/homework_3/out/v1/bitonicCUDA)
==PROF== Profiling "prephase" - 1: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 2: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 3: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 4: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 5: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 6: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 7: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 8: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 9: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 10: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 11: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 12: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 13: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 14: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 15: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 16: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 17: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 18: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 19: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 20: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 21: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 22: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 23: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 24: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 25: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 26: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 27: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 28: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 29: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 30: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 31: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 32: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 33: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 34: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 35: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 36: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 37: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 38: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 39: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 40: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 41: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 42: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 43: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 44: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 45: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 46: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 47: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 48: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 49: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 50: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 51: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 52: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 53: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 54: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 55: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 56: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 57: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 58: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 59: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 60: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 61: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 62: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 63: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 64: 0%....50%....100% - 6 passes
==PROF== Profiling "interBlockStep" - 65: 0%....50%....100% - 6 passes
==PROF== Profiling "inBlockStep" - 66: 0%....50%....100% - 6 passes
==PROF== Disconnected from process 38811
[38811] bitonicCUDA@127.0.0.1
  void prephase<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         msecond                           1.06
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.91
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          17.11
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           5.48
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                   1,052,474.71
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                      10,524.75
    smsp__inst_executed.avg                                                           inst                     770,268.77
    smsp__inst_executed.max                                                           inst                        770,551
    smsp__inst_executed.min                                                           inst                        770,034
    smsp__inst_executed.sum                                                           inst                     49,297,201
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          23.25
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.23
    smsp__cycles_active.avg                                                          cycle                   1,463,898.61
    smsp__cycles_active.sum                                                          cycle                     93,689,511
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.78
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,434.38
    smsp__inst_executed.max                                                           inst                         13,034
    smsp__inst_executed.min                                                           inst                         12,078
    smsp__inst_executed.sum                                                           inst                        795,800
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,392.50
    smsp__cycles_active.sum                                                          cycle                      4,633,120
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         182.78
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.72
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.71
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     158,915.20
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,589.15
    smsp__inst_executed.avg                                                           inst                     132,204.09
    smsp__inst_executed.max                                                           inst                        134,291
    smsp__inst_executed.min                                                           inst                        130,034
    smsp__inst_executed.sum                                                           inst                      8,461,062
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.76
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,696.25
    smsp__cycles_active.sum                                                          cycle                     16,172,560
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.86
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.96
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,300.02
    smsp__inst_executed.max                                                           inst                         12,527
    smsp__inst_executed.min                                                           inst                         11,906
    smsp__inst_executed.sum                                                           inst                        787,201
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,419.20
    smsp__cycles_active.sum                                                          cycle                      4,570,829
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.27
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.58
    smsp__inst_executed.max                                                           inst                         12,592
    smsp__inst_executed.min                                                           inst                         12,022
    smsp__inst_executed.sum                                                           inst                        787,813
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,582.45
    smsp__cycles_active.sum                                                          cycle                      4,581,277
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         185.60
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.71
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.71
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     160,972.19
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,609.72
    smsp__inst_executed.avg                                                           inst                     132,207.95
    smsp__inst_executed.max                                                           inst                        134,315
    smsp__inst_executed.min                                                           inst                        130,093
    smsp__inst_executed.sum                                                           inst                      8,461,309
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          21.08
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                        251,877
    smsp__cycles_active.sum                                                          cycle                     16,120,128
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.72
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.97
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,294.97
    smsp__inst_executed.max                                                           inst                         12,632
    smsp__inst_executed.min                                                           inst                         11,676
    smsp__inst_executed.sum                                                           inst                        786,878
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,658.42
    smsp__cycles_active.sum                                                          cycle                      4,650,139
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.27
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.35
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.64
    smsp__inst_executed.max                                                           inst                         12,609
    smsp__inst_executed.min                                                           inst                         11,896
    smsp__inst_executed.sum                                                           inst                        787,113
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,467.41
    smsp__cycles_active.sum                                                          cycle                      4,573,914
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.46
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,308.77
    smsp__inst_executed.max                                                           inst                         12,684
    smsp__inst_executed.min                                                           inst                         11,895
    smsp__inst_executed.sum                                                           inst                        787,761
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,717.34
    smsp__cycles_active.sum                                                          cycle                      4,653,910
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         186.30
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.71
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.71
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     159,835.16
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,598.35
    smsp__inst_executed.avg                                                           inst                     132,204.20
    smsp__inst_executed.max                                                           inst                        134,182
    smsp__inst_executed.min                                                           inst                        130,077
    smsp__inst_executed.sum                                                           inst                      8,461,069
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.87
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,623.66
    smsp__cycles_active.sum                                                          cycle                     16,167,914
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:08, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.24
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,291.53
    smsp__inst_executed.max                                                           inst                         12,717
    smsp__inst_executed.min                                                           inst                         11,826
    smsp__inst_executed.sum                                                           inst                        786,658
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,072.03
    smsp__cycles_active.sum                                                          cycle                      4,548,610
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.50
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,293.39
    smsp__inst_executed.max                                                           inst                         12,679
    smsp__inst_executed.min                                                           inst                         11,917
    smsp__inst_executed.sum                                                           inst                        786,777
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,284.91
    smsp__cycles_active.sum                                                          cycle                      4,626,234
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.95
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.35
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.83
    smsp__inst_executed.max                                                           inst                         12,502
    smsp__inst_executed.min                                                           inst                         12,048
    smsp__inst_executed.sum                                                           inst                        787,125
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,602.17
    smsp__cycles_active.sum                                                          cycle                      4,582,539
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.50
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.36
    smsp__inst_executed.max                                                           inst                         12,725
    smsp__inst_executed.min                                                           inst                         11,813
    smsp__inst_executed.sum                                                           inst                        787,799
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,676.52
    smsp__cycles_active.sum                                                          cycle                      4,587,297
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         185.50
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.72
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.71
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     157,267.79
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,572.68
    smsp__inst_executed.avg                                                           inst                     132,200.03
    smsp__inst_executed.max                                                           inst                        134,283
    smsp__inst_executed.min                                                           inst                        130,070
    smsp__inst_executed.sum                                                           inst                      8,460,802
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.56
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,497.38
    smsp__cycles_active.sum                                                          cycle                     16,159,832
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.98
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.03
    smsp__inst_executed.max                                                           inst                         12,632
    smsp__inst_executed.min                                                           inst                         12,096
    smsp__inst_executed.sum                                                           inst                        786,562
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,852.95
    smsp__cycles_active.sum                                                          cycle                      4,534,589
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.02
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,291.22
    smsp__inst_executed.max                                                           inst                         12,768
    smsp__inst_executed.min                                                           inst                         11,984
    smsp__inst_executed.sum                                                           inst                        786,638
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,387.03
    smsp__cycles_active.sum                                                          cycle                      4,504,770
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.43
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.43
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,293.27
    smsp__inst_executed.max                                                           inst                         12,615
    smsp__inst_executed.min                                                           inst                         11,964
    smsp__inst_executed.sum                                                           inst                        786,769
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                         72,163
    smsp__cycles_active.sum                                                          cycle                      4,618,432
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.95
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.78
    smsp__inst_executed.max                                                           inst                         12,912
    smsp__inst_executed.min                                                           inst                         11,741
    smsp__inst_executed.sum                                                           inst                        787,122
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,542.72
    smsp__cycles_active.sum                                                          cycle                      4,578,734
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.50
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.25
    smsp__inst_executed.max                                                           inst                         12,746
    smsp__inst_executed.min                                                           inst                         11,941
    smsp__inst_executed.sum                                                           inst                        787,792
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,521.23
    smsp__cycles_active.sum                                                          cycle                      4,577,359
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:09, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         185.66
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.72
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.71
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     160,534.14
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,605.34
    smsp__inst_executed.avg                                                           inst                     132,205.30
    smsp__inst_executed.max                                                           inst                        134,375
    smsp__inst_executed.min                                                           inst                        130,047
    smsp__inst_executed.sum                                                           inst                      8,461,139
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          21.03
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     251,948.69
    smsp__cycles_active.sum                                                          cycle                     16,124,716
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.14
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.38
    smsp__inst_executed.max                                                           inst                         12,640
    smsp__inst_executed.min                                                           inst                         11,952
    smsp__inst_executed.sum                                                           inst                        786,520
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,646.14
    smsp__cycles_active.sum                                                          cycle                      4,585,353
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.05
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.72
    smsp__inst_executed.max                                                           inst                         12,532
    smsp__inst_executed.min                                                           inst                         11,872
    smsp__inst_executed.sum                                                           inst                        786,542
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,515.61
    smsp__cycles_active.sum                                                          cycle                      4,576,999
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.82
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.48
    smsp__inst_executed.max                                                           inst                         12,775
    smsp__inst_executed.min                                                           inst                         11,898
    smsp__inst_executed.sum                                                           inst                        786,591
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,662.92
    smsp__cycles_active.sum                                                          cycle                      4,586,427
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.53
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.97
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,293.81
    smsp__inst_executed.max                                                           inst                         12,753
    smsp__inst_executed.min                                                           inst                         11,862
    smsp__inst_executed.sum                                                           inst                        786,804
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,455.17
    smsp__cycles_active.sum                                                          cycle                      4,637,131
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.02
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.96
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,299.31
    smsp__inst_executed.max                                                           inst                         12,673
    smsp__inst_executed.min                                                           inst                         12,034
    smsp__inst_executed.sum                                                           inst                        787,156
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,010.81
    smsp__cycles_active.sum                                                          cycle                      4,544,692
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.72
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,307.36
    smsp__inst_executed.max                                                           inst                         12,544
    smsp__inst_executed.min                                                           inst                         11,923
    smsp__inst_executed.sum                                                           inst                        787,671
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,317.72
    smsp__cycles_active.sum                                                          cycle                      4,628,334
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         183.36
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.70
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.71
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     160,035.27
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,600.35
    smsp__inst_executed.avg                                                           inst                     132,214.05
    smsp__inst_executed.max                                                           inst                        134,326
    smsp__inst_executed.min                                                           inst                        130,109
    smsp__inst_executed.sum                                                           inst                      8,461,699
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.87
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,974.50
    smsp__cycles_active.sum                                                          cycle                     16,190,368
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.69
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.52
    smsp__inst_executed.max                                                           inst                         12,488
    smsp__inst_executed.min                                                           inst                         11,936
    smsp__inst_executed.sum                                                           inst                        786,465
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,501.95
    smsp__cycles_active.sum                                                          cycle                      4,640,125
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.27
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.92
    smsp__inst_executed.max                                                           inst                         12,484
    smsp__inst_executed.min                                                           inst                         12,100
    smsp__inst_executed.sum                                                           inst                        786,427
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,503.14
    smsp__cycles_active.sum                                                          cycle                      4,576,201
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:10, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.08
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.14
    smsp__inst_executed.max                                                           inst                         12,869
    smsp__inst_executed.min                                                           inst                         11,892
    smsp__inst_executed.sum                                                           inst                        786,505
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,524.88
    smsp__cycles_active.sum                                                          cycle                      4,577,592
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.05
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.83
    smsp__inst_executed.max                                                           inst                         12,572
    smsp__inst_executed.min                                                           inst                         12,020
    smsp__inst_executed.sum                                                           inst                        786,613
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,350.59
    smsp__cycles_active.sum                                                          cycle                      4,502,438
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.43
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.43
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,292.59
    smsp__inst_executed.max                                                           inst                         12,681
    smsp__inst_executed.min                                                           inst                         11,988
    smsp__inst_executed.sum                                                           inst                        786,726
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,302.25
    smsp__cycles_active.sum                                                          cycle                      4,563,344
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.89
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.28
    smsp__inst_executed.max                                                           inst                         12,708
    smsp__inst_executed.min                                                           inst                         11,898
    smsp__inst_executed.sum                                                           inst                        787,090
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,771.03
    smsp__cycles_active.sum                                                          cycle                      4,593,346
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.53
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,310.67
    smsp__inst_executed.max                                                           inst                         12,575
    smsp__inst_executed.min                                                           inst                         12,060
    smsp__inst_executed.sum                                                           inst                        787,883
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                         73,137
    smsp__cycles_active.sum                                                          cycle                      4,680,768
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         184.67
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.72
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.71
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     161,865.73
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,618.66
    smsp__inst_executed.avg                                                           inst                     132,202.36
    smsp__inst_executed.max                                                           inst                        134,344
    smsp__inst_executed.min                                                           inst                        130,057
    smsp__inst_executed.sum                                                           inst                      8,460,951
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          21.11
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,870.69
    smsp__cycles_active.sum                                                          cycle                     16,183,724
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.23
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.84
    smsp__inst_executed.max                                                           inst                         12,700
    smsp__inst_executed.min                                                           inst                         11,884
    smsp__inst_executed.sum                                                           inst                        786,422
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,958.33
    smsp__cycles_active.sum                                                          cycle                      4,605,333
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.91
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.59
    smsp__inst_executed.max                                                           inst                         12,836
    smsp__inst_executed.min                                                           inst                         11,892
    smsp__inst_executed.sum                                                           inst                        786,470
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,352.05
    smsp__cycles_active.sum                                                          cycle                      4,630,531
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.43
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.62
    smsp__inst_executed.max                                                           inst                         12,636
    smsp__inst_executed.min                                                           inst                         11,942
    smsp__inst_executed.sum                                                           inst                        786,472
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,507.44
    smsp__cycles_active.sum                                                          cycle                      4,576,476
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.11
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.72
    smsp__inst_executed.max                                                           inst                         12,672
    smsp__inst_executed.min                                                           inst                         11,662
    smsp__inst_executed.sum                                                           inst                        786,542
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,165.02
    smsp__cycles_active.sum                                                          cycle                      4,554,561
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.02
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                         12,291
    smsp__inst_executed.max                                                           inst                         12,677
    smsp__inst_executed.min                                                           inst                         11,882
    smsp__inst_executed.sum                                                           inst                        786,624
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,224.42
    smsp__cycles_active.sum                                                          cycle                      4,494,363
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:11, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.72
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,294.19
    smsp__inst_executed.max                                                           inst                         12,761
    smsp__inst_executed.min                                                           inst                         11,776
    smsp__inst_executed.sum                                                           inst                        786,828
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,352.88
    smsp__cycles_active.sum                                                          cycle                      4,630,584
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.08
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.35
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,300.17
    smsp__inst_executed.max                                                           inst                         12,699
    smsp__inst_executed.min                                                           inst                         11,741
    smsp__inst_executed.sum                                                           inst                        787,211
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,852.11
    smsp__cycles_active.sum                                                          cycle                      4,598,535
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.69
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,305.34
    smsp__inst_executed.max                                                           inst                         12,557
    smsp__inst_executed.min                                                           inst                         12,098
    smsp__inst_executed.sum                                                           inst                        787,542
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,448.42
    smsp__cycles_active.sum                                                          cycle                      4,636,699
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         183.71
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.72
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.71
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     159,410.38
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,594.10
    smsp__inst_executed.avg                                                           inst                     132,239.30
    smsp__inst_executed.max                                                           inst                        134,389
    smsp__inst_executed.min                                                           inst                        130,159
    smsp__inst_executed.sum                                                           inst                      8,463,315
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.78
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     253,259.25
    smsp__cycles_active.sum                                                          cycle                     16,208,592
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.68
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.97
    smsp__inst_executed.max                                                           inst                         12,696
    smsp__inst_executed.min                                                           inst                         11,904
    smsp__inst_executed.sum                                                           inst                        786,430
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,186.48
    smsp__cycles_active.sum                                                          cycle                      4,683,935
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.14
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.12
    smsp__inst_executed.max                                                           inst                         12,680
    smsp__inst_executed.min                                                           inst                         12,068
    smsp__inst_executed.sum                                                           inst                        786,440
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,841.56
    smsp__cycles_active.sum                                                          cycle                      4,597,860
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.20
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.52
    smsp__inst_executed.max                                                           inst                         12,664
    smsp__inst_executed.min                                                           inst                         11,916
    smsp__inst_executed.sum                                                           inst                        786,465
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,395.02
    smsp__cycles_active.sum                                                          cycle                      4,569,281
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.37
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.83
    smsp__inst_executed.max                                                           inst                         12,652
    smsp__inst_executed.min                                                           inst                         12,092
    smsp__inst_executed.sum                                                           inst                        786,485
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,939.75
    smsp__cycles_active.sum                                                          cycle                      4,540,144
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.05
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.27
    smsp__inst_executed.max                                                           inst                         12,671
    smsp__inst_executed.min                                                           inst                         11,948
    smsp__inst_executed.sum                                                           inst                        786,513
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,398.56
    smsp__cycles_active.sum                                                          cycle                      4,505,508
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.89
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.94
    smsp__inst_executed.max                                                           inst                         12,634
    smsp__inst_executed.min                                                           inst                         11,856
    smsp__inst_executed.sum                                                           inst                        786,620
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,430.73
    smsp__cycles_active.sum                                                          cycle                      4,571,567
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:12, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.91
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.97
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,294.67
    smsp__inst_executed.max                                                           inst                         12,714
    smsp__inst_executed.min                                                           inst                         11,973
    smsp__inst_executed.sum                                                           inst                        786,859
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,485.34
    smsp__cycles_active.sum                                                          cycle                      4,639,062
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.11
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.35
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,300.77
    smsp__inst_executed.max                                                           inst                         12,715
    smsp__inst_executed.min                                                           inst                         11,880
    smsp__inst_executed.sum                                                           inst                        787,249
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,482.33
    smsp__cycles_active.sum                                                          cycle                      4,574,869
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.40
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,305.27
    smsp__inst_executed.max                                                           inst                         12,723
    smsp__inst_executed.min                                                           inst                         11,888
    smsp__inst_executed.sum                                                           inst                        787,537
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,478.97
    smsp__cycles_active.sum                                                          cycle                      4,574,654
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         182.66
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.71
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.71
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     159,442.50
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,594.42
    smsp__inst_executed.avg                                                           inst                     132,250.77
    smsp__inst_executed.max                                                           inst                        134,372
    smsp__inst_executed.min                                                           inst                        130,113
    smsp__inst_executed.sum                                                           inst                      8,464,049
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.82
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,682.78
    smsp__cycles_active.sum                                                          cycle                     16,171,698
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          56.86
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.31
    smsp__inst_executed.max                                                           inst                         12,684
    smsp__inst_executed.min                                                           inst                         12,072
    smsp__inst_executed.sum                                                           inst                        786,452
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      69,556.61
    smsp__cycles_active.sum                                                          cycle                      4,451,623
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.84
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.48
    smsp__inst_executed.max                                                           inst                         12,868
    smsp__inst_executed.min                                                           inst                         11,704
    smsp__inst_executed.sum                                                           inst                        786,399
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,568.34
    smsp__cycles_active.sum                                                          cycle                      4,708,374
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.88
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.06
    smsp__inst_executed.max                                                           inst                         12,672
    smsp__inst_executed.min                                                           inst                         11,712
    smsp__inst_executed.sum                                                           inst                        786,436
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,217.27
    smsp__cycles_active.sum                                                          cycle                      4,685,905
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.39
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.70
    smsp__inst_executed.max                                                           inst                         12,684
    smsp__inst_executed.min                                                           inst                         12,060
    smsp__inst_executed.sum                                                           inst                        786,477
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,586.44
    smsp__cycles_active.sum                                                          cycle                      4,645,532
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.24
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.72
    smsp__inst_executed.max                                                           inst                         12,496
    smsp__inst_executed.min                                                           inst                         12,076
    smsp__inst_executed.sum                                                           inst                        786,414
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,872.52
    smsp__cycles_active.sum                                                          cycle                      4,599,841
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.14
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.17
    smsp__inst_executed.max                                                           inst                         12,692
    smsp__inst_executed.min                                                           inst                         11,950
    smsp__inst_executed.sum                                                           inst                        786,507
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,569.31
    smsp__cycles_active.sum                                                          cycle                      4,580,436
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.98
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.83
    smsp__inst_executed.max                                                           inst                         12,676
    smsp__inst_executed.min                                                           inst                         12,066
    smsp__inst_executed.sum                                                           inst                        786,613
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,942.83
    smsp__cycles_active.sum                                                          cycle                      4,540,341
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:13, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.78
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.43
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,292.48
    smsp__inst_executed.max                                                           inst                         12,668
    smsp__inst_executed.min                                                           inst                         11,864
    smsp__inst_executed.sum                                                           inst                        786,719
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,652.72
    smsp__cycles_active.sum                                                          cycle                      4,585,774
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:14, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.92
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.35
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,297.83
    smsp__inst_executed.max                                                           inst                         12,507
    smsp__inst_executed.min                                                           inst                         12,080
    smsp__inst_executed.sum                                                           inst                        787,061
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,989.52
    smsp__cycles_active.sum                                                          cycle                      4,607,329
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:14, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.56
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.70
    smsp__inst_executed.max                                                           inst                         12,667
    smsp__inst_executed.min                                                           inst                         12,088
    smsp__inst_executed.sum                                                           inst                        787,821
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,280.86
    smsp__cycles_active.sum                                                          cycle                      4,625,975
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:14, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         183.58
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          10.83
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          14.70
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.70
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     159,496.29
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,594.96
    smsp__inst_executed.avg                                                           inst                     131,966.41
    smsp__inst_executed.max                                                           inst                        134,088
    smsp__inst_executed.min                                                           inst                        129,856
    smsp__inst_executed.sum                                                           inst                      8,445,850
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.79
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     253,055.50
    smsp__cycles_active.sum                                                          cycle                     16,195,552
    ---------------------------------------------------------------------- --------------- ------------------------------

