==PROF== Connected to process 22938 (/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 22938
[22938] bitonicCUDA@127.0.0.1
  void prephase<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, 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                   %                          17.12
    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                                 %                   1,054,051.50
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                      10,540.52
    smsp__inst_executed.avg                                                           inst                     770,272.39
    smsp__inst_executed.max                                                           inst                        782,344
    smsp__inst_executed.min                                                           inst                        758,292
    smsp__inst_executed.sum                                                           inst                     49,297,433
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          23.30
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.23
    smsp__cycles_active.avg                                                          cycle                   1,462,946.80
    smsp__cycles_active.sum                                                          cycle                     93,628,595
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.62
    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                      12,435.56
    smsp__inst_executed.max                                                           inst                         12,845
    smsp__inst_executed.min                                                           inst                         12,159
    smsp__inst_executed.sum                                                           inst                        795,876
    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                      73,038.88
    smsp__cycles_active.sum                                                          cycle                      4,674,488
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         183.52
    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                                 %                     159,299.29
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,592.99
    smsp__inst_executed.avg                                                           inst                     132,203.94
    smsp__inst_executed.max                                                           inst                        134,386
    smsp__inst_executed.min                                                           inst                        130,049
    smsp__inst_executed.sum                                                           inst                      8,461,052
    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                     251,805.25
    smsp__cycles_active.sum                                                          cycle                     16,115,536
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, 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                   %                          12.35
    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                      12,300.55
    smsp__inst_executed.max                                                           inst                         12,511
    smsp__inst_executed.min                                                           inst                         11,976
    smsp__inst_executed.sum                                                           inst                        787,235
    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                      71,663.48
    smsp__cycles_active.sum                                                          cycle                      4,586,463
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, 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                   %                          12.24
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.92
    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                         12,590
    smsp__inst_executed.min                                                           inst                         11,916
    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                      71,511.94
    smsp__cycles_active.sum                                                          cycle                      4,576,764
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         185.38
    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                                 %                     157,819.92
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,578.20
    smsp__inst_executed.avg                                                           inst                     132,202.20
    smsp__inst_executed.max                                                           inst                        134,335
    smsp__inst_executed.min                                                           inst                        130,058
    smsp__inst_executed.sum                                                           inst                      8,460,941
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.63
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,205.56
    smsp__cycles_active.sum                                                          cycle                     16,141,156
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.62
    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                      12,295.12
    smsp__inst_executed.max                                                           inst                         12,845
    smsp__inst_executed.min                                                           inst                         11,576
    smsp__inst_executed.sum                                                           inst                        786,888
    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                      72,152.91
    smsp__cycles_active.sum                                                          cycle                      4,617,786
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, 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                   %                          12.36
    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                      12,298.95
    smsp__inst_executed.max                                                           inst                         12,735
    smsp__inst_executed.min                                                           inst                         11,896
    smsp__inst_executed.sum                                                           inst                        787,133
    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                      71,377.27
    smsp__cycles_active.sum                                                          cycle                      4,568,145
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.66
    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                   %                          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                      12,309.39
    smsp__inst_executed.max                                                           inst                         12,687
    smsp__inst_executed.min                                                           inst                         11,876
    smsp__inst_executed.sum                                                           inst                        787,801
    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                      71,765.78
    smsp__cycles_active.sum                                                          cycle                      4,593,010
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:17, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         183.65
    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                                 %                     160,738.71
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,607.39
    smsp__inst_executed.avg                                                           inst                     132,202.83
    smsp__inst_executed.max                                                           inst                        134,317
    smsp__inst_executed.min                                                           inst                        130,020
    smsp__inst_executed.sum                                                           inst                      8,460,981
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.97
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     253,056.44
    smsp__cycles_active.sum                                                          cycle                     16,195,612
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.18
    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                      12,290.95
    smsp__inst_executed.max                                                           inst                         12,831
    smsp__inst_executed.min                                                           inst                         11,912
    smsp__inst_executed.sum                                                           inst                        786,621
    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                      70,120.38
    smsp__cycles_active.sum                                                          cycle                      4,487,704
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, 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                           3.98
    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                      12,294.12
    smsp__inst_executed.max                                                           inst                         12,790
    smsp__inst_executed.min                                                           inst                         11,908
    smsp__inst_executed.sum                                                           inst                        786,824
    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                      72,326.78
    smsp__cycles_active.sum                                                          cycle                      4,628,914
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, 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                      12,298.86
    smsp__inst_executed.max                                                           inst                         12,545
    smsp__inst_executed.min                                                           inst                         12,035
    smsp__inst_executed.sum                                                           inst                        787,127
    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                      71,534.31
    smsp__cycles_active.sum                                                          cycle                      4,578,196
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.59
    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                      12,307.75
    smsp__inst_executed.max                                                           inst                         12,590
    smsp__inst_executed.min                                                           inst                         11,663
    smsp__inst_executed.sum                                                           inst                        787,696
    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                      72,304.95
    smsp__cycles_active.sum                                                          cycle                      4,627,517
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         185.25
    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                                 %                     159,251.51
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,592.52
    smsp__inst_executed.avg                                                           inst                     132,211.53
    smsp__inst_executed.max                                                           inst                        134,374
    smsp__inst_executed.min                                                           inst                        130,131
    smsp__inst_executed.sum                                                           inst                      8,461,538
    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                     252,324.94
    smsp__cycles_active.sum                                                          cycle                     16,148,796
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.18
    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                      12,289.98
    smsp__inst_executed.max                                                           inst                         12,542
    smsp__inst_executed.min                                                           inst                         12,084
    smsp__inst_executed.sum                                                           inst                        786,559
    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                      70,892.06
    smsp__cycles_active.sum                                                          cycle                      4,537,092
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, 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                   %                          12.46
    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                      12,291.59
    smsp__inst_executed.max                                                           inst                         12,644
    smsp__inst_executed.min                                                           inst                         11,864
    smsp__inst_executed.sum                                                           inst                        786,662
    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                      71,680.12
    smsp__cycles_active.sum                                                          cycle                      4,587,528
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.34
    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                      12,293.95
    smsp__inst_executed.max                                                           inst                         12,565
    smsp__inst_executed.min                                                           inst                         11,908
    smsp__inst_executed.sum                                                           inst                        786,813
    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                      72,494.78
    smsp__cycles_active.sum                                                          cycle                      4,639,666
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, 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                      12,299.05
    smsp__inst_executed.max                                                           inst                         12,764
    smsp__inst_executed.min                                                           inst                         11,918
    smsp__inst_executed.sum                                                           inst                        787,139
    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                      70,412.25
    smsp__cycles_active.sum                                                          cycle                      4,506,384
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:18, 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                   %                          12.23
    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                      12,308.47
    smsp__inst_executed.max                                                           inst                         12,770
    smsp__inst_executed.min                                                           inst                         11,835
    smsp__inst_executed.sum                                                           inst                        787,742
    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                      72,493.03
    smsp__cycles_active.sum                                                          cycle                      4,639,554
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         183.30
    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                                 %                     160,924.14
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,609.24
    smsp__inst_executed.avg                                                           inst                     132,203.48
    smsp__inst_executed.max                                                           inst                        132,405
    smsp__inst_executed.min                                                           inst                        132,014
    smsp__inst_executed.sum                                                           inst                      8,461,023
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          21.00
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,862.81
    smsp__cycles_active.sum                                                          cycle                     16,183,220
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, 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                      12,288.66
    smsp__inst_executed.max                                                           inst                         12,472
    smsp__inst_executed.min                                                           inst                         12,102
    smsp__inst_executed.sum                                                           inst                        786,474
    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                      71,593.94
    smsp__cycles_active.sum                                                          cycle                      4,582,012
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, 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                           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                      12,288.95
    smsp__inst_executed.max                                                           inst                         12,688
    smsp__inst_executed.min                                                           inst                         11,936
    smsp__inst_executed.sum                                                           inst                        786,493
    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                      71,439.05
    smsp__cycles_active.sum                                                          cycle                      4,572,099
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, 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                   %                          12.47
    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                      12,290.78
    smsp__inst_executed.max                                                           inst                         12,548
    smsp__inst_executed.min                                                           inst                         11,926
    smsp__inst_executed.sum                                                           inst                        786,610
    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                      71,595.69
    smsp__cycles_active.sum                                                          cycle                      4,582,124
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, 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                   %                          12.43
    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                      12,293.39
    smsp__inst_executed.max                                                           inst                         12,562
    smsp__inst_executed.min                                                           inst                         11,983
    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                      72,335.70
    smsp__cycles_active.sum                                                          cycle                      4,629,485
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, 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
    smsp__inst_executed.max                                                           inst                         12,523
    smsp__inst_executed.min                                                           inst                         11,883
    smsp__inst_executed.sum                                                           inst                        787,072
    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                      71,859.33
    smsp__cycles_active.sum                                                          cycle                      4,598,997
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.75
    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                   %                          12.23
    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                      12,307.64
    smsp__inst_executed.max                                                           inst                         12,574
    smsp__inst_executed.min                                                           inst                         12,091
    smsp__inst_executed.sum                                                           inst                        787,689
    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                      72,764.64
    smsp__cycles_active.sum                                                          cycle                      4,656,937
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, 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                                 %                     158,443.01
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,584.43
    smsp__inst_executed.avg                                                           inst                     132,209.97
    smsp__inst_executed.max                                                           inst                        134,328
    smsp__inst_executed.min                                                           inst                        130,097
    smsp__inst_executed.sum                                                           inst                      8,461,438
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.67
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,761.25
    smsp__cycles_active.sum                                                          cycle                     16,176,720
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, 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                   %                          12.49
    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                      12,288.77
    smsp__inst_executed.max                                                           inst                         12,668
    smsp__inst_executed.min                                                           inst                         11,916
    smsp__inst_executed.sum                                                           inst                        786,481
    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                      72,578.50
    smsp__cycles_active.sum                                                          cycle                      4,645,024
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:19, 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                   %                          12.49
    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                      12,288.92
    smsp__inst_executed.max                                                           inst                         12,639
    smsp__inst_executed.min                                                           inst                         12,088
    smsp__inst_executed.sum                                                           inst                        786,491
    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                      71,972.80
    smsp__cycles_active.sum                                                          cycle                      4,606,259
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, 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                   %                          12.48
    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                      12,289.28
    smsp__inst_executed.max                                                           inst                         12,596
    smsp__inst_executed.min                                                           inst                         11,888
    smsp__inst_executed.sum                                                           inst                        786,514
    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                      71,734.44
    smsp__cycles_active.sum                                                          cycle                      4,591,004
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, 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                   %                          12.47
    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                      12,289.53
    smsp__inst_executed.max                                                           inst                         12,668
    smsp__inst_executed.min                                                           inst                         11,966
    smsp__inst_executed.sum                                                           inst                        786,530
    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                      70,884.67
    smsp__cycles_active.sum                                                          cycle                      4,536,619
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, 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                      12,292.44
    smsp__inst_executed.max                                                           inst                         12,568
    smsp__inst_executed.min                                                           inst                         12,004
    smsp__inst_executed.sum                                                           inst                        786,716
    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                      71,469.70
    smsp__cycles_active.sum                                                          cycle                      4,574,061
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, 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                      12,298.23
    smsp__inst_executed.max                                                           inst                         12,752
    smsp__inst_executed.min                                                           inst                         12,082
    smsp__inst_executed.sum                                                           inst                        787,087
    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                      70,690.11
    smsp__cycles_active.sum                                                          cycle                      4,524,167
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, 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                   %                          12.23
    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                      12,310.39
    smsp__inst_executed.max                                                           inst                         12,698
    smsp__inst_executed.min                                                           inst                         11,982
    smsp__inst_executed.sum                                                           inst                        787,865
    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                      72,817.17
    smsp__cycles_active.sum                                                          cycle                      4,660,299
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         183.30
    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                                 %                     160,300.52
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,603.01
    smsp__inst_executed.avg                                                           inst                     132,192.88
    smsp__inst_executed.max                                                           inst                        134,273
    smsp__inst_executed.min                                                           inst                        130,123
    smsp__inst_executed.sum                                                           inst                      8,460,344
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.96
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,499.88
    smsp__cycles_active.sum                                                          cycle                     16,159,992
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.46
    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                   %                          12.50
    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                      12,287.98
    smsp__inst_executed.max                                                           inst                         12,504
    smsp__inst_executed.min                                                           inst                         12,076
    smsp__inst_executed.sum                                                           inst                        786,431
    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                      72,785.80
    smsp__cycles_active.sum                                                          cycle                      4,658,291
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.94
    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                      12,288.17
    smsp__inst_executed.max                                                           inst                         12,684
    smsp__inst_executed.min                                                           inst                         11,880
    smsp__inst_executed.sum                                                           inst                        786,443
    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                      71,055.12
    smsp__cycles_active.sum                                                          cycle                      4,547,528
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, 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                      12,288.56
    smsp__inst_executed.max                                                           inst                         12,501
    smsp__inst_executed.min                                                           inst                         11,924
    smsp__inst_executed.sum                                                           inst                        786,468
    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                      71,654.25
    smsp__cycles_active.sum                                                          cycle                      4,585,872
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.21
    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                      12,289.83
    smsp__inst_executed.max                                                           inst                         12,524
    smsp__inst_executed.min                                                           inst                         11,928
    smsp__inst_executed.sum                                                           inst                        786,549
    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                      71,462.27
    smsp__cycles_active.sum                                                          cycle                      4,573,585
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:20, 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                   %                          12.45
    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                      12,291.52
    smsp__inst_executed.max                                                           inst                         12,785
    smsp__inst_executed.min                                                           inst                         11,986
    smsp__inst_executed.sum                                                           inst                        786,657
    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                      71,521.95
    smsp__cycles_active.sum                                                          cycle                      4,577,405
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, 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                   %                          12.43
    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                      12,293.20
    smsp__inst_executed.max                                                           inst                         12,707
    smsp__inst_executed.min                                                           inst                         11,874
    smsp__inst_executed.sum                                                           inst                        786,765
    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                      71,517.52
    smsp__cycles_active.sum                                                          cycle                      4,577,121
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, 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                   %                          12.36
    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                      12,298.66
    smsp__inst_executed.max                                                           inst                         12,494
    smsp__inst_executed.min                                                           inst                         12,032
    smsp__inst_executed.sum                                                           inst                        787,114
    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                      71,726.52
    smsp__cycles_active.sum                                                          cycle                      4,590,497
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, 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                   %                          12.21
    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                      12,308.78
    smsp__inst_executed.max                                                           inst                         12,573
    smsp__inst_executed.min                                                           inst                         11,874
    smsp__inst_executed.sum                                                           inst                        787,762
    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                      71,852.81
    smsp__cycles_active.sum                                                          cycle                      4,598,580
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, 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                                 %                     158,707.09
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,587.07
    smsp__inst_executed.avg                                                           inst                     132,223.38
    smsp__inst_executed.max                                                           inst                        134,277
    smsp__inst_executed.min                                                           inst                        130,147
    smsp__inst_executed.sum                                                           inst                      8,462,296
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.80
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     251,577.56
    smsp__cycles_active.sum                                                          cycle                     16,100,964
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.55
    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                      12,288.16
    smsp__inst_executed.max                                                           inst                         12,868
    smsp__inst_executed.min                                                           inst                         11,716
    smsp__inst_executed.sum                                                           inst                        786,442
    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                      72,504.88
    smsp__cycles_active.sum                                                          cycle                      4,640,312
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, 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                      12,288.09
    smsp__inst_executed.max                                                           inst                         12,496
    smsp__inst_executed.min                                                           inst                         11,912
    smsp__inst_executed.sum                                                           inst                        786,438
    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                      72,023.64
    smsp__cycles_active.sum                                                          cycle                      4,609,513
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, 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                   %                          12.50
    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                      12,287.92
    smsp__inst_executed.max                                                           inst                         12,480
    smsp__inst_executed.min                                                           inst                         11,908
    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                      72,365.19
    smsp__cycles_active.sum                                                          cycle                      4,631,372
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, 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                   %                          12.49
    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                      12,288.72
    smsp__inst_executed.max                                                           inst                         12,515
    smsp__inst_executed.min                                                           inst                         12,092
    smsp__inst_executed.sum                                                           inst                        786,478
    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                      71,533.81
    smsp__cycles_active.sum                                                          cycle                      4,578,164
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, 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                   %                          12.48
    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                      12,288.28
    smsp__inst_executed.max                                                           inst                         12,696
    smsp__inst_executed.min                                                           inst                         11,904
    smsp__inst_executed.sum                                                           inst                        786,450
    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                      71,528.86
    smsp__cycles_active.sum                                                          cycle                      4,577,847
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:21, 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                   %                          12.46
    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                      12,290.33
    smsp__inst_executed.max                                                           inst                         12,884
    smsp__inst_executed.min                                                           inst                         11,908
    smsp__inst_executed.sum                                                           inst                        786,581
    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                      70,784.72
    smsp__cycles_active.sum                                                          cycle                      4,530,222
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.85
    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                      12,293.06
    smsp__inst_executed.max                                                           inst                         12,512
    smsp__inst_executed.min                                                           inst                         12,014
    smsp__inst_executed.sum                                                           inst                        786,756
    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                      71,642.33
    smsp__cycles_active.sum                                                          cycle                      4,585,109
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, 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                      12,297.52
    smsp__inst_executed.max                                                           inst                         12,537
    smsp__inst_executed.min                                                           inst                         12,055
    smsp__inst_executed.sum                                                           inst                        787,041
    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                      70,705.81
    smsp__cycles_active.sum                                                          cycle                      4,525,172
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.66
    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                   %                          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                      12,310.97
    smsp__inst_executed.max                                                           inst                         12,739
    smsp__inst_executed.min                                                           inst                         12,075
    smsp__inst_executed.sum                                                           inst                        787,902
    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                      72,633.72
    smsp__cycles_active.sum                                                          cycle                      4,648,558
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         183.74
    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                                 %                     158,858.86
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,588.59
    smsp__inst_executed.avg                                                           inst                     132,194.42
    smsp__inst_executed.max                                                           inst                        134,318
    smsp__inst_executed.min                                                           inst                        130,076
    smsp__inst_executed.sum                                                           inst                      8,460,443
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.74
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,719.28
    smsp__cycles_active.sum                                                          cycle                     16,174,034
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          56.54
    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                      12,287.77
    smsp__inst_executed.max                                                           inst                         12,500
    smsp__inst_executed.min                                                           inst                         12,088
    smsp__inst_executed.sum                                                           inst                        786,417
    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                      69,383.22
    smsp__cycles_active.sum                                                          cycle                      4,440,526
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.62
    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                      12,288.28
    smsp__inst_executed.max                                                           inst                         12,856
    smsp__inst_executed.min                                                           inst                         11,904
    smsp__inst_executed.sum                                                           inst                        786,450
    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                      72,261.28
    smsp__cycles_active.sum                                                          cycle                      4,624,722
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.01
    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                      12,288.75
    smsp__inst_executed.max                                                           inst                         12,500
    smsp__inst_executed.min                                                           inst                         11,888
    smsp__inst_executed.sum                                                           inst                        786,480
    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                      71,742.92
    smsp__cycles_active.sum                                                          cycle                      4,591,547
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, 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                   %                          12.50
    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                      12,288.27
    smsp__inst_executed.max                                                           inst                         12,505
    smsp__inst_executed.min                                                           inst                         11,888
    smsp__inst_executed.sum                                                           inst                        786,449
    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                      71,612.34
    smsp__cycles_active.sum                                                          cycle                      4,583,190
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, 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                      12,288.44
    smsp__inst_executed.max                                                           inst                         12,539
    smsp__inst_executed.min                                                           inst                         11,888
    smsp__inst_executed.sum                                                           inst                        786,460
    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                      71,165.33
    smsp__cycles_active.sum                                                          cycle                      4,554,581
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, 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                      12,289.31
    smsp__inst_executed.max                                                           inst                         12,472
    smsp__inst_executed.min                                                           inst                         12,108
    smsp__inst_executed.sum                                                           inst                        786,516
    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                      70,451.98
    smsp__cycles_active.sum                                                          cycle                      4,508,927
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:22, 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                      12,291.08
    smsp__inst_executed.max                                                           inst                         12,576
    smsp__inst_executed.min                                                           inst                         11,684
    smsp__inst_executed.sum                                                           inst                        786,629
    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                      70,947.14
    smsp__cycles_active.sum                                                          cycle                      4,540,617
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:23, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.01
    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                      12,294.75
    smsp__inst_executed.max                                                           inst                         12,874
    smsp__inst_executed.min                                                           inst                         11,724
    smsp__inst_executed.sum                                                           inst                        786,864
    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                      72,199.77
    smsp__cycles_active.sum                                                          cycle                      4,620,785
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:23, 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                   %                          12.36
    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                      12,301.61
    smsp__inst_executed.max                                                           inst                         12,569
    smsp__inst_executed.min                                                           inst                         12,033
    smsp__inst_executed.sum                                                           inst                        787,303
    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                      71,236.08
    smsp__cycles_active.sum                                                          cycle                      4,559,109
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:23, 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                   %                          12.22
    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                      12,303.88
    smsp__inst_executed.max                                                           inst                         12,532
    smsp__inst_executed.min                                                           inst                         12,088
    smsp__inst_executed.sum                                                           inst                        787,448
    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                      71,734.66
    smsp__cycles_active.sum                                                          cycle                      4,591,018
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:23, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         184.90
    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                                 %                     160,046.97
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,600.47
    smsp__inst_executed.avg                                                           inst                     131,978.41
    smsp__inst_executed.max                                                           inst                        134,065
    smsp__inst_executed.min                                                           inst                        129,873
    smsp__inst_executed.sum                                                           inst                      8,446,618
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          20.89
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.21
    smsp__cycles_active.avg                                                          cycle                     252,655.50
    smsp__cycles_active.sum                                                          cycle                     16,169,952
    ---------------------------------------------------------------------- --------------- ------------------------------

