==PROF== Connected to process 38875 (/home/hoo2/Work/AUTH/PDS/homework_3/out/v2/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 38875
[38875] bitonicCUDA@127.0.0.1
  void prephase<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         msecond                           1.21
    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                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                       186,368
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                       186,368
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                       186,368
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                     2,981,888
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                   111,970.88
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                      112,151
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                      111,739
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                    1,791,534
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     637,077.10
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       6,370.77
    smsp__inst_executed.avg                                                           inst                   1,030,627.31
    smsp__inst_executed.max                                                           inst                      1,030,849
    smsp__inst_executed.min                                                           inst                      1,030,423
    smsp__inst_executed.sum                                                           inst                     65,960,148
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.38
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                   1,665,720.27
    smsp__cycles_active.sum                                                          cycle                    106,606,097
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.87
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.31
    smsp__inst_executed.max                                                           inst                         12,551
    smsp__inst_executed.min                                                           inst                         12,072
    smsp__inst_executed.sum                                                           inst                        787,796
    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                      72,981.36
    smsp__cycles_active.sum                                                          cycle                      4,670,807
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         230.75
    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                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,677.81
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,960
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,401
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,845
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     116,386.30
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,163.86
    smsp__inst_executed.avg                                                           inst                     189,038.39
    smsp__inst_executed.max                                                           inst                        192,131
    smsp__inst_executed.min                                                           inst                        185,953
    smsp__inst_executed.sum                                                           inst                     12,098,457
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.15
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     315,800.30
    smsp__cycles_active.sum                                                          cycle                     20,211,219
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:22, 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                   %                          12.35
    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                      12,299.28
    smsp__inst_executed.max                                                           inst                         12,618
    smsp__inst_executed.min                                                           inst                         11,935
    smsp__inst_executed.sum                                                           inst                        787,154
    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                      70,789.86
    smsp__cycles_active.sum                                                          cycle                      4,530,551
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.81
    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                   %                          12.20
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.90
    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                      12,309.86
    smsp__inst_executed.max                                                           inst                         12,524
    smsp__inst_executed.min                                                           inst                         11,866
    smsp__inst_executed.sum                                                           inst                        787,831
    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                      74,000.58
    smsp__cycles_active.sum                                                          cycle                      4,736,037
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:22, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         227.78
    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                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,678.44
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,985
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,420
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,855
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     116,807.09
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,168.07
    smsp__inst_executed.avg                                                           inst                     189,034.89
    smsp__inst_executed.max                                                           inst                        191,946
    smsp__inst_executed.min                                                           inst                        186,150
    smsp__inst_executed.sum                                                           inst                     12,098,233
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.15
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     316,724.77
    smsp__cycles_active.sum                                                          cycle                     20,270,385
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:22, 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                   %                          12.42
    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                      12,292.47
    smsp__inst_executed.max                                                           inst                         12,744
    smsp__inst_executed.min                                                           inst                         12,048
    smsp__inst_executed.sum                                                           inst                        786,718
    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                      70,511.59
    smsp__cycles_active.sum                                                          cycle                      4,512,742
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, 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                   %                          12.35
    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                      12,298.75
    smsp__inst_executed.max                                                           inst                         12,734
    smsp__inst_executed.min                                                           inst                         11,912
    smsp__inst_executed.sum                                                           inst                        787,120
    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                      71,007.67
    smsp__cycles_active.sum                                                          cycle                      4,544,491
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, 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                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.34
    smsp__inst_executed.max                                                           inst                         12,774
    smsp__inst_executed.min                                                           inst                         11,741
    smsp__inst_executed.sum                                                           inst                        787,798
    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                      73,984.34
    smsp__cycles_active.sum                                                          cycle                      4,734,998
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         228.67
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,686.81
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       20,018
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,390
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,989
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     117,091.55
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,170.92
    smsp__inst_executed.avg                                                           inst                     189,041.44
    smsp__inst_executed.max                                                           inst                        191,914
    smsp__inst_executed.min                                                           inst                        186,023
    smsp__inst_executed.sum                                                           inst                     12,098,652
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.19
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     316,433.83
    smsp__cycles_active.sum                                                          cycle                     20,251,765
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, 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                   %                          12.46
    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                      12,290.77
    smsp__inst_executed.max                                                           inst                         12,524
    smsp__inst_executed.min                                                           inst                         12,028
    smsp__inst_executed.sum                                                           inst                        786,609
    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                      71,664.83
    smsp__cycles_active.sum                                                          cycle                      4,586,549
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, 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                   %                          12.43
    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                      12,292.66
    smsp__inst_executed.max                                                           inst                         12,890
    smsp__inst_executed.min                                                           inst                         11,524
    smsp__inst_executed.sum                                                           inst                        786,730
    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                      71,510.14
    smsp__cycles_active.sum                                                          cycle                      4,576,649
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, 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                   %                          12.37
    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                      12,298.09
    smsp__inst_executed.max                                                           inst                         12,729
    smsp__inst_executed.min                                                           inst                         11,878
    smsp__inst_executed.sum                                                           inst                        787,078
    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                      70,087.36
    smsp__cycles_active.sum                                                          cycle                      4,485,591
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.65
    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                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,308.77
    smsp__inst_executed.max                                                           inst                         12,772
    smsp__inst_executed.min                                                           inst                         11,917
    smsp__inst_executed.sum                                                           inst                        787,761
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,945.83
    smsp__cycles_active.sum                                                          cycle                      4,668,533
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         231.20
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,679.50
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,958
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,366
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,872
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     117,303.63
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,173.04
    smsp__inst_executed.avg                                                           inst                     189,034.44
    smsp__inst_executed.max                                                           inst                        192,047
    smsp__inst_executed.min                                                           inst                        186,006
    smsp__inst_executed.sum                                                           inst                     12,098,204
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.29
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     314,652.92
    smsp__cycles_active.sum                                                          cycle                     20,137,787
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.24
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.17
    smsp__inst_executed.max                                                           inst                         12,704
    smsp__inst_executed.min                                                           inst                         11,772
    smsp__inst_executed.sum                                                           inst                        786,507
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,558.91
    smsp__cycles_active.sum                                                          cycle                      4,515,770
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, 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                      12,290.81
    smsp__inst_executed.max                                                           inst                         12,711
    smsp__inst_executed.min                                                           inst                         11,886
    smsp__inst_executed.sum                                                           inst                        786,612
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,430.86
    smsp__cycles_active.sum                                                          cycle                      4,571,575
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:23, 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                      12,293.34
    smsp__inst_executed.max                                                           inst                         12,505
    smsp__inst_executed.min                                                           inst                         11,800
    smsp__inst_executed.sum                                                           inst                        786,774
    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                      71,942.39
    smsp__cycles_active.sum                                                          cycle                      4,604,313
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, 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                   %                          12.36
    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                      12,298.81
    smsp__inst_executed.max                                                           inst                         12,649
    smsp__inst_executed.min                                                           inst                         12,114
    smsp__inst_executed.sum                                                           inst                        787,124
    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                      71,234.89
    smsp__cycles_active.sum                                                          cycle                      4,559,033
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.39
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,308.92
    smsp__inst_executed.max                                                           inst                         12,739
    smsp__inst_executed.min                                                           inst                         11,660
    smsp__inst_executed.sum                                                           inst                        787,771
    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                      73,053.95
    smsp__cycles_active.sum                                                          cycle                      4,675,453
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         228.06
    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                   %                          12.50
    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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,672.12
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       20,021
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,352
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,754
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     116,983.48
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,169.83
    smsp__inst_executed.avg                                                           inst                     189,031.84
    smsp__inst_executed.max                                                           inst                        192,116
    smsp__inst_executed.min                                                           inst                        185,910
    smsp__inst_executed.sum                                                           inst                     12,098,038
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.18
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     316,447.16
    smsp__cycles_active.sum                                                          cycle                     20,252,618
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.10
    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                      12,288.73
    smsp__inst_executed.max                                                           inst                         12,512
    smsp__inst_executed.min                                                           inst                         12,088
    smsp__inst_executed.sum                                                           inst                        786,479
    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                      74,125.95
    smsp__cycles_active.sum                                                          cycle                      4,744,061
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, 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                      12,289.52
    smsp__inst_executed.max                                                           inst                         12,659
    smsp__inst_executed.min                                                           inst                         12,064
    smsp__inst_executed.sum                                                           inst                        786,529
    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                      71,326.66
    smsp__cycles_active.sum                                                          cycle                      4,564,906
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, 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                   %                          12.47
    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                      12,290.06
    smsp__inst_executed.max                                                           inst                         12,821
    smsp__inst_executed.min                                                           inst                         11,676
    smsp__inst_executed.sum                                                           inst                        786,564
    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                      71,406.72
    smsp__cycles_active.sum                                                          cycle                      4,570,030
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.50
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.97
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,293.75
    smsp__inst_executed.max                                                           inst                         12,525
    smsp__inst_executed.min                                                           inst                         11,886
    smsp__inst_executed.sum                                                           inst                        786,800
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,203.08
    smsp__cycles_active.sum                                                          cycle                      4,620,997
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, 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                   %                          12.37
    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                      12,298.52
    smsp__inst_executed.max                                                           inst                         12,534
    smsp__inst_executed.min                                                           inst                         12,060
    smsp__inst_executed.sum                                                           inst                        787,105
    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                      70,465.11
    smsp__cycles_active.sum                                                          cycle                      4,509,767
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.39
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    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                      12,309.41
    smsp__inst_executed.max                                                           inst                         12,967
    smsp__inst_executed.min                                                           inst                         11,668
    smsp__inst_executed.sum                                                           inst                        787,802
    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                      73,798.33
    smsp__cycles_active.sum                                                          cycle                      4,723,093
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:24, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         228.83
    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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,669.75
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,971
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,352
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,716
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     118,094.62
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,180.95
    smsp__inst_executed.avg                                                           inst                     189,037.22
    smsp__inst_executed.max                                                           inst                        192,039
    smsp__inst_executed.min                                                           inst                        186,030
    smsp__inst_executed.sum                                                           inst                     12,098,382
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.36
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     315,017.08
    smsp__cycles_active.sum                                                          cycle                     20,161,093
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.72
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    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                      12,288.30
    smsp__inst_executed.max                                                           inst                         12,664
    smsp__inst_executed.min                                                           inst                         11,904
    smsp__inst_executed.sum                                                           inst                        786,451
    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                      72,385.16
    smsp__cycles_active.sum                                                          cycle                      4,632,650
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.03
    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                      12,288.97
    smsp__inst_executed.max                                                           inst                         12,828
    smsp__inst_executed.min                                                           inst                         11,696
    smsp__inst_executed.sum                                                           inst                        786,494
    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                      74,209.61
    smsp__cycles_active.sum                                                          cycle                      4,749,415
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, 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                   %                          12.48
    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                      12,289.61
    smsp__inst_executed.max                                                           inst                         12,704
    smsp__inst_executed.min                                                           inst                         11,952
    smsp__inst_executed.sum                                                           inst                        786,535
    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                      71,674.52
    smsp__cycles_active.sum                                                          cycle                      4,587,169
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, 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                   %                          12.46
    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                      12,291.02
    smsp__inst_executed.max                                                           inst                         12,520
    smsp__inst_executed.min                                                           inst                         12,108
    smsp__inst_executed.sum                                                           inst                        786,625
    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                      71,742.84
    smsp__cycles_active.sum                                                          cycle                      4,591,542
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, 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                      12,293.81
    smsp__inst_executed.max                                                           inst                         12,676
    smsp__inst_executed.min                                                           inst                         12,021
    smsp__inst_executed.sum                                                           inst                        786,804
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                         71,224
    smsp__cycles_active.sum                                                          cycle                      4,558,336
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, 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                   %                          12.36
    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                      12,298.45
    smsp__inst_executed.max                                                           inst                         12,492
    smsp__inst_executed.min                                                           inst                         11,896
    smsp__inst_executed.sum                                                           inst                        787,101
    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                      71,438.62
    smsp__cycles_active.sum                                                          cycle                      4,572,072
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, 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                   %                          12.22
    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                      12,309.52
    smsp__inst_executed.max                                                           inst                         12,762
    smsp__inst_executed.min                                                           inst                         11,951
    smsp__inst_executed.sum                                                           inst                        787,809
    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                      73,469.19
    smsp__cycles_active.sum                                                          cycle                      4,702,028
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                            228
    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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,690.44
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,977
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,373
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      315,047
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     116,796.43
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,167.96
    smsp__inst_executed.avg                                                           inst                     189,032.39
    smsp__inst_executed.max                                                           inst                        192,016
    smsp__inst_executed.min                                                           inst                        186,010
    smsp__inst_executed.sum                                                           inst                     12,098,073
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.20
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     315,448.41
    smsp__cycles_active.sum                                                          cycle                     20,188,698
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, 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                   %                          12.50
    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                      12,288.34
    smsp__inst_executed.max                                                           inst                         12,672
    smsp__inst_executed.min                                                           inst                         12,084
    smsp__inst_executed.sum                                                           inst                        786,454
    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                      72,637.31
    smsp__cycles_active.sum                                                          cycle                      4,648,788
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:25, 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                   %                          12.49
    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                      12,288.91
    smsp__inst_executed.max                                                           inst                         12,665
    smsp__inst_executed.min                                                           inst                         11,904
    smsp__inst_executed.sum                                                           inst                        786,490
    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                      72,738.33
    smsp__cycles_active.sum                                                          cycle                      4,655,253
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.22
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.70
    smsp__inst_executed.max                                                           inst                         12,664
    smsp__inst_executed.min                                                           inst                         11,496
    smsp__inst_executed.sum                                                           inst                        786,541
    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                      74,202.39
    smsp__cycles_active.sum                                                          cycle                      4,748,953
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.30
    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                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.03
    smsp__inst_executed.max                                                           inst                         12,656
    smsp__inst_executed.min                                                           inst                         11,886
    smsp__inst_executed.sum                                                           inst                        786,498
    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                         71,574
    smsp__cycles_active.sum                                                          cycle                      4,580,736
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.30
    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                   %                          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                      12,290.56
    smsp__inst_executed.max                                                           inst                         12,493
    smsp__inst_executed.min                                                           inst                         12,052
    smsp__inst_executed.sum                                                           inst                        786,596
    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                      71,559.62
    smsp__cycles_active.sum                                                          cycle                      4,579,816
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, 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                   %                          12.43
    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                         12,558
    smsp__inst_executed.min                                                           inst                         12,110
    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                      71,728.27
    smsp__cycles_active.sum                                                          cycle                      4,590,609
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, 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                   %                          12.36
    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                      12,297.78
    smsp__inst_executed.max                                                           inst                         12,685
    smsp__inst_executed.min                                                           inst                         12,030
    smsp__inst_executed.sum                                                           inst                        787,058
    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                      71,361.31
    smsp__cycles_active.sum                                                          cycle                      4,567,124
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.58
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,308.97
    smsp__inst_executed.max                                                           inst                         12,728
    smsp__inst_executed.min                                                           inst                         12,067
    smsp__inst_executed.sum                                                           inst                        787,774
    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                      73,261.38
    smsp__cycles_active.sum                                                          cycle                      4,688,728
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         228.22
    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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,686.12
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,951
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,409
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,978
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     117,160.55
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,171.61
    smsp__inst_executed.avg                                                           inst                     189,022.41
    smsp__inst_executed.max                                                           inst                        192,049
    smsp__inst_executed.min                                                           inst                        186,033
    smsp__inst_executed.sum                                                           inst                     12,097,434
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.23
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     315,736.44
    smsp__cycles_active.sum                                                          cycle                     20,207,132
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.86
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.12
    smsp__inst_executed.max                                                           inst                         12,680
    smsp__inst_executed.min                                                           inst                         11,716
    smsp__inst_executed.sum                                                           inst                        786,440
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      74,287.59
    smsp__cycles_active.sum                                                          cycle                      4,754,406
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, 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                   %                          12.50
    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                      12,288.20
    smsp__inst_executed.max                                                           inst                         12,672
    smsp__inst_executed.min                                                           inst                         12,092
    smsp__inst_executed.sum                                                           inst                        786,445
    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                      72,712.78
    smsp__cycles_active.sum                                                          cycle                      4,653,618
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:26, 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                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.97
    smsp__inst_executed.max                                                           inst                         12,860
    smsp__inst_executed.min                                                           inst                         12,094
    smsp__inst_executed.sum                                                           inst                        786,430
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,055.23
    smsp__cycles_active.sum                                                          cycle                      4,547,535
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.32
    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                         12,509
    smsp__inst_executed.min                                                           inst                         11,904
    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                      72,694.91
    smsp__cycles_active.sum                                                          cycle                      4,652,474
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.08
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.78
    smsp__inst_executed.max                                                           inst                         12,493
    smsp__inst_executed.min                                                           inst                         12,050
    smsp__inst_executed.sum                                                           inst                        786,546
    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                      70,318.98
    smsp__cycles_active.sum                                                          cycle                      4,500,415
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, 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                   %                          12.46
    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                      12,290.84
    smsp__inst_executed.max                                                           inst                         12,691
    smsp__inst_executed.min                                                           inst                         12,005
    smsp__inst_executed.sum                                                           inst                        786,614
    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                      70,641.02
    smsp__cycles_active.sum                                                          cycle                      4,521,025
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, 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                   %                          12.43
    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                      12,294.64
    smsp__inst_executed.max                                                           inst                         12,527
    smsp__inst_executed.min                                                           inst                         12,057
    smsp__inst_executed.sum                                                           inst                        786,857
    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                         72,218
    smsp__cycles_active.sum                                                          cycle                      4,621,952
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, 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                   %                          12.37
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.96
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,300.36
    smsp__inst_executed.max                                                           inst                         12,681
    smsp__inst_executed.min                                                           inst                         11,918
    smsp__inst_executed.sum                                                           inst                        787,223
    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                      71,114.91
    smsp__cycles_active.sum                                                          cycle                      4,551,354
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.42
    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                      12,315.06
    smsp__inst_executed.max                                                           inst                         12,754
    smsp__inst_executed.min                                                           inst                         11,731
    smsp__inst_executed.sum                                                           inst                        788,164
    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                      73,447.34
    smsp__cycles_active.sum                                                          cycle                      4,700,630
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         231.01
    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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,667.44
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,990
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,305
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,679
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     118,065.21
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,180.65
    smsp__inst_executed.avg                                                           inst                     189,024.22
    smsp__inst_executed.max                                                           inst                        192,046
    smsp__inst_executed.min                                                           inst                        186,039
    smsp__inst_executed.sum                                                           inst                     12,097,550
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.35
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     315,105.62
    smsp__cycles_active.sum                                                          cycle                     20,166,760
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          56.86
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.06
    smsp__inst_executed.max                                                           inst                         12,680
    smsp__inst_executed.min                                                           inst                         11,896
    smsp__inst_executed.sum                                                           inst                        786,436
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      69,539.08
    smsp__cycles_active.sum                                                          cycle                      4,450,501
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.74
    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                   %                          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                      12,288.19
    smsp__inst_executed.max                                                           inst                         12,488
    smsp__inst_executed.min                                                           inst                         11,700
    smsp__inst_executed.sum                                                           inst                        786,444
    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                      75,362.86
    smsp__cycles_active.sum                                                          cycle                      4,823,223
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, 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                   %                          12.50
    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                      12,288.42
    smsp__inst_executed.max                                                           inst                         12,668
    smsp__inst_executed.min                                                           inst                         11,916
    smsp__inst_executed.sum                                                           inst                        786,459
    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                      72,588.78
    smsp__cycles_active.sum                                                          cycle                      4,645,682
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:27, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.92
    smsp__inst_executed.max                                                           inst                         12,489
    smsp__inst_executed.min                                                           inst                         11,942
    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                      72,949.64
    smsp__cycles_active.sum                                                          cycle                      4,668,777
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.97
    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                      12,288.47
    smsp__inst_executed.max                                                           inst                         12,707
    smsp__inst_executed.min                                                           inst                         11,904
    smsp__inst_executed.sum                                                           inst                        786,462
    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                      74,444.11
    smsp__cycles_active.sum                                                          cycle                      4,764,423
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:28, 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                   %                          12.48
    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                      12,289.03
    smsp__inst_executed.max                                                           inst                         12,510
    smsp__inst_executed.min                                                           inst                         11,724
    smsp__inst_executed.sum                                                           inst                        786,498
    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                      70,381.17
    smsp__cycles_active.sum                                                          cycle                      4,504,395
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:28, 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                   %                          12.46
    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                      12,290.17
    smsp__inst_executed.max                                                           inst                         12,557
    smsp__inst_executed.min                                                           inst                         12,092
    smsp__inst_executed.sum                                                           inst                        786,571
    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                      70,414.30
    smsp__cycles_active.sum                                                          cycle                      4,506,515
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.24
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.43
    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                         12,927
    smsp__inst_executed.min                                                           inst                         11,694
    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                      70,712.52
    smsp__cycles_active.sum                                                          cycle                      4,525,601
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:28, 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                   %                          12.36
    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                      12,298.02
    smsp__inst_executed.max                                                           inst                         12,742
    smsp__inst_executed.min                                                           inst                         11,876
    smsp__inst_executed.sum                                                           inst                        787,073
    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                      70,394.77
    smsp__cycles_active.sum                                                          cycle                      4,505,265
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.39
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.23
    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                      12,308.81
    smsp__inst_executed.max                                                           inst                         12,825
    smsp__inst_executed.min                                                           inst                         11,716
    smsp__inst_executed.sum                                                           inst                        787,764
    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                      72,582.98
    smsp__cycles_active.sum                                                          cycle                      4,645,311
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 16:07:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         227.52
    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                   %                          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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,692.19
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       20,059
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,488
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      315,075
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     118,035.67
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,180.36
    smsp__inst_executed.avg                                                           inst                     188,792.84
    smsp__inst_executed.max                                                           inst                        191,758
    smsp__inst_executed.min                                                           inst                        185,797
    smsp__inst_executed.sum                                                           inst                     12,082,742
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.34
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.12
    smsp__cycles_active.avg                                                          cycle                     315,152.44
    smsp__cycles_active.sum                                                          cycle                     20,169,756
    ---------------------------------------------------------------------- --------------- ------------------------------

