==PROF== Connected to process 97867 (/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 97867
[97867] bitonicCUDA@127.0.0.1
  void prephase<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:25, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         msecond                           2.74
    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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                    424,497.75
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                       424,572
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                       424,430
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                     6,791,964
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                   307,967.38
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                      308,221
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                      307,721
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                    4,927,478
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                   1,710,758.26
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                      17,107.58
    smsp__inst_executed.avg                                                           inst                   2,094,137.72
    smsp__inst_executed.max                                                           inst                      2,094,574
    smsp__inst_executed.min                                                           inst                      2,093,816
    smsp__inst_executed.sum                                                           inst                    134,024,814
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          14.50
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.14
    smsp__cycles_active.avg                                                          cycle                   3,809,017.45
    smsp__cycles_active.sum                                                          cycle                    243,777,117
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:25, 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                   %                          12.40
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                      13,098.91
    smsp__inst_executed.max                                                           inst                         13,825
    smsp__inst_executed.min                                                           inst                         12,525
    smsp__inst_executed.sum                                                           inst                        838,330
    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                      73,635.02
    smsp__cycles_active.sum                                                          cycle                      4,712,641
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:25, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         262.30
    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                   %                          12.50
    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                                                     50,043.25
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        50,838
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,216
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,692
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    28,255.12
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       28,790
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,720
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,082
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     146,705.07
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,467.05
    smsp__inst_executed.avg                                                           inst                     201,993.16
    smsp__inst_executed.max                                                           inst                        205,329
    smsp__inst_executed.min                                                           inst                        198,680
    smsp__inst_executed.sum                                                           inst                     12,927,562
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.43
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     359,188.83
    smsp__cycles_active.sum                                                          cycle                     22,988,085
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:25, 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                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    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                      13,076.97
    smsp__inst_executed.max                                                           inst                         13,642
    smsp__inst_executed.min                                                           inst                         12,644
    smsp__inst_executed.sum                                                           inst                        836,926
    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                      70,829.16
    smsp__cycles_active.sum                                                          cycle                      4,533,066
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:25, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.90
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.41
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                      13,098.47
    smsp__inst_executed.max                                                           inst                         13,695
    smsp__inst_executed.min                                                           inst                         12,514
    smsp__inst_executed.sum                                                           inst                        838,302
    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                      73,821.30
    smsp__cycles_active.sum                                                          cycle                      4,724,563
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         261.92
    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                   %                          12.50
    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                                                     50,031.25
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        50,842
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,220
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,500
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    28,252.81
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       28,772
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,700
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,045
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     146,886.83
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,468.87
    smsp__inst_executed.avg                                                           inst                     201,980.12
    smsp__inst_executed.max                                                           inst                        205,383
    smsp__inst_executed.min                                                           inst                        198,773
    smsp__inst_executed.sum                                                           inst                     12,926,728
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.42
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     359,825.25
    smsp__cycles_active.sum                                                          cycle                     23,028,816
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, 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                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    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                      13,066.20
    smsp__inst_executed.max                                                           inst                         13,614
    smsp__inst_executed.min                                                           inst                         12,528
    smsp__inst_executed.sum                                                           inst                        836,237
    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                      71,445.25
    smsp__cycles_active.sum                                                          cycle                      4,572,496
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, 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                   %                          12.45
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.98
    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                      13,078.12
    smsp__inst_executed.max                                                           inst                         13,392
    smsp__inst_executed.min                                                           inst                         12,753
    smsp__inst_executed.sum                                                           inst                        837,000
    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                      70,808.16
    smsp__cycles_active.sum                                                          cycle                      4,531,722
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.84
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.41
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                      13,100.52
    smsp__inst_executed.max                                                           inst                         13,544
    smsp__inst_executed.min                                                           inst                         12,412
    smsp__inst_executed.sum                                                           inst                        838,433
    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                      73,285.58
    smsp__cycles_active.sum                                                          cycle                      4,690,277
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         262.56
    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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                     50,043.50
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        50,864
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,218
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,696
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    28,272.62
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       28,842
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,682
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,362
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     146,681.13
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,466.81
    smsp__inst_executed.avg                                                           inst                     201,994.86
    smsp__inst_executed.max                                                           inst                        205,278
    smsp__inst_executed.min                                                           inst                        198,784
    smsp__inst_executed.sum                                                           inst                     12,927,671
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.42
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     359,214.95
    smsp__cycles_active.sum                                                          cycle                     22,989,757
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,062.50
    smsp__inst_executed.max                                                           inst                         13,331
    smsp__inst_executed.min                                                           inst                         12,768
    smsp__inst_executed.sum                                                           inst                        836,000
    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                      70,902.33
    smsp__cycles_active.sum                                                          cycle                      4,537,749
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, 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                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    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                      13,065.06
    smsp__inst_executed.max                                                           inst                         13,572
    smsp__inst_executed.min                                                           inst                         12,398
    smsp__inst_executed.sum                                                           inst                        836,164
    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                      70,989.39
    smsp__cycles_active.sum                                                          cycle                      4,543,321
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, 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                   %                          12.45
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.98
    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                      13,078.56
    smsp__inst_executed.max                                                           inst                         13,535
    smsp__inst_executed.min                                                           inst                         12,643
    smsp__inst_executed.sum                                                           inst                        837,028
    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                         70,968
    smsp__cycles_active.sum                                                          cycle                      4,541,952
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, 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                   %                          12.40
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                      13,101.59
    smsp__inst_executed.max                                                           inst                         13,450
    smsp__inst_executed.min                                                           inst                         12,686
    smsp__inst_executed.sum                                                           inst                        838,502
    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                      73,303.42
    smsp__cycles_active.sum                                                          cycle                      4,691,419
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:26, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         262.02
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    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                                                     50,043.62
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        50,844
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,240
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,698
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    28,261.31
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       28,739
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,770
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,181
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     146,341.85
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,463.42
    smsp__inst_executed.avg                                                           inst                     201,989.12
    smsp__inst_executed.max                                                           inst                        205,318
    smsp__inst_executed.min                                                           inst                        198,758
    smsp__inst_executed.sum                                                           inst                     12,927,304
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.44
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     357,843.03
    smsp__cycles_active.sum                                                          cycle                     22,901,954
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,058.53
    smsp__inst_executed.max                                                           inst                         13,526
    smsp__inst_executed.min                                                           inst                         12,306
    smsp__inst_executed.sum                                                           inst                        835,746
    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                      71,787.86
    smsp__cycles_active.sum                                                          cycle                      4,594,423
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,059.02
    smsp__inst_executed.max                                                           inst                         13,478
    smsp__inst_executed.min                                                           inst                         12,830
    smsp__inst_executed.sum                                                           inst                        835,777
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,028.17
    smsp__cycles_active.sum                                                          cycle                      4,545,803
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, 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                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.44
    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                      13,065.78
    smsp__inst_executed.max                                                           inst                         13,438
    smsp__inst_executed.min                                                           inst                         12,574
    smsp__inst_executed.sum                                                           inst                        836,210
    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                      70,904.80
    smsp__cycles_active.sum                                                          cycle                      4,537,907
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, 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                   %                          12.45
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.98
    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                      13,078.08
    smsp__inst_executed.max                                                           inst                         13,449
    smsp__inst_executed.min                                                           inst                         12,852
    smsp__inst_executed.sum                                                           inst                        836,997
    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                      70,550.70
    smsp__cycles_active.sum                                                          cycle                      4,515,245
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, 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                   %                          12.40
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                      13,101.52
    smsp__inst_executed.max                                                           inst                         13,598
    smsp__inst_executed.min                                                           inst                         12,493
    smsp__inst_executed.sum                                                           inst                        838,497
    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                      73,532.58
    smsp__cycles_active.sum                                                          cycle                      4,706,085
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         262.91
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                     50,053.50
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        50,874
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,224
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,856
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                       28,271
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       28,836
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,727
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,336
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     146,501.01
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,465.01
    smsp__inst_executed.avg                                                           inst                     202,004.09
    smsp__inst_executed.max                                                           inst                        205,252
    smsp__inst_executed.min                                                           inst                        198,682
    smsp__inst_executed.sum                                                           inst                     12,928,262
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.39
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     359,682.91
    smsp__cycles_active.sum                                                          cycle                     23,019,706
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.35
    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                           4.00
    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                      13,057.83
    smsp__inst_executed.max                                                           inst                         13,496
    smsp__inst_executed.min                                                           inst                         12,644
    smsp__inst_executed.sum                                                           inst                        835,701
    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                      73,331.45
    smsp__cycles_active.sum                                                          cycle                      4,693,213
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.40
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      13,059.84
    smsp__inst_executed.max                                                           inst                         13,458
    smsp__inst_executed.min                                                           inst                         12,796
    smsp__inst_executed.sum                                                           inst                        835,830
    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                      70,956.33
    smsp__cycles_active.sum                                                          cycle                      4,541,205
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,061.11
    smsp__inst_executed.max                                                           inst                         13,295
    smsp__inst_executed.min                                                           inst                         12,718
    smsp__inst_executed.sum                                                           inst                        835,911
    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                      70,879.30
    smsp__cycles_active.sum                                                          cycle                      4,536,275
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, 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                   %                          12.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    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                      13,069.02
    smsp__inst_executed.max                                                           inst                         13,573
    smsp__inst_executed.min                                                           inst                         12,724
    smsp__inst_executed.sum                                                           inst                        836,417
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,109.20
    smsp__cycles_active.sum                                                          cycle                      4,550,989
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:27, 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                   %                          12.45
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.98
    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                      13,077.70
    smsp__inst_executed.max                                                           inst                         13,477
    smsp__inst_executed.min                                                           inst                         12,610
    smsp__inst_executed.sum                                                           inst                        836,973
    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                      70,790.67
    smsp__cycles_active.sum                                                          cycle                      4,530,603
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                             60
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.40
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                      13,100.05
    smsp__inst_executed.max                                                           inst                         13,648
    smsp__inst_executed.min                                                           inst                         12,388
    smsp__inst_executed.sum                                                           inst                        838,403
    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                      73,601.83
    smsp__cycles_active.sum                                                          cycle                      4,710,517
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         262.14
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                     50,043.62
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        50,840
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,234
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,698
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    28,256.06
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       28,782
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,767
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,097
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     146,621.11
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,466.21
    smsp__inst_executed.avg                                                           inst                     201,979.69
    smsp__inst_executed.max                                                           inst                        205,239
    smsp__inst_executed.min                                                           inst                        198,743
    smsp__inst_executed.sum                                                           inst                     12,926,700
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.42
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                        359,167
    smsp__cycles_active.sum                                                          cycle                     22,986,688
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, 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                           4.00
    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                      13,054.70
    smsp__inst_executed.max                                                           inst                         13,370
    smsp__inst_executed.min                                                           inst                         12,868
    smsp__inst_executed.sum                                                           inst                        835,501
    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                         72,049
    smsp__cycles_active.sum                                                          cycle                      4,611,136
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.06
    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                           4.00
    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                      13,056.12
    smsp__inst_executed.max                                                           inst                         13,659
    smsp__inst_executed.min                                                           inst                         12,536
    smsp__inst_executed.sum                                                           inst                        835,592
    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                      73,524.42
    smsp__cycles_active.sum                                                          cycle                      4,705,563
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,057.20
    smsp__inst_executed.max                                                           inst                         13,566
    smsp__inst_executed.min                                                           inst                         12,672
    smsp__inst_executed.sum                                                           inst                        835,661
    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                      70,965.64
    smsp__cycles_active.sum                                                          cycle                      4,541,801
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,061.50
    smsp__inst_executed.max                                                           inst                         13,438
    smsp__inst_executed.min                                                           inst                         12,632
    smsp__inst_executed.sum                                                           inst                        835,936
    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                      71,155.02
    smsp__cycles_active.sum                                                          cycle                      4,553,921
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, 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                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    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                      13,068.72
    smsp__inst_executed.max                                                           inst                         13,420
    smsp__inst_executed.min                                                           inst                         12,724
    smsp__inst_executed.sum                                                           inst                        836,398
    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                      71,460.50
    smsp__cycles_active.sum                                                          cycle                      4,573,472
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, 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                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    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                      13,078.17
    smsp__inst_executed.max                                                           inst                         13,504
    smsp__inst_executed.min                                                           inst                         12,664
    smsp__inst_executed.sum                                                           inst                        837,003
    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                      71,057.59
    smsp__cycles_active.sum                                                          cycle                      4,547,686
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.49
    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                   %                          12.41
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                           3.92
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      13,098.28
    smsp__inst_executed.max                                                           inst                         13,569
    smsp__inst_executed.min                                                           inst                         12,427
    smsp__inst_executed.sum                                                           inst                        838,290
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,038.50
    smsp__cycles_active.sum                                                          cycle                      4,674,464
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         261.92
    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                   %                          12.50
    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                                                     50,049.25
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        50,926
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,284
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,788
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    28,288.69
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       28,900
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,826
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,619
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     147,924.16
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,479.24
    smsp__inst_executed.avg                                                           inst                     202,010.41
    smsp__inst_executed.max                                                           inst                        205,310
    smsp__inst_executed.min                                                           inst                        198,801
    smsp__inst_executed.sum                                                           inst                     12,928,666
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.53
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.14
    smsp__cycles_active.avg                                                          cycle                     359,403.17
    smsp__cycles_active.sum                                                          cycle                     23,001,803
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:28, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.88
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,056.27
    smsp__inst_executed.max                                                           inst                         13,430
    smsp__inst_executed.min                                                           inst                         12,688
    smsp__inst_executed.sum                                                           inst                        835,601
    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                      72,117.38
    smsp__cycles_active.sum                                                          cycle                      4,615,512
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.10
    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                           4.00
    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                      13,057.19
    smsp__inst_executed.max                                                           inst                         13,468
    smsp__inst_executed.min                                                           inst                         12,648
    smsp__inst_executed.sum                                                           inst                        835,660
    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                      71,818.41
    smsp__cycles_active.sum                                                          cycle                      4,596,378
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, 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                           4.00
    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                      13,056.58
    smsp__inst_executed.max                                                           inst                         13,392
    smsp__inst_executed.min                                                           inst                         12,796
    smsp__inst_executed.sum                                                           inst                        835,621
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,603.70
    smsp__cycles_active.sum                                                          cycle                      4,710,637
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.69
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,060.06
    smsp__inst_executed.max                                                           inst                         13,759
    smsp__inst_executed.min                                                           inst                         12,626
    smsp__inst_executed.sum                                                           inst                        835,844
    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                      71,422.75
    smsp__cycles_active.sum                                                          cycle                      4,571,056
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,061.48
    smsp__inst_executed.max                                                           inst                         13,504
    smsp__inst_executed.min                                                           inst                         12,727
    smsp__inst_executed.sum                                                           inst                        835,935
    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                      71,423.25
    smsp__cycles_active.sum                                                          cycle                      4,571,088
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.40
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    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                      13,065.03
    smsp__inst_executed.max                                                           inst                         13,452
    smsp__inst_executed.min                                                           inst                         12,618
    smsp__inst_executed.sum                                                           inst                        836,162
    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                      70,757.98
    smsp__cycles_active.sum                                                          cycle                      4,528,511
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, 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                   %                          12.45
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.98
    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                      13,077.34
    smsp__inst_executed.max                                                           inst                         13,374
    smsp__inst_executed.min                                                           inst                         12,676
    smsp__inst_executed.sum                                                           inst                        836,950
    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                      71,080.64
    smsp__cycles_active.sum                                                          cycle                      4,549,161
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, 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                   %                          12.40
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                      13,098.39
    smsp__inst_executed.max                                                           inst                         13,471
    smsp__inst_executed.min                                                           inst                         12,696
    smsp__inst_executed.sum                                                           inst                        838,297
    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                      73,613.73
    smsp__cycles_active.sum                                                          cycle                      4,711,279
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         262.14
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        50,044
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        50,924
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,230
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,704
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    28,279.81
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       28,930
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,741
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,477
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     147,875.18
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,478.75
    smsp__inst_executed.avg                                                           inst                     201,980.91
    smsp__inst_executed.max                                                           inst                        205,280
    smsp__inst_executed.min                                                           inst                        198,678
    smsp__inst_executed.sum                                                           inst                     12,926,778
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.53
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.14
    smsp__cycles_active.avg                                                          cycle                     359,333.61
    smsp__cycles_active.sum                                                          cycle                     22,997,351
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.90
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,054.95
    smsp__inst_executed.max                                                           inst                         13,496
    smsp__inst_executed.min                                                           inst                         12,616
    smsp__inst_executed.sum                                                           inst                        835,517
    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                      74,933.08
    smsp__cycles_active.sum                                                          cycle                      4,795,717
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:29, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.10
    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                           4.00
    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                      13,057.78
    smsp__inst_executed.max                                                           inst                         13,340
    smsp__inst_executed.min                                                           inst                         12,836
    smsp__inst_executed.sum                                                           inst                        835,698
    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                      72,251.72
    smsp__cycles_active.sum                                                          cycle                      4,624,110
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.10
    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                           4.00
    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                      13,057.56
    smsp__inst_executed.max                                                           inst                         13,451
    smsp__inst_executed.min                                                           inst                         12,476
    smsp__inst_executed.sum                                                           inst                        835,684
    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                      71,830.58
    smsp__cycles_active.sum                                                          cycle                      4,597,157
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.35
    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                           4.00
    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                      13,056.78
    smsp__inst_executed.max                                                           inst                         13,655
    smsp__inst_executed.min                                                           inst                         12,680
    smsp__inst_executed.sum                                                           inst                        835,634
    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                      73,102.31
    smsp__cycles_active.sum                                                          cycle                      4,678,548
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.82
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,058.23
    smsp__inst_executed.max                                                           inst                         13,683
    smsp__inst_executed.min                                                           inst                         12,462
    smsp__inst_executed.sum                                                           inst                        835,727
    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                      71,104.28
    smsp__cycles_active.sum                                                          cycle                      4,550,674
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,061.97
    smsp__inst_executed.max                                                           inst                         13,440
    smsp__inst_executed.min                                                           inst                         12,672
    smsp__inst_executed.sum                                                           inst                        835,966
    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                      71,301.42
    smsp__cycles_active.sum                                                          cycle                      4,563,291
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, 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                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.44
    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                      13,066.27
    smsp__inst_executed.max                                                           inst                         13,392
    smsp__inst_executed.min                                                           inst                         12,467
    smsp__inst_executed.sum                                                           inst                        836,241
    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                      71,628.64
    smsp__cycles_active.sum                                                          cycle                      4,584,233
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, 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                   %                          12.45
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.98
    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                      13,080.28
    smsp__inst_executed.max                                                           inst                         13,453
    smsp__inst_executed.min                                                           inst                         12,667
    smsp__inst_executed.sum                                                           inst                        837,138
    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                      71,083.31
    smsp__cycles_active.sum                                                          cycle                      4,549,332
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.71
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.40
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                      13,107.33
    smsp__inst_executed.max                                                           inst                         13,571
    smsp__inst_executed.min                                                           inst                         12,788
    smsp__inst_executed.sum                                                           inst                        838,869
    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                      73,305.81
    smsp__cycles_active.sum                                                          cycle                      4,691,572
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         261.66
    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
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                     50,049.62
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        50,902
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,172
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,794
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    28,273.25
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       28,813
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,665
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,372
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     146,879.79
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,468.80
    smsp__inst_executed.avg                                                           inst                     202,028.11
    smsp__inst_executed.max                                                           inst                        205,339
    smsp__inst_executed.min                                                           inst                        198,670
    smsp__inst_executed.sum                                                           inst                     12,929,799
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.45
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     358,847.58
    smsp__cycles_active.sum                                                          cycle                     22,966,245
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.34
    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                           4.00
    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                      13,055.41
    smsp__inst_executed.max                                                           inst                         13,496
    smsp__inst_executed.min                                                           inst                         12,632
    smsp__inst_executed.sum                                                           inst                        835,546
    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                      69,485.11
    smsp__cycles_active.sum                                                          cycle                      4,447,047
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:30, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.83
    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                           4.00
    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                      13,054.95
    smsp__inst_executed.max                                                           inst                         13,280
    smsp__inst_executed.min                                                           inst                         12,644
    smsp__inst_executed.sum                                                           inst                        835,517
    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                      74,500.81
    smsp__cycles_active.sum                                                          cycle                      4,768,052
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:31, 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                           4.00
    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                      13,056.09
    smsp__inst_executed.max                                                           inst                         13,460
    smsp__inst_executed.min                                                           inst                         12,580
    smsp__inst_executed.sum                                                           inst                        835,590
    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                      71,786.02
    smsp__cycles_active.sum                                                          cycle                      4,594,305
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.20
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,056.41
    smsp__inst_executed.max                                                           inst                         13,448
    smsp__inst_executed.min                                                           inst                         12,688
    smsp__inst_executed.sum                                                           inst                        835,610
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,242.58
    smsp__cycles_active.sum                                                          cycle                      4,623,525
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.16
    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                           4.00
    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                      13,056.45
    smsp__inst_executed.max                                                           inst                         13,638
    smsp__inst_executed.min                                                           inst                         12,668
    smsp__inst_executed.sum                                                           inst                        835,613
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,627.94
    smsp__cycles_active.sum                                                          cycle                      4,712,188
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.69
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,060.33
    smsp__inst_executed.max                                                           inst                         13,688
    smsp__inst_executed.min                                                           inst                         12,548
    smsp__inst_executed.sum                                                           inst                        835,861
    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                         71,508
    smsp__cycles_active.sum                                                          cycle                      4,576,512
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:31, 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                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           4.00
    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                      13,058.94
    smsp__inst_executed.max                                                           inst                         13,522
    smsp__inst_executed.min                                                           inst                         12,708
    smsp__inst_executed.sum                                                           inst                        835,772
    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                      71,081.84
    smsp__cycles_active.sum                                                          cycle                      4,549,238
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.69
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.44
    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                      13,069.42
    smsp__inst_executed.max                                                           inst                         13,618
    smsp__inst_executed.min                                                           inst                         12,322
    smsp__inst_executed.sum                                                           inst                        836,443
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,235.78
    smsp__cycles_active.sum                                                          cycle                      4,559,090
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:31, 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                   %                          12.45
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.99
    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                      13,078.45
    smsp__inst_executed.max                                                           inst                         13,414
    smsp__inst_executed.min                                                           inst                         12,640
    smsp__inst_executed.sum                                                           inst                        837,021
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,165.06
    smsp__cycles_active.sum                                                          cycle                      4,554,564
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:31, 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                   %                          12.40
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                           3.97
    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                      13,100.33
    smsp__inst_executed.max                                                           inst                         13,504
    smsp__inst_executed.min                                                           inst                         12,711
    smsp__inst_executed.sum                                                           inst                        838,421
    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                      73,508.81
    smsp__cycles_active.sum                                                          cycle                      4,704,564
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 21:41:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         261.60
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          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                                                     50,050.25
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        51,026
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        49,180
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       800,804
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    28,281.12
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       29,045
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       27,669
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      452,498
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     146,579.33
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,465.79
    smsp__inst_executed.avg                                                           inst                     201,758.88
    smsp__inst_executed.max                                                           inst                        205,041
    smsp__inst_executed.min                                                           inst                        198,447
    smsp__inst_executed.sum                                                           inst                     12,912,568
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.46
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     358,041.27
    smsp__cycles_active.sum                                                          cycle                     22,914,641
    ---------------------------------------------------------------------- --------------- ------------------------------

