==PROF== Connected to process 23012 (/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 23012
[23012] bitonicCUDA@127.0.0.1
  void prephase<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         msecond                           1.20
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                       186,368
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                       186,368
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                       186,368
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                     2,981,888
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                   111,954.62
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                      112,106
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                      111,827
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                    1,791,274
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     644,639.76
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       6,446.40
    smsp__inst_executed.avg                                                           inst                   1,030,883.66
    smsp__inst_executed.max                                                           inst                      1,031,104
    smsp__inst_executed.min                                                           inst                      1,030,650
    smsp__inst_executed.sum                                                           inst                     65,976,554
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.50
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                   1,667,322.50
    smsp__cycles_active.sum                                                          cycle                    106,708,640
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.94
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,308.62
    smsp__inst_executed.max                                                           inst                         12,930
    smsp__inst_executed.min                                                           inst                         12,094
    smsp__inst_executed.sum                                                           inst                        787,752
    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                      73,839.28
    smsp__cycles_active.sum                                                          cycle                      4,725,714
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         231.58
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,673.56
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       20,005
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,385
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,777
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     123,076.57
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,230.77
    smsp__inst_executed.avg                                                           inst                     189,293.97
    smsp__inst_executed.max                                                           inst                        192,369
    smsp__inst_executed.min                                                           inst                        186,352
    smsp__inst_executed.sum                                                           inst                     12,114,814
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.78
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     316,320.25
    smsp__cycles_active.sum                                                          cycle                     20,244,496
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.08
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.77
    smsp__inst_executed.max                                                           inst                         12,539
    smsp__inst_executed.min                                                           inst                         12,060
    smsp__inst_executed.sum                                                           inst                        787,121
    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                      70,962.83
    smsp__cycles_active.sum                                                          cycle                      4,541,621
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:31, 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                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.31
    smsp__inst_executed.max                                                           inst                         12,697
    smsp__inst_executed.min                                                           inst                         11,822
    smsp__inst_executed.sum                                                           inst                        787,796
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,821.19
    smsp__cycles_active.sum                                                          cycle                      4,660,556
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         232.45
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,692.06
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       20,017
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,412
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      315,073
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     124,072.53
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,240.73
    smsp__inst_executed.avg                                                           inst                     189,295.75
    smsp__inst_executed.max                                                           inst                        192,417
    smsp__inst_executed.min                                                           inst                        186,276
    smsp__inst_executed.sum                                                           inst                     12,114,928
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.89
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     316,238.97
    smsp__cycles_active.sum                                                          cycle                     20,239,294
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:31, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.37
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,292.88
    smsp__inst_executed.max                                                           inst                         12,554
    smsp__inst_executed.min                                                           inst                         11,832
    smsp__inst_executed.sum                                                           inst                        786,744
    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                      71,835.05
    smsp__cycles_active.sum                                                          cycle                      4,597,443
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.89
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.73
    smsp__inst_executed.max                                                           inst                         12,788
    smsp__inst_executed.min                                                           inst                         11,840
    smsp__inst_executed.sum                                                           inst                        787,119
    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                      71,345.14
    smsp__cycles_active.sum                                                          cycle                      4,566,089
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, 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                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.23
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,308.28
    smsp__inst_executed.max                                                           inst                         12,596
    smsp__inst_executed.min                                                           inst                         11,926
    smsp__inst_executed.sum                                                           inst                        787,730
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,894.73
    smsp__cycles_active.sum                                                          cycle                      4,729,263
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         229.41
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,675.88
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,994
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,371
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,814
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     124,117.44
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,241.17
    smsp__inst_executed.avg                                                           inst                     189,295.52
    smsp__inst_executed.max                                                           inst                        192,256
    smsp__inst_executed.min                                                           inst                        186,332
    smsp__inst_executed.sum                                                           inst                     12,114,913
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.85
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     317,343.97
    smsp__cycles_active.sum                                                          cycle                     20,310,014
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.11
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.78
    smsp__inst_executed.max                                                           inst                         12,480
    smsp__inst_executed.min                                                           inst                         11,928
    smsp__inst_executed.sum                                                           inst                        786,610
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,846.03
    smsp__cycles_active.sum                                                          cycle                      4,534,146
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.59
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.43
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,293.23
    smsp__inst_executed.max                                                           inst                         12,604
    smsp__inst_executed.min                                                           inst                         11,836
    smsp__inst_executed.sum                                                           inst                        786,767
    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                      71,106.22
    smsp__cycles_active.sum                                                          cycle                      4,550,798
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.11
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.37
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.96
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.36
    smsp__inst_executed.max                                                           inst                         12,513
    smsp__inst_executed.min                                                           inst                         11,712
    smsp__inst_executed.sum                                                           inst                        787,095
    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                      70,202.59
    smsp__cycles_active.sum                                                          cycle                      4,492,966
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.52
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.22
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,308.52
    smsp__inst_executed.max                                                           inst                         12,682
    smsp__inst_executed.min                                                           inst                         11,859
    smsp__inst_executed.sum                                                           inst                        787,745
    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                      73,621.48
    smsp__cycles_active.sum                                                          cycle                      4,711,775
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         229.09
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,686.12
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,974
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,355
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,978
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     124,010.98
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,240.11
    smsp__inst_executed.avg                                                           inst                     189,293.06
    smsp__inst_executed.max                                                           inst                        192,343
    smsp__inst_executed.min                                                           inst                        186,209
    smsp__inst_executed.sum                                                           inst                     12,114,756
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.81
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     317,996.44
    smsp__cycles_active.sum                                                          cycle                     20,351,772
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.02
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.22
    smsp__inst_executed.max                                                           inst                         12,699
    smsp__inst_executed.min                                                           inst                         11,910
    smsp__inst_executed.sum                                                           inst                        786,510
    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                      71,268.28
    smsp__cycles_active.sum                                                          cycle                      4,561,170
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:32, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.24
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.45
    smsp__inst_executed.max                                                           inst                         12,669
    smsp__inst_executed.min                                                           inst                         11,950
    smsp__inst_executed.sum                                                           inst                        786,589
    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                      70,528.27
    smsp__cycles_active.sum                                                          cycle                      4,513,809
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:33, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.50
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.43
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,293.23
    smsp__inst_executed.max                                                           inst                         12,648
    smsp__inst_executed.min                                                           inst                         11,996
    smsp__inst_executed.sum                                                           inst                        786,767
    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                      70,717.06
    smsp__cycles_active.sum                                                          cycle                      4,525,892
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:33, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.02
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.96
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.44
    smsp__inst_executed.max                                                           inst                         12,776
    smsp__inst_executed.min                                                           inst                         11,972
    smsp__inst_executed.sum                                                           inst                        787,100
    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                      70,171.77
    smsp__cycles_active.sum                                                          cycle                      4,490,993
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:33, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.58
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.16
    smsp__inst_executed.max                                                           inst                         12,776
    smsp__inst_executed.min                                                           inst                         12,048
    smsp__inst_executed.sum                                                           inst                        787,786
    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                      73,678.91
    smsp__cycles_active.sum                                                          cycle                      4,715,450
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:33, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         228.96
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,689.06
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       20,011
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,382
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      315,025
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     125,081.44
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,250.81
    smsp__inst_executed.avg                                                           inst                     189,292.86
    smsp__inst_executed.max                                                           inst                        192,415
    smsp__inst_executed.min                                                           inst                        186,212
    smsp__inst_executed.sum                                                           inst                     12,114,743
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.96
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     316,855.81
    smsp__cycles_active.sum                                                          cycle                     20,278,772
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:33, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.97
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.30
    smsp__inst_executed.max                                                           inst                         12,684
    smsp__inst_executed.min                                                           inst                         11,920
    smsp__inst_executed.sum                                                           inst                        786,451
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,684.17
    smsp__cycles_active.sum                                                          cycle                      4,715,787
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:33, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.02
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.70
    smsp__inst_executed.max                                                           inst                         12,656
    smsp__inst_executed.min                                                           inst                         11,904
    smsp__inst_executed.sum                                                           inst                        786,477
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,366.16
    smsp__cycles_active.sum                                                          cycle                      4,567,434
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:33, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.95
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.27
    smsp__inst_executed.max                                                           inst                         12,693
    smsp__inst_executed.min                                                           inst                         12,042
    smsp__inst_executed.sum                                                           inst                        786,577
    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                      70,688.91
    smsp__cycles_active.sum                                                          cycle                      4,524,090
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:33, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.53
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,293.41
    smsp__inst_executed.max                                                           inst                         12,585
    smsp__inst_executed.min                                                           inst                         11,776
    smsp__inst_executed.sum                                                           inst                        786,778
    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                      71,063.67
    smsp__cycles_active.sum                                                          cycle                      4,548,075
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:33, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.46
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.96
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.94
    smsp__inst_executed.max                                                           inst                         12,684
    smsp__inst_executed.min                                                           inst                         11,776
    smsp__inst_executed.sum                                                           inst                        787,132
    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                      71,037.02
    smsp__cycles_active.sum                                                          cycle                      4,546,369
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.74
    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                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.58
    smsp__inst_executed.max                                                           inst                         12,726
    smsp__inst_executed.min                                                           inst                         12,072
    smsp__inst_executed.sum                                                           inst                        787,813
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                         73,656
    smsp__cycles_active.sum                                                          cycle                      4,713,984
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         231.42
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,682.75
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,995
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,336
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,924
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     124,533.56
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,245.34
    smsp__inst_executed.avg                                                           inst                     189,299.56
    smsp__inst_executed.max                                                           inst                        192,317
    smsp__inst_executed.min                                                           inst                        186,295
    smsp__inst_executed.sum                                                           inst                     12,115,172
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.91
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     316,917.50
    smsp__cycles_active.sum                                                          cycle                     20,282,720
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.56
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.72
    smsp__inst_executed.max                                                           inst                         12,664
    smsp__inst_executed.min                                                           inst                         11,916
    smsp__inst_executed.sum                                                           inst                        786,414
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,857.64
    smsp__cycles_active.sum                                                          cycle                      4,598,889
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.97
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.48
    smsp__inst_executed.max                                                           inst                         12,684
    smsp__inst_executed.min                                                           inst                         11,892
    smsp__inst_executed.sum                                                           inst                        786,463
    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                      73,070.30
    smsp__cycles_active.sum                                                          cycle                      4,676,499
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.24
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.53
    smsp__inst_executed.max                                                           inst                         12,851
    smsp__inst_executed.min                                                           inst                         11,908
    smsp__inst_executed.sum                                                           inst                        786,530
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,288.86
    smsp__cycles_active.sum                                                          cycle                      4,498,487
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.92
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.62
    smsp__inst_executed.max                                                           inst                         12,632
    smsp__inst_executed.min                                                           inst                         12,036
    smsp__inst_executed.sum                                                           inst                        786,600
    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                      71,317.92
    smsp__cycles_active.sum                                                          cycle                      4,564,347
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.53
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.43
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,293.17
    smsp__inst_executed.max                                                           inst                         12,673
    smsp__inst_executed.min                                                           inst                         11,880
    smsp__inst_executed.sum                                                           inst                        786,763
    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                      71,760.25
    smsp__cycles_active.sum                                                          cycle                      4,592,656
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.34
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.96
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.23
    smsp__inst_executed.max                                                           inst                         12,716
    smsp__inst_executed.min                                                           inst                         11,876
    smsp__inst_executed.sum                                                           inst                        787,087
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,216.77
    smsp__cycles_active.sum                                                          cycle                      4,557,873
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.39
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.23
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,308.69
    smsp__inst_executed.max                                                           inst                         12,831
    smsp__inst_executed.min                                                           inst                         11,757
    smsp__inst_executed.sum                                                           inst                        787,756
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,196.75
    smsp__cycles_active.sum                                                          cycle                      4,684,592
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         228.77
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,694.50
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,913
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,365
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      315,112
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     123,085.89
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,230.86
    smsp__inst_executed.avg                                                           inst                     189,320.77
    smsp__inst_executed.max                                                           inst                        192,334
    smsp__inst_executed.min                                                           inst                        186,279
    smsp__inst_executed.sum                                                           inst                     12,116,529
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.78
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                        316,332
    smsp__cycles_active.sum                                                          cycle                     20,245,248
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:34, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.72
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.30
    smsp__inst_executed.max                                                           inst                         12,488
    smsp__inst_executed.min                                                           inst                         11,916
    smsp__inst_executed.sum                                                           inst                        786,451
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,574.31
    smsp__cycles_active.sum                                                          cycle                      4,580,756
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.20
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.91
    smsp__inst_executed.max                                                           inst                         12,672
    smsp__inst_executed.min                                                           inst                         11,910
    smsp__inst_executed.sum                                                           inst                        786,490
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,645.88
    smsp__cycles_active.sum                                                          cycle                      4,585,336
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.29
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.03
    smsp__inst_executed.max                                                           inst                         12,492
    smsp__inst_executed.min                                                           inst                         11,892
    smsp__inst_executed.sum                                                           inst                        786,498
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      73,041.34
    smsp__cycles_active.sum                                                          cycle                      4,674,646
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.27
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.23
    smsp__inst_executed.max                                                           inst                         12,678
    smsp__inst_executed.min                                                           inst                         12,066
    smsp__inst_executed.sum                                                           inst                        786,511
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,712.69
    smsp__cycles_active.sum                                                          cycle                      4,525,612
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.21
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.47
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.75
    smsp__inst_executed.max                                                           inst                         12,526
    smsp__inst_executed.min                                                           inst                         12,050
    smsp__inst_executed.sum                                                           inst                        786,544
    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                      71,762.81
    smsp__cycles_active.sum                                                          cycle                      4,592,820
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.59
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,293.14
    smsp__inst_executed.max                                                           inst                         12,740
    smsp__inst_executed.min                                                           inst                         11,704
    smsp__inst_executed.sum                                                           inst                        786,761
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      72,097.56
    smsp__cycles_active.sum                                                          cycle                      4,614,244
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.05
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.39
    smsp__inst_executed.max                                                           inst                         12,695
    smsp__inst_executed.min                                                           inst                         11,854
    smsp__inst_executed.sum                                                           inst                        787,097
    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                      70,856.70
    smsp__cycles_active.sum                                                          cycle                      4,534,829
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.30
    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                   %                          12.20
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.80
    smsp__inst_executed.max                                                           inst                         12,711
    smsp__inst_executed.min                                                           inst                         11,932
    smsp__inst_executed.sum                                                           inst                        787,827
    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                      72,244.53
    smsp__cycles_active.sum                                                          cycle                      4,623,650
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         228.90
    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
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,686.06
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,967
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,333
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,977
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     124,987.84
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,249.88
    smsp__inst_executed.avg                                                           inst                     189,274.94
    smsp__inst_executed.max                                                           inst                        192,335
    smsp__inst_executed.min                                                           inst                        186,200
    smsp__inst_executed.sum                                                           inst                     12,113,596
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.97
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     316,573.25
    smsp__cycles_active.sum                                                          cycle                     20,260,688
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.42
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.78
    smsp__inst_executed.max                                                           inst                         12,852
    smsp__inst_executed.min                                                           inst                         11,520
    smsp__inst_executed.sum                                                           inst                        786,418
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      75,112.75
    smsp__cycles_active.sum                                                          cycle                      4,807,216
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.91
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.53
    smsp__inst_executed.max                                                           inst                         12,679
    smsp__inst_executed.min                                                           inst                         11,900
    smsp__inst_executed.sum                                                           inst                        786,466
    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                      72,599.36
    smsp__cycles_active.sum                                                          cycle                      4,646,359
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:35, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.59
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.06
    smsp__inst_executed.max                                                           inst                         12,478
    smsp__inst_executed.min                                                           inst                         12,100
    smsp__inst_executed.sum                                                           inst                        786,436
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,386.41
    smsp__cycles_active.sum                                                          cycle                      4,568,730
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.22
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.20
    smsp__inst_executed.max                                                           inst                         12,496
    smsp__inst_executed.min                                                           inst                         11,920
    smsp__inst_executed.sum                                                           inst                        786,509
    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                      73,866.02
    smsp__cycles_active.sum                                                          cycle                      4,727,425
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.59
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.89
    smsp__inst_executed.max                                                           inst                         12,675
    smsp__inst_executed.min                                                           inst                         11,914
    smsp__inst_executed.sum                                                           inst                        786,553
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,482.77
    smsp__cycles_active.sum                                                          cycle                      4,574,897
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.69
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,291.39
    smsp__inst_executed.max                                                           inst                         12,501
    smsp__inst_executed.min                                                           inst                         12,038
    smsp__inst_executed.sum                                                           inst                        786,649
    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                      71,637.31
    smsp__cycles_active.sum                                                          cycle                      4,584,788
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.56
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.43
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.98
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,294.56
    smsp__inst_executed.max                                                           inst                         12,543
    smsp__inst_executed.min                                                           inst                         11,712
    smsp__inst_executed.sum                                                           inst                        786,852
    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                      71,770.67
    smsp__cycles_active.sum                                                          cycle                      4,593,323
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.05
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.35
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.95
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,301.70
    smsp__inst_executed.max                                                           inst                         12,527
    smsp__inst_executed.min                                                           inst                         12,071
    smsp__inst_executed.sum                                                           inst                        787,309
    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                      71,540.92
    smsp__cycles_active.sum                                                          cycle                      4,578,619
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.23
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.23
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,314.02
    smsp__inst_executed.max                                                           inst                         12,699
    smsp__inst_executed.min                                                           inst                         11,912
    smsp__inst_executed.sum                                                           inst                        788,097
    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                      72,509.19
    smsp__cycles_active.sum                                                          cycle                      4,640,588
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         232.10
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,689.25
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       20,069
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,389
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      315,028
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     124,193.57
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,241.94
    smsp__inst_executed.avg                                                           inst                     189,278.17
    smsp__inst_executed.max                                                           inst                        192,324
    smsp__inst_executed.min                                                           inst                        186,272
    smsp__inst_executed.sum                                                           inst                     12,113,803
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          12.87
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     316,996.25
    smsp__cycles_active.sum                                                          cycle                     20,287,760
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          56.90
    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
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.95
    smsp__inst_executed.max                                                           inst                         12,680
    smsp__inst_executed.min                                                           inst                         11,896
    smsp__inst_executed.sum                                                           inst                        786,429
    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                      68,417.62
    smsp__cycles_active.sum                                                          cycle                      4,378,728
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          60.45
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.66
    smsp__inst_executed.max                                                           inst                         12,672
    smsp__inst_executed.min                                                           inst                         11,908
    smsp__inst_executed.sum                                                           inst                        786,410
    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                      74,576.05
    smsp__cycles_active.sum                                                          cycle                      4,772,867
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.85
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.80
    smsp__inst_executed.max                                                           inst                         12,492
    smsp__inst_executed.min                                                           inst                         12,088
    smsp__inst_executed.sum                                                           inst                        786,419
    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                      72,754.67
    smsp__cycles_active.sum                                                          cycle                      4,656,299
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:36, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.85
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,287.94
    smsp__inst_executed.max                                                           inst                         12,660
    smsp__inst_executed.min                                                           inst                         12,090
    smsp__inst_executed.sum                                                           inst                        786,428
    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                      72,405.38
    smsp__cycles_active.sum                                                          cycle                      4,633,944
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:37, 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                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.49
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           4.00
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,289.11
    smsp__inst_executed.max                                                           inst                         12,516
    smsp__inst_executed.min                                                           inst                         11,872
    smsp__inst_executed.sum                                                           inst                        786,503
    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                      74,029.31
    smsp__cycles_active.sum                                                          cycle                      4,737,876
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:37, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.08
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.48
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,288.77
    smsp__inst_executed.max                                                           inst                         12,648
    smsp__inst_executed.min                                                           inst                         11,890
    smsp__inst_executed.sum                                                           inst                        786,481
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      70,229.30
    smsp__cycles_active.sum                                                          cycle                      4,494,675
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:37, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.27
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.46
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.99
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,290.17
    smsp__inst_executed.max                                                           inst                         12,491
    smsp__inst_executed.min                                                           inst                         12,062
    smsp__inst_executed.sum                                                           inst                        786,571
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                              0
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                              0
    smsp__cycles_active.avg                                                          cycle                      71,537.89
    smsp__cycles_active.sum                                                          cycle                      4,578,425
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:37, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          58.46
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.42
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.97
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,294.28
    smsp__inst_executed.max                                                           inst                         12,521
    smsp__inst_executed.min                                                           inst                         12,037
    smsp__inst_executed.sum                                                           inst                        786,834
    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                      71,773.67
    smsp__cycles_active.sum                                                          cycle                      4,593,515
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:37, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          57.95
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.36
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.96
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,298.47
    smsp__inst_executed.max                                                           inst                         12,737
    smsp__inst_executed.min                                                           inst                         11,886
    smsp__inst_executed.sum                                                           inst                        787,102
    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                      71,021.17
    smsp__cycles_active.sum                                                          cycle                      4,545,355
    ---------------------------------------------------------------------- --------------- ------------------------------

  void interBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:37, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                          59.26
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.21
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                           3.91
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                             0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                            0
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                            0
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                              0
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                              0
    smsp__inst_executed.avg                                                           inst                      12,309.88
    smsp__inst_executed.max                                                           inst                         12,759
    smsp__inst_executed.min                                                           inst                         12,026
    smsp__inst_executed.sum                                                           inst                        787,832
    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                      72,721.27
    smsp__cycles_active.sum                                                          cycle                      4,654,161
    ---------------------------------------------------------------------- --------------- ------------------------------

  void inBlockStep<unsigned int>(T1 *, unsigned long, unsigned long, unsigned long), 2025-Feb-16 14:04:37, Context 1, Stream 7
    Section: Command line profiler metrics
    ---------------------------------------------------------------------- --------------- ------------------------------
    gpu__time_duration.sum                                                         usecond                         231.97
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_ld.sum                                                            0
    l1tex__data_bank_conflicts_pipe_lsu_mem_shared_op_st.sum                                                      (!) n/a
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_ld.ratio    sector/request                              4
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.pct                   %                          12.50
    l1tex__average_t_sectors_per_request_pipe_lsu_mem_global_op_st.ratio    sector/request                              4
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.avg                                                        32,768
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.max                                                        33,280
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.min                                                        32,256
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_read.sum                                                       524,288
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.avg                                                    19,679.75
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.max                                                       19,990
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.min                                                       19,275
    l1tex__data_pipe_lsu_wavefronts_mem_shared_cmd_write.sum                                                      314,876
    smsp__average_warp_latency_issue_stalled_barrier.pct                                 %                     125,400.79
    smsp__average_warp_latency_issue_stalled_barrier.ratio                                                       1,254.01
    smsp__inst_executed.avg                                                           inst                     189,032.33
    smsp__inst_executed.max                                                           inst                        192,028
    smsp__inst_executed.min                                                           inst                        186,044
    smsp__inst_executed.sum                                                           inst                     12,098,069
    smsp__warp_issue_stalled_barrier_per_warp_active.pct                                 %                          13.03
    smsp__warp_issue_stalled_barrier_per_warp_active.ratio                                                           0.13
    smsp__cycles_active.avg                                                          cycle                     316,085.12
    smsp__cycles_active.sum                                                          cycle                     20,229,448
    ---------------------------------------------------------------------- --------------- ------------------------------

