* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 569693 tid 569693 thread 0 bound to OS proc set {0}
OMP: pid 569693 tid 569792 thread 1 bound to OS proc set {24}
OMP: pid 569693 tid 569793 thread 2 bound to OS proc set {48}
OMP: pid 569693 tid 569794 thread 3 bound to OS proc set {72}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 4, "n_threads_batch": 4, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000001, "speed_pp": 0.000000, "t_tg": 8.407446, "speed_tg": 15.224600, "t": 8.407447, "speed": 15.224598}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_2
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_2 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_2 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_2 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_2 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_2 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_2 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_2 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_2 #
########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 569815 tid 569815 thread 0 bound to OS proc set {0}
OMP: pid 569815 tid 569916 thread 3 bound to OS proc set {36}
OMP: pid 569815 tid 569917 thread 4 bound to OS proc set {48}
OMP: pid 569815 tid 569914 thread 1 bound to OS proc set {12}
OMP: pid 569815 tid 569915 thread 2 bound to OS proc set {24}
OMP: pid 569815 tid 569919 thread 6 bound to OS proc set {72}
OMP: pid 569815 tid 569918 thread 5 bound to OS proc set {60}
OMP: pid 569815 tid 569920 thread 7 bound to OS proc set {84}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 8, "n_threads_batch": 8, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 4.935030, "speed_tg": 25.937025, "t": 4.935030, "speed": 25.937025}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_3
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_3 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_3 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_3 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_3 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_3 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_3 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_3 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_3 #
########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 569940 tid 569940 thread 0 bound to OS proc set {0}
OMP: pid 569940 tid 570041 thread 3 bound to OS proc set {18}
OMP: pid 569940 tid 570050 thread 12 bound to OS proc set {72}
OMP: pid 569940 tid 570040 thread 2 bound to OS proc set {12}
OMP: pid 569940 tid 570039 thread 1 bound to OS proc set {6}
OMP: pid 569940 tid 570042 thread 4 bound to OS proc set {24}
OMP: pid 569940 tid 570052 thread 14 bound to OS proc set {84}
OMP: pid 569940 tid 570051 thread 13 bound to OS proc set {78}
OMP: pid 569940 tid 570049 thread 11 bound to OS proc set {66}
OMP: pid 569940 tid 570045 thread 7 bound to OS proc set {42}
OMP: pid 569940 tid 570046 thread 8 bound to OS proc set {48}
OMP: pid 569940 tid 570044 thread 6 bound to OS proc set {36}
OMP: pid 569940 tid 570043 thread 5 bound to OS proc set {30}
OMP: pid 569940 tid 570048 thread 10 bound to OS proc set {60}
OMP: pid 569940 tid 570047 thread 9 bound to OS proc set {54}
OMP: pid 569940 tid 570053 thread 15 bound to OS proc set {90}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 16, "n_threads_batch": 16, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.285555, "speed_tg": 38.958412, "t": 3.285555, "speed": 38.958412}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_4
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_4 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_4 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_4 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_4 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_4 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_4 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_4 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_4 #
########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 570073 tid 570073 thread 0 bound to OS proc set {0}
OMP: pid 570073 tid 570173 thread 2 bound to OS proc set {8}
OMP: pid 570073 tid 570174 thread 3 bound to OS proc set {12}
OMP: pid 570073 tid 570186 thread 15 bound to OS proc set {60}
OMP: pid 570073 tid 570190 thread 19 bound to OS proc set {76}
OMP: pid 570073 tid 570175 thread 4 bound to OS proc set {16}
OMP: pid 570073 tid 570183 thread 12 bound to OS proc set {48}
OMP: pid 570073 tid 570172 thread 1 bound to OS proc set {4}
OMP: pid 570073 tid 570185 thread 14 bound to OS proc set {56}
OMP: pid 570073 tid 570179 thread 8 bound to OS proc set {32}
OMP: pid 570073 tid 570176 thread 5 bound to OS proc set {20}
OMP: pid 570073 tid 570178 thread 7 bound to OS proc set {28}
OMP: pid 570073 tid 570189 thread 18 bound to OS proc set {72}
OMP: pid 570073 tid 570187 thread 16 bound to OS proc set {64}
OMP: pid 570073 tid 570182 thread 11 bound to OS proc set {44}
OMP: pid 570073 tid 570177 thread 6 bound to OS proc set {24}
OMP: pid 570073 tid 570181 thread 10 bound to OS proc set {40}
OMP: pid 570073 tid 570180 thread 9 bound to OS proc set {36}
OMP: pid 570073 tid 570191 thread 20 bound to OS proc set {80}
OMP: pid 570073 tid 570184 thread 13 bound to OS proc set {52}
OMP: pid 570073 tid 570188 thread 17 bound to OS proc set {68}
OMP: pid 570073 tid 570192 thread 21 bound to OS proc set {84}
OMP: pid 570073 tid 570193 thread 22 bound to OS proc set {88}
OMP: pid 570073 tid 570194 thread 23 bound to OS proc set {92}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 24, "n_threads_batch": 24, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000001, "speed_pp": 0.000000, "t_tg": 2.772182, "speed_tg": 46.173016, "t": 2.772183, "speed": 46.173000}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_5
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_5 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_5 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_5 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_5 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_5 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_5 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_5 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_5 #
########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 570263 tid 570263 thread 0 bound to OS proc set {0}
OMP: pid 570263 tid 570363 thread 2 bound to OS proc set {6}
OMP: pid 570263 tid 570362 thread 1 bound to OS proc set {3}
OMP: pid 570263 tid 570367 thread 6 bound to OS proc set {18}
OMP: pid 570263 tid 570376 thread 15 bound to OS proc set {45}
OMP: pid 570263 tid 570366 thread 5 bound to OS proc set {15}
OMP: pid 570263 tid 570373 thread 12 bound to OS proc set {36}
OMP: pid 570263 tid 570371 thread 10 bound to OS proc set {30}
OMP: pid 570263 tid 570375 thread 14 bound to OS proc set {42}
OMP: pid 570263 tid 570365 thread 4 bound to OS proc set {12}
OMP: pid 570263 tid 570377 thread 16 bound to OS proc set {48}
OMP: pid 570263 tid 570364 thread 3 bound to OS proc set {9}
OMP: pid 570263 tid 570372 thread 11 bound to OS proc set {33}
OMP: pid 570263 tid 570389 thread 28 bound to OS proc set {84}
OMP: pid 570263 tid 570379 thread 18 bound to OS proc set {54}
OMP: pid 570263 tid 570391 thread 30 bound to OS proc set {90}
OMP: pid 570263 tid 570374 thread 13 bound to OS proc set {39}
OMP: pid 570263 tid 570369 thread 8 bound to OS proc set {24}
OMP: pid 570263 tid 570390 thread 29 bound to OS proc set {87}
OMP: pid 570263 tid 570378 thread 17 bound to OS proc set {51}
OMP: pid 570263 tid 570380 thread 19 bound to OS proc set {57}
OMP: pid 570263 tid 570388 thread 27 bound to OS proc set {81}
OMP: pid 570263 tid 570387 thread 26 bound to OS proc set {78}
OMP: pid 570263 tid 570370 thread 9 bound to OS proc set {27}
OMP: pid 570263 tid 570381 thread 20 bound to OS proc set {60}
OMP: pid 570263 tid 570383 thread 22 bound to OS proc set {66}
OMP: pid 570263 tid 570386 thread 25 bound to OS proc set {75}
OMP: pid 570263 tid 570385 thread 24 bound to OS proc set {72}
OMP: pid 570263 tid 570384 thread 23 bound to OS proc set {69}
OMP: pid 570263 tid 570392 thread 31 bound to OS proc set {93}
OMP: pid 570263 tid 570368 thread 7 bound to OS proc set {21}
OMP: pid 570263 tid 570382 thread 21 bound to OS proc set {63}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 32, "n_threads_batch": 32, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.801957, "speed_tg": 45.682358, "t": 2.801957, "speed": 45.682358}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_6
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_6 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_6 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_6 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_6 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_6 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_6 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_6 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_6 #
########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 570412 tid 570412 thread 0 bound to OS proc set {0}
OMP: pid 570412 tid 570525 thread 15 bound to OS proc set {36}
OMP: pid 570412 tid 570524 thread 14 bound to OS proc set {33}
OMP: pid 570412 tid 570511 thread 1 bound to OS proc set {2}
OMP: pid 570412 tid 570545 thread 35 bound to OS proc set {84}
OMP: pid 570412 tid 570513 thread 3 bound to OS proc set {7}
OMP: pid 570412 tid 570516 thread 6 bound to OS proc set {14}
OMP: pid 570412 tid 570518 thread 8 bound to OS proc set {19}
OMP: pid 570412 tid 570512 thread 2 bound to OS proc set {4}
OMP: pid 570412 tid 570542 thread 32 bound to OS proc set {77}
OMP: pid 570412 tid 570522 thread 12 bound to OS proc set {29}
OMP: pid 570412 tid 570520 thread 10 bound to OS proc set {24}
OMP: pid 570412 tid 570541 thread 31 bound to OS proc set {75}
OMP: pid 570412 tid 570549 thread 39 bound to OS proc set {94}
OMP: pid 570412 tid 570548 thread 38 bound to OS proc set {92}
OMP: pid 570412 tid 570521 thread 11 bound to OS proc set {26}
OMP: pid 570412 tid 570517 thread 7 bound to OS proc set {16}
OMP: pid 570412 tid 570529 thread 19 bound to OS proc set {46}
OMP: pid 570412 tid 570546 thread 36 bound to OS proc set {87}
OMP: pid 570412 tid 570544 thread 34 bound to OS proc set {82}
OMP: pid 570412 tid 570526 thread 16 bound to OS proc set {38}
OMP: pid 570412 tid 570537 thread 27 bound to OS proc set {65}
OMP: pid 570412 tid 570543 thread 33 bound to OS proc set {80}
OMP: pid 570412 tid 570523 thread 13 bound to OS proc set {31}
OMP: pid 570412 tid 570514 thread 4 bound to OS proc set {9}
OMP: pid 570412 tid 570538 thread 28 bound to OS proc set {67}
OMP: pid 570412 tid 570528 thread 18 bound to OS proc set {43}
OMP: pid 570412 tid 570534 thread 24 bound to OS proc set {58}
OMP: pid 570412 tid 570515 thread 5 bound to OS proc set {12}
OMP: pid 570412 tid 570536 thread 26 bound to OS proc set {63}
OMP: pid 570412 tid 570535 thread 25 bound to OS proc set {60}
OMP: pid 570412 tid 570540 thread 30 bound to OS proc set {72}
OMP: pid 570412 tid 570519 thread 9 bound to OS proc set {21}
OMP: pid 570412 tid 570527 thread 17 bound to OS proc set {41}
OMP: pid 570412 tid 570539 thread 29 bound to OS proc set {70}
OMP: pid 570412 tid 570547 thread 37 bound to OS proc set {89}
OMP: pid 570412 tid 570533 thread 23 bound to OS proc set {55}
OMP: pid 570412 tid 570530 thread 20 bound to OS proc set {48}
OMP: pid 570412 tid 570532 thread 22 bound to OS proc set {53}
OMP: pid 570412 tid 570531 thread 21 bound to OS proc set {50}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 40, "n_threads_batch": 40, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.875100, "speed_tg": 44.520191, "t": 2.875100, "speed": 44.520191}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_7
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_7 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_7 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_7 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_7 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_7 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_7 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_7 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_7 #
########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 570570 tid 570570 thread 0 bound to OS proc set {0}
OMP: pid 570570 tid 570680 thread 12 bound to OS proc set {24}
OMP: pid 570570 tid 570675 thread 7 bound to OS proc set {14}
OMP: pid 570570 tid 570671 thread 3 bound to OS proc set {6}
OMP: pid 570570 tid 570679 thread 11 bound to OS proc set {22}
OMP: pid 570570 tid 570670 thread 2 bound to OS proc set {4}
OMP: pid 570570 tid 570676 thread 8 bound to OS proc set {16}
OMP: pid 570570 tid 570674 thread 6 bound to OS proc set {12}
OMP: pid 570570 tid 570687 thread 19 bound to OS proc set {38}
OMP: pid 570570 tid 570672 thread 4 bound to OS proc set {8}
OMP: pid 570570 tid 570669 thread 1 bound to OS proc set {2}
OMP: pid 570570 tid 570678 thread 10 bound to OS proc set {20}
OMP: pid 570570 tid 570715 thread 47 bound to OS proc set {94}
OMP: pid 570570 tid 570703 thread 35 bound to OS proc set {70}
OMP: pid 570570 tid 570683 thread 15 bound to OS proc set {30}
OMP: pid 570570 tid 570700 thread 32 bound to OS proc set {64}
OMP: pid 570570 tid 570677 thread 9 bound to OS proc set {18}
OMP: pid 570570 tid 570681 thread 13 bound to OS proc set {26}
OMP: pid 570570 tid 570714 thread 46 bound to OS proc set {92}
OMP: pid 570570 tid 570691 thread 23 bound to OS proc set {46}
OMP: pid 570570 tid 570673 thread 5 bound to OS proc set {10}
OMP: pid 570570 tid 570699 thread 31 bound to OS proc set {62}
OMP: pid 570570 tid 570712 thread 44 bound to OS proc set {88}
OMP: pid 570570 tid 570696 thread 28 bound to OS proc set {56}
OMP: pid 570570 tid 570692 thread 24 bound to OS proc set {48}
OMP: pid 570570 tid 570693 thread 25 bound to OS proc set {50}
OMP: pid 570570 tid 570698 thread 30 bound to OS proc set {60}
OMP: pid 570570 tid 570686 thread 18 bound to OS proc set {36}
OMP: pid 570570 tid 570682 thread 14 bound to OS proc set {28}
OMP: pid 570570 tid 570695 thread 27 bound to OS proc set {54}
OMP: pid 570570 tid 570684 thread 16 bound to OS proc set {32}
OMP: pid 570570 tid 570685 thread 17 bound to OS proc set {34}
OMP: pid 570570 tid 570702 thread 34 bound to OS proc set {68}
OMP: pid 570570 tid 570688 thread 20 bound to OS proc set {40}
OMP: pid 570570 tid 570711 thread 43 bound to OS proc set {86}
OMP: pid 570570 tid 570704 thread 36 bound to OS proc set {72}
OMP: pid 570570 tid 570701 thread 33 bound to OS proc set {66}
OMP: pid 570570 tid 570707 thread 39 bound to OS proc set {78}
OMP: pid 570570 tid 570694 thread 26 bound to OS proc set {52}
OMP: pid 570570 tid 570697 thread 29 bound to OS proc set {58}
OMP: pid 570570 tid 570713 thread 45 bound to OS proc set {90}
OMP: pid 570570 tid 570706 thread 38 bound to OS proc set {76}
OMP: pid 570570 tid 570705 thread 37 bound to OS proc set {74}
OMP: pid 570570 tid 570710 thread 42 bound to OS proc set {84}
OMP: pid 570570 tid 570708 thread 40 bound to OS proc set {80}
OMP: pid 570570 tid 570689 thread 21 bound to OS proc set {42}
OMP: pid 570570 tid 570709 thread 41 bound to OS proc set {82}
OMP: pid 570570 tid 570690 thread 22 bound to OS proc set {44}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 48, "n_threads_batch": 48, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.837371, "speed_tg": 45.112183, "t": 2.837371, "speed": 45.112183}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_8
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_8 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_8 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_8 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_8 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_8 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_8 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_8 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_8 #
########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 570736 tid 570736 thread 0 bound to OS proc set {0}
OMP: pid 570736 tid 570835 thread 1 bound to OS proc set {1}
OMP: pid 570736 tid 570836 thread 2 bound to OS proc set {3}
OMP: pid 570736 tid 570844 thread 10 bound to OS proc set {17}
OMP: pid 570736 tid 570841 thread 7 bound to OS proc set {12}
OMP: pid 570736 tid 570842 thread 8 bound to OS proc set {13}
OMP: pid 570736 tid 570865 thread 31 bound to OS proc set {53}
OMP: pid 570736 tid 570866 thread 32 bound to OS proc set {55}
OMP: pid 570736 tid 570885 thread 51 bound to OS proc set {88}
OMP: pid 570736 tid 570851 thread 17 bound to OS proc set {29}
OMP: pid 570736 tid 570882 thread 48 bound to OS proc set {83}
OMP: pid 570736 tid 570884 thread 50 bound to OS proc set {86}
OMP: pid 570736 tid 570845 thread 11 bound to OS proc set {19}
OMP: pid 570736 tid 570846 thread 12 bound to OS proc set {20}
OMP: pid 570736 tid 570886 thread 52 bound to OS proc set {90}
OMP: pid 570736 tid 570883 thread 49 bound to OS proc set {84}
OMP: pid 570736 tid 570847 thread 13 bound to OS proc set {22}
OMP: pid 570736 tid 570888 thread 54 bound to OS proc set {93}
OMP: pid 570736 tid 570889 thread 55 bound to OS proc set {95}
OMP: pid 570736 tid 570837 thread 3 bound to OS proc set {5}
OMP: pid 570736 tid 570858 thread 24 bound to OS proc set {41}
OMP: pid 570736 tid 570843 thread 9 bound to OS proc set {15}
OMP: pid 570736 tid 570887 thread 53 bound to OS proc set {91}
OMP: pid 570736 tid 570869 thread 35 bound to OS proc set {60}
OMP: pid 570736 tid 570864 thread 30 bound to OS proc set {51}
OMP: pid 570736 tid 570853 thread 19 bound to OS proc set {32}
OMP: pid 570736 tid 570848 thread 14 bound to OS proc set {24}
OMP: pid 570736 tid 570868 thread 34 bound to OS proc set {58}
OMP: pid 570736 tid 570856 thread 22 bound to OS proc set {38}
OMP: pid 570736 tid 570838 thread 4 bound to OS proc set {6}
OMP: pid 570736 tid 570860 thread 26 bound to OS proc set {45}
OMP: pid 570736 tid 570849 thread 15 bound to OS proc set {25}
OMP: pid 570736 tid 570839 thread 5 bound to OS proc set {8}
OMP: pid 570736 tid 570863 thread 29 bound to OS proc set {50}
OMP: pid 570736 tid 570867 thread 33 bound to OS proc set {57}
OMP: pid 570736 tid 570852 thread 18 bound to OS proc set {31}
OMP: pid 570736 tid 570861 thread 27 bound to OS proc set {46}
OMP: pid 570736 tid 570854 thread 20 bound to OS proc set {34}
OMP: pid 570736 tid 570874 thread 40 bound to OS proc set {69}
OMP: pid 570736 tid 570840 thread 6 bound to OS proc set {10}
OMP: pid 570736 tid 570877 thread 43 bound to OS proc set {74}
OMP: pid 570736 tid 570862 thread 28 bound to OS proc set {48}
OMP: pid 570736 tid 570873 thread 39 bound to OS proc set {67}
OMP: pid 570736 tid 570855 thread 21 bound to OS proc set {36}
OMP: pid 570736 tid 570857 thread 23 bound to OS proc set {39}
OMP: pid 570736 tid 570870 thread 36 bound to OS proc set {62}
OMP: pid 570736 tid 570872 thread 38 bound to OS proc set {65}
OMP: pid 570736 tid 570850 thread 16 bound to OS proc set {27}
OMP: pid 570736 tid 570881 thread 47 bound to OS proc set {81}
OMP: pid 570736 tid 570876 thread 42 bound to OS proc set {72}
OMP: pid 570736 tid 570871 thread 37 bound to OS proc set {64}
OMP: pid 570736 tid 570859 thread 25 bound to OS proc set {43}
OMP: pid 570736 tid 570875 thread 41 bound to OS proc set {71}
OMP: pid 570736 tid 570879 thread 45 bound to OS proc set {77}
OMP: pid 570736 tid 570878 thread 44 bound to OS proc set {76}
OMP: pid 570736 tid 570880 thread 46 bound to OS proc set {79}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 56, "n_threads_batch": 56, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.843881, "speed_tg": 45.008919, "t": 2.843881, "speed": 45.008919}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_9
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_9 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_9 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_9 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_9 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_9 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_9 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_9 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_9 #
########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 570912 tid 570912 thread 0 bound to OS proc set {0}
OMP: pid 570912 tid 571013 thread 3 bound to OS proc set {4}
OMP: pid 570912 tid 571011 thread 1 bound to OS proc set {1}
OMP: pid 570912 tid 571012 thread 2 bound to OS proc set {3}
OMP: pid 570912 tid 571022 thread 12 bound to OS proc set {18}
OMP: pid 570912 tid 571042 thread 32 bound to OS proc set {48}
OMP: pid 570912 tid 571018 thread 8 bound to OS proc set {12}
OMP: pid 570912 tid 571053 thread 43 bound to OS proc set {65}
OMP: pid 570912 tid 571021 thread 11 bound to OS proc set {16}
OMP: pid 570912 tid 571073 thread 63 bound to OS proc set {95}
OMP: pid 570912 tid 571070 thread 60 bound to OS proc set {90}
OMP: pid 570912 tid 571072 thread 62 bound to OS proc set {93}
OMP: pid 570912 tid 571016 thread 6 bound to OS proc set {9}
OMP: pid 570912 tid 571020 thread 10 bound to OS proc set {15}
OMP: pid 570912 tid 571050 thread 40 bound to OS proc set {60}
OMP: pid 570912 tid 571061 thread 51 bound to OS proc set {77}
OMP: pid 570912 tid 571058 thread 48 bound to OS proc set {72}
OMP: pid 570912 tid 571057 thread 47 bound to OS proc set {71}
OMP: pid 570912 tid 571071 thread 61 bound to OS proc set {92}
OMP: pid 570912 tid 571054 thread 44 bound to OS proc set {66}
OMP: pid 570912 tid 571025 thread 15 bound to OS proc set {22}
OMP: pid 570912 tid 571023 thread 13 bound to OS proc set {19}
OMP: pid 570912 tid 571056 thread 46 bound to OS proc set {69}
OMP: pid 570912 tid 571060 thread 50 bound to OS proc set {75}
OMP: pid 570912 tid 571041 thread 31 bound to OS proc set {46}
OMP: pid 570912 tid 571045 thread 35 bound to OS proc set {53}
OMP: pid 570912 tid 571037 thread 27 bound to OS proc set {40}
OMP: pid 570912 tid 571049 thread 39 bound to OS proc set {59}
OMP: pid 570912 tid 571024 thread 14 bound to OS proc set {21}
OMP: pid 570912 tid 571029 thread 19 bound to OS proc set {28}
OMP: pid 570912 tid 571036 thread 26 bound to OS proc set {39}
OMP: pid 570912 tid 571026 thread 16 bound to OS proc set {24}
OMP: pid 570912 tid 571014 thread 4 bound to OS proc set {6}
OMP: pid 570912 tid 571069 thread 59 bound to OS proc set {89}
OMP: pid 570912 tid 571038 thread 28 bound to OS proc set {42}
OMP: pid 570912 tid 571052 thread 42 bound to OS proc set {63}
OMP: pid 570912 tid 571030 thread 20 bound to OS proc set {30}
OMP: pid 570912 tid 571035 thread 25 bound to OS proc set {37}
OMP: pid 570912 tid 571065 thread 55 bound to OS proc set {83}
OMP: pid 570912 tid 571044 thread 34 bound to OS proc set {51}
OMP: pid 570912 tid 571066 thread 56 bound to OS proc set {84}
OMP: pid 570912 tid 571046 thread 36 bound to OS proc set {54}
OMP: pid 570912 tid 571017 thread 7 bound to OS proc set {10}
OMP: pid 570912 tid 571032 thread 22 bound to OS proc set {33}
OMP: pid 570912 tid 571028 thread 18 bound to OS proc set {27}
OMP: pid 570912 tid 571039 thread 29 bound to OS proc set {43}
OMP: pid 570912 tid 571040 thread 30 bound to OS proc set {45}
OMP: pid 570912 tid 571034 thread 24 bound to OS proc set {36}
OMP: pid 570912 tid 571048 thread 38 bound to OS proc set {57}
OMP: pid 570912 tid 571062 thread 52 bound to OS proc set {78}
OMP: pid 570912 tid 571043 thread 33 bound to OS proc set {50}
OMP: pid 570912 tid 571059 thread 49 bound to OS proc set {74}
OMP: pid 570912 tid 571047 thread 37 bound to OS proc set {56}
OMP: pid 570912 tid 571027 thread 17 bound to OS proc set {25}
OMP: pid 570912 tid 571033 thread 23 bound to OS proc set {34}
OMP: pid 570912 tid 571015 thread 5 bound to OS proc set {7}
OMP: pid 570912 tid 571031 thread 21 bound to OS proc set {31}
OMP: pid 570912 tid 571051 thread 41 bound to OS proc set {62}
OMP: pid 570912 tid 571055 thread 45 bound to OS proc set {68}
OMP: pid 570912 tid 571064 thread 54 bound to OS proc set {81}
OMP: pid 570912 tid 571019 thread 9 bound to OS proc set {13}
OMP: pid 570912 tid 571063 thread 53 bound to OS proc set {80}
OMP: pid 570912 tid 571067 thread 57 bound to OS proc set {86}
OMP: pid 570912 tid 571068 thread 58 bound to OS proc set {87}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 64, "n_threads_batch": 64, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.843993, "speed_tg": 45.007145, "t": 2.843993, "speed": 45.007145}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_10
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_10 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_10 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_10 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_10 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_10 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_10 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_10 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_10 #
#########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 571141 tid 571141 thread 0 bound to OS proc set {0}
OMP: pid 571141 tid 571241 thread 2 bound to OS proc set {2}
OMP: pid 571141 tid 571240 thread 1 bound to OS proc set {1}
OMP: pid 571141 tid 571287 thread 48 bound to OS proc set {64}
OMP: pid 571141 tid 571303 thread 64 bound to OS proc set {86}
OMP: pid 571141 tid 571306 thread 67 bound to OS proc set {90}
OMP: pid 571141 tid 571251 thread 12 bound to OS proc set {16}
OMP: pid 571141 tid 571246 thread 7 bound to OS proc set {9}
OMP: pid 571141 tid 571310 thread 71 bound to OS proc set {95}
OMP: pid 571141 tid 571249 thread 10 bound to OS proc set {13}
OMP: pid 571141 tid 571250 thread 11 bound to OS proc set {14}
OMP: pid 571141 tid 571247 thread 8 bound to OS proc set {10}
OMP: pid 571141 tid 571305 thread 66 bound to OS proc set {88}
OMP: pid 571141 tid 571290 thread 51 bound to OS proc set {68}
OMP: pid 571141 tid 571248 thread 9 bound to OS proc set {12}
OMP: pid 571141 tid 571273 thread 34 bound to OS proc set {45}
OMP: pid 571141 tid 571304 thread 65 bound to OS proc set {87}
OMP: pid 571141 tid 571254 thread 15 bound to OS proc set {20}
OMP: pid 571141 tid 571285 thread 46 bound to OS proc set {61}
OMP: pid 571141 tid 571279 thread 40 bound to OS proc set {53}
OMP: pid 571141 tid 571272 thread 33 bound to OS proc set {44}
OMP: pid 571141 tid 571267 thread 28 bound to OS proc set {37}
OMP: pid 571141 tid 571286 thread 47 bound to OS proc set {63}
OMP: pid 571141 tid 571252 thread 13 bound to OS proc set {17}
OMP: pid 571141 tid 571307 thread 68 bound to OS proc set {91}
OMP: pid 571141 tid 571281 thread 42 bound to OS proc set {56}
OMP: pid 571141 tid 571291 thread 52 bound to OS proc set {70}
OMP: pid 571141 tid 571270 thread 31 bound to OS proc set {41}
OMP: pid 571141 tid 571245 thread 6 bound to OS proc set {8}
OMP: pid 571141 tid 571282 thread 43 bound to OS proc set {57}
OMP: pid 571141 tid 571288 thread 49 bound to OS proc set {66}
OMP: pid 571141 tid 571271 thread 32 bound to OS proc set {43}
OMP: pid 571141 tid 571299 thread 60 bound to OS proc set {80}
OMP: pid 571141 tid 571302 thread 63 bound to OS proc set {84}
OMP: pid 571141 tid 571257 thread 18 bound to OS proc set {24}
OMP: pid 571141 tid 571274 thread 35 bound to OS proc set {47}
OMP: pid 571141 tid 571283 thread 44 bound to OS proc set {59}
OMP: pid 571141 tid 571280 thread 41 bound to OS proc set {55}
OMP: pid 571141 tid 571309 thread 70 bound to OS proc set {94}
OMP: pid 571141 tid 571262 thread 23 bound to OS proc set {30}
OMP: pid 571141 tid 571298 thread 59 bound to OS proc set {79}
OMP: pid 571141 tid 571253 thread 14 bound to OS proc set {18}
OMP: pid 571141 tid 571258 thread 19 bound to OS proc set {25}
OMP: pid 571141 tid 571242 thread 3 bound to OS proc set {4}
OMP: pid 571141 tid 571275 thread 36 bound to OS proc set {48}
OMP: pid 571141 tid 571243 thread 4 bound to OS proc set {5}
OMP: pid 571141 tid 571269 thread 30 bound to OS proc set {40}
OMP: pid 571141 tid 571293 thread 54 bound to OS proc set {72}
OMP: pid 571141 tid 571277 thread 38 bound to OS proc set {51}
OMP: pid 571141 tid 571308 thread 69 bound to OS proc set {92}
OMP: pid 571141 tid 571278 thread 39 bound to OS proc set {52}
OMP: pid 571141 tid 571255 thread 16 bound to OS proc set {21}
OMP: pid 571141 tid 571263 thread 24 bound to OS proc set {32}
OMP: pid 571141 tid 571268 thread 29 bound to OS proc set {39}
OMP: pid 571141 tid 571301 thread 62 bound to OS proc set {83}
OMP: pid 571141 tid 571284 thread 45 bound to OS proc set {60}
OMP: pid 571141 tid 571276 thread 37 bound to OS proc set {49}
OMP: pid 571141 tid 571266 thread 27 bound to OS proc set {36}
OMP: pid 571141 tid 571264 thread 25 bound to OS proc set {33}
OMP: pid 571141 tid 571300 thread 61 bound to OS proc set {82}
OMP: pid 571141 tid 571259 thread 20 bound to OS proc set {26}
OMP: pid 571141 tid 571260 thread 21 bound to OS proc set {28}
OMP: pid 571141 tid 571292 thread 53 bound to OS proc set {71}
OMP: pid 571141 tid 571294 thread 55 bound to OS proc set {74}
OMP: pid 571141 tid 571297 thread 58 bound to OS proc set {78}
OMP: pid 571141 tid 571244 thread 5 bound to OS proc set {6}
OMP: pid 571141 tid 571256 thread 17 bound to OS proc set {22}
OMP: pid 571141 tid 571296 thread 57 bound to OS proc set {76}
OMP: pid 571141 tid 571295 thread 56 bound to OS proc set {75}
OMP: pid 571141 tid 571261 thread 22 bound to OS proc set {29}
OMP: pid 571141 tid 571265 thread 26 bound to OS proc set {35}
OMP: pid 571141 tid 571289 thread 50 bound to OS proc set {67}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 72, "n_threads_batch": 72, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.935293, "speed_tg": 43.607231, "t": 2.935293, "speed": 43.607231}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_11
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_11 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_11 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_11 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_11 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_11 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_11 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_11 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_11 #
#########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 571330 tid 571330 thread 0 bound to OS proc set {0}
OMP: pid 571330 tid 571431 thread 3 bound to OS proc set {3}
OMP: pid 571330 tid 571430 thread 2 bound to OS proc set {2}
OMP: pid 571330 tid 571432 thread 4 bound to OS proc set {4}
OMP: pid 571330 tid 571429 thread 1 bound to OS proc set {1}
OMP: pid 571330 tid 571494 thread 66 bound to OS proc set {80}
OMP: pid 571330 tid 571492 thread 64 bound to OS proc set {77}
OMP: pid 571330 tid 571440 thread 12 bound to OS proc set {14}
OMP: pid 571330 tid 571455 thread 27 bound to OS proc set {32}
OMP: pid 571330 tid 571478 thread 50 bound to OS proc set {60}
OMP: pid 571330 tid 571504 thread 76 bound to OS proc set {92}
OMP: pid 571330 tid 571506 thread 78 bound to OS proc set {94}
OMP: pid 571330 tid 571493 thread 65 bound to OS proc set {78}
OMP: pid 571330 tid 571495 thread 67 bound to OS proc set {81}
OMP: pid 571330 tid 571434 thread 6 bound to OS proc set {7}
OMP: pid 571330 tid 571507 thread 79 bound to OS proc set {95}
OMP: pid 571330 tid 571442 thread 14 bound to OS proc set {16}
OMP: pid 571330 tid 571468 thread 40 bound to OS proc set {48}
OMP: pid 571330 tid 571439 thread 11 bound to OS proc set {13}
OMP: pid 571330 tid 571443 thread 15 bound to OS proc set {18}
OMP: pid 571330 tid 571491 thread 63 bound to OS proc set {76}
OMP: pid 571330 tid 571435 thread 7 bound to OS proc set {8}
OMP: pid 571330 tid 571441 thread 13 bound to OS proc set {15}
OMP: pid 571330 tid 571474 thread 46 bound to OS proc set {55}
OMP: pid 571330 tid 571505 thread 77 bound to OS proc set {93}
OMP: pid 571330 tid 571477 thread 49 bound to OS proc set {59}
OMP: pid 571330 tid 571471 thread 43 bound to OS proc set {52}
OMP: pid 571330 tid 571463 thread 35 bound to OS proc set {42}
OMP: pid 571330 tid 571475 thread 47 bound to OS proc set {56}
OMP: pid 571330 tid 571454 thread 26 bound to OS proc set {31}
OMP: pid 571330 tid 571438 thread 10 bound to OS proc set {12}
OMP: pid 571330 tid 571456 thread 28 bound to OS proc set {33}
OMP: pid 571330 tid 571487 thread 59 bound to OS proc set {71}
OMP: pid 571330 tid 571458 thread 30 bound to OS proc set {36}
OMP: pid 571330 tid 571462 thread 34 bound to OS proc set {41}
OMP: pid 571330 tid 571473 thread 45 bound to OS proc set {54}
OMP: pid 571330 tid 571503 thread 75 bound to OS proc set {90}
OMP: pid 571330 tid 571452 thread 24 bound to OS proc set {29}
OMP: pid 571330 tid 571447 thread 19 bound to OS proc set {23}
OMP: pid 571330 tid 571450 thread 22 bound to OS proc set {26}
OMP: pid 571330 tid 571485 thread 57 bound to OS proc set {69}
OMP: pid 571330 tid 571460 thread 32 bound to OS proc set {38}
OMP: pid 571330 tid 571499 thread 71 bound to OS proc set {86}
OMP: pid 571330 tid 571464 thread 36 bound to OS proc set {43}
OMP: pid 571330 tid 571436 thread 8 bound to OS proc set {9}
OMP: pid 571330 tid 571467 thread 39 bound to OS proc set {47}
OMP: pid 571330 tid 571490 thread 62 bound to OS proc set {75}
OMP: pid 571330 tid 571472 thread 44 bound to OS proc set {53}
OMP: pid 571330 tid 571444 thread 16 bound to OS proc set {19}
OMP: pid 571330 tid 571489 thread 61 bound to OS proc set {73}
OMP: pid 571330 tid 571445 thread 17 bound to OS proc set {20}
OMP: pid 571330 tid 571482 thread 54 bound to OS proc set {65}
OMP: pid 571330 tid 571481 thread 53 bound to OS proc set {64}
OMP: pid 571330 tid 571446 thread 18 bound to OS proc set {21}
OMP: pid 571330 tid 571459 thread 31 bound to OS proc set {37}
OMP: pid 571330 tid 571465 thread 37 bound to OS proc set {44}
OMP: pid 571330 tid 571470 thread 42 bound to OS proc set {50}
OMP: pid 571330 tid 571449 thread 21 bound to OS proc set {25}
OMP: pid 571330 tid 571457 thread 29 bound to OS proc set {35}
OMP: pid 571330 tid 571483 thread 55 bound to OS proc set {66}
OMP: pid 571330 tid 571453 thread 25 bound to OS proc set {30}
OMP: pid 571330 tid 571486 thread 58 bound to OS proc set {70}
OMP: pid 571330 tid 571451 thread 23 bound to OS proc set {27}
OMP: pid 571330 tid 571461 thread 33 bound to OS proc set {40}
OMP: pid 571330 tid 571466 thread 38 bound to OS proc set {46}
OMP: pid 571330 tid 571433 thread 5 bound to OS proc set {6}
OMP: pid 571330 tid 571501 thread 73 bound to OS proc set {88}
OMP: pid 571330 tid 571437 thread 9 bound to OS proc set {10}
OMP: pid 571330 tid 571500 thread 72 bound to OS proc set {87}
OMP: pid 571330 tid 571488 thread 60 bound to OS proc set {72}
OMP: pid 571330 tid 571502 thread 74 bound to OS proc set {89}
OMP: pid 571330 tid 571448 thread 20 bound to OS proc set {24}
OMP: pid 571330 tid 571469 thread 41 bound to OS proc set {49}
OMP: pid 571330 tid 571480 thread 52 bound to OS proc set {63}
OMP: pid 571330 tid 571476 thread 48 bound to OS proc set {58}
OMP: pid 571330 tid 571479 thread 51 bound to OS proc set {61}
OMP: pid 571330 tid 571496 thread 68 bound to OS proc set {82}
OMP: pid 571330 tid 571497 thread 69 bound to OS proc set {83}
OMP: pid 571330 tid 571498 thread 70 bound to OS proc set {84}
OMP: pid 571330 tid 571484 thread 56 bound to OS proc set {67}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 80, "n_threads_batch": 80, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.987505, "speed_tg": 42.845116, "t": 2.987505, "speed": 42.845116}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_12
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_12 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_12 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_12 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_12 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_12 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_12 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_12 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_12 #
#########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 571527 tid 571527 thread 0 bound to OS proc set {0}
OMP: pid 571527 tid 571640 thread 15 bound to OS proc set {16}
OMP: pid 571527 tid 571628 thread 3 bound to OS proc set {3}
OMP: pid 571527 tid 571627 thread 2 bound to OS proc set {2}
OMP: pid 571527 tid 571639 thread 14 bound to OS proc set {15}
OMP: pid 571527 tid 571633 thread 8 bound to OS proc set {8}
OMP: pid 571527 tid 571626 thread 1 bound to OS proc set {1}
OMP: pid 571527 tid 571629 thread 4 bound to OS proc set {4}
OMP: pid 571527 tid 571638 thread 13 bound to OS proc set {14}
OMP: pid 571527 tid 571644 thread 19 bound to OS proc set {20}
OMP: pid 571527 tid 571632 thread 7 bound to OS proc set {7}
OMP: pid 571527 tid 571631 thread 6 bound to OS proc set {6}
OMP: pid 571527 tid 571641 thread 16 bound to OS proc set {17}
OMP: pid 571527 tid 571634 thread 9 bound to OS proc set {9}
OMP: pid 571527 tid 571643 thread 18 bound to OS proc set {19}
OMP: pid 571527 tid 571630 thread 5 bound to OS proc set {5}
OMP: pid 571527 tid 571642 thread 17 bound to OS proc set {18}
OMP: pid 571527 tid 571636 thread 11 bound to OS proc set {12}
OMP: pid 571527 tid 571684 thread 59 bound to OS proc set {65}
OMP: pid 571527 tid 571688 thread 63 bound to OS proc set {69}
OMP: pid 571527 tid 571656 thread 31 bound to OS proc set {34}
OMP: pid 571527 tid 571637 thread 12 bound to OS proc set {13}
OMP: pid 571527 tid 571673 thread 48 bound to OS proc set {52}
OMP: pid 571527 tid 571652 thread 27 bound to OS proc set {29}
OMP: pid 571527 tid 571635 thread 10 bound to OS proc set {11}
OMP: pid 571527 tid 571685 thread 60 bound to OS proc set {66}
OMP: pid 571527 tid 571680 thread 55 bound to OS proc set {60}
OMP: pid 571527 tid 571672 thread 47 bound to OS proc set {51}
OMP: pid 571527 tid 571683 thread 58 bound to OS proc set {63}
OMP: pid 571527 tid 571681 thread 56 bound to OS proc set {61}
OMP: pid 571527 tid 571664 thread 39 bound to OS proc set {42}
OMP: pid 571527 tid 571708 thread 83 bound to OS proc set {91}
OMP: pid 571527 tid 571674 thread 49 bound to OS proc set {54}
OMP: pid 571527 tid 571671 thread 46 bound to OS proc set {50}
OMP: pid 571527 tid 571687 thread 62 bound to OS proc set {68}
OMP: pid 571527 tid 571701 thread 76 bound to OS proc set {83}
OMP: pid 571527 tid 571676 thread 51 bound to OS proc set {56}
OMP: pid 571527 tid 571655 thread 30 bound to OS proc set {33}
OMP: pid 571527 tid 571669 thread 44 bound to OS proc set {48}
OMP: pid 571527 tid 571653 thread 28 bound to OS proc set {30}
OMP: pid 571527 tid 571686 thread 61 bound to OS proc set {67}
OMP: pid 571527 tid 571665 thread 40 bound to OS proc set {44}
OMP: pid 571527 tid 571651 thread 26 bound to OS proc set {28}
OMP: pid 571527 tid 571659 thread 34 bound to OS proc set {37}
OMP: pid 571527 tid 571691 thread 66 bound to OS proc set {72}
OMP: pid 571527 tid 571648 thread 23 bound to OS proc set {25}
OMP: pid 571527 tid 571660 thread 35 bound to OS proc set {38}
OMP: pid 571527 tid 571667 thread 42 bound to OS proc set {46}
OMP: pid 571527 tid 571679 thread 54 bound to OS proc set {59}
OMP: pid 571527 tid 571682 thread 57 bound to OS proc set {62}
OMP: pid 571527 tid 571668 thread 43 bound to OS proc set {47}
OMP: pid 571527 tid 571658 thread 33 bound to OS proc set {36}
OMP: pid 571527 tid 571654 thread 29 bound to OS proc set {31}
OMP: pid 571527 tid 571657 thread 32 bound to OS proc set {35}
OMP: pid 571527 tid 571663 thread 38 bound to OS proc set {41}
OMP: pid 571527 tid 571696 thread 71 bound to OS proc set {78}
OMP: pid 571527 tid 571677 thread 52 bound to OS proc set {57}
OMP: pid 571527 tid 571666 thread 41 bound to OS proc set {45}
OMP: pid 571527 tid 571692 thread 67 bound to OS proc set {73}
OMP: pid 571527 tid 571699 thread 74 bound to OS proc set {81}
OMP: pid 571527 tid 571670 thread 45 bound to OS proc set {49}
OMP: pid 571527 tid 571697 thread 72 bound to OS proc set {79}
OMP: pid 571527 tid 571700 thread 75 bound to OS proc set {82}
OMP: pid 571527 tid 571649 thread 24 bound to OS proc set {26}
OMP: pid 571527 tid 571650 thread 25 bound to OS proc set {27}
OMP: pid 571527 tid 571661 thread 36 bound to OS proc set {39}
OMP: pid 571527 tid 571675 thread 50 bound to OS proc set {55}
OMP: pid 571527 tid 571645 thread 20 bound to OS proc set {22}
OMP: pid 571527 tid 571695 thread 70 bound to OS proc set {77}
OMP: pid 571527 tid 571662 thread 37 bound to OS proc set {40}
OMP: pid 571527 tid 571690 thread 65 bound to OS proc set {71}
OMP: pid 571527 tid 571694 thread 69 bound to OS proc set {76}
OMP: pid 571527 tid 571702 thread 77 bound to OS proc set {84}
OMP: pid 571527 tid 571703 thread 78 bound to OS proc set {85}
OMP: pid 571527 tid 571704 thread 79 bound to OS proc set {87}
OMP: pid 571527 tid 571646 thread 21 bound to OS proc set {23}
OMP: pid 571527 tid 571693 thread 68 bound to OS proc set {74}
OMP: pid 571527 tid 571689 thread 64 bound to OS proc set {70}
OMP: pid 571527 tid 571705 thread 80 bound to OS proc set {88}
OMP: pid 571527 tid 571678 thread 53 bound to OS proc set {58}
OMP: pid 571527 tid 571698 thread 73 bound to OS proc set {80}
OMP: pid 571527 tid 571706 thread 81 bound to OS proc set {89}
OMP: pid 571527 tid 571707 thread 82 bound to OS proc set {90}
OMP: pid 571527 tid 571647 thread 22 bound to OS proc set {24}
OMP: pid 571527 tid 571709 thread 84 bound to OS proc set {92}
OMP: pid 571527 tid 571711 thread 86 bound to OS proc set {94}
OMP: pid 571527 tid 571712 thread 87 bound to OS proc set {95}
OMP: pid 571527 tid 571710 thread 85 bound to OS proc set {93}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 88, "n_threads_batch": 88, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.149524, "speed_tg": 40.641064, "t": 3.149524, "speed": 40.641064}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_13
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_13 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_13 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_13 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_13 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_13 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_13 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_13 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_13 #
#########################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-35-140.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 571732 tid 571732 thread 0 bound to OS proc set {0}
OMP: pid 571732 tid 571833 thread 3 bound to OS proc set {3}
OMP: pid 571732 tid 571832 thread 2 bound to OS proc set {2}
OMP: pid 571732 tid 571838 thread 8 bound to OS proc set {8}
OMP: pid 571732 tid 571831 thread 1 bound to OS proc set {1}
OMP: pid 571732 tid 571837 thread 7 bound to OS proc set {7}
OMP: pid 571732 tid 571834 thread 4 bound to OS proc set {4}
OMP: pid 571732 tid 571836 thread 6 bound to OS proc set {6}
OMP: pid 571732 tid 571835 thread 5 bound to OS proc set {5}
OMP: pid 571732 tid 571844 thread 14 bound to OS proc set {14}
OMP: pid 571732 tid 571845 thread 15 bound to OS proc set {15}
OMP: pid 571732 tid 571862 thread 32 bound to OS proc set {32}
OMP: pid 571732 tid 571842 thread 12 bound to OS proc set {12}
OMP: pid 571732 tid 571881 thread 51 bound to OS proc set {51}
OMP: pid 571732 tid 571841 thread 11 bound to OS proc set {11}
OMP: pid 571732 tid 571878 thread 48 bound to OS proc set {48}
OMP: pid 571732 tid 571843 thread 13 bound to OS proc set {13}
OMP: pid 571732 tid 571892 thread 62 bound to OS proc set {62}
OMP: pid 571732 tid 571906 thread 76 bound to OS proc set {76}
OMP: pid 571732 tid 571846 thread 16 bound to OS proc set {16}
OMP: pid 571732 tid 571893 thread 63 bound to OS proc set {63}
OMP: pid 571732 tid 571840 thread 10 bound to OS proc set {10}
OMP: pid 571732 tid 571877 thread 47 bound to OS proc set {47}
OMP: pid 571732 tid 571880 thread 50 bound to OS proc set {50}
OMP: pid 571732 tid 571849 thread 19 bound to OS proc set {19}
OMP: pid 571732 tid 571886 thread 56 bound to OS proc set {56}
OMP: pid 571732 tid 571861 thread 31 bound to OS proc set {31}
OMP: pid 571732 tid 571882 thread 52 bound to OS proc set {52}
OMP: pid 571732 tid 571894 thread 64 bound to OS proc set {64}
OMP: pid 571732 tid 571874 thread 44 bound to OS proc set {44}
OMP: pid 571732 tid 571858 thread 28 bound to OS proc set {28}
OMP: pid 571732 tid 571865 thread 35 bound to OS proc set {35}
OMP: pid 571732 tid 571890 thread 60 bound to OS proc set {60}
OMP: pid 571732 tid 571879 thread 49 bound to OS proc set {49}
OMP: pid 571732 tid 571864 thread 34 bound to OS proc set {34}
OMP: pid 571732 tid 571891 thread 61 bound to OS proc set {61}
OMP: pid 571732 tid 571897 thread 67 bound to OS proc set {67}
OMP: pid 571732 tid 571854 thread 24 bound to OS proc set {24}
OMP: pid 571732 tid 571909 thread 79 bound to OS proc set {79}
OMP: pid 571732 tid 571848 thread 18 bound to OS proc set {18}
OMP: pid 571732 tid 571863 thread 33 bound to OS proc set {33}
OMP: pid 571732 tid 571860 thread 30 bound to OS proc set {30}
OMP: pid 571732 tid 571866 thread 36 bound to OS proc set {36}
OMP: pid 571732 tid 571839 thread 9 bound to OS proc set {9}
OMP: pid 571732 tid 571876 thread 46 bound to OS proc set {46}
OMP: pid 571732 tid 571857 thread 27 bound to OS proc set {27}
OMP: pid 571732 tid 571902 thread 72 bound to OS proc set {72}
OMP: pid 571732 tid 571870 thread 40 bound to OS proc set {40}
OMP: pid 571732 tid 571885 thread 55 bound to OS proc set {55}
OMP: pid 571732 tid 571850 thread 20 bound to OS proc set {20}
OMP: pid 571732 tid 571905 thread 75 bound to OS proc set {75}
OMP: pid 571732 tid 571847 thread 17 bound to OS proc set {17}
OMP: pid 571732 tid 571856 thread 26 bound to OS proc set {26}
OMP: pid 571732 tid 571910 thread 80 bound to OS proc set {80}
OMP: pid 571732 tid 571869 thread 39 bound to OS proc set {39}
OMP: pid 571732 tid 571852 thread 22 bound to OS proc set {22}
OMP: pid 571732 tid 571859 thread 29 bound to OS proc set {29}
OMP: pid 571732 tid 571889 thread 59 bound to OS proc set {59}
OMP: pid 571732 tid 571884 thread 54 bound to OS proc set {54}
OMP: pid 571732 tid 571896 thread 66 bound to OS proc set {66}
OMP: pid 571732 tid 571853 thread 23 bound to OS proc set {23}
OMP: pid 571732 tid 571888 thread 58 bound to OS proc set {58}
OMP: pid 571732 tid 571922 thread 92 bound to OS proc set {92}
OMP: pid 571732 tid 571925 thread 95 bound to OS proc set {95}
OMP: pid 571732 tid 571875 thread 45 bound to OS proc set {45}
OMP: pid 571732 tid 571907 thread 77 bound to OS proc set {77}
OMP: pid 571732 tid 571883 thread 53 bound to OS proc set {53}
OMP: pid 571732 tid 571923 thread 93 bound to OS proc set {93}
OMP: pid 571732 tid 571871 thread 41 bound to OS proc set {41}
OMP: pid 571732 tid 571901 thread 71 bound to OS proc set {71}
OMP: pid 571732 tid 571912 thread 82 bound to OS proc set {82}
OMP: pid 571732 tid 571913 thread 83 bound to OS proc set {83}
OMP: pid 571732 tid 571921 thread 91 bound to OS proc set {91}
OMP: pid 571732 tid 571924 thread 94 bound to OS proc set {94}
OMP: pid 571732 tid 571851 thread 21 bound to OS proc set {21}
OMP: pid 571732 tid 571855 thread 25 bound to OS proc set {25}
OMP: pid 571732 tid 571867 thread 37 bound to OS proc set {37}
OMP: pid 571732 tid 571868 thread 38 bound to OS proc set {38}
OMP: pid 571732 tid 571872 thread 42 bound to OS proc set {42}
OMP: pid 571732 tid 571887 thread 57 bound to OS proc set {57}
OMP: pid 571732 tid 571903 thread 73 bound to OS proc set {73}
OMP: pid 571732 tid 571904 thread 74 bound to OS proc set {74}
OMP: pid 571732 tid 571908 thread 78 bound to OS proc set {78}
OMP: pid 571732 tid 571911 thread 81 bound to OS proc set {81}
OMP: pid 571732 tid 571918 thread 88 bound to OS proc set {88}
OMP: pid 571732 tid 571873 thread 43 bound to OS proc set {43}
OMP: pid 571732 tid 571914 thread 84 bound to OS proc set {84}
OMP: pid 571732 tid 571915 thread 85 bound to OS proc set {85}
OMP: pid 571732 tid 571916 thread 86 bound to OS proc set {86}
OMP: pid 571732 tid 571917 thread 87 bound to OS proc set {87}
OMP: pid 571732 tid 571920 thread 90 bound to OS proc set {90}
OMP: pid 571732 tid 571919 thread 89 bound to OS proc set {89}
OMP: pid 571732 tid 571895 thread 65 bound to OS proc set {65}
OMP: pid 571732 tid 571898 thread 68 bound to OS proc set {68}
OMP: pid 571732 tid 571900 thread 70 bound to OS proc set {70}
OMP: pid 571732 tid 571899 thread 69 bound to OS proc set {69}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 96, "n_threads_batch": 96, "pp": 0, "tg": 128, "pl": 1, "n_kv": 128, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.246482, "speed_tg": 39.427296, "t": 3.246482, "speed": 39.427296}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_14
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_14 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_14 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_14 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_14 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_14 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_14 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_14 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-0470/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-23-04/tools/lprof_npsu_run_14 #
#########################################################################################################################################################################################################################################
