* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 3923832 tid 3923832 thread 0 bound to OS proc set {0}
OMP: pid 3923832 tid 3923900 thread 2 bound to OS proc set {32}
OMP: pid 3923832 tid 3923899 thread 1 bound to OS proc set {16}
OMP: pid 3923832 tid 3923901 thread 3 bound to OS proc set {48}
{"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": 128, "tg": 0, "pl": 1, "n_kv": 128, "t_pp": 7.945389, "speed_pp": 16.109974, "t_tg": 0.000000, "speed_tg": nan, "t": 7.945389, "speed": 16.109974}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/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-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_2 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_2 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_2 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_2 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_2 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_2 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_2 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_2 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 3924585 tid 3924585 thread 0 bound to OS proc set {0}
OMP: pid 3924585 tid 3924654 thread 3 bound to OS proc set {24}
OMP: pid 3924585 tid 3924653 thread 2 bound to OS proc set {16}
OMP: pid 3924585 tid 3924655 thread 4 bound to OS proc set {32}
OMP: pid 3924585 tid 3924652 thread 1 bound to OS proc set {8}
OMP: pid 3924585 tid 3924657 thread 6 bound to OS proc set {48}
OMP: pid 3924585 tid 3924656 thread 5 bound to OS proc set {40}
OMP: pid 3924585 tid 3924658 thread 7 bound to OS proc set {56}
{"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": 128, "tg": 0, "pl": 1, "n_kv": 128, "t_pp": 5.221538, "speed_pp": 24.513849, "t_tg": 0.000000, "speed_tg": nan, "t": 5.221538, "speed": 24.513849}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/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-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_3 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_3 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_3 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_3 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_3 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_3 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_3 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_3 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 3926227 tid 3926227 thread 0 bound to OS proc set {0}
OMP: pid 3926227 tid 3926296 thread 3 bound to OS proc set {12}
OMP: pid 3926227 tid 3926295 thread 2 bound to OS proc set {8}
OMP: pid 3926227 tid 3926294 thread 1 bound to OS proc set {4}
OMP: pid 3926227 tid 3926305 thread 12 bound to OS proc set {48}
OMP: pid 3926227 tid 3926307 thread 14 bound to OS proc set {56}
OMP: pid 3926227 tid 3926297 thread 4 bound to OS proc set {16}
OMP: pid 3926227 tid 3926301 thread 8 bound to OS proc set {32}
OMP: pid 3926227 tid 3926306 thread 13 bound to OS proc set {52}
OMP: pid 3926227 tid 3926303 thread 10 bound to OS proc set {40}
OMP: pid 3926227 tid 3926304 thread 11 bound to OS proc set {44}
OMP: pid 3926227 tid 3926300 thread 7 bound to OS proc set {28}
OMP: pid 3926227 tid 3926299 thread 6 bound to OS proc set {24}
OMP: pid 3926227 tid 3926308 thread 15 bound to OS proc set {60}
OMP: pid 3926227 tid 3926298 thread 5 bound to OS proc set {20}
OMP: pid 3926227 tid 3926302 thread 9 bound to OS proc set {36}
{"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": 128, "tg": 0, "pl": 1, "n_kv": 128, "t_pp": 4.434254, "speed_pp": 28.866184, "t_tg": 0.000000, "speed_tg": nan, "t": 4.434254, "speed": 28.866184}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/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-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_4 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_4 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_4 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_4 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_4 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_4 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_4 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_4 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 3929643 tid 3929643 thread 0 bound to OS proc set {0}
OMP: pid 3929643 tid 3929712 thread 3 bound to OS proc set {8}
OMP: pid 3929643 tid 3929717 thread 8 bound to OS proc set {21}
OMP: pid 3929643 tid 3929710 thread 1 bound to OS proc set {2}
OMP: pid 3929643 tid 3929727 thread 18 bound to OS proc set {48}
OMP: pid 3929643 tid 3929725 thread 16 bound to OS proc set {43}
OMP: pid 3929643 tid 3929713 thread 4 bound to OS proc set {10}
OMP: pid 3929643 tid 3929718 thread 9 bound to OS proc set {24}
OMP: pid 3929643 tid 3929728 thread 19 bound to OS proc set {51}
OMP: pid 3929643 tid 3929715 thread 6 bound to OS proc set {16}
OMP: pid 3929643 tid 3929721 thread 12 bound to OS proc set {32}
OMP: pid 3929643 tid 3929724 thread 15 bound to OS proc set {40}
OMP: pid 3929643 tid 3929716 thread 7 bound to OS proc set {18}
OMP: pid 3929643 tid 3929720 thread 11 bound to OS proc set {29}
OMP: pid 3929643 tid 3929726 thread 17 bound to OS proc set {46}
OMP: pid 3929643 tid 3929723 thread 14 bound to OS proc set {37}
OMP: pid 3929643 tid 3929722 thread 13 bound to OS proc set {35}
OMP: pid 3929643 tid 3929729 thread 20 bound to OS proc set {54}
OMP: pid 3929643 tid 3929711 thread 2 bound to OS proc set {5}
OMP: pid 3929643 tid 3929719 thread 10 bound to OS proc set {27}
OMP: pid 3929643 tid 3929731 thread 22 bound to OS proc set {59}
OMP: pid 3929643 tid 3929732 thread 23 bound to OS proc set {62}
OMP: pid 3929643 tid 3929714 thread 5 bound to OS proc set {13}
OMP: pid 3929643 tid 3929730 thread 21 bound to OS proc set {56}
{"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": 128, "tg": 0, "pl": 1, "n_kv": 128, "t_pp": 4.440776, "speed_pp": 28.823792, "t_tg": 0.000000, "speed_tg": nan, "t": 4.440776, "speed": 28.823792}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/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-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_5 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_5 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_5 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_5 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_5 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_5 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_5 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_5 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 3934890 tid 3934890 thread 0 bound to OS proc set {0}
OMP: pid 3934890 tid 3934957 thread 1 bound to OS proc set {2}
OMP: pid 3934890 tid 3934967 thread 11 bound to OS proc set {22}
OMP: pid 3934890 tid 3934963 thread 7 bound to OS proc set {14}
OMP: pid 3934890 tid 3934958 thread 2 bound to OS proc set {4}
OMP: pid 3934890 tid 3934959 thread 3 bound to OS proc set {6}
OMP: pid 3934890 tid 3934964 thread 8 bound to OS proc set {16}
OMP: pid 3934890 tid 3934961 thread 5 bound to OS proc set {10}
OMP: pid 3934890 tid 3934960 thread 4 bound to OS proc set {8}
OMP: pid 3934890 tid 3934962 thread 6 bound to OS proc set {12}
OMP: pid 3934890 tid 3934968 thread 12 bound to OS proc set {24}
OMP: pid 3934890 tid 3934972 thread 16 bound to OS proc set {32}
OMP: pid 3934890 tid 3934970 thread 14 bound to OS proc set {28}
OMP: pid 3934890 tid 3934965 thread 9 bound to OS proc set {18}
OMP: pid 3934890 tid 3934984 thread 28 bound to OS proc set {56}
OMP: pid 3934890 tid 3934975 thread 19 bound to OS proc set {38}
OMP: pid 3934890 tid 3934986 thread 30 bound to OS proc set {60}
OMP: pid 3934890 tid 3934987 thread 31 bound to OS proc set {62}
OMP: pid 3934890 tid 3934980 thread 24 bound to OS proc set {48}
OMP: pid 3934890 tid 3934966 thread 10 bound to OS proc set {20}
OMP: pid 3934890 tid 3934971 thread 15 bound to OS proc set {30}
OMP: pid 3934890 tid 3934983 thread 27 bound to OS proc set {54}
OMP: pid 3934890 tid 3934969 thread 13 bound to OS proc set {26}
OMP: pid 3934890 tid 3934982 thread 26 bound to OS proc set {52}
OMP: pid 3934890 tid 3934973 thread 17 bound to OS proc set {34}
OMP: pid 3934890 tid 3934974 thread 18 bound to OS proc set {36}
OMP: pid 3934890 tid 3934981 thread 25 bound to OS proc set {50}
OMP: pid 3934890 tid 3934979 thread 23 bound to OS proc set {46}
OMP: pid 3934890 tid 3934985 thread 29 bound to OS proc set {58}
OMP: pid 3934890 tid 3934976 thread 20 bound to OS proc set {40}
OMP: pid 3934890 tid 3934977 thread 21 bound to OS proc set {42}
OMP: pid 3934890 tid 3934978 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": 32, "n_threads_batch": 32, "pp": 128, "tg": 0, "pl": 1, "n_kv": 128, "t_pp": 4.638610, "speed_pp": 27.594475, "t_tg": 0.000001, "speed_tg": 0.000000, "t": 4.638611, "speed": 27.594469}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/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-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_6 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_6 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_6 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_6 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_6 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_6 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_6 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_6 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 3941878 tid 3941878 thread 0 bound to OS proc set {0}
OMP: pid 3941878 tid 3941945 thread 1 bound to OS proc set {1}
OMP: pid 3941878 tid 3941946 thread 2 bound to OS proc set {3}
OMP: pid 3941878 tid 3941958 thread 14 bound to OS proc set {22}
OMP: pid 3941878 tid 3941959 thread 15 bound to OS proc set {24}
OMP: pid 3941878 tid 3941951 thread 7 bound to OS proc set {11}
OMP: pid 3941878 tid 3941952 thread 8 bound to OS proc set {13}
OMP: pid 3941878 tid 3941976 thread 32 bound to OS proc set {52}
OMP: pid 3941878 tid 3941947 thread 3 bound to OS proc set {4}
OMP: pid 3941878 tid 3941948 thread 4 bound to OS proc set {6}
OMP: pid 3941878 tid 3941956 thread 12 bound to OS proc set {19}
OMP: pid 3941878 tid 3941953 thread 9 bound to OS proc set {14}
OMP: pid 3941878 tid 3941949 thread 5 bound to OS proc set {8}
OMP: pid 3941878 tid 3941950 thread 6 bound to OS proc set {9}
OMP: pid 3941878 tid 3941979 thread 35 bound to OS proc set {56}
OMP: pid 3941878 tid 3941980 thread 36 bound to OS proc set {58}
OMP: pid 3941878 tid 3941978 thread 34 bound to OS proc set {55}
OMP: pid 3941878 tid 3941963 thread 19 bound to OS proc set {30}
OMP: pid 3941878 tid 3941954 thread 10 bound to OS proc set {16}
OMP: pid 3941878 tid 3941977 thread 33 bound to OS proc set {53}
OMP: pid 3941878 tid 3941962 thread 18 bound to OS proc set {29}
OMP: pid 3941878 tid 3941983 thread 39 bound to OS proc set {63}
OMP: pid 3941878 tid 3941982 thread 38 bound to OS proc set {61}
OMP: pid 3941878 tid 3941957 thread 13 bound to OS proc set {21}
OMP: pid 3941878 tid 3941975 thread 31 bound to OS proc set {50}
OMP: pid 3941878 tid 3941972 thread 28 bound to OS proc set {45}
OMP: pid 3941878 tid 3941964 thread 20 bound to OS proc set {32}
OMP: pid 3941878 tid 3941955 thread 11 bound to OS proc set {17}
OMP: pid 3941878 tid 3941967 thread 23 bound to OS proc set {37}
OMP: pid 3941878 tid 3941960 thread 16 bound to OS proc set {26}
OMP: pid 3941878 tid 3941961 thread 17 bound to OS proc set {27}
OMP: pid 3941878 tid 3941974 thread 30 bound to OS proc set {48}
OMP: pid 3941878 tid 3941981 thread 37 bound to OS proc set {60}
OMP: pid 3941878 tid 3941973 thread 29 bound to OS proc set {47}
OMP: pid 3941878 tid 3941966 thread 22 bound to OS proc set {35}
OMP: pid 3941878 tid 3941968 thread 24 bound to OS proc set {39}
OMP: pid 3941878 tid 3941965 thread 21 bound to OS proc set {34}
OMP: pid 3941878 tid 3941970 thread 26 bound to OS proc set {42}
OMP: pid 3941878 tid 3941969 thread 25 bound to OS proc set {40}
OMP: pid 3941878 tid 3941971 thread 27 bound to OS proc set {43}
{"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": 128, "tg": 0, "pl": 1, "n_kv": 128, "t_pp": 5.109737, "speed_pp": 25.050213, "t_tg": 0.000000, "speed_tg": nan, "t": 5.109737, "speed": 25.050213}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/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-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_7 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_7 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_7 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_7 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_7 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_7 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_7 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_7 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 3950623 tid 3950623 thread 0 bound to OS proc set {0}
OMP: pid 3950623 tid 3950691 thread 2 bound to OS proc set {2}
OMP: pid 3950623 tid 3950690 thread 1 bound to OS proc set {1}
OMP: pid 3950623 tid 3950700 thread 11 bound to OS proc set {14}
OMP: pid 3950623 tid 3950697 thread 8 bound to OS proc set {10}
OMP: pid 3950623 tid 3950692 thread 3 bound to OS proc set {4}
OMP: pid 3950623 tid 3950699 thread 10 bound to OS proc set {13}
OMP: pid 3950623 tid 3950724 thread 35 bound to OS proc set {47}
OMP: pid 3950623 tid 3950701 thread 12 bound to OS proc set {16}
OMP: pid 3950623 tid 3950695 thread 6 bound to OS proc set {8}
OMP: pid 3950623 tid 3950722 thread 33 bound to OS proc set {44}
OMP: pid 3950623 tid 3950736 thread 47 bound to OS proc set {63}
OMP: pid 3950623 tid 3950720 thread 31 bound to OS proc set {41}
OMP: pid 3950623 tid 3950696 thread 7 bound to OS proc set {9}
OMP: pid 3950623 tid 3950702 thread 13 bound to OS proc set {17}
OMP: pid 3950623 tid 3950703 thread 14 bound to OS proc set {18}
OMP: pid 3950623 tid 3950716 thread 27 bound to OS proc set {36}
OMP: pid 3950623 tid 3950693 thread 4 bound to OS proc set {5}
OMP: pid 3950623 tid 3950694 thread 5 bound to OS proc set {6}
OMP: pid 3950623 tid 3950735 thread 46 bound to OS proc set {62}
OMP: pid 3950623 tid 3950721 thread 32 bound to OS proc set {43}
OMP: pid 3950623 tid 3950719 thread 30 bound to OS proc set {40}
OMP: pid 3950623 tid 3950723 thread 34 bound to OS proc set {46}
OMP: pid 3950623 tid 3950704 thread 15 bound to OS proc set {20}
OMP: pid 3950623 tid 3950733 thread 44 bound to OS proc set {59}
OMP: pid 3950623 tid 3950732 thread 43 bound to OS proc set {58}
OMP: pid 3950623 tid 3950715 thread 26 bound to OS proc set {35}
OMP: pid 3950623 tid 3950717 thread 28 bound to OS proc set {37}
OMP: pid 3950623 tid 3950718 thread 29 bound to OS proc set {39}
OMP: pid 3950623 tid 3950711 thread 22 bound to OS proc set {29}
OMP: pid 3950623 tid 3950729 thread 40 bound to OS proc set {54}
OMP: pid 3950623 tid 3950709 thread 20 bound to OS proc set {27}
OMP: pid 3950623 tid 3950714 thread 25 bound to OS proc set {33}
OMP: pid 3950623 tid 3950725 thread 36 bound to OS proc set {48}
OMP: pid 3950623 tid 3950698 thread 9 bound to OS proc set {12}
OMP: pid 3950623 tid 3950713 thread 24 bound to OS proc set {32}
OMP: pid 3950623 tid 3950708 thread 19 bound to OS proc set {25}
OMP: pid 3950623 tid 3950712 thread 23 bound to OS proc set {31}
OMP: pid 3950623 tid 3950707 thread 18 bound to OS proc set {24}
OMP: pid 3950623 tid 3950705 thread 16 bound to OS proc set {21}
OMP: pid 3950623 tid 3950710 thread 21 bound to OS proc set {28}
OMP: pid 3950623 tid 3950731 thread 42 bound to OS proc set {56}
OMP: pid 3950623 tid 3950730 thread 41 bound to OS proc set {55}
OMP: pid 3950623 tid 3950728 thread 39 bound to OS proc set {52}
OMP: pid 3950623 tid 3950726 thread 37 bound to OS proc set {50}
OMP: pid 3950623 tid 3950734 thread 45 bound to OS proc set {60}
OMP: pid 3950623 tid 3950727 thread 38 bound to OS proc set {51}
OMP: pid 3950623 tid 3950706 thread 17 bound to OS proc set {23}
{"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": 128, "tg": 0, "pl": 1, "n_kv": 128, "t_pp": 5.566083, "speed_pp": 22.996424, "t_tg": 0.000001, "speed_tg": 0.000000, "t": 5.566084, "speed": 22.996420}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/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-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_8 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_8 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_8 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_8 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_8 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_8 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_8 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_8 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 3961148 tid 3961148 thread 0 bound to OS proc set {0}
OMP: pid 3961148 tid 3961217 thread 3 bound to OS proc set {3}
OMP: pid 3961148 tid 3961216 thread 2 bound to OS proc set {2}
OMP: pid 3961148 tid 3961215 thread 1 bound to OS proc set {1}
OMP: pid 3961148 tid 3961218 thread 4 bound to OS proc set {4}
OMP: pid 3961148 tid 3961220 thread 6 bound to OS proc set {6}
OMP: pid 3961148 tid 3961219 thread 5 bound to OS proc set {5}
OMP: pid 3961148 tid 3961225 thread 11 bound to OS proc set {12}
OMP: pid 3961148 tid 3961224 thread 10 bound to OS proc set {11}
OMP: pid 3961148 tid 3961221 thread 7 bound to OS proc set {8}
OMP: pid 3961148 tid 3961226 thread 12 bound to OS proc set {13}
OMP: pid 3961148 tid 3961228 thread 14 bound to OS proc set {16}
OMP: pid 3961148 tid 3961263 thread 49 bound to OS proc set {56}
OMP: pid 3961148 tid 3961265 thread 51 bound to OS proc set {59}
OMP: pid 3961148 tid 3961230 thread 16 bound to OS proc set {18}
OMP: pid 3961148 tid 3961227 thread 13 bound to OS proc set {15}
OMP: pid 3961148 tid 3961264 thread 50 bound to OS proc set {58}
OMP: pid 3961148 tid 3961262 thread 48 bound to OS proc set {55}
OMP: pid 3961148 tid 3961223 thread 9 bound to OS proc set {10}
OMP: pid 3961148 tid 3961261 thread 47 bound to OS proc set {54}
OMP: pid 3961148 tid 3961269 thread 55 bound to OS proc set {63}
OMP: pid 3961148 tid 3961266 thread 52 bound to OS proc set {60}
OMP: pid 3961148 tid 3961257 thread 43 bound to OS proc set {49}
OMP: pid 3961148 tid 3961245 thread 31 bound to OS proc set {35}
OMP: pid 3961148 tid 3961241 thread 27 bound to OS proc set {31}
OMP: pid 3961148 tid 3961258 thread 44 bound to OS proc set {51}
OMP: pid 3961148 tid 3961268 thread 54 bound to OS proc set {62}
OMP: pid 3961148 tid 3961255 thread 41 bound to OS proc set {47}
OMP: pid 3961148 tid 3961246 thread 32 bound to OS proc set {37}
OMP: pid 3961148 tid 3961249 thread 35 bound to OS proc set {40}
OMP: pid 3961148 tid 3961238 thread 24 bound to OS proc set {27}
OMP: pid 3961148 tid 3961231 thread 17 bound to OS proc set {19}
OMP: pid 3961148 tid 3961240 thread 26 bound to OS proc set {30}
OMP: pid 3961148 tid 3961242 thread 28 bound to OS proc set {32}
OMP: pid 3961148 tid 3961222 thread 8 bound to OS proc set {9}
OMP: pid 3961148 tid 3961229 thread 15 bound to OS proc set {17}
OMP: pid 3961148 tid 3961243 thread 29 bound to OS proc set {33}
OMP: pid 3961148 tid 3961250 thread 36 bound to OS proc set {41}
OMP: pid 3961148 tid 3961234 thread 20 bound to OS proc set {23}
OMP: pid 3961148 tid 3961232 thread 18 bound to OS proc set {20}
OMP: pid 3961148 tid 3961237 thread 23 bound to OS proc set {26}
OMP: pid 3961148 tid 3961239 thread 25 bound to OS proc set {29}
OMP: pid 3961148 tid 3961233 thread 19 bound to OS proc set {22}
OMP: pid 3961148 tid 3961254 thread 40 bound to OS proc set {46}
OMP: pid 3961148 tid 3961248 thread 34 bound to OS proc set {39}
OMP: pid 3961148 tid 3961252 thread 38 bound to OS proc set {44}
OMP: pid 3961148 tid 3961236 thread 22 bound to OS proc set {25}
OMP: pid 3961148 tid 3961247 thread 33 bound to OS proc set {38}
OMP: pid 3961148 tid 3961235 thread 21 bound to OS proc set {24}
OMP: pid 3961148 tid 3961251 thread 37 bound to OS proc set {42}
OMP: pid 3961148 tid 3961259 thread 45 bound to OS proc set {52}
OMP: pid 3961148 tid 3961253 thread 39 bound to OS proc set {45}
OMP: pid 3961148 tid 3961244 thread 30 bound to OS proc set {34}
OMP: pid 3961148 tid 3961256 thread 42 bound to OS proc set {48}
OMP: pid 3961148 tid 3961267 thread 53 bound to OS proc set {61}
OMP: pid 3961148 tid 3961260 thread 46 bound to OS proc set {53}
{"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": 128, "tg": 0, "pl": 1, "n_kv": 128, "t_pp": 6.068693, "speed_pp": 21.091856, "t_tg": 0.000000, "speed_tg": nan, "t": 6.068693, "speed": 21.091856}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/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-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_9 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_9 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_9 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_9 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_9 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_9 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_9 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_9 #
#######################################################################################################################################################################################################################################
* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-46-37.ec2.internal.
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 3973496 tid 3973496 thread 0 bound to OS proc set {0}
OMP: pid 3973496 tid 3973565 thread 3 bound to OS proc set {3}
OMP: pid 3973496 tid 3973577 thread 15 bound to OS proc set {15}
OMP: pid 3973496 tid 3973564 thread 2 bound to OS proc set {2}
OMP: pid 3973496 tid 3973574 thread 12 bound to OS proc set {12}
OMP: pid 3973496 tid 3973573 thread 11 bound to OS proc set {11}
OMP: pid 3973496 tid 3973570 thread 8 bound to OS proc set {8}
OMP: pid 3973496 tid 3973563 thread 1 bound to OS proc set {1}
OMP: pid 3973496 tid 3973569 thread 7 bound to OS proc set {7}
OMP: pid 3973496 tid 3973590 thread 28 bound to OS proc set {28}
OMP: pid 3973496 tid 3973572 thread 10 bound to OS proc set {10}
OMP: pid 3973496 tid 3973566 thread 4 bound to OS proc set {4}
OMP: pid 3973496 tid 3973575 thread 13 bound to OS proc set {13}
OMP: pid 3973496 tid 3973581 thread 19 bound to OS proc set {19}
OMP: pid 3973496 tid 3973576 thread 14 bound to OS proc set {14}
OMP: pid 3973496 tid 3973578 thread 16 bound to OS proc set {16}
OMP: pid 3973496 tid 3973568 thread 6 bound to OS proc set {6}
OMP: pid 3973496 tid 3973580 thread 18 bound to OS proc set {18}
OMP: pid 3973496 tid 3973571 thread 9 bound to OS proc set {9}
OMP: pid 3973496 tid 3973591 thread 29 bound to OS proc set {29}
OMP: pid 3973496 tid 3973589 thread 27 bound to OS proc set {27}
OMP: pid 3973496 tid 3973567 thread 5 bound to OS proc set {5}
OMP: pid 3973496 tid 3973586 thread 24 bound to OS proc set {24}
OMP: pid 3973496 tid 3973579 thread 17 bound to OS proc set {17}
OMP: pid 3973496 tid 3973585 thread 23 bound to OS proc set {23}
OMP: pid 3973496 tid 3973588 thread 26 bound to OS proc set {26}
OMP: pid 3973496 tid 3973587 thread 25 bound to OS proc set {25}
OMP: pid 3973496 tid 3973584 thread 22 bound to OS proc set {22}
OMP: pid 3973496 tid 3973582 thread 20 bound to OS proc set {20}
OMP: pid 3973496 tid 3973594 thread 32 bound to OS proc set {32}
OMP: pid 3973496 tid 3973593 thread 31 bound to OS proc set {31}
OMP: pid 3973496 tid 3973597 thread 35 bound to OS proc set {35}
OMP: pid 3973496 tid 3973622 thread 60 bound to OS proc set {60}
OMP: pid 3973496 tid 3973609 thread 47 bound to OS proc set {47}
OMP: pid 3973496 tid 3973606 thread 44 bound to OS proc set {44}
OMP: pid 3973496 tid 3973625 thread 63 bound to OS proc set {63}
OMP: pid 3973496 tid 3973624 thread 62 bound to OS proc set {62}
OMP: pid 3973496 tid 3973610 thread 48 bound to OS proc set {48}
OMP: pid 3973496 tid 3973598 thread 36 bound to OS proc set {36}
OMP: pid 3973496 tid 3973602 thread 40 bound to OS proc set {40}
OMP: pid 3973496 tid 3973613 thread 51 bound to OS proc set {51}
OMP: pid 3973496 tid 3973605 thread 43 bound to OS proc set {43}
OMP: pid 3973496 tid 3973621 thread 59 bound to OS proc set {59}
OMP: pid 3973496 tid 3973608 thread 46 bound to OS proc set {46}
OMP: pid 3973496 tid 3973603 thread 41 bound to OS proc set {41}
OMP: pid 3973496 tid 3973618 thread 56 bound to OS proc set {56}
OMP: pid 3973496 tid 3973604 thread 42 bound to OS proc set {42}
OMP: pid 3973496 tid 3973601 thread 39 bound to OS proc set {39}
OMP: pid 3973496 tid 3973596 thread 34 bound to OS proc set {34}
OMP: pid 3973496 tid 3973619 thread 57 bound to OS proc set {57}
OMP: pid 3973496 tid 3973595 thread 33 bound to OS proc set {33}
OMP: pid 3973496 tid 3973599 thread 37 bound to OS proc set {37}
OMP: pid 3973496 tid 3973620 thread 58 bound to OS proc set {58}
OMP: pid 3973496 tid 3973600 thread 38 bound to OS proc set {38}
OMP: pid 3973496 tid 3973614 thread 52 bound to OS proc set {52}
OMP: pid 3973496 tid 3973612 thread 50 bound to OS proc set {50}
OMP: pid 3973496 tid 3973617 thread 55 bound to OS proc set {55}
OMP: pid 3973496 tid 3973616 thread 54 bound to OS proc set {54}
OMP: pid 3973496 tid 3973611 thread 49 bound to OS proc set {49}
OMP: pid 3973496 tid 3973592 thread 30 bound to OS proc set {30}
OMP: pid 3973496 tid 3973615 thread 53 bound to OS proc set {53}
OMP: pid 3973496 tid 3973623 thread 61 bound to OS proc set {61}
OMP: pid 3973496 tid 3973583 thread 21 bound to OS proc set {21}
OMP: pid 3973496 tid 3973607 thread 45 bound to OS proc set {45}
{"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": 128, "tg": 0, "pl": 1, "n_kv": 128, "t_pp": 8.745816, "speed_pp": 14.635570, "t_tg": 0.000001, "speed_tg": 0.000000, "t": 8.745817, "speed": 14.635568}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/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-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_10 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_10 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_10 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_10 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_10 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_10 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_10 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-26_15-16-18/tools/lprof_npsu_run_10 #
########################################################################################################################################################################################################################################
