* [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 868221 tid 868221 thread 0 bound to OS proc set {0}
OMP: pid 868221 tid 868320 thread 1 bound to OS proc set {24}
OMP: pid 868221 tid 868321 thread 2 bound to OS proc set {48}
OMP: pid 868221 tid 868322 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": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 3.903601, "speed_pp": 65.580475, "t_tg": 0.000000, "speed_tg": nan, "t": 3.903601, "speed": 65.580475}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 868342 tid 868342 thread 0 bound to OS proc set {0}
OMP: pid 868342 tid 868442 thread 2 bound to OS proc set {24}
OMP: pid 868342 tid 868443 thread 3 bound to OS proc set {36}
OMP: pid 868342 tid 868444 thread 4 bound to OS proc set {48}
OMP: pid 868342 tid 868441 thread 1 bound to OS proc set {12}
OMP: pid 868342 tid 868446 thread 6 bound to OS proc set {72}
OMP: pid 868342 tid 868445 thread 5 bound to OS proc set {60}
OMP: pid 868342 tid 868447 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": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 1.964428, "speed_pp": 130.317841, "t_tg": 0.000000, "speed_tg": nan, "t": 1.964428, "speed": 130.317841}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 868467 tid 868467 thread 0 bound to OS proc set {0}
OMP: pid 868467 tid 868567 thread 2 bound to OS proc set {12}
OMP: pid 868467 tid 868568 thread 3 bound to OS proc set {18}
OMP: pid 868467 tid 868577 thread 12 bound to OS proc set {72}
OMP: pid 868467 tid 868566 thread 1 bound to OS proc set {6}
OMP: pid 868467 tid 868579 thread 14 bound to OS proc set {84}
OMP: pid 868467 tid 868569 thread 4 bound to OS proc set {24}
OMP: pid 868467 tid 868576 thread 11 bound to OS proc set {66}
OMP: pid 868467 tid 868572 thread 7 bound to OS proc set {42}
OMP: pid 868467 tid 868573 thread 8 bound to OS proc set {48}
OMP: pid 868467 tid 868571 thread 6 bound to OS proc set {36}
OMP: pid 868467 tid 868578 thread 13 bound to OS proc set {78}
OMP: pid 868467 tid 868574 thread 9 bound to OS proc set {54}
OMP: pid 868467 tid 868570 thread 5 bound to OS proc set {30}
OMP: pid 868467 tid 868575 thread 10 bound to OS proc set {60}
OMP: pid 868467 tid 868580 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": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 1.001333, "speed_pp": 255.659210, "t_tg": 0.000000, "speed_tg": nan, "t": 1.001333, "speed": 255.659210}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 868600 tid 868600 thread 0 bound to OS proc set {0}
OMP: pid 868600 tid 868700 thread 2 bound to OS proc set {8}
OMP: pid 868600 tid 868702 thread 4 bound to OS proc set {16}
OMP: pid 868600 tid 868701 thread 3 bound to OS proc set {12}
OMP: pid 868600 tid 868699 thread 1 bound to OS proc set {4}
OMP: pid 868600 tid 868705 thread 7 bound to OS proc set {28}
OMP: pid 868600 tid 868713 thread 15 bound to OS proc set {60}
OMP: pid 868600 tid 868703 thread 5 bound to OS proc set {20}
OMP: pid 868600 tid 868714 thread 16 bound to OS proc set {64}
OMP: pid 868600 tid 868706 thread 8 bound to OS proc set {32}
OMP: pid 868600 tid 868709 thread 11 bound to OS proc set {44}
OMP: pid 868600 tid 868710 thread 12 bound to OS proc set {48}
OMP: pid 868600 tid 868717 thread 19 bound to OS proc set {76}
OMP: pid 868600 tid 868704 thread 6 bound to OS proc set {24}
OMP: pid 868600 tid 868711 thread 13 bound to OS proc set {52}
OMP: pid 868600 tid 868707 thread 9 bound to OS proc set {36}
OMP: pid 868600 tid 868708 thread 10 bound to OS proc set {40}
OMP: pid 868600 tid 868716 thread 18 bound to OS proc set {72}
OMP: pid 868600 tid 868718 thread 20 bound to OS proc set {80}
OMP: pid 868600 tid 868712 thread 14 bound to OS proc set {56}
OMP: pid 868600 tid 868720 thread 22 bound to OS proc set {88}
OMP: pid 868600 tid 868715 thread 17 bound to OS proc set {68}
OMP: pid 868600 tid 868721 thread 23 bound to OS proc set {92}
OMP: pid 868600 tid 868719 thread 21 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": 24, "n_threads_batch": 24, "pp": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 0.737832, "speed_pp": 346.962433, "t_tg": 0.000000, "speed_tg": nan, "t": 0.737832, "speed": 346.962433}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 868790 tid 868790 thread 0 bound to OS proc set {0}
OMP: pid 868790 tid 868895 thread 7 bound to OS proc set {21}
OMP: pid 868790 tid 868889 thread 1 bound to OS proc set {3}
OMP: pid 868790 tid 868903 thread 15 bound to OS proc set {45}
OMP: pid 868790 tid 868898 thread 10 bound to OS proc set {30}
OMP: pid 868790 tid 868892 thread 4 bound to OS proc set {12}
OMP: pid 868790 tid 868902 thread 14 bound to OS proc set {42}
OMP: pid 868790 tid 868891 thread 3 bound to OS proc set {9}
OMP: pid 868790 tid 868900 thread 12 bound to OS proc set {36}
OMP: pid 868790 tid 868890 thread 2 bound to OS proc set {6}
OMP: pid 868790 tid 868901 thread 13 bound to OS proc set {39}
OMP: pid 868790 tid 868918 thread 30 bound to OS proc set {90}
OMP: pid 868790 tid 868916 thread 28 bound to OS proc set {84}
OMP: pid 868790 tid 868906 thread 18 bound to OS proc set {54}
OMP: pid 868790 tid 868904 thread 16 bound to OS proc set {48}
OMP: pid 868790 tid 868893 thread 5 bound to OS proc set {15}
OMP: pid 868790 tid 868899 thread 11 bound to OS proc set {33}
OMP: pid 868790 tid 868894 thread 6 bound to OS proc set {18}
OMP: pid 868790 tid 868897 thread 9 bound to OS proc set {27}
OMP: pid 868790 tid 868915 thread 27 bound to OS proc set {81}
OMP: pid 868790 tid 868907 thread 19 bound to OS proc set {57}
OMP: pid 868790 tid 868917 thread 29 bound to OS proc set {87}
OMP: pid 868790 tid 868914 thread 26 bound to OS proc set {78}
OMP: pid 868790 tid 868919 thread 31 bound to OS proc set {93}
OMP: pid 868790 tid 868896 thread 8 bound to OS proc set {24}
OMP: pid 868790 tid 868905 thread 17 bound to OS proc set {51}
OMP: pid 868790 tid 868912 thread 24 bound to OS proc set {72}
OMP: pid 868790 tid 868913 thread 25 bound to OS proc set {75}
OMP: pid 868790 tid 868908 thread 20 bound to OS proc set {60}
OMP: pid 868790 tid 868911 thread 23 bound to OS proc set {69}
OMP: pid 868790 tid 868910 thread 22 bound to OS proc set {66}
OMP: pid 868790 tid 868909 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": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 0.586789, "speed_pp": 436.272644, "t_tg": 0.000000, "speed_tg": nan, "t": 0.586789, "speed": 436.272644}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 868939 tid 868939 thread 0 bound to OS proc set {0}
OMP: pid 868939 tid 869052 thread 15 bound to OS proc set {36}
OMP: pid 868939 tid 869072 thread 35 bound to OS proc set {84}
OMP: pid 868939 tid 869069 thread 32 bound to OS proc set {77}
OMP: pid 868939 tid 869051 thread 14 bound to OS proc set {33}
OMP: pid 868939 tid 869038 thread 1 bound to OS proc set {2}
OMP: pid 868939 tid 869040 thread 3 bound to OS proc set {7}
OMP: pid 868939 tid 869073 thread 36 bound to OS proc set {87}
OMP: pid 868939 tid 869071 thread 34 bound to OS proc set {82}
OMP: pid 868939 tid 869044 thread 7 bound to OS proc set {16}
OMP: pid 868939 tid 869039 thread 2 bound to OS proc set {4}
OMP: pid 868939 tid 869053 thread 16 bound to OS proc set {38}
OMP: pid 868939 tid 869075 thread 38 bound to OS proc set {92}
OMP: pid 868939 tid 869042 thread 5 bound to OS proc set {12}
OMP: pid 868939 tid 869041 thread 4 bound to OS proc set {9}
OMP: pid 868939 tid 869046 thread 9 bound to OS proc set {21}
OMP: pid 868939 tid 869076 thread 39 bound to OS proc set {94}
OMP: pid 868939 tid 869068 thread 31 bound to OS proc set {75}
OMP: pid 868939 tid 869070 thread 33 bound to OS proc set {80}
OMP: pid 868939 tid 869045 thread 8 bound to OS proc set {19}
OMP: pid 868939 tid 869043 thread 6 bound to OS proc set {14}
OMP: pid 868939 tid 869047 thread 10 bound to OS proc set {24}
OMP: pid 868939 tid 869049 thread 12 bound to OS proc set {29}
OMP: pid 868939 tid 869048 thread 11 bound to OS proc set {26}
OMP: pid 868939 tid 869055 thread 18 bound to OS proc set {43}
OMP: pid 868939 tid 869074 thread 37 bound to OS proc set {89}
OMP: pid 868939 tid 869064 thread 27 bound to OS proc set {65}
OMP: pid 868939 tid 869062 thread 25 bound to OS proc set {60}
OMP: pid 868939 tid 869061 thread 24 bound to OS proc set {58}
OMP: pid 868939 tid 869063 thread 26 bound to OS proc set {63}
OMP: pid 868939 tid 869054 thread 17 bound to OS proc set {41}
OMP: pid 868939 tid 869065 thread 28 bound to OS proc set {67}
OMP: pid 868939 tid 869056 thread 19 bound to OS proc set {46}
OMP: pid 868939 tid 869050 thread 13 bound to OS proc set {31}
OMP: pid 868939 tid 869066 thread 29 bound to OS proc set {70}
OMP: pid 868939 tid 869067 thread 30 bound to OS proc set {72}
OMP: pid 868939 tid 869060 thread 23 bound to OS proc set {55}
OMP: pid 868939 tid 869059 thread 22 bound to OS proc set {53}
OMP: pid 868939 tid 869057 thread 20 bound to OS proc set {48}
OMP: pid 868939 tid 869058 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": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 0.501877, "speed_pp": 510.085144, "t_tg": 0.000000, "speed_tg": nan, "t": 0.501877, "speed": 510.085144}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 869096 tid 869096 thread 0 bound to OS proc set {0}
OMP: pid 869096 tid 869209 thread 15 bound to OS proc set {30}
OMP: pid 869096 tid 869205 thread 11 bound to OS proc set {22}
OMP: pid 869096 tid 869195 thread 1 bound to OS proc set {2}
OMP: pid 869096 tid 869197 thread 3 bound to OS proc set {6}
OMP: pid 869096 tid 869200 thread 6 bound to OS proc set {12}
OMP: pid 869096 tid 869202 thread 8 bound to OS proc set {16}
OMP: pid 869096 tid 869210 thread 16 bound to OS proc set {32}
OMP: pid 869096 tid 869207 thread 13 bound to OS proc set {26}
OMP: pid 869096 tid 869201 thread 7 bound to OS proc set {14}
OMP: pid 869096 tid 869196 thread 2 bound to OS proc set {4}
OMP: pid 869096 tid 869199 thread 5 bound to OS proc set {10}
OMP: pid 869096 tid 869229 thread 35 bound to OS proc set {70}
OMP: pid 869096 tid 869240 thread 46 bound to OS proc set {92}
OMP: pid 869096 tid 869238 thread 44 bound to OS proc set {88}
OMP: pid 869096 tid 869218 thread 24 bound to OS proc set {48}
OMP: pid 869096 tid 869206 thread 12 bound to OS proc set {24}
OMP: pid 869096 tid 869241 thread 47 bound to OS proc set {94}
OMP: pid 869096 tid 869208 thread 14 bound to OS proc set {28}
OMP: pid 869096 tid 869226 thread 32 bound to OS proc set {64}
OMP: pid 869096 tid 869217 thread 23 bound to OS proc set {46}
OMP: pid 869096 tid 869239 thread 45 bound to OS proc set {90}
OMP: pid 869096 tid 869225 thread 31 bound to OS proc set {62}
OMP: pid 869096 tid 869222 thread 28 bound to OS proc set {56}
OMP: pid 869096 tid 869203 thread 9 bound to OS proc set {18}
OMP: pid 869096 tid 869228 thread 34 bound to OS proc set {68}
OMP: pid 869096 tid 869198 thread 4 bound to OS proc set {8}
OMP: pid 869096 tid 869211 thread 17 bound to OS proc set {34}
OMP: pid 869096 tid 869224 thread 30 bound to OS proc set {60}
OMP: pid 869096 tid 869221 thread 27 bound to OS proc set {54}
OMP: pid 869096 tid 869204 thread 10 bound to OS proc set {20}
OMP: pid 869096 tid 869212 thread 18 bound to OS proc set {36}
OMP: pid 869096 tid 869214 thread 20 bound to OS proc set {40}
OMP: pid 869096 tid 869216 thread 22 bound to OS proc set {44}
OMP: pid 869096 tid 869220 thread 26 bound to OS proc set {52}
OMP: pid 869096 tid 869219 thread 25 bound to OS proc set {50}
OMP: pid 869096 tid 869227 thread 33 bound to OS proc set {66}
OMP: pid 869096 tid 869237 thread 43 bound to OS proc set {86}
OMP: pid 869096 tid 869233 thread 39 bound to OS proc set {78}
OMP: pid 869096 tid 869234 thread 40 bound to OS proc set {80}
OMP: pid 869096 tid 869230 thread 36 bound to OS proc set {72}
OMP: pid 869096 tid 869232 thread 38 bound to OS proc set {76}
OMP: pid 869096 tid 869236 thread 42 bound to OS proc set {84}
OMP: pid 869096 tid 869213 thread 19 bound to OS proc set {38}
OMP: pid 869096 tid 869235 thread 41 bound to OS proc set {82}
OMP: pid 869096 tid 869215 thread 21 bound to OS proc set {42}
OMP: pid 869096 tid 869223 thread 29 bound to OS proc set {58}
OMP: pid 869096 tid 869231 thread 37 bound to OS proc set {74}
{"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": 2, "n_kv": 256, "t_pp": 0.440170, "speed_pp": 581.593506, "t_tg": 0.000000, "speed_tg": nan, "t": 0.440170, "speed": 581.593506}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 869261 tid 869261 thread 0 bound to OS proc set {0}
OMP: pid 869261 tid 869360 thread 1 bound to OS proc set {1}
OMP: pid 869261 tid 869361 thread 2 bound to OS proc set {3}
OMP: pid 869261 tid 869414 thread 55 bound to OS proc set {95}
OMP: pid 869261 tid 869391 thread 32 bound to OS proc set {55}
OMP: pid 869261 tid 869410 thread 51 bound to OS proc set {88}
OMP: pid 869261 tid 869407 thread 48 bound to OS proc set {83}
OMP: pid 869261 tid 869366 thread 7 bound to OS proc set {12}
OMP: pid 869261 tid 869367 thread 8 bound to OS proc set {13}
OMP: pid 869261 tid 869411 thread 52 bound to OS proc set {90}
OMP: pid 869261 tid 869365 thread 6 bound to OS proc set {10}
OMP: pid 869261 tid 869390 thread 31 bound to OS proc set {53}
OMP: pid 869261 tid 869363 thread 4 bound to OS proc set {6}
OMP: pid 869261 tid 869409 thread 50 bound to OS proc set {86}
OMP: pid 869261 tid 869413 thread 54 bound to OS proc set {93}
OMP: pid 869261 tid 869374 thread 15 bound to OS proc set {25}
OMP: pid 869261 tid 869378 thread 19 bound to OS proc set {32}
OMP: pid 869261 tid 869387 thread 28 bound to OS proc set {48}
OMP: pid 869261 tid 869370 thread 11 bound to OS proc set {19}
OMP: pid 869261 tid 869386 thread 27 bound to OS proc set {46}
OMP: pid 869261 tid 869362 thread 3 bound to OS proc set {5}
OMP: pid 869261 tid 869368 thread 9 bound to OS proc set {15}
OMP: pid 869261 tid 869394 thread 35 bound to OS proc set {60}
OMP: pid 869261 tid 869369 thread 10 bound to OS proc set {17}
OMP: pid 869261 tid 869389 thread 30 bound to OS proc set {51}
OMP: pid 869261 tid 869406 thread 47 bound to OS proc set {81}
OMP: pid 869261 tid 869408 thread 49 bound to OS proc set {84}
OMP: pid 869261 tid 869388 thread 29 bound to OS proc set {50}
OMP: pid 869261 tid 869364 thread 5 bound to OS proc set {8}
OMP: pid 869261 tid 869393 thread 34 bound to OS proc set {58}
OMP: pid 869261 tid 869377 thread 18 bound to OS proc set {31}
OMP: pid 869261 tid 869385 thread 26 bound to OS proc set {45}
OMP: pid 869261 tid 869402 thread 43 bound to OS proc set {74}
OMP: pid 869261 tid 869373 thread 14 bound to OS proc set {24}
OMP: pid 869261 tid 869392 thread 33 bound to OS proc set {57}
OMP: pid 869261 tid 869403 thread 44 bound to OS proc set {76}
OMP: pid 869261 tid 869380 thread 21 bound to OS proc set {36}
OMP: pid 869261 tid 869376 thread 17 bound to OS proc set {29}
OMP: pid 869261 tid 869384 thread 25 bound to OS proc set {43}
OMP: pid 869261 tid 869398 thread 39 bound to OS proc set {67}
OMP: pid 869261 tid 869371 thread 12 bound to OS proc set {20}
OMP: pid 869261 tid 869375 thread 16 bound to OS proc set {27}
OMP: pid 869261 tid 869412 thread 53 bound to OS proc set {91}
OMP: pid 869261 tid 869395 thread 36 bound to OS proc set {62}
OMP: pid 869261 tid 869383 thread 24 bound to OS proc set {41}
OMP: pid 869261 tid 869405 thread 46 bound to OS proc set {79}
OMP: pid 869261 tid 869397 thread 38 bound to OS proc set {65}
OMP: pid 869261 tid 869399 thread 40 bound to OS proc set {69}
OMP: pid 869261 tid 869404 thread 45 bound to OS proc set {77}
OMP: pid 869261 tid 869379 thread 20 bound to OS proc set {34}
OMP: pid 869261 tid 869401 thread 42 bound to OS proc set {72}
OMP: pid 869261 tid 869382 thread 23 bound to OS proc set {39}
OMP: pid 869261 tid 869381 thread 22 bound to OS proc set {38}
OMP: pid 869261 tid 869400 thread 41 bound to OS proc set {71}
OMP: pid 869261 tid 869396 thread 37 bound to OS proc set {64}
OMP: pid 869261 tid 869372 thread 13 bound to OS proc set {22}
{"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": 2, "n_kv": 256, "t_pp": 0.395621, "speed_pp": 647.083923, "t_tg": 0.000000, "speed_tg": nan, "t": 0.395621, "speed": 647.083923}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 869434 tid 869434 thread 0 bound to OS proc set {0}
OMP: pid 869434 tid 869533 thread 1 bound to OS proc set {1}
OMP: pid 869434 tid 869540 thread 8 bound to OS proc set {12}
OMP: pid 869434 tid 869539 thread 7 bound to OS proc set {10}
OMP: pid 869434 tid 869541 thread 9 bound to OS proc set {13}
OMP: pid 869434 tid 869534 thread 2 bound to OS proc set {3}
OMP: pid 869434 tid 869547 thread 15 bound to OS proc set {22}
OMP: pid 869434 tid 869535 thread 3 bound to OS proc set {4}
OMP: pid 869434 tid 869542 thread 10 bound to OS proc set {15}
OMP: pid 869434 tid 869543 thread 11 bound to OS proc set {16}
OMP: pid 869434 tid 869595 thread 63 bound to OS proc set {95}
OMP: pid 869434 tid 869592 thread 60 bound to OS proc set {90}
OMP: pid 869434 tid 869576 thread 44 bound to OS proc set {66}
OMP: pid 869434 tid 869594 thread 62 bound to OS proc set {93}
OMP: pid 869434 tid 869536 thread 4 bound to OS proc set {6}
OMP: pid 869434 tid 869566 thread 34 bound to OS proc set {51}
OMP: pid 869434 tid 869583 thread 51 bound to OS proc set {77}
OMP: pid 869434 tid 869579 thread 47 bound to OS proc set {71}
OMP: pid 869434 tid 869537 thread 5 bound to OS proc set {7}
OMP: pid 869434 tid 869567 thread 35 bound to OS proc set {53}
OMP: pid 869434 tid 869545 thread 13 bound to OS proc set {19}
OMP: pid 869434 tid 869591 thread 59 bound to OS proc set {89}
OMP: pid 869434 tid 869538 thread 6 bound to OS proc set {9}
OMP: pid 869434 tid 869550 thread 18 bound to OS proc set {27}
OMP: pid 869434 tid 869561 thread 29 bound to OS proc set {43}
OMP: pid 869434 tid 869563 thread 31 bound to OS proc set {46}
OMP: pid 869434 tid 869593 thread 61 bound to OS proc set {92}
OMP: pid 869434 tid 869555 thread 23 bound to OS proc set {34}
OMP: pid 869434 tid 869551 thread 19 bound to OS proc set {28}
OMP: pid 869434 tid 869558 thread 26 bound to OS proc set {39}
OMP: pid 869434 tid 869560 thread 28 bound to OS proc set {42}
OMP: pid 869434 tid 869568 thread 36 bound to OS proc set {54}
OMP: pid 869434 tid 869580 thread 48 bound to OS proc set {72}
OMP: pid 869434 tid 869575 thread 43 bound to OS proc set {65}
OMP: pid 869434 tid 869556 thread 24 bound to OS proc set {36}
OMP: pid 869434 tid 869571 thread 39 bound to OS proc set {59}
OMP: pid 869434 tid 869553 thread 21 bound to OS proc set {31}
OMP: pid 869434 tid 869564 thread 32 bound to OS proc set {48}
OMP: pid 869434 tid 869578 thread 46 bound to OS proc set {69}
OMP: pid 869434 tid 869562 thread 30 bound to OS proc set {45}
OMP: pid 869434 tid 869570 thread 38 bound to OS proc set {57}
OMP: pid 869434 tid 869572 thread 40 bound to OS proc set {60}
OMP: pid 869434 tid 869565 thread 33 bound to OS proc set {50}
OMP: pid 869434 tid 869549 thread 17 bound to OS proc set {25}
OMP: pid 869434 tid 869546 thread 14 bound to OS proc set {21}
OMP: pid 869434 tid 869573 thread 41 bound to OS proc set {62}
OMP: pid 869434 tid 869588 thread 56 bound to OS proc set {84}
OMP: pid 869434 tid 869544 thread 12 bound to OS proc set {18}
OMP: pid 869434 tid 869569 thread 37 bound to OS proc set {56}
OMP: pid 869434 tid 869557 thread 25 bound to OS proc set {37}
OMP: pid 869434 tid 869559 thread 27 bound to OS proc set {40}
OMP: pid 869434 tid 869574 thread 42 bound to OS proc set {63}
OMP: pid 869434 tid 869584 thread 52 bound to OS proc set {78}
OMP: pid 869434 tid 869548 thread 16 bound to OS proc set {24}
OMP: pid 869434 tid 869582 thread 50 bound to OS proc set {75}
OMP: pid 869434 tid 869581 thread 49 bound to OS proc set {74}
OMP: pid 869434 tid 869552 thread 20 bound to OS proc set {30}
OMP: pid 869434 tid 869554 thread 22 bound to OS proc set {33}
OMP: pid 869434 tid 869587 thread 55 bound to OS proc set {83}
OMP: pid 869434 tid 869586 thread 54 bound to OS proc set {81}
OMP: pid 869434 tid 869585 thread 53 bound to OS proc set {80}
OMP: pid 869434 tid 869577 thread 45 bound to OS proc set {68}
OMP: pid 869434 tid 869589 thread 57 bound to OS proc set {86}
OMP: pid 869434 tid 869590 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": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 0.358762, "speed_pp": 713.565002, "t_tg": 0.000000, "speed_tg": nan, "t": 0.358762, "speed": 713.565002}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 869615 tid 869615 thread 0 bound to OS proc set {0}
OMP: pid 869615 tid 869715 thread 2 bound to OS proc set {2}
OMP: pid 869615 tid 869714 thread 1 bound to OS proc set {1}
OMP: pid 869615 tid 869724 thread 11 bound to OS proc set {14}
OMP: pid 869615 tid 869764 thread 51 bound to OS proc set {68}
OMP: pid 869615 tid 869761 thread 48 bound to OS proc set {64}
OMP: pid 869615 tid 869780 thread 67 bound to OS proc set {90}
OMP: pid 869615 tid 869777 thread 64 bound to OS proc set {86}
OMP: pid 869615 tid 869779 thread 66 bound to OS proc set {88}
OMP: pid 869615 tid 869748 thread 35 bound to OS proc set {47}
OMP: pid 869615 tid 869784 thread 71 bound to OS proc set {95}
OMP: pid 869615 tid 869783 thread 70 bound to OS proc set {94}
OMP: pid 869615 tid 869781 thread 68 bound to OS proc set {91}
OMP: pid 869615 tid 869719 thread 6 bound to OS proc set {8}
OMP: pid 869615 tid 869778 thread 65 bound to OS proc set {87}
OMP: pid 869615 tid 869746 thread 33 bound to OS proc set {44}
OMP: pid 869615 tid 869721 thread 8 bound to OS proc set {10}
OMP: pid 869615 tid 869776 thread 63 bound to OS proc set {84}
OMP: pid 869615 tid 869763 thread 50 bound to OS proc set {67}
OMP: pid 869615 tid 869772 thread 59 bound to OS proc set {79}
OMP: pid 869615 tid 869725 thread 12 bound to OS proc set {16}
OMP: pid 869615 tid 869744 thread 31 bound to OS proc set {41}
OMP: pid 869615 tid 869716 thread 3 bound to OS proc set {4}
OMP: pid 869615 tid 869747 thread 34 bound to OS proc set {45}
OMP: pid 869615 tid 869756 thread 43 bound to OS proc set {57}
OMP: pid 869615 tid 869727 thread 14 bound to OS proc set {18}
OMP: pid 869615 tid 869743 thread 30 bound to OS proc set {40}
OMP: pid 869615 tid 869720 thread 7 bound to OS proc set {9}
OMP: pid 869615 tid 869723 thread 10 bound to OS proc set {13}
OMP: pid 869615 tid 869757 thread 44 bound to OS proc set {59}
OMP: pid 869615 tid 869759 thread 46 bound to OS proc set {61}
OMP: pid 869615 tid 869760 thread 47 bound to OS proc set {63}
OMP: pid 869615 tid 869717 thread 4 bound to OS proc set {5}
OMP: pid 869615 tid 869736 thread 23 bound to OS proc set {30}
OMP: pid 869615 tid 869722 thread 9 bound to OS proc set {12}
OMP: pid 869615 tid 869749 thread 36 bound to OS proc set {48}
OMP: pid 869615 tid 869762 thread 49 bound to OS proc set {66}
OMP: pid 869615 tid 869752 thread 39 bound to OS proc set {52}
OMP: pid 869615 tid 869741 thread 28 bound to OS proc set {37}
OMP: pid 869615 tid 869742 thread 29 bound to OS proc set {39}
OMP: pid 869615 tid 869782 thread 69 bound to OS proc set {92}
OMP: pid 869615 tid 869745 thread 32 bound to OS proc set {43}
OMP: pid 869615 tid 869767 thread 54 bound to OS proc set {72}
OMP: pid 869615 tid 869751 thread 38 bound to OS proc set {51}
OMP: pid 869615 tid 869731 thread 18 bound to OS proc set {24}
OMP: pid 869615 tid 869726 thread 13 bound to OS proc set {17}
OMP: pid 869615 tid 869773 thread 60 bound to OS proc set {80}
OMP: pid 869615 tid 869718 thread 5 bound to OS proc set {6}
OMP: pid 869615 tid 869754 thread 41 bound to OS proc set {55}
OMP: pid 869615 tid 869740 thread 27 bound to OS proc set {36}
OMP: pid 869615 tid 869768 thread 55 bound to OS proc set {74}
OMP: pid 869615 tid 869730 thread 17 bound to OS proc set {22}
OMP: pid 869615 tid 869728 thread 15 bound to OS proc set {20}
OMP: pid 869615 tid 869737 thread 24 bound to OS proc set {32}
OMP: pid 869615 tid 869733 thread 20 bound to OS proc set {26}
OMP: pid 869615 tid 869769 thread 56 bound to OS proc set {75}
OMP: pid 869615 tid 869738 thread 25 bound to OS proc set {33}
OMP: pid 869615 tid 869739 thread 26 bound to OS proc set {35}
OMP: pid 869615 tid 869753 thread 40 bound to OS proc set {53}
OMP: pid 869615 tid 869735 thread 22 bound to OS proc set {29}
OMP: pid 869615 tid 869758 thread 45 bound to OS proc set {60}
OMP: pid 869615 tid 869750 thread 37 bound to OS proc set {49}
OMP: pid 869615 tid 869732 thread 19 bound to OS proc set {25}
OMP: pid 869615 tid 869765 thread 52 bound to OS proc set {70}
OMP: pid 869615 tid 869771 thread 58 bound to OS proc set {78}
OMP: pid 869615 tid 869774 thread 61 bound to OS proc set {82}
OMP: pid 869615 tid 869775 thread 62 bound to OS proc set {83}
OMP: pid 869615 tid 869734 thread 21 bound to OS proc set {28}
OMP: pid 869615 tid 869766 thread 53 bound to OS proc set {71}
OMP: pid 869615 tid 869729 thread 16 bound to OS proc set {21}
OMP: pid 869615 tid 869755 thread 42 bound to OS proc set {56}
OMP: pid 869615 tid 869770 thread 57 bound to OS proc set {76}
{"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": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 0.335161, "speed_pp": 763.812012, "t_tg": 0.000000, "speed_tg": nan, "t": 0.335161, "speed": 763.812012}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 869852 tid 869852 thread 0 bound to OS proc set {0}
OMP: pid 869852 tid 869952 thread 2 bound to OS proc set {2}
OMP: pid 869852 tid 869953 thread 3 bound to OS proc set {3}
OMP: pid 869852 tid 869951 thread 1 bound to OS proc set {1}
OMP: pid 869852 tid 869954 thread 4 bound to OS proc set {4}
OMP: pid 869852 tid 870016 thread 66 bound to OS proc set {80}
OMP: pid 869852 tid 870000 thread 50 bound to OS proc set {60}
OMP: pid 869852 tid 870006 thread 56 bound to OS proc set {67}
OMP: pid 869852 tid 870017 thread 67 bound to OS proc set {81}
OMP: pid 869852 tid 870001 thread 51 bound to OS proc set {61}
OMP: pid 869852 tid 870014 thread 64 bound to OS proc set {77}
OMP: pid 869852 tid 870029 thread 79 bound to OS proc set {95}
OMP: pid 869852 tid 870013 thread 63 bound to OS proc set {76}
OMP: pid 869852 tid 869957 thread 7 bound to OS proc set {8}
OMP: pid 869852 tid 869962 thread 12 bound to OS proc set {14}
OMP: pid 869852 tid 870010 thread 60 bound to OS proc set {72}
OMP: pid 869852 tid 869999 thread 49 bound to OS proc set {59}
OMP: pid 869852 tid 869966 thread 16 bound to OS proc set {19}
OMP: pid 869852 tid 870028 thread 78 bound to OS proc set {94}
OMP: pid 869852 tid 869964 thread 14 bound to OS proc set {16}
OMP: pid 869852 tid 869956 thread 6 bound to OS proc set {7}
OMP: pid 869852 tid 869993 thread 43 bound to OS proc set {52}
OMP: pid 869852 tid 870026 thread 76 bound to OS proc set {92}
OMP: pid 869852 tid 869965 thread 15 bound to OS proc set {18}
OMP: pid 869852 tid 870005 thread 55 bound to OS proc set {66}
OMP: pid 869852 tid 869961 thread 11 bound to OS proc set {13}
OMP: pid 869852 tid 869997 thread 47 bound to OS proc set {56}
OMP: pid 869852 tid 870012 thread 62 bound to OS proc set {75}
OMP: pid 869852 tid 869994 thread 44 bound to OS proc set {53}
OMP: pid 869852 tid 870011 thread 61 bound to OS proc set {73}
OMP: pid 869852 tid 869958 thread 8 bound to OS proc set {9}
OMP: pid 869852 tid 869974 thread 24 bound to OS proc set {29}
OMP: pid 869852 tid 869996 thread 46 bound to OS proc set {55}
OMP: pid 869852 tid 869960 thread 10 bound to OS proc set {12}
OMP: pid 869852 tid 869998 thread 48 bound to OS proc set {58}
OMP: pid 869852 tid 869976 thread 26 bound to OS proc set {31}
OMP: pid 869852 tid 869979 thread 29 bound to OS proc set {35}
OMP: pid 869852 tid 869977 thread 27 bound to OS proc set {32}
OMP: pid 869852 tid 869992 thread 42 bound to OS proc set {50}
OMP: pid 869852 tid 869985 thread 35 bound to OS proc set {42}
OMP: pid 869852 tid 869970 thread 20 bound to OS proc set {24}
OMP: pid 869852 tid 869989 thread 39 bound to OS proc set {47}
OMP: pid 869852 tid 870004 thread 54 bound to OS proc set {65}
OMP: pid 869852 tid 869955 thread 5 bound to OS proc set {6}
OMP: pid 869852 tid 869967 thread 17 bound to OS proc set {20}
OMP: pid 869852 tid 869972 thread 22 bound to OS proc set {26}
OMP: pid 869852 tid 870009 thread 59 bound to OS proc set {71}
OMP: pid 869852 tid 870025 thread 75 bound to OS proc set {90}
OMP: pid 869852 tid 870018 thread 68 bound to OS proc set {82}
OMP: pid 869852 tid 870021 thread 71 bound to OS proc set {86}
OMP: pid 869852 tid 869984 thread 34 bound to OS proc set {41}
OMP: pid 869852 tid 869959 thread 9 bound to OS proc set {10}
OMP: pid 869852 tid 870015 thread 65 bound to OS proc set {78}
OMP: pid 869852 tid 869963 thread 13 bound to OS proc set {15}
OMP: pid 869852 tid 870003 thread 53 bound to OS proc set {64}
OMP: pid 869852 tid 870007 thread 57 bound to OS proc set {69}
OMP: pid 869852 tid 869982 thread 32 bound to OS proc set {38}
OMP: pid 869852 tid 869978 thread 28 bound to OS proc set {33}
OMP: pid 869852 tid 869988 thread 38 bound to OS proc set {46}
OMP: pid 869852 tid 870024 thread 74 bound to OS proc set {89}
OMP: pid 869852 tid 869995 thread 45 bound to OS proc set {54}
OMP: pid 869852 tid 869980 thread 30 bound to OS proc set {36}
OMP: pid 869852 tid 870022 thread 72 bound to OS proc set {87}
OMP: pid 869852 tid 870008 thread 58 bound to OS proc set {70}
OMP: pid 869852 tid 869969 thread 19 bound to OS proc set {23}
OMP: pid 869852 tid 869991 thread 41 bound to OS proc set {49}
OMP: pid 869852 tid 869986 thread 36 bound to OS proc set {43}
OMP: pid 869852 tid 869968 thread 18 bound to OS proc set {21}
OMP: pid 869852 tid 869987 thread 37 bound to OS proc set {44}
OMP: pid 869852 tid 869975 thread 25 bound to OS proc set {30}
OMP: pid 869852 tid 869981 thread 31 bound to OS proc set {37}
OMP: pid 869852 tid 869971 thread 21 bound to OS proc set {25}
OMP: pid 869852 tid 870002 thread 52 bound to OS proc set {63}
OMP: pid 869852 tid 869973 thread 23 bound to OS proc set {27}
OMP: pid 869852 tid 869983 thread 33 bound to OS proc set {40}
OMP: pid 869852 tid 870027 thread 77 bound to OS proc set {93}
OMP: pid 869852 tid 870020 thread 70 bound to OS proc set {84}
OMP: pid 869852 tid 870023 thread 73 bound to OS proc set {88}
OMP: pid 869852 tid 870019 thread 69 bound to OS proc set {83}
OMP: pid 869852 tid 869990 thread 40 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": 80, "n_threads_batch": 80, "pp": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 0.318161, "speed_pp": 804.624023, "t_tg": 0.000000, "speed_tg": nan, "t": 0.318161, "speed": 804.624023}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 870049 tid 870049 thread 0 bound to OS proc set {0}
OMP: pid 870049 tid 870150 thread 3 bound to OS proc set {3}
OMP: pid 870049 tid 870149 thread 2 bound to OS proc set {2}
OMP: pid 870049 tid 870155 thread 8 bound to OS proc set {8}
OMP: pid 870049 tid 870195 thread 48 bound to OS proc set {52}
OMP: pid 870049 tid 870175 thread 28 bound to OS proc set {30}
OMP: pid 870049 tid 870151 thread 4 bound to OS proc set {4}
OMP: pid 870049 tid 870154 thread 7 bound to OS proc set {7}
OMP: pid 870049 tid 870166 thread 19 bound to OS proc set {20}
OMP: pid 870049 tid 870148 thread 1 bound to OS proc set {1}
OMP: pid 870049 tid 870153 thread 6 bound to OS proc set {6}
OMP: pid 870049 tid 870165 thread 18 bound to OS proc set {19}
OMP: pid 870049 tid 870174 thread 27 bound to OS proc set {29}
OMP: pid 870049 tid 870156 thread 9 bound to OS proc set {9}
OMP: pid 870049 tid 870194 thread 47 bound to OS proc set {51}
OMP: pid 870049 tid 870176 thread 29 bound to OS proc set {31}
OMP: pid 870049 tid 870152 thread 5 bound to OS proc set {5}
OMP: pid 870049 tid 870164 thread 17 bound to OS proc set {18}
OMP: pid 870049 tid 870173 thread 26 bound to OS proc set {28}
OMP: pid 870049 tid 870191 thread 44 bound to OS proc set {48}
OMP: pid 870049 tid 870193 thread 46 bound to OS proc set {50}
OMP: pid 870049 tid 870161 thread 14 bound to OS proc set {15}
OMP: pid 870049 tid 870172 thread 25 bound to OS proc set {27}
OMP: pid 870049 tid 870226 thread 79 bound to OS proc set {87}
OMP: pid 870049 tid 870190 thread 43 bound to OS proc set {47}
OMP: pid 870049 tid 870197 thread 50 bound to OS proc set {55}
OMP: pid 870049 tid 870185 thread 38 bound to OS proc set {41}
OMP: pid 870049 tid 870223 thread 76 bound to OS proc set {83}
OMP: pid 870049 tid 870187 thread 40 bound to OS proc set {44}
OMP: pid 870049 tid 870159 thread 12 bound to OS proc set {13}
OMP: pid 870049 tid 870192 thread 45 bound to OS proc set {49}
OMP: pid 870049 tid 870183 thread 36 bound to OS proc set {39}
OMP: pid 870049 tid 870189 thread 42 bound to OS proc set {46}
OMP: pid 870049 tid 870157 thread 10 bound to OS proc set {11}
OMP: pid 870049 tid 870214 thread 67 bound to OS proc set {73}
OMP: pid 870049 tid 870188 thread 41 bound to OS proc set {45}
OMP: pid 870049 tid 870162 thread 15 bound to OS proc set {16}
OMP: pid 870049 tid 870209 thread 62 bound to OS proc set {68}
OMP: pid 870049 tid 870184 thread 37 bound to OS proc set {40}
OMP: pid 870049 tid 870207 thread 60 bound to OS proc set {66}
OMP: pid 870049 tid 870222 thread 75 bound to OS proc set {82}
OMP: pid 870049 tid 870177 thread 30 bound to OS proc set {33}
OMP: pid 870049 tid 870202 thread 55 bound to OS proc set {60}
OMP: pid 870049 tid 870206 thread 59 bound to OS proc set {65}
OMP: pid 870049 tid 870198 thread 51 bound to OS proc set {56}
OMP: pid 870049 tid 870218 thread 71 bound to OS proc set {78}
OMP: pid 870049 tid 870211 thread 64 bound to OS proc set {70}
OMP: pid 870049 tid 870163 thread 16 bound to OS proc set {17}
OMP: pid 870049 tid 870221 thread 74 bound to OS proc set {81}
OMP: pid 870049 tid 870170 thread 23 bound to OS proc set {25}
OMP: pid 870049 tid 870205 thread 58 bound to OS proc set {63}
OMP: pid 870049 tid 870208 thread 61 bound to OS proc set {67}
OMP: pid 870049 tid 870160 thread 13 bound to OS proc set {14}
OMP: pid 870049 tid 870158 thread 11 bound to OS proc set {12}
OMP: pid 870049 tid 870196 thread 49 bound to OS proc set {54}
OMP: pid 870049 tid 870225 thread 78 bound to OS proc set {85}
OMP: pid 870049 tid 870210 thread 63 bound to OS proc set {69}
OMP: pid 870049 tid 870201 thread 54 bound to OS proc set {59}
OMP: pid 870049 tid 870178 thread 31 bound to OS proc set {34}
OMP: pid 870049 tid 870199 thread 52 bound to OS proc set {57}
OMP: pid 870049 tid 870227 thread 80 bound to OS proc set {88}
OMP: pid 870049 tid 870220 thread 73 bound to OS proc set {80}
OMP: pid 870049 tid 870182 thread 35 bound to OS proc set {38}
OMP: pid 870049 tid 870212 thread 65 bound to OS proc set {71}
OMP: pid 870049 tid 870203 thread 56 bound to OS proc set {61}
OMP: pid 870049 tid 870181 thread 34 bound to OS proc set {37}
OMP: pid 870049 tid 870213 thread 66 bound to OS proc set {72}
OMP: pid 870049 tid 870200 thread 53 bound to OS proc set {58}
OMP: pid 870049 tid 870219 thread 72 bound to OS proc set {79}
OMP: pid 870049 tid 870230 thread 83 bound to OS proc set {91}
OMP: pid 870049 tid 870167 thread 20 bound to OS proc set {22}
OMP: pid 870049 tid 870169 thread 22 bound to OS proc set {24}
OMP: pid 870049 tid 870204 thread 57 bound to OS proc set {62}
OMP: pid 870049 tid 870179 thread 32 bound to OS proc set {35}
OMP: pid 870049 tid 870229 thread 82 bound to OS proc set {90}
OMP: pid 870049 tid 870180 thread 33 bound to OS proc set {36}
OMP: pid 870049 tid 870217 thread 70 bound to OS proc set {77}
OMP: pid 870049 tid 870168 thread 21 bound to OS proc set {23}
OMP: pid 870049 tid 870215 thread 68 bound to OS proc set {74}
OMP: pid 870049 tid 870228 thread 81 bound to OS proc set {89}
OMP: pid 870049 tid 870234 thread 87 bound to OS proc set {95}
OMP: pid 870049 tid 870171 thread 24 bound to OS proc set {26}
OMP: pid 870049 tid 870186 thread 39 bound to OS proc set {42}
OMP: pid 870049 tid 870233 thread 86 bound to OS proc set {94}
OMP: pid 870049 tid 870231 thread 84 bound to OS proc set {92}
OMP: pid 870049 tid 870232 thread 85 bound to OS proc set {93}
OMP: pid 870049 tid 870224 thread 77 bound to OS proc set {84}
OMP: pid 870049 tid 870216 thread 69 bound to OS proc set {76}
{"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": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 0.298797, "speed_pp": 856.768921, "t_tg": 0.000000, "speed_tg": nan, "t": 0.298797, "speed": 856.768921}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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 870254 tid 870254 thread 0 bound to OS proc set {0}
OMP: pid 870254 tid 870367 thread 15 bound to OS proc set {15}
OMP: pid 870254 tid 870355 thread 3 bound to OS proc set {3}
OMP: pid 870254 tid 870364 thread 12 bound to OS proc set {12}
OMP: pid 870254 tid 870415 thread 63 bound to OS proc set {63}
OMP: pid 870254 tid 870354 thread 2 bound to OS proc set {2}
OMP: pid 870254 tid 870366 thread 14 bound to OS proc set {14}
OMP: pid 870254 tid 870403 thread 51 bound to OS proc set {51}
OMP: pid 870254 tid 870384 thread 32 bound to OS proc set {32}
OMP: pid 870254 tid 870383 thread 31 bound to OS proc set {31}
OMP: pid 870254 tid 870387 thread 35 bound to OS proc set {35}
OMP: pid 870254 tid 870431 thread 79 bound to OS proc set {79}
OMP: pid 870254 tid 870363 thread 11 bound to OS proc set {11}
OMP: pid 870254 tid 870399 thread 47 bound to OS proc set {47}
OMP: pid 870254 tid 870380 thread 28 bound to OS proc set {28}
OMP: pid 870254 tid 870412 thread 60 bound to OS proc set {60}
OMP: pid 870254 tid 870400 thread 48 bound to OS proc set {48}
OMP: pid 870254 tid 870411 thread 59 bound to OS proc set {59}
OMP: pid 870254 tid 870360 thread 8 bound to OS proc set {8}
OMP: pid 870254 tid 870396 thread 44 bound to OS proc set {44}
OMP: pid 870254 tid 870414 thread 62 bound to OS proc set {62}
OMP: pid 870254 tid 870362 thread 10 bound to OS proc set {10}
OMP: pid 870254 tid 870398 thread 46 bound to OS proc set {46}
OMP: pid 870254 tid 870365 thread 13 bound to OS proc set {13}
OMP: pid 870254 tid 870359 thread 7 bound to OS proc set {7}
OMP: pid 870254 tid 870379 thread 27 bound to OS proc set {27}
OMP: pid 870254 tid 870368 thread 16 bound to OS proc set {16}
OMP: pid 870254 tid 870371 thread 19 bound to OS proc set {19}
OMP: pid 870254 tid 870356 thread 4 bound to OS proc set {4}
OMP: pid 870254 tid 870410 thread 58 bound to OS proc set {58}
OMP: pid 870254 tid 870419 thread 67 bound to OS proc set {67}
OMP: pid 870254 tid 870408 thread 56 bound to OS proc set {56}
OMP: pid 870254 tid 870358 thread 6 bound to OS proc set {6}
OMP: pid 870254 tid 870402 thread 50 bound to OS proc set {50}
OMP: pid 870254 tid 870353 thread 1 bound to OS proc set {1}
OMP: pid 870254 tid 870407 thread 55 bound to OS proc set {55}
OMP: pid 870254 tid 870427 thread 75 bound to OS proc set {75}
OMP: pid 870254 tid 870416 thread 64 bound to OS proc set {64}
OMP: pid 870254 tid 870418 thread 66 bound to OS proc set {66}
OMP: pid 870254 tid 870395 thread 43 bound to OS proc set {43}
OMP: pid 870254 tid 870361 thread 9 bound to OS proc set {9}
OMP: pid 870254 tid 870401 thread 49 bound to OS proc set {49}
OMP: pid 870254 tid 870382 thread 30 bound to OS proc set {30}
OMP: pid 870254 tid 870386 thread 34 bound to OS proc set {34}
OMP: pid 870254 tid 870428 thread 76 bound to OS proc set {76}
OMP: pid 870254 tid 870424 thread 72 bound to OS proc set {72}
OMP: pid 870254 tid 870376 thread 24 bound to OS proc set {24}
OMP: pid 870254 tid 870404 thread 52 bound to OS proc set {52}
OMP: pid 870254 tid 870370 thread 18 bound to OS proc set {18}
OMP: pid 870254 tid 870423 thread 71 bound to OS proc set {71}
OMP: pid 870254 tid 870392 thread 40 bound to OS proc set {40}
OMP: pid 870254 tid 870430 thread 78 bound to OS proc set {78}
OMP: pid 870254 tid 870391 thread 39 bound to OS proc set {39}
OMP: pid 870254 tid 870413 thread 61 bound to OS proc set {61}
OMP: pid 870254 tid 870381 thread 29 bound to OS proc set {29}
OMP: pid 870254 tid 870357 thread 5 bound to OS proc set {5}
OMP: pid 870254 tid 870409 thread 57 bound to OS proc set {57}
OMP: pid 870254 tid 870378 thread 26 bound to OS proc set {26}
OMP: pid 870254 tid 870397 thread 45 bound to OS proc set {45}
OMP: pid 870254 tid 870369 thread 17 bound to OS proc set {17}
OMP: pid 870254 tid 870394 thread 42 bound to OS proc set {42}
OMP: pid 870254 tid 870406 thread 54 bound to OS proc set {54}
OMP: pid 870254 tid 870426 thread 74 bound to OS proc set {74}
OMP: pid 870254 tid 870420 thread 68 bound to OS proc set {68}
OMP: pid 870254 tid 870432 thread 80 bound to OS proc set {80}
OMP: pid 870254 tid 870372 thread 20 bound to OS proc set {20}
OMP: pid 870254 tid 870375 thread 23 bound to OS proc set {23}
OMP: pid 870254 tid 870429 thread 77 bound to OS proc set {77}
OMP: pid 870254 tid 870374 thread 22 bound to OS proc set {22}
OMP: pid 870254 tid 870417 thread 65 bound to OS proc set {65}
OMP: pid 870254 tid 870388 thread 36 bound to OS proc set {36}
OMP: pid 870254 tid 870422 thread 70 bound to OS proc set {70}
OMP: pid 870254 tid 870425 thread 73 bound to OS proc set {73}
OMP: pid 870254 tid 870434 thread 82 bound to OS proc set {82}
OMP: pid 870254 tid 870373 thread 21 bound to OS proc set {21}
OMP: pid 870254 tid 870377 thread 25 bound to OS proc set {25}
OMP: pid 870254 tid 870385 thread 33 bound to OS proc set {33}
OMP: pid 870254 tid 870389 thread 37 bound to OS proc set {37}
OMP: pid 870254 tid 870390 thread 38 bound to OS proc set {38}
OMP: pid 870254 tid 870433 thread 81 bound to OS proc set {81}
OMP: pid 870254 tid 870393 thread 41 bound to OS proc set {41}
OMP: pid 870254 tid 870405 thread 53 bound to OS proc set {53}
OMP: pid 870254 tid 870421 thread 69 bound to OS proc set {69}
OMP: pid 870254 tid 870444 thread 92 bound to OS proc set {92}
OMP: pid 870254 tid 870446 thread 94 bound to OS proc set {94}
OMP: pid 870254 tid 870445 thread 93 bound to OS proc set {93}
OMP: pid 870254 tid 870439 thread 87 bound to OS proc set {87}
OMP: pid 870254 tid 870436 thread 84 bound to OS proc set {84}
OMP: pid 870254 tid 870438 thread 86 bound to OS proc set {86}
OMP: pid 870254 tid 870437 thread 85 bound to OS proc set {85}
OMP: pid 870254 tid 870442 thread 90 bound to OS proc set {90}
OMP: pid 870254 tid 870443 thread 91 bound to OS proc set {91}
OMP: pid 870254 tid 870440 thread 88 bound to OS proc set {88}
OMP: pid 870254 tid 870441 thread 89 bound to OS proc set {89}
OMP: pid 870254 tid 870435 thread 83 bound to OS proc set {83}
OMP: pid 870254 tid 870447 thread 95 bound to OS proc set {95}
{"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": 128, "tg": 0, "pl": 2, "n_kv": 256, "t_pp": 0.290032, "speed_pp": 882.661255, "t_tg": 0.000000, "speed_tg": nan, "t": 0.290032, "speed": 882.661255}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/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/176-399-5611/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-24_14-59-42/tools/lprof_npsu_run_14 #
#########################################################################################################################################################################################################################################
