* [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 582729 tid 582729 thread 0 bound to OS proc set {0}
OMP: pid 582729 tid 582829 thread 2 bound to OS proc set {48}
OMP: pid 582729 tid 582828 thread 1 bound to OS proc set {24}
OMP: pid 582729 tid 582830 thread 3 bound to OS proc set {72}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 4, "n_threads_batch": 4, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 11.896580, "speed_tg": 21.518789, "t": 11.896580, "speed": 21.518789}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_2
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_2 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_2 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_2 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_2 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_2 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_2 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_2 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 582899 tid 582899 thread 0 bound to OS proc set {0}
OMP: pid 582899 tid 582999 thread 2 bound to OS proc set {24}
OMP: pid 582899 tid 582998 thread 1 bound to OS proc set {12}
OMP: pid 582899 tid 583003 thread 6 bound to OS proc set {72}
OMP: pid 582899 tid 583002 thread 5 bound to OS proc set {60}
OMP: pid 582899 tid 583000 thread 3 bound to OS proc set {36}
OMP: pid 582899 tid 583001 thread 4 bound to OS proc set {48}
OMP: pid 582899 tid 583004 thread 7 bound to OS proc set {84}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 8, "n_threads_batch": 8, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000001, "speed_pp": 0.000000, "t_tg": 6.389633, "speed_tg": 40.064899, "t": 6.389634, "speed": 40.064892}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_3
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_3 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_3 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_3 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_3 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_3 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_3 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_3 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 583024 tid 583024 thread 0 bound to OS proc set {0}
OMP: pid 583024 tid 583124 thread 2 bound to OS proc set {12}
OMP: pid 583024 tid 583125 thread 3 bound to OS proc set {18}
OMP: pid 583024 tid 583123 thread 1 bound to OS proc set {6}
OMP: pid 583024 tid 583134 thread 12 bound to OS proc set {72}
OMP: pid 583024 tid 583136 thread 14 bound to OS proc set {84}
OMP: pid 583024 tid 583129 thread 7 bound to OS proc set {42}
OMP: pid 583024 tid 583130 thread 8 bound to OS proc set {48}
OMP: pid 583024 tid 583126 thread 4 bound to OS proc set {24}
OMP: pid 583024 tid 583135 thread 13 bound to OS proc set {78}
OMP: pid 583024 tid 583128 thread 6 bound to OS proc set {36}
OMP: pid 583024 tid 583132 thread 10 bound to OS proc set {60}
OMP: pid 583024 tid 583127 thread 5 bound to OS proc set {30}
OMP: pid 583024 tid 583133 thread 11 bound to OS proc set {66}
OMP: pid 583024 tid 583131 thread 9 bound to OS proc set {54}
OMP: pid 583024 tid 583137 thread 15 bound to OS proc set {90}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 16, "n_threads_batch": 16, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.887423, "speed_tg": 65.853394, "t": 3.887423, "speed": 65.853394}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_4
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_4 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_4 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_4 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_4 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_4 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_4 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_4 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 583157 tid 583157 thread 0 bound to OS proc set {0}
OMP: pid 583157 tid 583258 thread 3 bound to OS proc set {12}
OMP: pid 583157 tid 583256 thread 1 bound to OS proc set {4}
OMP: pid 583157 tid 583259 thread 4 bound to OS proc set {16}
OMP: pid 583157 tid 583257 thread 2 bound to OS proc set {8}
OMP: pid 583157 tid 583267 thread 12 bound to OS proc set {48}
OMP: pid 583157 tid 583262 thread 7 bound to OS proc set {28}
OMP: pid 583157 tid 583260 thread 5 bound to OS proc set {20}
OMP: pid 583157 tid 583270 thread 15 bound to OS proc set {60}
OMP: pid 583157 tid 583269 thread 14 bound to OS proc set {56}
OMP: pid 583157 tid 583266 thread 11 bound to OS proc set {44}
OMP: pid 583157 tid 583263 thread 8 bound to OS proc set {32}
OMP: pid 583157 tid 583271 thread 16 bound to OS proc set {64}
OMP: pid 583157 tid 583268 thread 13 bound to OS proc set {52}
OMP: pid 583157 tid 583261 thread 6 bound to OS proc set {24}
OMP: pid 583157 tid 583273 thread 18 bound to OS proc set {72}
OMP: pid 583157 tid 583274 thread 19 bound to OS proc set {76}
OMP: pid 583157 tid 583272 thread 17 bound to OS proc set {68}
OMP: pid 583157 tid 583264 thread 9 bound to OS proc set {36}
OMP: pid 583157 tid 583265 thread 10 bound to OS proc set {40}
OMP: pid 583157 tid 583275 thread 20 bound to OS proc set {80}
OMP: pid 583157 tid 583277 thread 22 bound to OS proc set {88}
OMP: pid 583157 tid 583276 thread 21 bound to OS proc set {84}
OMP: pid 583157 tid 583278 thread 23 bound to OS proc set {92}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 24, "n_threads_batch": 24, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.264899, "speed_tg": 78.409775, "t": 3.264899, "speed": 78.409775}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_5
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_5 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_5 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_5 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_5 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_5 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_5 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_5 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 583298 tid 583298 thread 0 bound to OS proc set {0}
OMP: pid 583298 tid 583397 thread 1 bound to OS proc set {3}
OMP: pid 583298 tid 583407 thread 11 bound to OS proc set {33}
OMP: pid 583298 tid 583398 thread 2 bound to OS proc set {6}
OMP: pid 583298 tid 583408 thread 12 bound to OS proc set {36}
OMP: pid 583298 tid 583400 thread 4 bound to OS proc set {12}
OMP: pid 583298 tid 583411 thread 15 bound to OS proc set {45}
OMP: pid 583298 tid 583410 thread 14 bound to OS proc set {42}
OMP: pid 583298 tid 583402 thread 6 bound to OS proc set {18}
OMP: pid 583298 tid 583401 thread 5 bound to OS proc set {15}
OMP: pid 583298 tid 583424 thread 28 bound to OS proc set {84}
OMP: pid 583298 tid 583412 thread 16 bound to OS proc set {48}
OMP: pid 583298 tid 583399 thread 3 bound to OS proc set {9}
OMP: pid 583298 tid 583426 thread 30 bound to OS proc set {90}
OMP: pid 583298 tid 583409 thread 13 bound to OS proc set {39}
OMP: pid 583298 tid 583420 thread 24 bound to OS proc set {72}
OMP: pid 583298 tid 583415 thread 19 bound to OS proc set {57}
OMP: pid 583298 tid 583406 thread 10 bound to OS proc set {30}
OMP: pid 583298 tid 583403 thread 7 bound to OS proc set {21}
OMP: pid 583298 tid 583414 thread 18 bound to OS proc set {54}
OMP: pid 583298 tid 583405 thread 9 bound to OS proc set {27}
OMP: pid 583298 tid 583425 thread 29 bound to OS proc set {87}
OMP: pid 583298 tid 583423 thread 27 bound to OS proc set {81}
OMP: pid 583298 tid 583421 thread 25 bound to OS proc set {75}
OMP: pid 583298 tid 583413 thread 17 bound to OS proc set {51}
OMP: pid 583298 tid 583422 thread 26 bound to OS proc set {78}
OMP: pid 583298 tid 583404 thread 8 bound to OS proc set {24}
OMP: pid 583298 tid 583419 thread 23 bound to OS proc set {69}
OMP: pid 583298 tid 583416 thread 20 bound to OS proc set {60}
OMP: pid 583298 tid 583418 thread 22 bound to OS proc set {66}
OMP: pid 583298 tid 583417 thread 21 bound to OS proc set {63}
OMP: pid 583298 tid 583427 thread 31 bound to OS proc set {93}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 32, "n_threads_batch": 32, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.992788, "speed_tg": 85.538963, "t": 2.992788, "speed": 85.538963}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_6
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_6 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_6 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_6 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_6 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_6 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_6 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_6 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 583447 tid 583447 thread 0 bound to OS proc set {0}
OMP: pid 583447 tid 583547 thread 2 bound to OS proc set {4}
OMP: pid 583447 tid 583580 thread 35 bound to OS proc set {84}
OMP: pid 583447 tid 583548 thread 3 bound to OS proc set {7}
OMP: pid 583447 tid 583577 thread 32 bound to OS proc set {77}
OMP: pid 583447 tid 583552 thread 7 bound to OS proc set {16}
OMP: pid 583447 tid 583581 thread 36 bound to OS proc set {87}
OMP: pid 583447 tid 583549 thread 4 bound to OS proc set {9}
OMP: pid 583447 tid 583584 thread 39 bound to OS proc set {94}
OMP: pid 583447 tid 583583 thread 38 bound to OS proc set {92}
OMP: pid 583447 tid 583560 thread 15 bound to OS proc set {36}
OMP: pid 583447 tid 583579 thread 34 bound to OS proc set {82}
OMP: pid 583447 tid 583546 thread 1 bound to OS proc set {2}
OMP: pid 583447 tid 583561 thread 16 bound to OS proc set {38}
OMP: pid 583447 tid 583551 thread 6 bound to OS proc set {14}
OMP: pid 583447 tid 583559 thread 14 bound to OS proc set {33}
OMP: pid 583447 tid 583550 thread 5 bound to OS proc set {12}
OMP: pid 583447 tid 583558 thread 13 bound to OS proc set {31}
OMP: pid 583447 tid 583556 thread 11 bound to OS proc set {26}
OMP: pid 583447 tid 583576 thread 31 bound to OS proc set {75}
OMP: pid 583447 tid 583553 thread 8 bound to OS proc set {19}
OMP: pid 583447 tid 583578 thread 33 bound to OS proc set {80}
OMP: pid 583447 tid 583582 thread 37 bound to OS proc set {89}
OMP: pid 583447 tid 583557 thread 12 bound to OS proc set {29}
OMP: pid 583447 tid 583562 thread 17 bound to OS proc set {41}
OMP: pid 583447 tid 583575 thread 30 bound to OS proc set {72}
OMP: pid 583447 tid 583572 thread 27 bound to OS proc set {65}
OMP: pid 583447 tid 583573 thread 28 bound to OS proc set {67}
OMP: pid 583447 tid 583554 thread 9 bound to OS proc set {21}
OMP: pid 583447 tid 583564 thread 19 bound to OS proc set {46}
OMP: pid 583447 tid 583574 thread 29 bound to OS proc set {70}
OMP: pid 583447 tid 583569 thread 24 bound to OS proc set {58}
OMP: pid 583447 tid 583555 thread 10 bound to OS proc set {24}
OMP: pid 583447 tid 583570 thread 25 bound to OS proc set {60}
OMP: pid 583447 tid 583571 thread 26 bound to OS proc set {63}
OMP: pid 583447 tid 583563 thread 18 bound to OS proc set {43}
OMP: pid 583447 tid 583567 thread 22 bound to OS proc set {53}
OMP: pid 583447 tid 583566 thread 21 bound to OS proc set {50}
OMP: pid 583447 tid 583565 thread 20 bound to OS proc set {48}
OMP: pid 583447 tid 583568 thread 23 bound to OS proc set {55}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 40, "n_threads_batch": 40, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.886924, "speed_tg": 88.675697, "t": 2.886924, "speed": 88.675697}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_7
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_7 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_7 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_7 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_7 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_7 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_7 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_7 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 583652 tid 583652 thread 0 bound to OS proc set {0}
OMP: pid 583652 tid 583765 thread 15 bound to OS proc set {30}
OMP: pid 583652 tid 583757 thread 7 bound to OS proc set {14}
OMP: pid 583652 tid 583751 thread 1 bound to OS proc set {2}
OMP: pid 583652 tid 583752 thread 2 bound to OS proc set {4}
OMP: pid 583652 tid 583753 thread 3 bound to OS proc set {6}
OMP: pid 583652 tid 583768 thread 18 bound to OS proc set {36}
OMP: pid 583652 tid 583758 thread 8 bound to OS proc set {16}
OMP: pid 583652 tid 583759 thread 9 bound to OS proc set {18}
OMP: pid 583652 tid 583756 thread 6 bound to OS proc set {12}
OMP: pid 583652 tid 583766 thread 16 bound to OS proc set {32}
OMP: pid 583652 tid 583762 thread 12 bound to OS proc set {24}
OMP: pid 583652 tid 583782 thread 32 bound to OS proc set {64}
OMP: pid 583652 tid 583785 thread 35 bound to OS proc set {70}
OMP: pid 583652 tid 583794 thread 44 bound to OS proc set {88}
OMP: pid 583652 tid 583796 thread 46 bound to OS proc set {92}
OMP: pid 583652 tid 583764 thread 14 bound to OS proc set {28}
OMP: pid 583652 tid 583773 thread 23 bound to OS proc set {46}
OMP: pid 583652 tid 583781 thread 31 bound to OS proc set {62}
OMP: pid 583652 tid 583795 thread 45 bound to OS proc set {90}
OMP: pid 583652 tid 583784 thread 34 bound to OS proc set {68}
OMP: pid 583652 tid 583763 thread 13 bound to OS proc set {26}
OMP: pid 583652 tid 583793 thread 43 bound to OS proc set {86}
OMP: pid 583652 tid 583767 thread 17 bound to OS proc set {34}
OMP: pid 583652 tid 583760 thread 10 bound to OS proc set {20}
OMP: pid 583652 tid 583754 thread 4 bound to OS proc set {8}
OMP: pid 583652 tid 583774 thread 24 bound to OS proc set {48}
OMP: pid 583652 tid 583777 thread 27 bound to OS proc set {54}
OMP: pid 583652 tid 583778 thread 28 bound to OS proc set {56}
OMP: pid 583652 tid 583780 thread 30 bound to OS proc set {60}
OMP: pid 583652 tid 583792 thread 42 bound to OS proc set {84}
OMP: pid 583652 tid 583755 thread 5 bound to OS proc set {10}
OMP: pid 583652 tid 583783 thread 33 bound to OS proc set {66}
OMP: pid 583652 tid 583770 thread 20 bound to OS proc set {40}
OMP: pid 583652 tid 583771 thread 21 bound to OS proc set {42}
OMP: pid 583652 tid 583776 thread 26 bound to OS proc set {52}
OMP: pid 583652 tid 583772 thread 22 bound to OS proc set {44}
OMP: pid 583652 tid 583789 thread 39 bound to OS proc set {78}
OMP: pid 583652 tid 583790 thread 40 bound to OS proc set {80}
OMP: pid 583652 tid 583761 thread 11 bound to OS proc set {22}
OMP: pid 583652 tid 583775 thread 25 bound to OS proc set {50}
OMP: pid 583652 tid 583769 thread 19 bound to OS proc set {38}
OMP: pid 583652 tid 583788 thread 38 bound to OS proc set {76}
OMP: pid 583652 tid 583791 thread 41 bound to OS proc set {82}
OMP: pid 583652 tid 583786 thread 36 bound to OS proc set {72}
OMP: pid 583652 tid 583779 thread 29 bound to OS proc set {58}
OMP: pid 583652 tid 583797 thread 47 bound to OS proc set {94}
OMP: pid 583652 tid 583787 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": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000001, "speed_pp": 0.000000, "t_tg": 2.836042, "speed_tg": 90.266647, "t": 2.836043, "speed": 90.266617}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_8
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_8 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_8 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_8 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_8 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_8 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_8 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_8 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 583817 tid 583817 thread 0 bound to OS proc set {0}
OMP: pid 583817 tid 583916 thread 1 bound to OS proc set {1}
OMP: pid 583817 tid 583923 thread 8 bound to OS proc set {13}
OMP: pid 583817 tid 583966 thread 51 bound to OS proc set {88}
OMP: pid 583817 tid 583922 thread 7 bound to OS proc set {12}
OMP: pid 583817 tid 583947 thread 32 bound to OS proc set {55}
OMP: pid 583817 tid 583963 thread 48 bound to OS proc set {83}
OMP: pid 583817 tid 583917 thread 2 bound to OS proc set {3}
OMP: pid 583817 tid 583970 thread 55 bound to OS proc set {95}
OMP: pid 583817 tid 583967 thread 52 bound to OS proc set {90}
OMP: pid 583817 tid 583965 thread 50 bound to OS proc set {86}
OMP: pid 583817 tid 583964 thread 49 bound to OS proc set {84}
OMP: pid 583817 tid 583919 thread 4 bound to OS proc set {6}
OMP: pid 583817 tid 583942 thread 27 bound to OS proc set {46}
OMP: pid 583817 tid 583946 thread 31 bound to OS proc set {53}
OMP: pid 583817 tid 583969 thread 54 bound to OS proc set {93}
OMP: pid 583817 tid 583921 thread 6 bound to OS proc set {10}
OMP: pid 583817 tid 583931 thread 16 bound to OS proc set {27}
OMP: pid 583817 tid 583941 thread 26 bound to OS proc set {45}
OMP: pid 583817 tid 583926 thread 11 bound to OS proc set {19}
OMP: pid 583817 tid 583934 thread 19 bound to OS proc set {32}
OMP: pid 583817 tid 583924 thread 9 bound to OS proc set {15}
OMP: pid 583817 tid 583930 thread 15 bound to OS proc set {25}
OMP: pid 583817 tid 583945 thread 30 bound to OS proc set {51}
OMP: pid 583817 tid 583939 thread 24 bound to OS proc set {41}
OMP: pid 583817 tid 583925 thread 10 bound to OS proc set {17}
OMP: pid 583817 tid 583948 thread 33 bound to OS proc set {57}
OMP: pid 583817 tid 583932 thread 17 bound to OS proc set {29}
OMP: pid 583817 tid 583943 thread 28 bound to OS proc set {48}
OMP: pid 583817 tid 583918 thread 3 bound to OS proc set {5}
OMP: pid 583817 tid 583968 thread 53 bound to OS proc set {91}
OMP: pid 583817 tid 583920 thread 5 bound to OS proc set {8}
OMP: pid 583817 tid 583944 thread 29 bound to OS proc set {50}
OMP: pid 583817 tid 583959 thread 44 bound to OS proc set {76}
OMP: pid 583817 tid 583929 thread 14 bound to OS proc set {24}
OMP: pid 583817 tid 583940 thread 25 bound to OS proc set {43}
OMP: pid 583817 tid 583927 thread 12 bound to OS proc set {20}
OMP: pid 583817 tid 583950 thread 35 bound to OS proc set {60}
OMP: pid 583817 tid 583949 thread 34 bound to OS proc set {58}
OMP: pid 583817 tid 583933 thread 18 bound to OS proc set {31}
OMP: pid 583817 tid 583935 thread 20 bound to OS proc set {34}
OMP: pid 583817 tid 583958 thread 43 bound to OS proc set {74}
OMP: pid 583817 tid 583937 thread 22 bound to OS proc set {38}
OMP: pid 583817 tid 583962 thread 47 bound to OS proc set {81}
OMP: pid 583817 tid 583928 thread 13 bound to OS proc set {22}
OMP: pid 583817 tid 583936 thread 21 bound to OS proc set {36}
OMP: pid 583817 tid 583955 thread 40 bound to OS proc set {69}
OMP: pid 583817 tid 583953 thread 38 bound to OS proc set {65}
OMP: pid 583817 tid 583954 thread 39 bound to OS proc set {67}
OMP: pid 583817 tid 583938 thread 23 bound to OS proc set {39}
OMP: pid 583817 tid 583951 thread 36 bound to OS proc set {62}
OMP: pid 583817 tid 583957 thread 42 bound to OS proc set {72}
OMP: pid 583817 tid 583961 thread 46 bound to OS proc set {79}
OMP: pid 583817 tid 583956 thread 41 bound to OS proc set {71}
OMP: pid 583817 tid 583952 thread 37 bound to OS proc set {64}
OMP: pid 583817 tid 583960 thread 45 bound to OS proc set {77}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 56, "n_threads_batch": 56, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.890606, "speed_tg": 88.562744, "t": 2.890606, "speed": 88.562744}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_9
To display your profiling results:
########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_9 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_9 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_9 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_9 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_9 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_9 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_9 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 583990 tid 583990 thread 0 bound to OS proc set {0}
OMP: pid 583990 tid 584089 thread 1 bound to OS proc set {1}
OMP: pid 583990 tid 584103 thread 15 bound to OS proc set {22}
OMP: pid 583990 tid 584096 thread 8 bound to OS proc set {12}
OMP: pid 583990 tid 584091 thread 3 bound to OS proc set {4}
OMP: pid 583990 tid 584123 thread 35 bound to OS proc set {53}
OMP: pid 583990 tid 584090 thread 2 bound to OS proc set {3}
OMP: pid 583990 tid 584151 thread 63 bound to OS proc set {95}
OMP: pid 583990 tid 584095 thread 7 bound to OS proc set {10}
OMP: pid 583990 tid 584100 thread 12 bound to OS proc set {18}
OMP: pid 583990 tid 584139 thread 51 bound to OS proc set {77}
OMP: pid 583990 tid 584098 thread 10 bound to OS proc set {15}
OMP: pid 583990 tid 584150 thread 62 bound to OS proc set {93}
OMP: pid 583990 tid 584136 thread 48 bound to OS proc set {72}
OMP: pid 583990 tid 584094 thread 6 bound to OS proc set {9}
OMP: pid 583990 tid 584097 thread 9 bound to OS proc set {13}
OMP: pid 583990 tid 584148 thread 60 bound to OS proc set {90}
OMP: pid 583990 tid 584119 thread 31 bound to OS proc set {46}
OMP: pid 583990 tid 584092 thread 4 bound to OS proc set {6}
OMP: pid 583990 tid 584135 thread 47 bound to OS proc set {71}
OMP: pid 583990 tid 584099 thread 11 bound to OS proc set {16}
OMP: pid 583990 tid 584118 thread 30 bound to OS proc set {45}
OMP: pid 583990 tid 584116 thread 28 bound to OS proc set {42}
OMP: pid 583990 tid 584122 thread 34 bound to OS proc set {51}
OMP: pid 583990 tid 584132 thread 44 bound to OS proc set {66}
OMP: pid 583990 tid 584101 thread 13 bound to OS proc set {19}
OMP: pid 583990 tid 584117 thread 29 bound to OS proc set {43}
OMP: pid 583990 tid 584126 thread 38 bound to OS proc set {57}
OMP: pid 583990 tid 584093 thread 5 bound to OS proc set {7}
OMP: pid 583990 tid 584127 thread 39 bound to OS proc set {59}
OMP: pid 583990 tid 584112 thread 24 bound to OS proc set {36}
OMP: pid 583990 tid 584130 thread 42 bound to OS proc set {63}
OMP: pid 583990 tid 584129 thread 41 bound to OS proc set {62}
OMP: pid 583990 tid 584138 thread 50 bound to OS proc set {75}
OMP: pid 583990 tid 584105 thread 17 bound to OS proc set {25}
OMP: pid 583990 tid 584107 thread 19 bound to OS proc set {28}
OMP: pid 583990 tid 584115 thread 27 bound to OS proc set {40}
OMP: pid 583990 tid 584137 thread 49 bound to OS proc set {74}
OMP: pid 583990 tid 584125 thread 37 bound to OS proc set {56}
OMP: pid 583990 tid 584120 thread 32 bound to OS proc set {48}
OMP: pid 583990 tid 584104 thread 16 bound to OS proc set {24}
OMP: pid 583990 tid 584131 thread 43 bound to OS proc set {65}
OMP: pid 583990 tid 584134 thread 46 bound to OS proc set {69}
OMP: pid 583990 tid 584124 thread 36 bound to OS proc set {54}
OMP: pid 583990 tid 584110 thread 22 bound to OS proc set {33}
OMP: pid 583990 tid 584106 thread 18 bound to OS proc set {27}
OMP: pid 583990 tid 584113 thread 25 bound to OS proc set {37}
OMP: pid 583990 tid 584128 thread 40 bound to OS proc set {60}
OMP: pid 583990 tid 584149 thread 61 bound to OS proc set {92}
OMP: pid 583990 tid 584147 thread 59 bound to OS proc set {89}
OMP: pid 583990 tid 584114 thread 26 bound to OS proc set {39}
OMP: pid 583990 tid 584102 thread 14 bound to OS proc set {21}
OMP: pid 583990 tid 584143 thread 55 bound to OS proc set {83}
OMP: pid 583990 tid 584144 thread 56 bound to OS proc set {84}
OMP: pid 583990 tid 584140 thread 52 bound to OS proc set {78}
OMP: pid 583990 tid 584146 thread 58 bound to OS proc set {87}
OMP: pid 583990 tid 584142 thread 54 bound to OS proc set {81}
OMP: pid 583990 tid 584133 thread 45 bound to OS proc set {68}
OMP: pid 583990 tid 584141 thread 53 bound to OS proc set {80}
OMP: pid 583990 tid 584145 thread 57 bound to OS proc set {86}
OMP: pid 583990 tid 584109 thread 21 bound to OS proc set {31}
OMP: pid 583990 tid 584111 thread 23 bound to OS proc set {34}
OMP: pid 583990 tid 584108 thread 20 bound to OS proc set {30}
OMP: pid 583990 tid 584121 thread 33 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": 64, "n_threads_batch": 64, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 2.963451, "speed_tg": 86.385773, "t": 2.963451, "speed": 86.385773}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_10
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_10 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_10 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_10 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_10 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_10 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_10 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_10 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 584172 tid 584172 thread 0 bound to OS proc set {0}
OMP: pid 584172 tid 584272 thread 2 bound to OS proc set {2}
OMP: pid 584172 tid 584271 thread 1 bound to OS proc set {1}
OMP: pid 584172 tid 584281 thread 11 bound to OS proc set {14}
OMP: pid 584172 tid 584321 thread 51 bound to OS proc set {68}
OMP: pid 584172 tid 584337 thread 67 bound to OS proc set {90}
OMP: pid 584172 tid 584334 thread 64 bound to OS proc set {86}
OMP: pid 584172 tid 584305 thread 35 bound to OS proc set {47}
OMP: pid 584172 tid 584336 thread 66 bound to OS proc set {88}
OMP: pid 584172 tid 584341 thread 71 bound to OS proc set {95}
OMP: pid 584172 tid 584304 thread 34 bound to OS proc set {45}
OMP: pid 584172 tid 584278 thread 8 bound to OS proc set {10}
OMP: pid 584172 tid 584273 thread 3 bound to OS proc set {4}
OMP: pid 584172 tid 584338 thread 68 bound to OS proc set {91}
OMP: pid 584172 tid 584335 thread 65 bound to OS proc set {87}
OMP: pid 584172 tid 584284 thread 14 bound to OS proc set {18}
OMP: pid 584172 tid 584333 thread 63 bound to OS proc set {84}
OMP: pid 584172 tid 584320 thread 50 bound to OS proc set {67}
OMP: pid 584172 tid 584340 thread 70 bound to OS proc set {94}
OMP: pid 584172 tid 584288 thread 18 bound to OS proc set {24}
OMP: pid 584172 tid 584297 thread 27 bound to OS proc set {36}
OMP: pid 584172 tid 584276 thread 6 bound to OS proc set {8}
OMP: pid 584172 tid 584294 thread 24 bound to OS proc set {32}
OMP: pid 584172 tid 584316 thread 46 bound to OS proc set {61}
OMP: pid 584172 tid 584274 thread 4 bound to OS proc set {5}
OMP: pid 584172 tid 584302 thread 32 bound to OS proc set {43}
OMP: pid 584172 tid 584275 thread 5 bound to OS proc set {6}
OMP: pid 584172 tid 584277 thread 7 bound to OS proc set {9}
OMP: pid 584172 tid 584301 thread 31 bound to OS proc set {41}
OMP: pid 584172 tid 584318 thread 48 bound to OS proc set {64}
OMP: pid 584172 tid 584282 thread 12 bound to OS proc set {16}
OMP: pid 584172 tid 584309 thread 39 bound to OS proc set {52}
OMP: pid 584172 tid 584283 thread 13 bound to OS proc set {17}
OMP: pid 584172 tid 584310 thread 40 bound to OS proc set {53}
OMP: pid 584172 tid 584303 thread 33 bound to OS proc set {44}
OMP: pid 584172 tid 584322 thread 52 bound to OS proc set {70}
OMP: pid 584172 tid 584285 thread 15 bound to OS proc set {20}
OMP: pid 584172 tid 584330 thread 60 bound to OS proc set {80}
OMP: pid 584172 tid 584298 thread 28 bound to OS proc set {37}
OMP: pid 584172 tid 584315 thread 45 bound to OS proc set {60}
OMP: pid 584172 tid 584280 thread 10 bound to OS proc set {13}
OMP: pid 584172 tid 584317 thread 47 bound to OS proc set {63}
OMP: pid 584172 tid 584306 thread 36 bound to OS proc set {48}
OMP: pid 584172 tid 584319 thread 49 bound to OS proc set {66}
OMP: pid 584172 tid 584296 thread 26 bound to OS proc set {35}
OMP: pid 584172 tid 584293 thread 23 bound to OS proc set {30}
OMP: pid 584172 tid 584299 thread 29 bound to OS proc set {39}
OMP: pid 584172 tid 584308 thread 38 bound to OS proc set {51}
OMP: pid 584172 tid 584324 thread 54 bound to OS proc set {72}
OMP: pid 584172 tid 584279 thread 9 bound to OS proc set {12}
OMP: pid 584172 tid 584300 thread 30 bound to OS proc set {40}
OMP: pid 584172 tid 584339 thread 69 bound to OS proc set {92}
OMP: pid 584172 tid 584289 thread 19 bound to OS proc set {25}
OMP: pid 584172 tid 584290 thread 20 bound to OS proc set {26}
OMP: pid 584172 tid 584295 thread 25 bound to OS proc set {33}
OMP: pid 584172 tid 584326 thread 56 bound to OS proc set {75}
OMP: pid 584172 tid 584329 thread 59 bound to OS proc set {79}
OMP: pid 584172 tid 584312 thread 42 bound to OS proc set {56}
OMP: pid 584172 tid 584307 thread 37 bound to OS proc set {49}
OMP: pid 584172 tid 584314 thread 44 bound to OS proc set {59}
OMP: pid 584172 tid 584287 thread 17 bound to OS proc set {22}
OMP: pid 584172 tid 584313 thread 43 bound to OS proc set {57}
OMP: pid 584172 tid 584323 thread 53 bound to OS proc set {71}
OMP: pid 584172 tid 584292 thread 22 bound to OS proc set {29}
OMP: pid 584172 tid 584286 thread 16 bound to OS proc set {21}
OMP: pid 584172 tid 584332 thread 62 bound to OS proc set {83}
OMP: pid 584172 tid 584328 thread 58 bound to OS proc set {78}
OMP: pid 584172 tid 584291 thread 21 bound to OS proc set {28}
OMP: pid 584172 tid 584311 thread 41 bound to OS proc set {55}
OMP: pid 584172 tid 584331 thread 61 bound to OS proc set {82}
OMP: pid 584172 tid 584327 thread 57 bound to OS proc set {76}
OMP: pid 584172 tid 584325 thread 55 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": 72, "n_threads_batch": 72, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.006940, "speed_tg": 85.136391, "t": 3.006940, "speed": 85.136391}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_11
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_11 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_11 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_11 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_11 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_11 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_11 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_11 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 584361 tid 584361 thread 0 bound to OS proc set {0}
OMP: pid 584361 tid 584462 thread 3 bound to OS proc set {3}
OMP: pid 584361 tid 584461 thread 2 bound to OS proc set {2}
OMP: pid 584361 tid 584460 thread 1 bound to OS proc set {1}
OMP: pid 584361 tid 584463 thread 4 bound to OS proc set {4}
OMP: pid 584361 tid 584466 thread 7 bound to OS proc set {8}
OMP: pid 584361 tid 584538 thread 79 bound to OS proc set {95}
OMP: pid 584361 tid 584471 thread 12 bound to OS proc set {14}
OMP: pid 584361 tid 584469 thread 10 bound to OS proc set {12}
OMP: pid 584361 tid 584523 thread 64 bound to OS proc set {77}
OMP: pid 584361 tid 584510 thread 51 bound to OS proc set {61}
OMP: pid 584361 tid 584509 thread 50 bound to OS proc set {60}
OMP: pid 584361 tid 584525 thread 66 bound to OS proc set {80}
OMP: pid 584361 tid 584470 thread 11 bound to OS proc set {13}
OMP: pid 584361 tid 584483 thread 24 bound to OS proc set {29}
OMP: pid 584361 tid 584472 thread 13 bound to OS proc set {15}
OMP: pid 584361 tid 584465 thread 6 bound to OS proc set {7}
OMP: pid 584361 tid 584473 thread 14 bound to OS proc set {16}
OMP: pid 584361 tid 584475 thread 16 bound to OS proc set {19}
OMP: pid 584361 tid 584502 thread 43 bound to OS proc set {52}
OMP: pid 584361 tid 584467 thread 8 bound to OS proc set {9}
OMP: pid 584361 tid 584522 thread 63 bound to OS proc set {76}
OMP: pid 584361 tid 584508 thread 49 bound to OS proc set {59}
OMP: pid 584361 tid 584468 thread 9 bound to OS proc set {10}
OMP: pid 584361 tid 584487 thread 28 bound to OS proc set {33}
OMP: pid 584361 tid 584537 thread 78 bound to OS proc set {94}
OMP: pid 584361 tid 584535 thread 76 bound to OS proc set {92}
OMP: pid 584361 tid 584486 thread 27 bound to OS proc set {32}
OMP: pid 584361 tid 584506 thread 47 bound to OS proc set {56}
OMP: pid 584361 tid 584526 thread 67 bound to OS proc set {81}
OMP: pid 584361 tid 584514 thread 55 bound to OS proc set {66}
OMP: pid 584361 tid 584534 thread 75 bound to OS proc set {90}
OMP: pid 584361 tid 584464 thread 5 bound to OS proc set {6}
OMP: pid 584361 tid 584499 thread 40 bound to OS proc set {48}
OMP: pid 584361 tid 584515 thread 56 bound to OS proc set {67}
OMP: pid 584361 tid 584493 thread 34 bound to OS proc set {41}
OMP: pid 584361 tid 584474 thread 15 bound to OS proc set {18}
OMP: pid 584361 tid 584488 thread 29 bound to OS proc set {35}
OMP: pid 584361 tid 584485 thread 26 bound to OS proc set {31}
OMP: pid 584361 tid 584519 thread 60 bound to OS proc set {72}
OMP: pid 584361 tid 584484 thread 25 bound to OS proc set {30}
OMP: pid 584361 tid 584489 thread 30 bound to OS proc set {36}
OMP: pid 584361 tid 584492 thread 33 bound to OS proc set {40}
OMP: pid 584361 tid 584516 thread 57 bound to OS proc set {69}
OMP: pid 584361 tid 584507 thread 48 bound to OS proc set {58}
OMP: pid 584361 tid 584524 thread 65 bound to OS proc set {78}
OMP: pid 584361 tid 584503 thread 44 bound to OS proc set {53}
OMP: pid 584361 tid 584498 thread 39 bound to OS proc set {47}
OMP: pid 584361 tid 584494 thread 35 bound to OS proc set {42}
OMP: pid 584361 tid 584495 thread 36 bound to OS proc set {43}
OMP: pid 584361 tid 584520 thread 61 bound to OS proc set {73}
OMP: pid 584361 tid 584501 thread 42 bound to OS proc set {50}
OMP: pid 584361 tid 584478 thread 19 bound to OS proc set {23}
OMP: pid 584361 tid 584511 thread 52 bound to OS proc set {63}
OMP: pid 584361 tid 584521 thread 62 bound to OS proc set {75}
OMP: pid 584361 tid 584536 thread 77 bound to OS proc set {93}
OMP: pid 584361 tid 584490 thread 31 bound to OS proc set {37}
OMP: pid 584361 tid 584505 thread 46 bound to OS proc set {55}
OMP: pid 584361 tid 584479 thread 20 bound to OS proc set {24}
OMP: pid 584361 tid 584476 thread 17 bound to OS proc set {20}
OMP: pid 584361 tid 584481 thread 22 bound to OS proc set {26}
OMP: pid 584361 tid 584497 thread 38 bound to OS proc set {46}
OMP: pid 584361 tid 584513 thread 54 bound to OS proc set {65}
OMP: pid 584361 tid 584500 thread 41 bound to OS proc set {49}
OMP: pid 584361 tid 584496 thread 37 bound to OS proc set {44}
OMP: pid 584361 tid 584491 thread 32 bound to OS proc set {38}
OMP: pid 584361 tid 584517 thread 58 bound to OS proc set {70}
OMP: pid 584361 tid 584512 thread 53 bound to OS proc set {64}
OMP: pid 584361 tid 584518 thread 59 bound to OS proc set {71}
OMP: pid 584361 tid 584477 thread 18 bound to OS proc set {21}
OMP: pid 584361 tid 584504 thread 45 bound to OS proc set {54}
OMP: pid 584361 tid 584530 thread 71 bound to OS proc set {86}
OMP: pid 584361 tid 584480 thread 21 bound to OS proc set {25}
OMP: pid 584361 tid 584527 thread 68 bound to OS proc set {82}
OMP: pid 584361 tid 584531 thread 72 bound to OS proc set {87}
OMP: pid 584361 tid 584533 thread 74 bound to OS proc set {89}
OMP: pid 584361 tid 584529 thread 70 bound to OS proc set {84}
OMP: pid 584361 tid 584528 thread 69 bound to OS proc set {83}
OMP: pid 584361 tid 584532 thread 73 bound to OS proc set {88}
OMP: pid 584361 tid 584482 thread 23 bound to OS proc set {27}
{"n_kv_max": 16384, "n_batch": 2048, "n_ubatch": 512, "flash_attn": -1, "is_pp_shared": 0, "n_gpu_layers": -1, "n_threads": 80, "n_threads_batch": 80, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.065732, "speed_tg": 83.503708, "t": 3.065732, "speed": 83.503708}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_12
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_12 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_12 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_12 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_12 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_12 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_12 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_12 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 584607 tid 584607 thread 0 bound to OS proc set {0}
OMP: pid 584607 tid 584708 thread 3 bound to OS proc set {3}
OMP: pid 584607 tid 584707 thread 2 bound to OS proc set {2}
OMP: pid 584607 tid 584713 thread 8 bound to OS proc set {8}
OMP: pid 584607 tid 584712 thread 7 bound to OS proc set {7}
OMP: pid 584607 tid 584706 thread 1 bound to OS proc set {1}
OMP: pid 584607 tid 584709 thread 4 bound to OS proc set {4}
OMP: pid 584607 tid 584711 thread 6 bound to OS proc set {6}
OMP: pid 584607 tid 584716 thread 11 bound to OS proc set {12}
OMP: pid 584607 tid 584753 thread 48 bound to OS proc set {52}
OMP: pid 584607 tid 584720 thread 15 bound to OS proc set {16}
OMP: pid 584607 tid 584719 thread 14 bound to OS proc set {15}
OMP: pid 584607 tid 584714 thread 9 bound to OS proc set {9}
OMP: pid 584607 tid 584764 thread 59 bound to OS proc set {65}
OMP: pid 584607 tid 584717 thread 12 bound to OS proc set {13}
OMP: pid 584607 tid 584710 thread 5 bound to OS proc set {5}
OMP: pid 584607 tid 584715 thread 10 bound to OS proc set {11}
OMP: pid 584607 tid 584761 thread 56 bound to OS proc set {61}
OMP: pid 584607 tid 584723 thread 18 bound to OS proc set {19}
OMP: pid 584607 tid 584718 thread 13 bound to OS proc set {14}
OMP: pid 584607 tid 584752 thread 47 bound to OS proc set {51}
OMP: pid 584607 tid 584760 thread 55 bound to OS proc set {60}
OMP: pid 584607 tid 584749 thread 44 bound to OS proc set {48}
OMP: pid 584607 tid 584745 thread 40 bound to OS proc set {44}
OMP: pid 584607 tid 584763 thread 58 bound to OS proc set {63}
OMP: pid 584607 tid 584751 thread 46 bound to OS proc set {50}
OMP: pid 584607 tid 584747 thread 42 bound to OS proc set {46}
OMP: pid 584607 tid 584748 thread 43 bound to OS proc set {47}
OMP: pid 584607 tid 584733 thread 28 bound to OS proc set {30}
OMP: pid 584607 tid 584754 thread 49 bound to OS proc set {54}
OMP: pid 584607 tid 584724 thread 19 bound to OS proc set {20}
OMP: pid 584607 tid 584721 thread 16 bound to OS proc set {17}
OMP: pid 584607 tid 584735 thread 30 bound to OS proc set {33}
OMP: pid 584607 tid 584756 thread 51 bound to OS proc set {56}
OMP: pid 584607 tid 584750 thread 45 bound to OS proc set {49}
OMP: pid 584607 tid 584737 thread 32 bound to OS proc set {35}
OMP: pid 584607 tid 584746 thread 41 bound to OS proc set {45}
OMP: pid 584607 tid 584744 thread 39 bound to OS proc set {42}
OMP: pid 584607 tid 584729 thread 24 bound to OS proc set {26}
OMP: pid 584607 tid 584759 thread 54 bound to OS proc set {59}
OMP: pid 584607 tid 584736 thread 31 bound to OS proc set {34}
OMP: pid 584607 tid 584739 thread 34 bound to OS proc set {37}
OMP: pid 584607 tid 584788 thread 83 bound to OS proc set {91}
OMP: pid 584607 tid 584734 thread 29 bound to OS proc set {31}
OMP: pid 584607 tid 584732 thread 27 bound to OS proc set {29}
OMP: pid 584607 tid 584762 thread 57 bound to OS proc set {62}
OMP: pid 584607 tid 584742 thread 37 bound to OS proc set {40}
OMP: pid 584607 tid 584725 thread 20 bound to OS proc set {22}
OMP: pid 584607 tid 584731 thread 26 bound to OS proc set {28}
OMP: pid 584607 tid 584740 thread 35 bound to OS proc set {38}
OMP: pid 584607 tid 584741 thread 36 bound to OS proc set {39}
OMP: pid 584607 tid 584722 thread 17 bound to OS proc set {18}
OMP: pid 584607 tid 584765 thread 60 bound to OS proc set {66}
OMP: pid 584607 tid 584727 thread 22 bound to OS proc set {24}
OMP: pid 584607 tid 584757 thread 52 bound to OS proc set {57}
OMP: pid 584607 tid 584730 thread 25 bound to OS proc set {27}
OMP: pid 584607 tid 584768 thread 63 bound to OS proc set {69}
OMP: pid 584607 tid 584728 thread 23 bound to OS proc set {25}
OMP: pid 584607 tid 584783 thread 78 bound to OS proc set {85}
OMP: pid 584607 tid 584777 thread 72 bound to OS proc set {79}
OMP: pid 584607 tid 584767 thread 62 bound to OS proc set {68}
OMP: pid 584607 tid 584782 thread 77 bound to OS proc set {84}
OMP: pid 584607 tid 584755 thread 50 bound to OS proc set {55}
OMP: pid 584607 tid 584779 thread 74 bound to OS proc set {81}
OMP: pid 584607 tid 584784 thread 79 bound to OS proc set {87}
OMP: pid 584607 tid 584776 thread 71 bound to OS proc set {78}
OMP: pid 584607 tid 584726 thread 21 bound to OS proc set {23}
OMP: pid 584607 tid 584780 thread 75 bound to OS proc set {82}
OMP: pid 584607 tid 584766 thread 61 bound to OS proc set {67}
OMP: pid 584607 tid 584758 thread 53 bound to OS proc set {58}
OMP: pid 584607 tid 584787 thread 82 bound to OS proc set {90}
OMP: pid 584607 tid 584769 thread 64 bound to OS proc set {70}
OMP: pid 584607 tid 584772 thread 67 bound to OS proc set {73}
OMP: pid 584607 tid 584774 thread 69 bound to OS proc set {76}
OMP: pid 584607 tid 584778 thread 73 bound to OS proc set {80}
OMP: pid 584607 tid 584785 thread 80 bound to OS proc set {88}
OMP: pid 584607 tid 584743 thread 38 bound to OS proc set {41}
OMP: pid 584607 tid 584781 thread 76 bound to OS proc set {83}
OMP: pid 584607 tid 584773 thread 68 bound to OS proc set {74}
OMP: pid 584607 tid 584770 thread 65 bound to OS proc set {71}
OMP: pid 584607 tid 584771 thread 66 bound to OS proc set {72}
OMP: pid 584607 tid 584775 thread 70 bound to OS proc set {77}
OMP: pid 584607 tid 584792 thread 87 bound to OS proc set {95}
OMP: pid 584607 tid 584789 thread 84 bound to OS proc set {92}
OMP: pid 584607 tid 584786 thread 81 bound to OS proc set {89}
OMP: pid 584607 tid 584791 thread 86 bound to OS proc set {94}
OMP: pid 584607 tid 584790 thread 85 bound to OS proc set {93}
OMP: pid 584607 tid 584738 thread 33 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": 88, "n_threads_batch": 88, "pp": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.289747, "speed_tg": 77.817535, "t": 3.289747, "speed": 77.817535}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_13
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_13 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_13 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_13 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_13 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_13 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_13 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_13 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/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 584812 tid 584812 thread 0 bound to OS proc set {0}
OMP: pid 584812 tid 584914 thread 3 bound to OS proc set {3}
OMP: pid 584812 tid 584926 thread 15 bound to OS proc set {15}
OMP: pid 584812 tid 584913 thread 2 bound to OS proc set {2}
OMP: pid 584812 tid 584923 thread 12 bound to OS proc set {12}
OMP: pid 584812 tid 584919 thread 8 bound to OS proc set {8}
OMP: pid 584812 tid 584922 thread 11 bound to OS proc set {11}
OMP: pid 584812 tid 584958 thread 47 bound to OS proc set {47}
OMP: pid 584812 tid 584925 thread 14 bound to OS proc set {14}
OMP: pid 584812 tid 584962 thread 51 bound to OS proc set {51}
OMP: pid 584812 tid 584915 thread 4 bound to OS proc set {4}
OMP: pid 584812 tid 584971 thread 60 bound to OS proc set {60}
OMP: pid 584812 tid 584942 thread 31 bound to OS proc set {31}
OMP: pid 584812 tid 584918 thread 7 bound to OS proc set {7}
OMP: pid 584812 tid 584943 thread 32 bound to OS proc set {32}
OMP: pid 584812 tid 584946 thread 35 bound to OS proc set {35}
OMP: pid 584812 tid 584959 thread 48 bound to OS proc set {48}
OMP: pid 584812 tid 584939 thread 28 bound to OS proc set {28}
OMP: pid 584812 tid 584930 thread 19 bound to OS proc set {19}
OMP: pid 584812 tid 584935 thread 24 bound to OS proc set {24}
OMP: pid 584812 tid 584970 thread 59 bound to OS proc set {59}
OMP: pid 584812 tid 584924 thread 13 bound to OS proc set {13}
OMP: pid 584812 tid 584938 thread 27 bound to OS proc set {27}
OMP: pid 584812 tid 584912 thread 1 bound to OS proc set {1}
OMP: pid 584812 tid 584957 thread 46 bound to OS proc set {46}
OMP: pid 584812 tid 584921 thread 10 bound to OS proc set {10}
OMP: pid 584812 tid 584955 thread 44 bound to OS proc set {44}
OMP: pid 584812 tid 584961 thread 50 bound to OS proc set {50}
OMP: pid 584812 tid 584937 thread 26 bound to OS proc set {26}
OMP: pid 584812 tid 584941 thread 30 bound to OS proc set {30}
OMP: pid 584812 tid 584927 thread 16 bound to OS proc set {16}
OMP: pid 584812 tid 584920 thread 9 bound to OS proc set {9}
OMP: pid 584812 tid 584954 thread 43 bound to OS proc set {43}
OMP: pid 584812 tid 584917 thread 6 bound to OS proc set {6}
OMP: pid 584812 tid 584929 thread 18 bound to OS proc set {18}
OMP: pid 584812 tid 584969 thread 58 bound to OS proc set {58}
OMP: pid 584812 tid 584940 thread 29 bound to OS proc set {29}
OMP: pid 584812 tid 584956 thread 45 bound to OS proc set {45}
OMP: pid 584812 tid 584916 thread 5 bound to OS proc set {5}
OMP: pid 584812 tid 584966 thread 55 bound to OS proc set {55}
OMP: pid 584812 tid 584936 thread 25 bound to OS proc set {25}
OMP: pid 584812 tid 584931 thread 20 bound to OS proc set {20}
OMP: pid 584812 tid 584945 thread 34 bound to OS proc set {34}
OMP: pid 584812 tid 584928 thread 17 bound to OS proc set {17}
OMP: pid 584812 tid 584934 thread 23 bound to OS proc set {23}
OMP: pid 584812 tid 584963 thread 52 bound to OS proc set {52}
OMP: pid 584812 tid 584967 thread 56 bound to OS proc set {56}
OMP: pid 584812 tid 584953 thread 42 bound to OS proc set {42}
OMP: pid 584812 tid 584968 thread 57 bound to OS proc set {57}
OMP: pid 584812 tid 584933 thread 22 bound to OS proc set {22}
OMP: pid 584812 tid 584965 thread 54 bound to OS proc set {54}
OMP: pid 584812 tid 584951 thread 40 bound to OS proc set {40}
OMP: pid 584812 tid 584944 thread 33 bound to OS proc set {33}
OMP: pid 584812 tid 584950 thread 39 bound to OS proc set {39}
OMP: pid 584812 tid 584932 thread 21 bound to OS proc set {21}
OMP: pid 584812 tid 584947 thread 36 bound to OS proc set {36}
OMP: pid 584812 tid 584964 thread 53 bound to OS proc set {53}
OMP: pid 584812 tid 584960 thread 49 bound to OS proc set {49}
OMP: pid 584812 tid 584952 thread 41 bound to OS proc set {41}
OMP: pid 584812 tid 584949 thread 38 bound to OS proc set {38}
OMP: pid 584812 tid 584948 thread 37 bound to OS proc set {37}
OMP: pid 584812 tid 584978 thread 67 bound to OS proc set {67}
OMP: pid 584812 tid 584975 thread 64 bound to OS proc set {64}
OMP: pid 584812 tid 584990 thread 79 bound to OS proc set {79}
OMP: pid 584812 tid 584973 thread 62 bound to OS proc set {62}
OMP: pid 584812 tid 584974 thread 63 bound to OS proc set {63}
OMP: pid 584812 tid 584987 thread 76 bound to OS proc set {76}
OMP: pid 584812 tid 584983 thread 72 bound to OS proc set {72}
OMP: pid 584812 tid 584986 thread 75 bound to OS proc set {75}
OMP: pid 584812 tid 584976 thread 65 bound to OS proc set {65}
OMP: pid 584812 tid 584977 thread 66 bound to OS proc set {66}
OMP: pid 584812 tid 584988 thread 77 bound to OS proc set {77}
OMP: pid 584812 tid 584991 thread 80 bound to OS proc set {80}
OMP: pid 584812 tid 584989 thread 78 bound to OS proc set {78}
OMP: pid 584812 tid 585003 thread 92 bound to OS proc set {92}
OMP: pid 584812 tid 584999 thread 88 bound to OS proc set {88}
OMP: pid 584812 tid 584994 thread 83 bound to OS proc set {83}
OMP: pid 584812 tid 584982 thread 71 bound to OS proc set {71}
OMP: pid 584812 tid 584984 thread 73 bound to OS proc set {73}
OMP: pid 584812 tid 584985 thread 74 bound to OS proc set {74}
OMP: pid 584812 tid 584995 thread 84 bound to OS proc set {84}
OMP: pid 584812 tid 584981 thread 70 bound to OS proc set {70}
OMP: pid 584812 tid 585002 thread 91 bound to OS proc set {91}
OMP: pid 584812 tid 585005 thread 94 bound to OS proc set {94}
OMP: pid 584812 tid 584980 thread 69 bound to OS proc set {69}
OMP: pid 584812 tid 584992 thread 81 bound to OS proc set {81}
OMP: pid 584812 tid 584998 thread 87 bound to OS proc set {87}
OMP: pid 584812 tid 585001 thread 90 bound to OS proc set {90}
OMP: pid 584812 tid 585004 thread 93 bound to OS proc set {93}
OMP: pid 584812 tid 584993 thread 82 bound to OS proc set {82}
OMP: pid 584812 tid 584996 thread 85 bound to OS proc set {85}
OMP: pid 584812 tid 584997 thread 86 bound to OS proc set {86}
OMP: pid 584812 tid 585000 thread 89 bound to OS proc set {89}
OMP: pid 584812 tid 584972 thread 61 bound to OS proc set {61}
OMP: pid 584812 tid 584979 thread 68 bound to OS proc set {68}
OMP: pid 584812 tid 585006 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": 0, "tg": 128, "pl": 2, "n_kv": 256, "t_pp": 0.000000, "speed_pp": nan, "t_tg": 3.439726, "speed_tg": 74.424530, "t": 3.439726, "speed": 74.424530}
Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_14
To display your profiling results:
#########################################################################################################################################################################################################################################
# LEVEL | REPORT | COMMAND #
#########################################################################################################################################################################################################################################
# Functions | Cluster-wide | maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_14 #
# Functions | Per-node | maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_14 #
# Functions | Per-process | maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_14 #
# Functions | Per-thread | maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_14 #
# Loops | Cluster-wide | maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_14 #
# Loops | Per-node | maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_14 #
# Loops | Per-process | maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_14 #
# Loops | Per-thread | maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-406-3192/llama.cpp/run/oneview_runs/multicore/armclang/maqao_2025-11-25_09-52-02/tools/lprof_npsu_run_14 #
#########################################################################################################################################################################################################################################
