* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 28628 tid 28695 thread 1 bound to OS proc set {1}
OMP: pid 28628 tid 28696 thread 2 bound to OS proc set {2}
OMP: pid 28628 tid 28628 thread 0 bound to OS proc set {0}
OMP: pid 28628 tid 28703 thread 9 bound to OS proc set {9}
OMP: pid 28628 tid 28704 thread 10 bound to OS proc set {10}
OMP: pid 28628 tid 28702 thread 8 bound to OS proc set {8}
OMP: pid 28628 tid 28698 thread 4 bound to OS proc set {4}
OMP: pid 28628 tid 28699 thread 5 bound to OS proc set {5}
OMP: pid 28628 tid 28707 thread 13 bound to OS proc set {13}
OMP: pid 28628 tid 28697 thread 3 bound to OS proc set {3}
OMP: pid 28628 tid 28700 thread 6 bound to OS proc set {6}
OMP: pid 28628 tid 28701 thread 7 bound to OS proc set {7}
OMP: pid 28628 tid 28709 thread 15 bound to OS proc set {15}
OMP: pid 28628 tid 28708 thread 14 bound to OS proc set {14}
OMP: pid 28628 tid 28711 thread 17 bound to OS proc set {17}
OMP: pid 28628 tid 28710 thread 16 bound to OS proc set {16}
OMP: pid 28628 tid 28713 thread 19 bound to OS proc set {19}
OMP: pid 28628 tid 28706 thread 12 bound to OS proc set {12}
OMP: pid 28628 tid 28712 thread 18 bound to OS proc set {18}
OMP: pid 28628 tid 28705 thread 11 bound to OS proc set {11}
OMP: pid 28628 tid 28727 thread 33 bound to OS proc set {33}
OMP: pid 28628 tid 28728 thread 34 bound to OS proc set {34}
OMP: pid 28628 tid 28743 thread 49 bound to OS proc set {49}
OMP: pid 28628 tid 28714 thread 20 bound to OS proc set {20}
OMP: pid 28628 tid 28729 thread 35 bound to OS proc set {35}
OMP: pid 28628 tid 28715 thread 21 bound to OS proc set {21}
OMP: pid 28628 tid 28716 thread 22 bound to OS proc set {22}
OMP: pid 28628 tid 28718 thread 24 bound to OS proc set {24}
OMP: pid 28628 tid 28717 thread 23 bound to OS proc set {23}
OMP: pid 28628 tid 28745 thread 51 bound to OS proc set {51}
OMP: pid 28628 tid 28719 thread 25 bound to OS proc set {25}
OMP: pid 28628 tid 28720 thread 26 bound to OS proc set {26}
OMP: pid 28628 tid 28744 thread 50 bound to OS proc set {50}
OMP: pid 28628 tid 28722 thread 28 bound to OS proc set {28}
OMP: pid 28628 tid 28726 thread 32 bound to OS proc set {32}
OMP: pid 28628 tid 28721 thread 27 bound to OS proc set {27}
OMP: pid 28628 tid 28723 thread 29 bound to OS proc set {29}
OMP: pid 28628 tid 28730 thread 36 bound to OS proc set {36}
OMP: pid 28628 tid 28742 thread 48 bound to OS proc set {48}
OMP: pid 28628 tid 28738 thread 44 bound to OS proc set {44}
OMP: pid 28628 tid 28732 thread 38 bound to OS proc set {38}
OMP: pid 28628 tid 28741 thread 47 bound to OS proc set {47}
OMP: pid 28628 tid 28735 thread 41 bound to OS proc set {41}
OMP: pid 28628 tid 28747 thread 53 bound to OS proc set {53}
OMP: pid 28628 tid 28739 thread 45 bound to OS proc set {45}
OMP: pid 28628 tid 28746 thread 52 bound to OS proc set {52}
OMP: pid 28628 tid 28736 thread 42 bound to OS proc set {42}
OMP: pid 28628 tid 28725 thread 31 bound to OS proc set {31}
OMP: pid 28628 tid 28740 thread 46 bound to OS proc set {46}
OMP: pid 28628 tid 28748 thread 54 bound to OS proc set {54}
OMP: pid 28628 tid 28724 thread 30 bound to OS proc set {30}
OMP: pid 28628 tid 28750 thread 56 bound to OS proc set {56}
OMP: pid 28628 tid 28751 thread 57 bound to OS proc set {57}
OMP: pid 28628 tid 28749 thread 55 bound to OS proc set {55}
OMP: pid 28628 tid 28754 thread 60 bound to OS proc set {60}
OMP: pid 28628 tid 28757 thread 63 bound to OS proc set {63}
OMP: pid 28628 tid 28755 thread 61 bound to OS proc set {61}
OMP: pid 28628 tid 28733 thread 39 bound to OS proc set {39}
OMP: pid 28628 tid 28753 thread 59 bound to OS proc set {59}
OMP: pid 28628 tid 28731 thread 37 bound to OS proc set {37}
OMP: pid 28628 tid 28756 thread 62 bound to OS proc set {62}
OMP: pid 28628 tid 28752 thread 58 bound to OS proc set {58}
OMP: pid 28628 tid 28737 thread 43 bound to OS proc set {43}
OMP: pid 28628 tid 28734 thread 40 bound to OS proc set {40}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_0

To display your profiling results:
#############################################################################################################################################################################################################################
#    LEVEL    |     REPORT     |                                                                                          COMMAND                                                                                           #
#############################################################################################################################################################################################################################
#  Functions  |  Cluster-wide  |  maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_0      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_0  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_0  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_0  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_0      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_0  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_0  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_0  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 28789 tid 28789 thread 0 bound to OS proc set {0}
OMP: pid 28789 tid 28864 thread 9 bound to OS proc set {9}
OMP: pid 28789 tid 28863 thread 8 bound to OS proc set {8}
OMP: pid 28789 tid 28858 thread 3 bound to OS proc set {3}
OMP: pid 28789 tid 28865 thread 10 bound to OS proc set {10}
OMP: pid 28789 tid 28868 thread 13 bound to OS proc set {13}
OMP: pid 28789 tid 28857 thread 2 bound to OS proc set {2}
OMP: pid 28789 tid 28856 thread 1 bound to OS proc set {1}
OMP: pid 28789 tid 28867 thread 12 bound to OS proc set {12}
OMP: pid 28789 tid 28866 thread 11 bound to OS proc set {11}
OMP: pid 28789 tid 28869 thread 14 bound to OS proc set {14}
OMP: pid 28789 tid 28872 thread 17 bound to OS proc set {17}
OMP: pid 28789 tid 28873 thread 18 bound to OS proc set {18}
OMP: pid 28789 tid 28888 thread 33 bound to OS proc set {33}
OMP: pid 28789 tid 28859 thread 4 bound to OS proc set {4}
OMP: pid 28789 tid 28871 thread 16 bound to OS proc set {16}
OMP: pid 28789 tid 28889 thread 34 bound to OS proc set {34}
OMP: pid 28789 tid 28860 thread 5 bound to OS proc set {5}
OMP: pid 28789 tid 28861 thread 6 bound to OS proc set {6}
OMP: pid 28789 tid 28890 thread 35 bound to OS proc set {35}
OMP: pid 28789 tid 28862 thread 7 bound to OS proc set {7}
OMP: pid 28789 tid 28904 thread 49 bound to OS proc set {49}
OMP: pid 28789 tid 28870 thread 15 bound to OS proc set {15}
OMP: pid 28789 tid 28887 thread 32 bound to OS proc set {32}
OMP: pid 28789 tid 28874 thread 19 bound to OS proc set {19}
OMP: pid 28789 tid 28880 thread 25 bound to OS proc set {25}
OMP: pid 28789 tid 28879 thread 24 bound to OS proc set {24}
OMP: pid 28789 tid 28884 thread 29 bound to OS proc set {29}
OMP: pid 28789 tid 28883 thread 28 bound to OS proc set {28}
OMP: pid 28789 tid 28906 thread 51 bound to OS proc set {51}
OMP: pid 28789 tid 28892 thread 37 bound to OS proc set {37}
OMP: pid 28789 tid 28905 thread 50 bound to OS proc set {50}
OMP: pid 28789 tid 28903 thread 48 bound to OS proc set {48}
OMP: pid 28789 tid 28885 thread 30 bound to OS proc set {30}
OMP: pid 28789 tid 28891 thread 36 bound to OS proc set {36}
OMP: pid 28789 tid 28893 thread 38 bound to OS proc set {38}
OMP: pid 28789 tid 28875 thread 20 bound to OS proc set {20}
OMP: pid 28789 tid 28895 thread 40 bound to OS proc set {40}
OMP: pid 28789 tid 28876 thread 21 bound to OS proc set {21}
OMP: pid 28789 tid 28881 thread 26 bound to OS proc set {26}
OMP: pid 28789 tid 28877 thread 22 bound to OS proc set {22}
OMP: pid 28789 tid 28909 thread 54 bound to OS proc set {54}
OMP: pid 28789 tid 28878 thread 23 bound to OS proc set {23}
OMP: pid 28789 tid 28908 thread 53 bound to OS proc set {53}
OMP: pid 28789 tid 28907 thread 52 bound to OS proc set {52}
OMP: pid 28789 tid 28912 thread 57 bound to OS proc set {57}
OMP: pid 28789 tid 28882 thread 27 bound to OS proc set {27}
OMP: pid 28789 tid 28915 thread 60 bound to OS proc set {60}
OMP: pid 28789 tid 28913 thread 58 bound to OS proc set {58}
OMP: pid 28789 tid 28894 thread 39 bound to OS proc set {39}
OMP: pid 28789 tid 28900 thread 45 bound to OS proc set {45}
OMP: pid 28789 tid 28916 thread 61 bound to OS proc set {61}
OMP: pid 28789 tid 28918 thread 63 bound to OS proc set {63}
OMP: pid 28789 tid 28914 thread 59 bound to OS proc set {59}
OMP: pid 28789 tid 28897 thread 42 bound to OS proc set {42}
OMP: pid 28789 tid 28898 thread 43 bound to OS proc set {43}
OMP: pid 28789 tid 28902 thread 47 bound to OS proc set {47}
OMP: pid 28789 tid 28910 thread 55 bound to OS proc set {55}
OMP: pid 28789 tid 28911 thread 56 bound to OS proc set {56}
OMP: pid 28789 tid 28917 thread 62 bound to OS proc set {62}
OMP: pid 28789 tid 28901 thread 46 bound to OS proc set {46}
OMP: pid 28789 tid 28896 thread 41 bound to OS proc set {41}
OMP: pid 28789 tid 28899 thread 44 bound to OS proc set {44}
OMP: pid 28789 tid 28886 thread 31 bound to OS proc set {31}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_1

To display your profiling results:
#############################################################################################################################################################################################################################
#    LEVEL    |     REPORT     |                                                                                          COMMAND                                                                                           #
#############################################################################################################################################################################################################################
#  Functions  |  Cluster-wide  |  maqao lprof -df xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_1      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_1  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_1  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_1  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_1      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_1  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_1  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_1  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 28947 tid 28947 thread 0 bound to OS proc set {0}
OMP: pid 28947 tid 29014 thread 1 bound to OS proc set {1}
OMP: pid 28947 tid 29015 thread 2 bound to OS proc set {2}
OMP: pid 28947 tid 29021 thread 8 bound to OS proc set {8}
OMP: pid 28947 tid 29022 thread 9 bound to OS proc set {9}
OMP: pid 28947 tid 29025 thread 12 bound to OS proc set {12}
OMP: pid 28947 tid 29016 thread 3 bound to OS proc set {3}
OMP: pid 28947 tid 29023 thread 10 bound to OS proc set {10}
OMP: pid 28947 tid 29026 thread 13 bound to OS proc set {13}
OMP: pid 28947 tid 29027 thread 14 bound to OS proc set {14}
OMP: pid 28947 tid 29030 thread 17 bound to OS proc set {17}
OMP: pid 28947 tid 29024 thread 11 bound to OS proc set {11}
OMP: pid 28947 tid 29028 thread 15 bound to OS proc set {15}
OMP: pid 28947 tid 29031 thread 18 bound to OS proc set {18}
OMP: pid 28947 tid 29046 thread 33 bound to OS proc set {33}
OMP: pid 28947 tid 29017 thread 4 bound to OS proc set {4}
OMP: pid 28947 tid 29032 thread 19 bound to OS proc set {19}
OMP: pid 28947 tid 29047 thread 34 bound to OS proc set {34}
OMP: pid 28947 tid 29018 thread 5 bound to OS proc set {5}
OMP: pid 28947 tid 29029 thread 16 bound to OS proc set {16}
OMP: pid 28947 tid 29019 thread 6 bound to OS proc set {6}
OMP: pid 28947 tid 29048 thread 35 bound to OS proc set {35}
OMP: pid 28947 tid 29045 thread 32 bound to OS proc set {32}
OMP: pid 28947 tid 29034 thread 21 bound to OS proc set {21}
OMP: pid 28947 tid 29037 thread 24 bound to OS proc set {24}
OMP: pid 28947 tid 29038 thread 25 bound to OS proc set {25}
OMP: pid 28947 tid 29033 thread 20 bound to OS proc set {20}
OMP: pid 28947 tid 29035 thread 22 bound to OS proc set {22}
OMP: pid 28947 tid 29050 thread 37 bound to OS proc set {37}
OMP: pid 28947 tid 29039 thread 26 bound to OS proc set {26}
OMP: pid 28947 tid 29042 thread 29 bound to OS proc set {29}
OMP: pid 28947 tid 29041 thread 28 bound to OS proc set {28}
OMP: pid 28947 tid 29040 thread 27 bound to OS proc set {27}
OMP: pid 28947 tid 29036 thread 23 bound to OS proc set {23}
OMP: pid 28947 tid 29063 thread 50 bound to OS proc set {50}
OMP: pid 28947 tid 29049 thread 36 bound to OS proc set {36}
OMP: pid 28947 tid 29051 thread 38 bound to OS proc set {38}
OMP: pid 28947 tid 29020 thread 7 bound to OS proc set {7}
OMP: pid 28947 tid 29043 thread 30 bound to OS proc set {30}
OMP: pid 28947 tid 29054 thread 41 bound to OS proc set {41}
OMP: pid 28947 tid 29052 thread 39 bound to OS proc set {39}
OMP: pid 28947 tid 29044 thread 31 bound to OS proc set {31}
OMP: pid 28947 tid 29058 thread 45 bound to OS proc set {45}
OMP: pid 28947 tid 29053 thread 40 bound to OS proc set {40}
OMP: pid 28947 tid 29064 thread 51 bound to OS proc set {51}
OMP: pid 28947 tid 29057 thread 44 bound to OS proc set {44}
OMP: pid 28947 tid 29062 thread 49 bound to OS proc set {49}
OMP: pid 28947 tid 29061 thread 48 bound to OS proc set {48}
OMP: pid 28947 tid 29066 thread 53 bound to OS proc set {53}
OMP: pid 28947 tid 29065 thread 52 bound to OS proc set {52}
OMP: pid 28947 tid 29059 thread 46 bound to OS proc set {46}
OMP: pid 28947 tid 29060 thread 47 bound to OS proc set {47}
OMP: pid 28947 tid 29068 thread 55 bound to OS proc set {55}
OMP: pid 28947 tid 29070 thread 57 bound to OS proc set {57}
OMP: pid 28947 tid 29071 thread 58 bound to OS proc set {58}
OMP: pid 28947 tid 29056 thread 43 bound to OS proc set {43}
OMP: pid 28947 tid 29067 thread 54 bound to OS proc set {54}
OMP: pid 28947 tid 29055 thread 42 bound to OS proc set {42}
OMP: pid 28947 tid 29073 thread 60 bound to OS proc set {60}
OMP: pid 28947 tid 29074 thread 61 bound to OS proc set {61}
OMP: pid 28947 tid 29072 thread 59 bound to OS proc set {59}
OMP: pid 28947 tid 29069 thread 56 bound to OS proc set {56}
OMP: pid 28947 tid 29075 thread 62 bound to OS proc set {62}
OMP: pid 28947 tid 29076 thread 63 bound to OS proc set {63}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/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-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_2      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_2  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_2  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_2  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_2      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_2  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_2  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_2  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 29105 tid 29105 thread 0 bound to OS proc set {0}
OMP: pid 29105 tid 29172 thread 1 bound to OS proc set {1}
OMP: pid 29105 tid 29173 thread 2 bound to OS proc set {2}
OMP: pid 29105 tid 29174 thread 3 bound to OS proc set {3}
OMP: pid 29105 tid 29175 thread 4 bound to OS proc set {4}
OMP: pid 29105 tid 29176 thread 5 bound to OS proc set {5}
OMP: pid 29105 tid 29180 thread 9 bound to OS proc set {9}
OMP: pid 29105 tid 29177 thread 6 bound to OS proc set {6}
OMP: pid 29105 tid 29181 thread 10 bound to OS proc set {10}
OMP: pid 29105 tid 29184 thread 13 bound to OS proc set {13}
OMP: pid 29105 tid 29182 thread 11 bound to OS proc set {11}
OMP: pid 29105 tid 29179 thread 8 bound to OS proc set {8}
OMP: pid 29105 tid 29185 thread 14 bound to OS proc set {14}
OMP: pid 29105 tid 29186 thread 15 bound to OS proc set {15}
OMP: pid 29105 tid 29178 thread 7 bound to OS proc set {7}
OMP: pid 29105 tid 29188 thread 17 bound to OS proc set {17}
OMP: pid 29105 tid 29189 thread 18 bound to OS proc set {18}
OMP: pid 29105 tid 29183 thread 12 bound to OS proc set {12}
OMP: pid 29105 tid 29204 thread 33 bound to OS proc set {33}
OMP: pid 29105 tid 29220 thread 49 bound to OS proc set {49}
OMP: pid 29105 tid 29190 thread 19 bound to OS proc set {19}
OMP: pid 29105 tid 29187 thread 16 bound to OS proc set {16}
OMP: pid 29105 tid 29205 thread 34 bound to OS proc set {34}
OMP: pid 29105 tid 29221 thread 50 bound to OS proc set {50}
OMP: pid 29105 tid 29222 thread 51 bound to OS proc set {51}
OMP: pid 29105 tid 29191 thread 20 bound to OS proc set {20}
OMP: pid 29105 tid 29206 thread 35 bound to OS proc set {35}
OMP: pid 29105 tid 29195 thread 24 bound to OS proc set {24}
OMP: pid 29105 tid 29219 thread 48 bound to OS proc set {48}
OMP: pid 29105 tid 29192 thread 21 bound to OS proc set {21}
OMP: pid 29105 tid 29193 thread 22 bound to OS proc set {22}
OMP: pid 29105 tid 29199 thread 28 bound to OS proc set {28}
OMP: pid 29105 tid 29196 thread 25 bound to OS proc set {25}
OMP: pid 29105 tid 29197 thread 26 bound to OS proc set {26}
OMP: pid 29105 tid 29194 thread 23 bound to OS proc set {23}
OMP: pid 29105 tid 29211 thread 40 bound to OS proc set {40}
OMP: pid 29105 tid 29203 thread 32 bound to OS proc set {32}
OMP: pid 29105 tid 29200 thread 29 bound to OS proc set {29}
OMP: pid 29105 tid 29223 thread 52 bound to OS proc set {52}
OMP: pid 29105 tid 29209 thread 38 bound to OS proc set {38}
OMP: pid 29105 tid 29202 thread 31 bound to OS proc set {31}
OMP: pid 29105 tid 29226 thread 55 bound to OS proc set {55}
OMP: pid 29105 tid 29228 thread 57 bound to OS proc set {57}
OMP: pid 29105 tid 29201 thread 30 bound to OS proc set {30}
OMP: pid 29105 tid 29207 thread 36 bound to OS proc set {36}
OMP: pid 29105 tid 29227 thread 56 bound to OS proc set {56}
OMP: pid 29105 tid 29231 thread 60 bound to OS proc set {60}
OMP: pid 29105 tid 29225 thread 54 bound to OS proc set {54}
OMP: pid 29105 tid 29217 thread 46 bound to OS proc set {46}
OMP: pid 29105 tid 29212 thread 41 bound to OS proc set {41}
OMP: pid 29105 tid 29229 thread 58 bound to OS proc set {58}
OMP: pid 29105 tid 29230 thread 59 bound to OS proc set {59}
OMP: pid 29105 tid 29234 thread 63 bound to OS proc set {63}
OMP: pid 29105 tid 29216 thread 45 bound to OS proc set {45}
OMP: pid 29105 tid 29208 thread 37 bound to OS proc set {37}
OMP: pid 29105 tid 29213 thread 42 bound to OS proc set {42}
OMP: pid 29105 tid 29224 thread 53 bound to OS proc set {53}
OMP: pid 29105 tid 29218 thread 47 bound to OS proc set {47}
OMP: pid 29105 tid 29198 thread 27 bound to OS proc set {27}
OMP: pid 29105 tid 29233 thread 62 bound to OS proc set {62}
OMP: pid 29105 tid 29232 thread 61 bound to OS proc set {61}
OMP: pid 29105 tid 29214 thread 43 bound to OS proc set {43}
OMP: pid 29105 tid 29215 thread 44 bound to OS proc set {44}
OMP: pid 29105 tid 29210 thread 39 bound to OS proc set {39}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/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-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_3      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_3  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_3  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_3  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_3      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_3  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_3  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_3  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 29263 tid 29330 thread 1 bound to OS proc set {1}
OMP: pid 29263 tid 29331 thread 2 bound to OS proc set {2}
OMP: pid 29263 tid 29263 thread 0 bound to OS proc set {0}
OMP: pid 29263 tid 29332 thread 3 bound to OS proc set {3}
OMP: pid 29263 tid 29334 thread 5 bound to OS proc set {5}
OMP: pid 29263 tid 29333 thread 4 bound to OS proc set {4}
OMP: pid 29263 tid 29338 thread 9 bound to OS proc set {9}
OMP: pid 29263 tid 29341 thread 12 bound to OS proc set {12}
OMP: pid 29263 tid 29337 thread 8 bound to OS proc set {8}
OMP: pid 29263 tid 29335 thread 6 bound to OS proc set {6}
OMP: pid 29263 tid 29342 thread 13 bound to OS proc set {13}
OMP: pid 29263 tid 29339 thread 10 bound to OS proc set {10}
OMP: pid 29263 tid 29343 thread 14 bound to OS proc set {14}
OMP: pid 29263 tid 29340 thread 11 bound to OS proc set {11}
OMP: pid 29263 tid 29344 thread 15 bound to OS proc set {15}
OMP: pid 29263 tid 29346 thread 17 bound to OS proc set {17}
OMP: pid 29263 tid 29336 thread 7 bound to OS proc set {7}
OMP: pid 29263 tid 29347 thread 18 bound to OS proc set {18}
OMP: pid 29263 tid 29345 thread 16 bound to OS proc set {16}
OMP: pid 29263 tid 29348 thread 19 bound to OS proc set {19}
OMP: pid 29263 tid 29362 thread 33 bound to OS proc set {33}
OMP: pid 29263 tid 29378 thread 49 bound to OS proc set {49}
OMP: pid 29263 tid 29361 thread 32 bound to OS proc set {32}
OMP: pid 29263 tid 29349 thread 20 bound to OS proc set {20}
OMP: pid 29263 tid 29354 thread 25 bound to OS proc set {25}
OMP: pid 29263 tid 29353 thread 24 bound to OS proc set {24}
OMP: pid 29263 tid 29355 thread 26 bound to OS proc set {26}
OMP: pid 29263 tid 29363 thread 34 bound to OS proc set {34}
OMP: pid 29263 tid 29357 thread 28 bound to OS proc set {28}
OMP: pid 29263 tid 29358 thread 29 bound to OS proc set {29}
OMP: pid 29263 tid 29364 thread 35 bound to OS proc set {35}
OMP: pid 29263 tid 29359 thread 30 bound to OS proc set {30}
OMP: pid 29263 tid 29380 thread 51 bound to OS proc set {51}
OMP: pid 29263 tid 29379 thread 50 bound to OS proc set {50}
OMP: pid 29263 tid 29350 thread 21 bound to OS proc set {21}
OMP: pid 29263 tid 29351 thread 22 bound to OS proc set {22}
OMP: pid 29263 tid 29365 thread 36 bound to OS proc set {36}
OMP: pid 29263 tid 29352 thread 23 bound to OS proc set {23}
OMP: pid 29263 tid 29356 thread 27 bound to OS proc set {27}
OMP: pid 29263 tid 29366 thread 37 bound to OS proc set {37}
OMP: pid 29263 tid 29381 thread 52 bound to OS proc set {52}
OMP: pid 29263 tid 29367 thread 38 bound to OS proc set {38}
OMP: pid 29263 tid 29370 thread 41 bound to OS proc set {41}
OMP: pid 29263 tid 29371 thread 42 bound to OS proc set {42}
OMP: pid 29263 tid 29360 thread 31 bound to OS proc set {31}
OMP: pid 29263 tid 29369 thread 40 bound to OS proc set {40}
OMP: pid 29263 tid 29382 thread 53 bound to OS proc set {53}
OMP: pid 29263 tid 29383 thread 54 bound to OS proc set {54}
OMP: pid 29263 tid 29375 thread 46 bound to OS proc set {46}
OMP: pid 29263 tid 29374 thread 45 bound to OS proc set {45}
OMP: pid 29263 tid 29376 thread 47 bound to OS proc set {47}
OMP: pid 29263 tid 29385 thread 56 bound to OS proc set {56}
OMP: pid 29263 tid 29386 thread 57 bound to OS proc set {57}
OMP: pid 29263 tid 29387 thread 58 bound to OS proc set {58}
OMP: pid 29263 tid 29389 thread 60 bound to OS proc set {60}
OMP: pid 29263 tid 29368 thread 39 bound to OS proc set {39}
OMP: pid 29263 tid 29373 thread 44 bound to OS proc set {44}
OMP: pid 29263 tid 29372 thread 43 bound to OS proc set {43}
OMP: pid 29263 tid 29377 thread 48 bound to OS proc set {48}
OMP: pid 29263 tid 29390 thread 61 bound to OS proc set {61}
OMP: pid 29263 tid 29391 thread 62 bound to OS proc set {62}
OMP: pid 29263 tid 29388 thread 59 bound to OS proc set {59}
OMP: pid 29263 tid 29384 thread 55 bound to OS proc set {55}
OMP: pid 29263 tid 29392 thread 63 bound to OS proc set {63}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/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-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_4      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_4  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_4  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_4  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_4      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_4  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_4  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_4  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 29421 tid 29421 thread 0 bound to OS proc set {0}
OMP: pid 29421 tid 29488 thread 1 bound to OS proc set {1}
OMP: pid 29421 tid 29489 thread 2 bound to OS proc set {2}
OMP: pid 29421 tid 29496 thread 9 bound to OS proc set {9}
OMP: pid 29421 tid 29495 thread 8 bound to OS proc set {8}
OMP: pid 29421 tid 29490 thread 3 bound to OS proc set {3}
OMP: pid 29421 tid 29497 thread 10 bound to OS proc set {10}
OMP: pid 29421 tid 29500 thread 13 bound to OS proc set {13}
OMP: pid 29421 tid 29499 thread 12 bound to OS proc set {12}
OMP: pid 29421 tid 29504 thread 17 bound to OS proc set {17}
OMP: pid 29421 tid 29498 thread 11 bound to OS proc set {11}
OMP: pid 29421 tid 29505 thread 18 bound to OS proc set {18}
OMP: pid 29421 tid 29501 thread 14 bound to OS proc set {14}
OMP: pid 29421 tid 29520 thread 33 bound to OS proc set {33}
OMP: pid 29421 tid 29521 thread 34 bound to OS proc set {34}
OMP: pid 29421 tid 29491 thread 4 bound to OS proc set {4}
OMP: pid 29421 tid 29536 thread 49 bound to OS proc set {49}
OMP: pid 29421 tid 29522 thread 35 bound to OS proc set {35}
OMP: pid 29421 tid 29492 thread 5 bound to OS proc set {5}
OMP: pid 29421 tid 29493 thread 6 bound to OS proc set {6}
OMP: pid 29421 tid 29503 thread 16 bound to OS proc set {16}
OMP: pid 29421 tid 29537 thread 50 bound to OS proc set {50}
OMP: pid 29421 tid 29538 thread 51 bound to OS proc set {51}
OMP: pid 29421 tid 29519 thread 32 bound to OS proc set {32}
OMP: pid 29421 tid 29494 thread 7 bound to OS proc set {7}
OMP: pid 29421 tid 29502 thread 15 bound to OS proc set {15}
OMP: pid 29421 tid 29535 thread 48 bound to OS proc set {48}
OMP: pid 29421 tid 29506 thread 19 bound to OS proc set {19}
OMP: pid 29421 tid 29524 thread 37 bound to OS proc set {37}
OMP: pid 29421 tid 29512 thread 25 bound to OS proc set {25}
OMP: pid 29421 tid 29515 thread 28 bound to OS proc set {28}
OMP: pid 29421 tid 29511 thread 24 bound to OS proc set {24}
OMP: pid 29421 tid 29525 thread 38 bound to OS proc set {38}
OMP: pid 29421 tid 29516 thread 29 bound to OS proc set {29}
OMP: pid 29421 tid 29527 thread 40 bound to OS proc set {40}
OMP: pid 29421 tid 29523 thread 36 bound to OS proc set {36}
OMP: pid 29421 tid 29532 thread 45 bound to OS proc set {45}
OMP: pid 29421 tid 29528 thread 41 bound to OS proc set {41}
OMP: pid 29421 tid 29518 thread 31 bound to OS proc set {31}
OMP: pid 29421 tid 29526 thread 39 bound to OS proc set {39}
OMP: pid 29421 tid 29529 thread 42 bound to OS proc set {42}
OMP: pid 29421 tid 29531 thread 44 bound to OS proc set {44}
OMP: pid 29421 tid 29508 thread 21 bound to OS proc set {21}
OMP: pid 29421 tid 29509 thread 22 bound to OS proc set {22}
OMP: pid 29421 tid 29513 thread 26 bound to OS proc set {26}
OMP: pid 29421 tid 29514 thread 27 bound to OS proc set {27}
OMP: pid 29421 tid 29540 thread 53 bound to OS proc set {53}
OMP: pid 29421 tid 29544 thread 57 bound to OS proc set {57}
OMP: pid 29421 tid 29541 thread 54 bound to OS proc set {54}
OMP: pid 29421 tid 29545 thread 58 bound to OS proc set {58}
OMP: pid 29421 tid 29543 thread 56 bound to OS proc set {56}
OMP: pid 29421 tid 29542 thread 55 bound to OS proc set {55}
OMP: pid 29421 tid 29507 thread 20 bound to OS proc set {20}
OMP: pid 29421 tid 29517 thread 30 bound to OS proc set {30}
OMP: pid 29421 tid 29534 thread 47 bound to OS proc set {47}
OMP: pid 29421 tid 29530 thread 43 bound to OS proc set {43}
OMP: pid 29421 tid 29510 thread 23 bound to OS proc set {23}
OMP: pid 29421 tid 29547 thread 60 bound to OS proc set {60}
OMP: pid 29421 tid 29539 thread 52 bound to OS proc set {52}
OMP: pid 29421 tid 29533 thread 46 bound to OS proc set {46}
OMP: pid 29421 tid 29548 thread 61 bound to OS proc set {61}
OMP: pid 29421 tid 29550 thread 63 bound to OS proc set {63}
OMP: pid 29421 tid 29549 thread 62 bound to OS proc set {62}
OMP: pid 29421 tid 29546 thread 59 bound to OS proc set {59}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/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-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_5      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_5  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_5  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_5  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_5      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_5  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_5  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_5  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 29579 tid 29648 thread 3 bound to OS proc set {3}
OMP: pid 29579 tid 29646 thread 1 bound to OS proc set {1}
OMP: pid 29579 tid 29647 thread 2 bound to OS proc set {2}
OMP: pid 29579 tid 29579 thread 0 bound to OS proc set {0}
OMP: pid 29579 tid 29650 thread 5 bound to OS proc set {5}
OMP: pid 29579 tid 29649 thread 4 bound to OS proc set {4}
OMP: pid 29579 tid 29651 thread 6 bound to OS proc set {6}
OMP: pid 29579 tid 29655 thread 10 bound to OS proc set {10}
OMP: pid 29579 tid 29657 thread 12 bound to OS proc set {12}
OMP: pid 29579 tid 29654 thread 9 bound to OS proc set {9}
OMP: pid 29579 tid 29659 thread 14 bound to OS proc set {14}
OMP: pid 29579 tid 29652 thread 7 bound to OS proc set {7}
OMP: pid 29579 tid 29653 thread 8 bound to OS proc set {8}
OMP: pid 29579 tid 29658 thread 13 bound to OS proc set {13}
OMP: pid 29579 tid 29656 thread 11 bound to OS proc set {11}
OMP: pid 29579 tid 29660 thread 15 bound to OS proc set {15}
OMP: pid 29579 tid 29662 thread 17 bound to OS proc set {17}
OMP: pid 29579 tid 29664 thread 19 bound to OS proc set {19}
OMP: pid 29579 tid 29678 thread 33 bound to OS proc set {33}
OMP: pid 29579 tid 29663 thread 18 bound to OS proc set {18}
OMP: pid 29579 tid 29694 thread 49 bound to OS proc set {49}
OMP: pid 29579 tid 29661 thread 16 bound to OS proc set {16}
OMP: pid 29579 tid 29680 thread 35 bound to OS proc set {35}
OMP: pid 29579 tid 29696 thread 51 bound to OS proc set {51}
OMP: pid 29579 tid 29666 thread 21 bound to OS proc set {21}
OMP: pid 29579 tid 29679 thread 34 bound to OS proc set {34}
OMP: pid 29579 tid 29665 thread 20 bound to OS proc set {20}
OMP: pid 29579 tid 29695 thread 50 bound to OS proc set {50}
OMP: pid 29579 tid 29669 thread 24 bound to OS proc set {24}
OMP: pid 29579 tid 29667 thread 22 bound to OS proc set {22}
OMP: pid 29579 tid 29673 thread 28 bound to OS proc set {28}
OMP: pid 29579 tid 29671 thread 26 bound to OS proc set {26}
OMP: pid 29579 tid 29682 thread 37 bound to OS proc set {37}
OMP: pid 29579 tid 29668 thread 23 bound to OS proc set {23}
OMP: pid 29579 tid 29670 thread 25 bound to OS proc set {25}
OMP: pid 29579 tid 29683 thread 38 bound to OS proc set {38}
OMP: pid 29579 tid 29685 thread 40 bound to OS proc set {40}
OMP: pid 29579 tid 29681 thread 36 bound to OS proc set {36}
OMP: pid 29579 tid 29672 thread 27 bound to OS proc set {27}
OMP: pid 29579 tid 29677 thread 32 bound to OS proc set {32}
OMP: pid 29579 tid 29674 thread 29 bound to OS proc set {29}
OMP: pid 29579 tid 29688 thread 43 bound to OS proc set {43}
OMP: pid 29579 tid 29686 thread 41 bound to OS proc set {41}
OMP: pid 29579 tid 29690 thread 45 bound to OS proc set {45}
OMP: pid 29579 tid 29693 thread 48 bound to OS proc set {48}
OMP: pid 29579 tid 29691 thread 46 bound to OS proc set {46}
OMP: pid 29579 tid 29675 thread 30 bound to OS proc set {30}
OMP: pid 29579 tid 29689 thread 44 bound to OS proc set {44}
OMP: pid 29579 tid 29699 thread 54 bound to OS proc set {54}
OMP: pid 29579 tid 29697 thread 52 bound to OS proc set {52}
OMP: pid 29579 tid 29687 thread 42 bound to OS proc set {42}
OMP: pid 29579 tid 29684 thread 39 bound to OS proc set {39}
OMP: pid 29579 tid 29698 thread 53 bound to OS proc set {53}
OMP: pid 29579 tid 29706 thread 61 bound to OS proc set {61}
OMP: pid 29579 tid 29676 thread 31 bound to OS proc set {31}
OMP: pid 29579 tid 29702 thread 57 bound to OS proc set {57}
OMP: pid 29579 tid 29707 thread 62 bound to OS proc set {62}
OMP: pid 29579 tid 29692 thread 47 bound to OS proc set {47}
OMP: pid 29579 tid 29700 thread 55 bound to OS proc set {55}
OMP: pid 29579 tid 29703 thread 58 bound to OS proc set {58}
OMP: pid 29579 tid 29701 thread 56 bound to OS proc set {56}
OMP: pid 29579 tid 29704 thread 59 bound to OS proc set {59}
OMP: pid 29579 tid 29705 thread 60 bound to OS proc set {60}
OMP: pid 29579 tid 29708 thread 63 bound to OS proc set {63}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/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-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_6      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_6  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_6  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_6  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_6      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_6  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_6  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_6  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 29737 tid 29804 thread 1 bound to OS proc set {1}
OMP: pid 29737 tid 29805 thread 2 bound to OS proc set {2}
OMP: pid 29737 tid 29806 thread 3 bound to OS proc set {3}
OMP: pid 29737 tid 29737 thread 0 bound to OS proc set {0}
OMP: pid 29737 tid 29808 thread 5 bound to OS proc set {5}
OMP: pid 29737 tid 29807 thread 4 bound to OS proc set {4}
OMP: pid 29737 tid 29816 thread 13 bound to OS proc set {13}
OMP: pid 29737 tid 29811 thread 8 bound to OS proc set {8}
OMP: pid 29737 tid 29812 thread 9 bound to OS proc set {9}
OMP: pid 29737 tid 29809 thread 6 bound to OS proc set {6}
OMP: pid 29737 tid 29815 thread 12 bound to OS proc set {12}
OMP: pid 29737 tid 29810 thread 7 bound to OS proc set {7}
OMP: pid 29737 tid 29813 thread 10 bound to OS proc set {10}
OMP: pid 29737 tid 29817 thread 14 bound to OS proc set {14}
OMP: pid 29737 tid 29814 thread 11 bound to OS proc set {11}
OMP: pid 29737 tid 29821 thread 18 bound to OS proc set {18}
OMP: pid 29737 tid 29822 thread 19 bound to OS proc set {19}
OMP: pid 29737 tid 29818 thread 15 bound to OS proc set {15}
OMP: pid 29737 tid 29836 thread 33 bound to OS proc set {33}
OMP: pid 29737 tid 29820 thread 17 bound to OS proc set {17}
OMP: pid 29737 tid 29819 thread 16 bound to OS proc set {16}
OMP: pid 29737 tid 29852 thread 49 bound to OS proc set {49}
OMP: pid 29737 tid 29838 thread 35 bound to OS proc set {35}
OMP: pid 29737 tid 29837 thread 34 bound to OS proc set {34}
OMP: pid 29737 tid 29853 thread 50 bound to OS proc set {50}
OMP: pid 29737 tid 29823 thread 20 bound to OS proc set {20}
OMP: pid 29737 tid 29824 thread 21 bound to OS proc set {21}
OMP: pid 29737 tid 29835 thread 32 bound to OS proc set {32}
OMP: pid 29737 tid 29827 thread 24 bound to OS proc set {24}
OMP: pid 29737 tid 29826 thread 23 bound to OS proc set {23}
OMP: pid 29737 tid 29839 thread 36 bound to OS proc set {36}
OMP: pid 29737 tid 29829 thread 26 bound to OS proc set {26}
OMP: pid 29737 tid 29845 thread 42 bound to OS proc set {42}
OMP: pid 29737 tid 29828 thread 25 bound to OS proc set {25}
OMP: pid 29737 tid 29825 thread 22 bound to OS proc set {22}
OMP: pid 29737 tid 29840 thread 37 bound to OS proc set {37}
OMP: pid 29737 tid 29831 thread 28 bound to OS proc set {28}
OMP: pid 29737 tid 29847 thread 44 bound to OS proc set {44}
OMP: pid 29737 tid 29846 thread 43 bound to OS proc set {43}
OMP: pid 29737 tid 29843 thread 40 bound to OS proc set {40}
OMP: pid 29737 tid 29832 thread 29 bound to OS proc set {29}
OMP: pid 29737 tid 29851 thread 48 bound to OS proc set {48}
OMP: pid 29737 tid 29830 thread 27 bound to OS proc set {27}
OMP: pid 29737 tid 29855 thread 52 bound to OS proc set {52}
OMP: pid 29737 tid 29844 thread 41 bound to OS proc set {41}
OMP: pid 29737 tid 29854 thread 51 bound to OS proc set {51}
OMP: pid 29737 tid 29841 thread 38 bound to OS proc set {38}
OMP: pid 29737 tid 29848 thread 45 bound to OS proc set {45}
OMP: pid 29737 tid 29860 thread 57 bound to OS proc set {57}
OMP: pid 29737 tid 29859 thread 56 bound to OS proc set {56}
OMP: pid 29737 tid 29833 thread 30 bound to OS proc set {30}
OMP: pid 29737 tid 29842 thread 39 bound to OS proc set {39}
OMP: pid 29737 tid 29862 thread 59 bound to OS proc set {59}
OMP: pid 29737 tid 29850 thread 47 bound to OS proc set {47}
OMP: pid 29737 tid 29834 thread 31 bound to OS proc set {31}
OMP: pid 29737 tid 29861 thread 58 bound to OS proc set {58}
OMP: pid 29737 tid 29857 thread 54 bound to OS proc set {54}
OMP: pid 29737 tid 29858 thread 55 bound to OS proc set {55}
OMP: pid 29737 tid 29863 thread 60 bound to OS proc set {60}
OMP: pid 29737 tid 29864 thread 61 bound to OS proc set {61}
OMP: pid 29737 tid 29849 thread 46 bound to OS proc set {46}
OMP: pid 29737 tid 29865 thread 62 bound to OS proc set {62}
OMP: pid 29737 tid 29856 thread 53 bound to OS proc set {53}
OMP: pid 29737 tid 29866 thread 63 bound to OS proc set {63}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/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-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_7      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_7  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_7  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_7  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_7      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_7  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_7  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_7  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 29895 tid 29895 thread 0 bound to OS proc set {0}
OMP: pid 29895 tid 29962 thread 1 bound to OS proc set {1}
OMP: pid 29895 tid 29970 thread 9 bound to OS proc set {9}
OMP: pid 29895 tid 29963 thread 2 bound to OS proc set {2}
OMP: pid 29895 tid 29964 thread 3 bound to OS proc set {3}
OMP: pid 29895 tid 29969 thread 8 bound to OS proc set {8}
OMP: pid 29895 tid 29974 thread 13 bound to OS proc set {13}
OMP: pid 29895 tid 29973 thread 12 bound to OS proc set {12}
OMP: pid 29895 tid 29971 thread 10 bound to OS proc set {10}
OMP: pid 29895 tid 29978 thread 17 bound to OS proc set {17}
OMP: pid 29895 tid 29975 thread 14 bound to OS proc set {14}
OMP: pid 29895 tid 29965 thread 4 bound to OS proc set {4}
OMP: pid 29895 tid 29966 thread 5 bound to OS proc set {5}
OMP: pid 29895 tid 29967 thread 6 bound to OS proc set {6}
OMP: pid 29895 tid 29977 thread 16 bound to OS proc set {16}
OMP: pid 29895 tid 29968 thread 7 bound to OS proc set {7}
OMP: pid 29895 tid 29972 thread 11 bound to OS proc set {11}
OMP: pid 29895 tid 29976 thread 15 bound to OS proc set {15}
OMP: pid 29895 tid 29979 thread 18 bound to OS proc set {18}
OMP: pid 29895 tid 30010 thread 49 bound to OS proc set {49}
OMP: pid 29895 tid 29994 thread 33 bound to OS proc set {33}
OMP: pid 29895 tid 29980 thread 19 bound to OS proc set {19}
OMP: pid 29895 tid 29986 thread 25 bound to OS proc set {25}
OMP: pid 29895 tid 29996 thread 35 bound to OS proc set {35}
OMP: pid 29895 tid 30012 thread 51 bound to OS proc set {51}
OMP: pid 29895 tid 29985 thread 24 bound to OS proc set {24}
OMP: pid 29895 tid 29995 thread 34 bound to OS proc set {34}
OMP: pid 29895 tid 30011 thread 50 bound to OS proc set {50}
OMP: pid 29895 tid 29981 thread 20 bound to OS proc set {20}
OMP: pid 29895 tid 29997 thread 36 bound to OS proc set {36}
OMP: pid 29895 tid 30013 thread 52 bound to OS proc set {52}
OMP: pid 29895 tid 29982 thread 21 bound to OS proc set {21}
OMP: pid 29895 tid 30009 thread 48 bound to OS proc set {48}
OMP: pid 29895 tid 29998 thread 37 bound to OS proc set {37}
OMP: pid 29895 tid 29999 thread 38 bound to OS proc set {38}
OMP: pid 29895 tid 30015 thread 54 bound to OS proc set {54}
OMP: pid 29895 tid 30003 thread 42 bound to OS proc set {42}
OMP: pid 29895 tid 29990 thread 29 bound to OS proc set {29}
OMP: pid 29895 tid 30005 thread 44 bound to OS proc set {44}
OMP: pid 29895 tid 30001 thread 40 bound to OS proc set {40}
OMP: pid 29895 tid 29983 thread 22 bound to OS proc set {22}
OMP: pid 29895 tid 29993 thread 32 bound to OS proc set {32}
OMP: pid 29895 tid 30002 thread 41 bound to OS proc set {41}
OMP: pid 29895 tid 29987 thread 26 bound to OS proc set {26}
OMP: pid 29895 tid 29989 thread 28 bound to OS proc set {28}
OMP: pid 29895 tid 30017 thread 56 bound to OS proc set {56}
OMP: pid 29895 tid 30006 thread 45 bound to OS proc set {45}
OMP: pid 29895 tid 30021 thread 60 bound to OS proc set {60}
OMP: pid 29895 tid 30014 thread 53 bound to OS proc set {53}
OMP: pid 29895 tid 29984 thread 23 bound to OS proc set {23}
OMP: pid 29895 tid 29991 thread 30 bound to OS proc set {30}
OMP: pid 29895 tid 30016 thread 55 bound to OS proc set {55}
OMP: pid 29895 tid 30024 thread 63 bound to OS proc set {63}
OMP: pid 29895 tid 30022 thread 61 bound to OS proc set {61}
OMP: pid 29895 tid 29988 thread 27 bound to OS proc set {27}
OMP: pid 29895 tid 30018 thread 57 bound to OS proc set {57}
OMP: pid 29895 tid 30020 thread 59 bound to OS proc set {59}
OMP: pid 29895 tid 30007 thread 46 bound to OS proc set {46}
OMP: pid 29895 tid 30000 thread 39 bound to OS proc set {39}
OMP: pid 29895 tid 30019 thread 58 bound to OS proc set {58}
OMP: pid 29895 tid 30023 thread 62 bound to OS proc set {62}
OMP: pid 29895 tid 30008 thread 47 bound to OS proc set {47}
OMP: pid 29895 tid 30004 thread 43 bound to OS proc set {43}
OMP: pid 29895 tid 29992 thread 31 bound to OS proc set {31}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/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-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_8      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_8  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_8  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_8  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_8      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_8  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_8  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_8  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 30053 tid 30053 thread 0 bound to OS proc set {0}
OMP: pid 30053 tid 30120 thread 1 bound to OS proc set {1}
OMP: pid 30053 tid 30128 thread 9 bound to OS proc set {9}
OMP: pid 30053 tid 30122 thread 3 bound to OS proc set {3}
OMP: pid 30053 tid 30121 thread 2 bound to OS proc set {2}
OMP: pid 30053 tid 30127 thread 8 bound to OS proc set {8}
OMP: pid 30053 tid 30131 thread 12 bound to OS proc set {12}
OMP: pid 30053 tid 30132 thread 13 bound to OS proc set {13}
OMP: pid 30053 tid 30129 thread 10 bound to OS proc set {10}
OMP: pid 30053 tid 30133 thread 14 bound to OS proc set {14}
OMP: pid 30053 tid 30136 thread 17 bound to OS proc set {17}
OMP: pid 30053 tid 30123 thread 4 bound to OS proc set {4}
OMP: pid 30053 tid 30124 thread 5 bound to OS proc set {5}
OMP: pid 30053 tid 30135 thread 16 bound to OS proc set {16}
OMP: pid 30053 tid 30125 thread 6 bound to OS proc set {6}
OMP: pid 30053 tid 30126 thread 7 bound to OS proc set {7}
OMP: pid 30053 tid 30130 thread 11 bound to OS proc set {11}
OMP: pid 30053 tid 30134 thread 15 bound to OS proc set {15}
OMP: pid 30053 tid 30137 thread 18 bound to OS proc set {18}
OMP: pid 30053 tid 30153 thread 34 bound to OS proc set {34}
OMP: pid 30053 tid 30168 thread 49 bound to OS proc set {49}
OMP: pid 30053 tid 30138 thread 19 bound to OS proc set {19}
OMP: pid 30053 tid 30144 thread 25 bound to OS proc set {25}
OMP: pid 30053 tid 30143 thread 24 bound to OS proc set {24}
OMP: pid 30053 tid 30152 thread 33 bound to OS proc set {33}
OMP: pid 30053 tid 30148 thread 29 bound to OS proc set {29}
OMP: pid 30053 tid 30154 thread 35 bound to OS proc set {35}
OMP: pid 30053 tid 30151 thread 32 bound to OS proc set {32}
OMP: pid 30053 tid 30147 thread 28 bound to OS proc set {28}
OMP: pid 30053 tid 30169 thread 50 bound to OS proc set {50}
OMP: pid 30053 tid 30139 thread 20 bound to OS proc set {20}
OMP: pid 30053 tid 30170 thread 51 bound to OS proc set {51}
OMP: pid 30053 tid 30140 thread 21 bound to OS proc set {21}
OMP: pid 30053 tid 30167 thread 48 bound to OS proc set {48}
OMP: pid 30053 tid 30160 thread 41 bound to OS proc set {41}
OMP: pid 30053 tid 30165 thread 46 bound to OS proc set {46}
OMP: pid 30053 tid 30157 thread 38 bound to OS proc set {38}
OMP: pid 30053 tid 30156 thread 37 bound to OS proc set {37}
OMP: pid 30053 tid 30161 thread 42 bound to OS proc set {42}
OMP: pid 30053 tid 30172 thread 53 bound to OS proc set {53}
OMP: pid 30053 tid 30171 thread 52 bound to OS proc set {52}
OMP: pid 30053 tid 30164 thread 45 bound to OS proc set {45}
OMP: pid 30053 tid 30163 thread 44 bound to OS proc set {44}
OMP: pid 30053 tid 30166 thread 47 bound to OS proc set {47}
OMP: pid 30053 tid 30155 thread 36 bound to OS proc set {36}
OMP: pid 30053 tid 30150 thread 31 bound to OS proc set {31}
OMP: pid 30053 tid 30162 thread 43 bound to OS proc set {43}
OMP: pid 30053 tid 30176 thread 57 bound to OS proc set {57}
OMP: pid 30053 tid 30159 thread 40 bound to OS proc set {40}
OMP: pid 30053 tid 30158 thread 39 bound to OS proc set {39}
OMP: pid 30053 tid 30174 thread 55 bound to OS proc set {55}
OMP: pid 30053 tid 30141 thread 22 bound to OS proc set {22}
OMP: pid 30053 tid 30175 thread 56 bound to OS proc set {56}
OMP: pid 30053 tid 30177 thread 58 bound to OS proc set {58}
OMP: pid 30053 tid 30146 thread 27 bound to OS proc set {27}
OMP: pid 30053 tid 30173 thread 54 bound to OS proc set {54}
OMP: pid 30053 tid 30180 thread 61 bound to OS proc set {61}
OMP: pid 30053 tid 30142 thread 23 bound to OS proc set {23}
OMP: pid 30053 tid 30182 thread 63 bound to OS proc set {63}
OMP: pid 30053 tid 30178 thread 59 bound to OS proc set {59}
OMP: pid 30053 tid 30179 thread 60 bound to OS proc set {60}
OMP: pid 30053 tid 30145 thread 26 bound to OS proc set {26}
OMP: pid 30053 tid 30149 thread 30 bound to OS proc set {30}
OMP: pid 30053 tid 30181 thread 62 bound to OS proc set {62}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/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-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_9      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_9  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_9  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_9  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_9      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_9  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_9  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_9  #
#############################################################################################################################################################################################################################

* [MAQAO] Info: Detected 1 Lprof instances in ip-172-31-18-66. 
If this is incorrect, rerun with number-processes-per-node=X
OMP: pid 30212 tid 30212 thread 0 bound to OS proc set {0}
OMP: pid 30212 tid 30279 thread 1 bound to OS proc set {1}
OMP: pid 30212 tid 30280 thread 2 bound to OS proc set {2}
OMP: pid 30212 tid 30281 thread 3 bound to OS proc set {3}
OMP: pid 30212 tid 30287 thread 9 bound to OS proc set {9}
OMP: pid 30212 tid 30286 thread 8 bound to OS proc set {8}
OMP: pid 30212 tid 30288 thread 10 bound to OS proc set {10}
OMP: pid 30212 tid 30291 thread 13 bound to OS proc set {13}
OMP: pid 30212 tid 30289 thread 11 bound to OS proc set {11}
OMP: pid 30212 tid 30290 thread 12 bound to OS proc set {12}
OMP: pid 30212 tid 30283 thread 5 bound to OS proc set {5}
OMP: pid 30212 tid 30284 thread 6 bound to OS proc set {6}
OMP: pid 30212 tid 30296 thread 18 bound to OS proc set {18}
OMP: pid 30212 tid 30285 thread 7 bound to OS proc set {7}
OMP: pid 30212 tid 30292 thread 14 bound to OS proc set {14}
OMP: pid 30212 tid 30293 thread 15 bound to OS proc set {15}
OMP: pid 30212 tid 30327 thread 49 bound to OS proc set {49}
OMP: pid 30212 tid 30297 thread 19 bound to OS proc set {19}
OMP: pid 30212 tid 30311 thread 33 bound to OS proc set {33}
OMP: pid 30212 tid 30295 thread 17 bound to OS proc set {17}
OMP: pid 30212 tid 30328 thread 50 bound to OS proc set {50}
OMP: pid 30212 tid 30313 thread 35 bound to OS proc set {35}
OMP: pid 30212 tid 30282 thread 4 bound to OS proc set {4}
OMP: pid 30212 tid 30294 thread 16 bound to OS proc set {16}
OMP: pid 30212 tid 30312 thread 34 bound to OS proc set {34}
OMP: pid 30212 tid 30329 thread 51 bound to OS proc set {51}
OMP: pid 30212 tid 30310 thread 32 bound to OS proc set {32}
OMP: pid 30212 tid 30299 thread 21 bound to OS proc set {21}
OMP: pid 30212 tid 30315 thread 37 bound to OS proc set {37}
OMP: pid 30212 tid 30306 thread 28 bound to OS proc set {28}
OMP: pid 30212 tid 30318 thread 40 bound to OS proc set {40}
OMP: pid 30212 tid 30304 thread 26 bound to OS proc set {26}
OMP: pid 30212 tid 30319 thread 41 bound to OS proc set {41}
OMP: pid 30212 tid 30323 thread 45 bound to OS proc set {45}
OMP: pid 30212 tid 30303 thread 25 bound to OS proc set {25}
OMP: pid 30212 tid 30326 thread 48 bound to OS proc set {48}
OMP: pid 30212 tid 30298 thread 20 bound to OS proc set {20}
OMP: pid 30212 tid 30301 thread 23 bound to OS proc set {23}
OMP: pid 30212 tid 30322 thread 44 bound to OS proc set {44}
OMP: pid 30212 tid 30307 thread 29 bound to OS proc set {29}
OMP: pid 30212 tid 30305 thread 27 bound to OS proc set {27}
OMP: pid 30212 tid 30331 thread 53 bound to OS proc set {53}
OMP: pid 30212 tid 30335 thread 57 bound to OS proc set {57}
OMP: pid 30212 tid 30314 thread 36 bound to OS proc set {36}
OMP: pid 30212 tid 30321 thread 43 bound to OS proc set {43}
OMP: pid 30212 tid 30325 thread 47 bound to OS proc set {47}
OMP: pid 30212 tid 30330 thread 52 bound to OS proc set {52}
OMP: pid 30212 tid 30324 thread 46 bound to OS proc set {46}
OMP: pid 30212 tid 30320 thread 42 bound to OS proc set {42}
OMP: pid 30212 tid 30300 thread 22 bound to OS proc set {22}
OMP: pid 30212 tid 30317 thread 39 bound to OS proc set {39}
OMP: pid 30212 tid 30333 thread 55 bound to OS proc set {55}
OMP: pid 30212 tid 30309 thread 31 bound to OS proc set {31}
OMP: pid 30212 tid 30336 thread 58 bound to OS proc set {58}
OMP: pid 30212 tid 30302 thread 24 bound to OS proc set {24}
OMP: pid 30212 tid 30308 thread 30 bound to OS proc set {30}
OMP: pid 30212 tid 30316 thread 38 bound to OS proc set {38}
OMP: pid 30212 tid 30337 thread 59 bound to OS proc set {59}
OMP: pid 30212 tid 30339 thread 61 bound to OS proc set {61}
OMP: pid 30212 tid 30332 thread 54 bound to OS proc set {54}
OMP: pid 30212 tid 30334 thread 56 bound to OS proc set {56}
OMP: pid 30212 tid 30338 thread 60 bound to OS proc set {60}
OMP: pid 30212 tid 30340 thread 62 bound to OS proc set {62}
OMP: pid 30212 tid 30341 thread 63 bound to OS proc set {63}
what is a LLM? and why should i care?
A Large Language Model (LLM) is a type of artificial intelligence (AI) that can process and generate human-like text based on the input it receives. LLMs are trained on vast amounts of text data, which allows them to learn patterns, relationships, and context in language. This enables them to generate coherent and often informative responses to user queries.

Here are some reasons why you should care about LLMs:

1.  **Improved search and content generation:** LLMs can help improve search results by providing more accurate and relevant information. They can also generate content such as articles, blog posts, and even entire books.
2.  **Personalized experiences:** LLMs can be used to create personalized experiences for users. For example, they can generate customized news feeds, product recommendations, or even entire stories based on a user's interests and preferences.
3.  **Customer support:** LLMs can be used to provide 24/7 customer support by answering frequently asked questions, helping with simple transactions, and even handling complex issues.
4.  **Language learning:** LLMs can help language learners by providing personalized feedback, practicing conversations, and even generating language learning materials.
5.  **Content creation:** LLMs can be used to create content such as dialogue, scripts, and even entire stories. This can help writers, filmmakers, and other creators to generate ideas and develop their projects.

Some popular examples of LLMs include:

1.  **Chatbots:** Many companies use LLMs to power their chatbots, which can help customers with simple transactions, answer frequently asked questions, and even provide customer support.
2.  **Virtual assistants:** LLMs are used in virtual assistants like Siri, Google Assistant, and Alexa to provide information, set reminders, and even control smart home devices.
3.  **Language translation:** LLMs are used in language translation tools like Google Translate to provide accurate and context-specific translations.

Overall, LLMs have the potential to revolutionize the way we interact with technology, from simple tasks like search and customer support to more complex tasks like content creation and language learning. As LLMs continue to evolve, we can expect to see even more innovative applications and uses for these powerful tools. [end of text]




Your experiment path is /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/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-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_10      #
#  Functions  |  Per-node      |  maqao lprof -df -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_10  #
#  Functions  |  Per-process   |  maqao lprof -df -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_10  #
#  Functions  |  Per-thread    |  maqao lprof -df -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_10  #
#  Loops      |  Cluster-wide  |  maqao lprof -dl xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_10      #
#  Loops      |  Per-node      |  maqao lprof -dl -dn xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_10  #
#  Loops      |  Per-process   |  maqao lprof -dl -dp xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_10  #
#  Loops      |  Per-thread    |  maqao lprof -dl -dt xp=/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/175-768-6804/llama.cpp/run/oneview_runs/multicore/armclang_4/oneview_results_1757689479/tools/lprof_npsu_run_10  #
##############################################################################################################################################################################################################################