********************************************************************************
MAQAO 2025.1.2 - ad4b42c12cfbc289a7a711f3ded92abe2eb90c0a::20250917-142411 || 2025/09/17
/beegfs/hackathon/users/eoseret/MAQAO_ad4b42/bin/maqao oneview -R1 WP=/home/eoseret/MAQAO_src/src/maqao/libprompt/libprompt_clang.so -WS -c=/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/config.json --with-FLOPS object-coverage-threshold=0.1 lprof_params=btm=fp --replace xp=/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241 -of=html
CPY: [true] /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/binaries/aocc_4/exec --> /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec
CPY: [true] /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/../aocc_4/bin/libggml-base.so --> /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/libs/libggml-base.so
CPY: [true] /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/../aocc_4/bin/libggml-blas.so --> /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/libs/libggml-blas.so
CPY: [true] /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/../aocc_4/bin/libggml-cpu.so --> /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/libs/libggml-cpu.so
CPY: [true] /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/../aocc_4/bin/libggml.so --> /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/libs/libggml.so
CPY: [true] /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/../aocc_4/bin/libllama.so --> /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/libs/libllama.so
CMD: OMP_NUM_THREADS=6 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads /beegfs/hackathon/users/eoseret/MAQAO_ad4b42/bin/maqao lprof _caller=oneview btm=fp --xp="/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/tools/lprof_npsu_run_0" --mpi-command="mpirun -n 1 " --collect-CPU-time-intervals -p=SSE_AVX_FLOP --collect-topology tpp=6 -ldi=libggml-base.so,libggml-blas.so,libggml-cpu.so,libggml.so,libllama.so -- /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 6 -n 512 -p \"what is a LLM?\" --seed 0
CMD: OMP_NUM_THREADS=72 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads /beegfs/hackathon/users/eoseret/MAQAO_ad4b42/bin/maqao lprof _caller=oneview btm=fp --xp="/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/tools/lprof_npsu_run_1" --mpi-command="mpirun -n 1 " --collect-CPU-time-intervals -p=SSE_AVX_FLOP --collect-topology tpp=72 -ldi=libggml-base.so,libggml-blas.so,libggml-cpu.so,libggml.so,libllama.so -- /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 72 -n 512 -p \"what is a LLM?\" --seed 0
CMD: OMP_NUM_THREADS=96 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads /beegfs/hackathon/users/eoseret/MAQAO_ad4b42/bin/maqao lprof _caller=oneview btm=fp --xp="/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/tools/lprof_npsu_run_2" --mpi-command="mpirun -n 1 " --collect-CPU-time-intervals -p=SSE_AVX_FLOP --collect-topology tpp=96 -ldi=libggml-base.so,libggml-blas.so,libggml-cpu.so,libggml.so,libllama.so -- /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 96 -n 512 -p \"what is a LLM?\" --seed 0
CMD: OMP_NUM_THREADS=120 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads /beegfs/hackathon/users/eoseret/MAQAO_ad4b42/bin/maqao lprof _caller=oneview btm=fp --xp="/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/tools/lprof_npsu_run_3" --mpi-command="mpirun -n 1 " --collect-CPU-time-intervals -p=SSE_AVX_FLOP --collect-topology tpp=120 -ldi=libggml-base.so,libggml-blas.so,libggml-cpu.so,libggml.so,libllama.so -- /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 120 -n 512 -p \"what is a LLM?\" --seed 0
CMD: OMP_NUM_THREADS=128 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads /beegfs/hackathon/users/eoseret/MAQAO_ad4b42/bin/maqao lprof _caller=oneview btm=fp --xp="/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/tools/lprof_npsu_run_4" --mpi-command="mpirun -n 1 " --collect-CPU-time-intervals -p=SSE_AVX_FLOP --collect-topology tpp=128 -ldi=libggml-base.so,libggml-blas.so,libggml-cpu.so,libggml.so,libllama.so -- /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 128 -n 512 -p \"what is a LLM?\" --seed 0
CMD: OMP_NUM_THREADS=144 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads /beegfs/hackathon/users/eoseret/MAQAO_ad4b42/bin/maqao lprof _caller=oneview btm=fp --xp="/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/tools/lprof_npsu_run_5" --mpi-command="mpirun -n 1 " --collect-CPU-time-intervals -p=SSE_AVX_FLOP --collect-topology tpp=144 -ldi=libggml-base.so,libggml-blas.so,libggml-cpu.so,libggml.so,libllama.so -- /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 144 -n 512 -p \"what is a LLM?\" --seed 0
CMD: OMP_NUM_THREADS=168 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads /beegfs/hackathon/users/eoseret/MAQAO_ad4b42/bin/maqao lprof _caller=oneview btm=fp --xp="/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/tools/lprof_npsu_run_6" --mpi-command="mpirun -n 1 " --collect-CPU-time-intervals -p=SSE_AVX_FLOP --collect-topology tpp=168 -ldi=libggml-base.so,libggml-blas.so,libggml-cpu.so,libggml.so,libllama.so -- /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 168 -n 512 -p \"what is a LLM?\" --seed 0
CMD: OMP_NUM_THREADS=192 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads /beegfs/hackathon/users/eoseret/MAQAO_ad4b42/bin/maqao lprof _caller=oneview btm=fp --xp="/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/tools/lprof_npsu_run_7" --mpi-command="mpirun -n 1 " --collect-CPU-time-intervals -p=SSE_AVX_FLOP --collect-topology tpp=192 -ldi=libggml-base.so,libggml-blas.so,libggml-cpu.so,libggml.so,libllama.so -- /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 192 -n 512 -p \"what is a LLM?\" --seed 0
In run 1x6, 36 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.29940117313527% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
69 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.33137605665252% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run 1x72, 28 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.055277734063565% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
33 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.027892434736714% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run 1x96, 28 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.038121946243336% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
15 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.0064807308954186% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run 1x120, 28 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.045512658427469% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
9 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.003525628359057% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run 1x128, 31 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.047603967541363% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
16 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.0052210801513866% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run 1x144, 30 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.030328955268487% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
13 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.0035983505076729% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run 1x168, 29 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.043141451547854% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
10 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.0018831586348825% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
In run 1x192, 34 loops were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.047768252567039% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
9 functions were discarded from static analysis because their coverage
are lower than object_coverage_threshold value (0.1%).
That represents 0.0012988347007195% of the execution time. To include them, change the value
in the experiment directory configuration file, then rerun the command with the additionnal parameter
--force-static-analysis
CMD: cd "/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_run_1759256241"; OMP_TOOL_LIBRARIES=/home/eoseret/MAQAO_src/src/maqao/libprompt/libprompt_clang.so TARGET_PARALLEL_SECTION=ALL OMP_NUM_THREADS=6 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads mpirun -n 1 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 6 -n 512 -p "what is a LLM?" --seed 0
CMD: cd "/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_run_1759256241"; OMP_TOOL_LIBRARIES=/home/eoseret/MAQAO_src/src/maqao/libprompt/libprompt_clang.so TARGET_PARALLEL_SECTION=ALL OMP_NUM_THREADS=72 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads mpirun -n 1 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 72 -n 512 -p "what is a LLM?" --seed 0
CMD: cd "/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_run_1759256241"; OMP_TOOL_LIBRARIES=/home/eoseret/MAQAO_src/src/maqao/libprompt/libprompt_clang.so TARGET_PARALLEL_SECTION=ALL OMP_NUM_THREADS=96 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads mpirun -n 1 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 96 -n 512 -p "what is a LLM?" --seed 0
CMD: cd "/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_run_1759256241"; OMP_TOOL_LIBRARIES=/home/eoseret/MAQAO_src/src/maqao/libprompt/libprompt_clang.so TARGET_PARALLEL_SECTION=ALL OMP_NUM_THREADS=120 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads mpirun -n 1 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 120 -n 512 -p "what is a LLM?" --seed 0
CMD: cd "/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_run_1759256241"; OMP_TOOL_LIBRARIES=/home/eoseret/MAQAO_src/src/maqao/libprompt/libprompt_clang.so TARGET_PARALLEL_SECTION=ALL OMP_NUM_THREADS=128 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads mpirun -n 1 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 128 -n 512 -p "what is a LLM?" --seed 0
CMD: cd "/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_run_1759256241"; OMP_TOOL_LIBRARIES=/home/eoseret/MAQAO_src/src/maqao/libprompt/libprompt_clang.so TARGET_PARALLEL_SECTION=ALL OMP_NUM_THREADS=144 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads mpirun -n 1 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 144 -n 512 -p "what is a LLM?" --seed 0
CMD: cd "/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_run_1759256241"; OMP_TOOL_LIBRARIES=/home/eoseret/MAQAO_src/src/maqao/libprompt/libprompt_clang.so TARGET_PARALLEL_SECTION=ALL OMP_NUM_THREADS=168 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads mpirun -n 1 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 168 -n 512 -p "what is a LLM?" --seed 0
CMD: cd "/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_run_1759256241"; OMP_TOOL_LIBRARIES=/home/eoseret/MAQAO_src/src/maqao/libprompt/libprompt_clang.so TARGET_PARALLEL_SECTION=ALL OMP_NUM_THREADS=192 I_MPI_PIN_ORDER=bunch OMP_DISPLAY_AFFINITY=TRUE OMP_PROC_BIND=spread OMP_AFFINITY_FORMAT='OMP: pid %P tid %i thread %n bound to OS proc set {%A}' OMP_DISPLAY_ENV=TRUE I_MPI_PIN_DOMAIN=auto I_MPI_DEBUG=4 OMP_PLACES=threads mpirun -n 1 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/run/oneview_runs/multicore/aocc_4/oneview_results_1759256241/binaries/exec -m meta-llama-3.1-8b-instruct-Q8_0.gguf -no-cnv -t 192 -n 512 -p "what is a LLM?" --seed 0
