OV - exec - Topology

Software Topology

▼Scalability - 1x1

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threadsOMP_NUM_THREADS: 1

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	1	148.82
►Process 18275+		1	148.82
○Thread 18275			148.82	151.23	98.41	0.00	0.00	17.29

▶Scalability - 1x2

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 2OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	2	74.96
►Process 18369+		2	74.96
○Thread 18369			74.96	77.31	96.97	0.00	0.00	74.58
○Thread 18436			74.02	74.59	99.24	2.71	0.01	74.13

▶Scalability - 1x4

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 4OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	4	38.07
►Process 18464+		4	38.07
○Thread 18464			38.07	40.33	94.39	0.00	0.00	37.64
○Thread 18531			37.13	37.65	98.62	2.67	0.01	37.20
○Thread 18532			37.13	37.65	98.62	2.67	0.01	37.20
○Thread 18533			37.12	37.65	98.60	2.67	0.01	37.20

▶Scalability - 1x8

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 8OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	8	19.60
►Process 18560+		8	19.60
○Thread 18560			19.60	22.02	89.02	0.00	0.00	19.27
○Thread 18627			18.75	19.27	97.31	2.73	0.01	18.83
○Thread 18628			18.76	19.27	97.36	2.73	0.01	18.83
○Thread 18629			18.75	19.27	97.31	2.73	0.01	18.82
○Thread 18630			18.73	19.27	97.18	2.73	0.01	18.83
○Thread 18631			18.73	19.27	97.21	2.73	0.01	18.83
○Thread 18632			18.76	19.27	97.34	2.73	0.01	18.83
○Thread 18633			18.76	19.27	97.34	2.73	0.01	18.83

▶Scalability - 1x16

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 16OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	16	10.42
►Process 18660+		16	10.42
○Thread 18660			10.42	12.77	81.55	0.00	0.00	10.05
○Thread 18727			9.51	10.05	94.58	2.71	0.01	9.58
○Thread 18728			9.52	10.05	94.68	2.71	0.01	9.60
○Thread 18729			9.52	10.05	94.68	2.71	0.01	9.61
○Thread 18730			9.55	10.05	94.98	2.71	0.01	9.60
○Thread 18731			9.53	10.05	94.79	2.71	0.01	9.60
○Thread 18732			9.51	10.05	94.54	2.71	0.01	9.60
○Thread 18733			9.52	10.05	94.64	2.71	0.01	9.60
○Thread 18734			9.52	10.05	94.64	2.71	0.01	9.60
○Thread 18735			9.55	10.05	94.94	2.71	0.01	9.61
○Thread 18736			9.55	10.05	95.04	2.71	0.01	9.61
○Thread 18737			9.53	10.05	94.74	2.71	0.01	9.60
○Thread 18738			9.53	10.05	94.74	2.71	0.01	9.60
○Thread 18739			9.51	10.05	94.59	2.71	0.01	9.60
○Thread 18740			9.54	10.05	94.94	2.71	0.01	9.60
○Thread 18741			9.52	10.05	94.69	2.71	0.01	9.60

▶Scalability - 1x24

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 24OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	24	8.19
►Process 18769+		24	8.19
○Thread 18769			8.19	10.43	78.50	0.00	0.00	7.73
○Thread 18836			7.19	7.75	92.76	2.67	0.01	7.28
○Thread 18837			7.23	7.75	93.27	2.67	0.01	7.30
○Thread 18838			7.20	7.75	93.02	2.67	0.01	7.30
○Thread 18839			7.21	7.75	93.08	2.67	0.01	7.29
○Thread 18840			7.21	7.75	93.02	2.67	0.01	7.30
○Thread 18841			7.20	7.75	92.89	2.67	0.01	7.30
○Thread 18842			7.18	7.75	92.70	2.67	0.01	7.29
○Thread 18843			7.21	7.75	93.08	2.67	0.01	7.29
○Thread 18844			7.19	7.75	92.83	2.67	0.01	7.29
○Thread 18845			7.20	7.75	92.96	2.67	0.01	7.30
○Thread 18846			7.22	7.75	93.15	2.67	0.01	7.30
○Thread 18847			7.19	7.75	92.89	2.67	0.01	7.29
○Thread 18848			7.20	7.75	92.89	2.67	0.01	7.30
○Thread 18849			7.22	7.75	93.15	2.67	0.01	7.30
○Thread 18850			7.21	7.75	93.02	2.67	0.01	7.29
○Thread 18851			7.24	7.75	93.41	2.67	0.01	7.30
○Thread 18852			7.23	7.75	93.35	2.67	0.01	7.30
○Thread 18853			7.20	7.75	92.96	2.67	0.01	7.29
○Thread 18854			7.24	7.75	93.41	2.67	0.01	7.30
○Thread 18855			7.18	7.75	92.70	2.67	0.01	7.30
○Thread 18856			7.19	7.75	92.83	2.67	0.01	7.30
○Thread 18857			7.22	7.74	93.22	2.67	0.01	7.30
○Thread 18858			6.93	7.74	89.48	2.67	0.01	7.30

▶Scalability - 1x32

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 32OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	32	6.71
►Process 18885+		32	6.71
○Thread 18885			6.71	8.99	74.62	0.00	0.00	6.29
○Thread 18952			5.76	6.30	91.44	2.68	0.01	5.85
○Thread 18953			5.76	6.30	91.44	2.68	0.01	5.86
○Thread 18954			5.78	6.30	91.68	2.68	0.01	5.86
○Thread 18955			5.74	6.30	91.13	2.68	0.01	5.86
○Thread 18956			5.78	6.30	91.68	2.68	0.01	5.86
○Thread 18957			5.71	6.30	90.65	2.68	0.01	5.85
○Thread 18958			5.78	6.30	91.69	2.68	0.01	5.86
○Thread 18959			5.77	6.30	91.53	2.68	0.01	5.86
○Thread 18960			5.75	6.30	91.29	2.68	0.01	5.86
○Thread 18961			5.78	6.30	91.77	2.68	0.01	5.86
○Thread 18962			5.74	6.30	91.13	2.68	0.01	5.85
○Thread 18963			5.75	6.30	91.29	2.68	0.01	5.85
○Thread 18964			5.76	6.30	91.37	2.68	0.01	5.85
○Thread 18965			5.79	6.30	91.85	2.68	0.01	5.85
○Thread 18966			5.79	6.30	91.93	2.68	0.01	5.86
○Thread 18967			5.76	6.30	91.46	2.68	0.01	5.86
○Thread 18968			5.76	6.30	91.54	2.68	0.01	5.86
○Thread 18969			5.79	6.30	91.93	2.68	0.01	5.86
○Thread 18970			5.74	6.30	91.06	2.68	0.01	5.86
○Thread 18971			5.72	6.30	90.90	2.68	0.01	5.84
○Thread 18972			5.80	6.30	92.10	2.68	0.01	5.86
○Thread 18973			5.77	6.30	91.54	2.68	0.01	5.86
○Thread 18974			5.76	6.30	91.38	2.68	0.01	5.86
○Thread 18975			5.77	6.30	91.62	2.68	0.01	5.86
○Thread 18976			5.76	6.30	91.54	2.68	0.01	5.85
○Thread 18977			5.77	6.30	91.54	2.68	0.01	5.86
○Thread 18978			5.77	6.30	91.62	2.68	0.01	5.86
○Thread 18979			5.77	6.30	91.55	2.68	0.01	5.84
○Thread 18980			5.78	6.30	91.78	2.68	0.01	5.85
○Thread 18981			5.78	6.30	91.86	2.68	0.01	5.86
○Thread 18982			5.78	6.30	91.71	2.68	0.01	5.86

▶Scalability - 1x40

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 40OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	40	5.72
►Process 19009+		40	5.72
○Thread 19009			5.72	8.13	70.40	0.00	0.00	5.42
○Thread 19076			4.95	5.43	91.18	2.69	0.01	4.98
○Thread 19077			4.89	5.43	89.98	2.69	0.01	4.98
○Thread 19078			4.92	5.43	90.53	2.69	0.01	4.98
○Thread 19079			4.91	5.43	90.44	2.69	0.01	4.98
○Thread 19080			4.90	5.43	90.26	2.69	0.01	4.98
○Thread 19081			4.91	5.43	90.35	2.69	0.01	4.98
○Thread 19082			4.88	5.43	89.80	2.69	0.01	4.98
○Thread 19083			4.86	5.43	89.43	2.69	0.01	4.98
○Thread 19084			4.90	5.43	90.17	2.69	0.01	4.98
○Thread 19085			4.92	5.43	90.63	2.69	0.01	4.98
○Thread 19086			4.88	5.43	89.90	2.69	0.01	4.98
○Thread 19087			4.87	5.43	89.71	2.69	0.01	4.98
○Thread 19088			4.91	5.43	90.36	2.69	0.01	4.97
○Thread 19089			4.89	5.43	90.18	2.69	0.01	4.97
○Thread 19090			4.94	5.43	91.01	2.69	0.01	4.98
○Thread 19091			4.90	5.43	90.27	2.69	0.01	4.98
○Thread 19092			4.91	5.43	90.36	2.69	0.01	4.98
○Thread 19093			4.89	5.43	90.09	2.69	0.01	4.97
○Thread 19094			4.86	5.43	89.44	2.69	0.01	4.98
○Thread 19095			4.90	5.43	90.27	2.69	0.01	4.98
○Thread 19096			4.92	5.43	90.64	2.69	0.01	4.98
○Thread 19097			4.89	5.43	90.18	2.69	0.01	4.98
○Thread 19098			4.89	5.43	90.09	2.69	0.01	4.98
○Thread 19099			4.91	5.43	90.37	2.69	0.01	4.98
○Thread 19100			4.91	5.43	90.46	2.69	0.01	4.98
○Thread 19101			4.89	5.43	90.00	2.69	0.01	4.98
○Thread 19102			4.92	5.43	90.56	2.69	0.01	4.98
○Thread 19103			4.91	5.43	90.46	2.69	0.01	4.98
○Thread 19104			4.89	5.43	90.10	2.69	0.01	4.98
○Thread 19105			4.89	5.43	90.10	2.69	0.01	4.98
○Thread 19106			4.87	5.43	89.73	2.69	0.01	4.98
○Thread 19107			4.90	5.43	90.29	2.69	0.01	4.98
○Thread 19108			4.88	5.43	89.92	2.69	0.01	4.98
○Thread 19109			4.91	5.43	90.38	2.69	0.01	4.98
○Thread 19110			4.88	5.43	89.92	2.69	0.01	4.98
○Thread 19111			4.84	5.43	89.18	2.69	0.01	4.97
○Thread 19112			4.85	5.43	89.28	2.69	0.01	4.98
○Thread 19113			4.87	5.43	89.65	2.69	0.01	4.97
○Thread 19114			4.49	5.43	82.74	2.69	0.01	4.96

▶Scalability - 1x48

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 48OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	48	5.06
►Process 19141+		48	5.06
○Thread 19141			5.06	7.50	67.38	0.00	0.00	4.79
○Thread 19208			4.23	4.81	87.95	2.68	0.01	4.36
○Thread 19209			4.27	4.81	88.78	2.68	0.01	4.36
○Thread 19210			4.25	4.81	88.47	2.68	0.01	4.36
○Thread 19211			4.23	4.81	87.95	2.68	0.01	4.36
○Thread 19212			4.24	4.81	88.26	2.68	0.01	4.36
○Thread 19213			4.26	4.81	88.58	2.68	0.01	4.35
○Thread 19214			4.24	4.81	88.16	2.68	0.01	4.35
○Thread 19215			4.25	4.81	88.37	2.68	0.01	4.35
○Thread 19216			4.27	4.81	88.79	2.68	0.01	4.35
○Thread 19217			4.29	4.81	89.31	2.68	0.01	4.36
○Thread 19218			4.27	4.81	88.79	2.68	0.01	4.36
○Thread 19219			4.25	4.81	88.48	2.68	0.01	4.36
○Thread 19220			4.22	4.81	87.85	2.68	0.01	4.36
○Thread 19221			4.27	4.81	88.79	2.68	0.01	4.36
○Thread 19222			4.28	4.81	89.00	2.68	0.01	4.36
○Thread 19223			4.26	4.81	88.58	2.68	0.01	4.36
○Thread 19224			4.26	4.81	88.69	2.68	0.01	4.36
○Thread 19225			4.24	4.81	88.27	2.68	0.01	4.36
○Thread 19226			4.28	4.81	89.11	2.68	0.01	4.35
○Thread 19227			4.23	4.81	87.97	2.68	0.01	4.36
○Thread 19228			4.26	4.81	88.59	2.68	0.01	4.35
○Thread 19229			4.23	4.81	87.97	2.68	0.01	4.34
○Thread 19230			4.26	4.81	88.70	2.68	0.01	4.36
○Thread 19231			4.25	4.81	88.39	2.68	0.01	4.35
○Thread 19232			4.24	4.81	88.18	2.68	0.01	4.36
○Thread 19233			4.24	4.81	88.18	2.68	0.01	4.36
○Thread 19234			4.21	4.81	87.56	2.68	0.01	4.36
○Thread 19235			4.27	4.81	88.91	2.68	0.01	4.35
○Thread 19236			4.24	4.81	88.18	2.68	0.01	4.36
○Thread 19237			4.26	4.81	88.70	2.68	0.01	4.36
○Thread 19238			4.26	4.81	88.60	2.68	0.01	4.35
○Thread 19239			4.29	4.81	89.33	2.68	0.01	4.36
○Thread 19240			4.27	4.81	88.91	2.68	0.01	4.36
○Thread 19241			4.25	4.81	88.40	2.68	0.01	4.36
○Thread 19242			4.20	4.81	87.46	2.68	0.01	4.36
○Thread 19243			4.27	4.81	88.92	2.68	0.01	4.36
○Thread 19244			4.25	4.81	88.40	2.68	0.01	4.35
○Thread 19245			4.24	4.81	88.19	2.68	0.01	4.35
○Thread 19246			4.25	4.81	88.40	2.69	0.01	4.36
○Thread 19247			4.24	4.81	88.30	2.69	0.01	4.36
○Thread 19248			4.28	4.81	89.03	2.69	0.01	4.36
○Thread 19249			4.26	4.81	88.61	2.69	0.01	4.36
○Thread 19250			4.21	4.81	87.57	2.69	0.01	4.37
○Thread 19251			4.23	4.81	87.99	2.69	0.01	4.36
○Thread 19252			4.20	4.81	87.47	2.69	0.01	4.36
○Thread 19253			4.03	4.81	83.83	2.69	0.01	4.35
○Thread 19254			3.73	4.81	77.69	2.69	0.01	4.35

▶Scalability - 1x56

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 56OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	56	4.63
►Process 19381+		56	4.63
○Thread 19381			4.63	7.01	66.08	0.00	0.00	4.30
○Thread 19448			3.79	4.31	88.01	2.68	0.01	3.86
○Thread 19449			3.76	4.31	87.31	2.68	0.01	3.86
○Thread 19450			3.77	4.31	87.55	2.68	0.01	3.86
○Thread 19451			3.74	4.31	86.85	2.68	0.01	3.86
○Thread 19452			3.77	4.31	87.55	2.68	0.01	3.86
○Thread 19453			3.75	4.31	87.09	2.68	0.01	3.86
○Thread 19454			3.74	4.31	86.74	2.68	0.01	3.86
○Thread 19455			3.78	4.31	87.78	2.68	0.01	3.86
○Thread 19456			3.76	4.31	87.20	2.68	0.01	3.87
○Thread 19457			3.74	4.31	86.86	2.68	0.01	3.86
○Thread 19458			3.74	4.31	86.74	2.68	0.01	3.87
○Thread 19459			3.78	4.31	87.67	2.68	0.01	3.86
○Thread 19460			3.70	4.31	85.93	2.68	0.01	3.85
○Thread 19461			3.73	4.31	86.51	2.68	0.01	3.86
○Thread 19462			3.70	4.31	85.93	2.68	0.01	3.86
○Thread 19463			3.71	4.31	86.05	2.68	0.01	3.87
○Thread 19464			3.74	4.31	86.86	2.68	0.01	3.86
○Thread 19465			3.77	4.31	87.45	2.68	0.01	3.86
○Thread 19466			3.73	4.31	86.63	2.68	0.01	3.87
○Thread 19467			3.74	4.31	86.87	2.68	0.01	3.86
○Thread 19468			3.74	4.31	86.75	2.68	0.01	3.87
○Thread 19469			3.74	4.31	86.75	2.69	0.01	3.87
○Thread 19470			3.70	4.31	85.83	2.69	0.01	3.86
○Thread 19471			3.72	4.31	86.41	2.69	0.01	3.86
○Thread 19472			3.72	4.31	86.29	2.69	0.01	3.86
○Thread 19473			3.77	4.31	87.45	2.69	0.01	3.85
○Thread 19474			3.73	4.31	86.64	2.69	0.01	3.87
○Thread 19475			3.76	4.31	87.34	2.69	0.01	3.86
○Thread 19476			3.76	4.31	87.34	2.69	0.01	3.87
○Thread 19477			3.76	4.31	87.23	2.69	0.01	3.86
○Thread 19478			3.76	4.31	87.34	2.69	0.01	3.86
○Thread 19479			3.75	4.31	87.11	2.69	0.01	3.87
○Thread 19480			3.72	4.31	86.30	2.69	0.01	3.87
○Thread 19481			3.76	4.31	87.35	2.69	0.01	3.87
○Thread 19482			3.75	4.31	87.00	2.69	0.01	3.86
○Thread 19483			3.74	4.31	86.88	2.69	0.01	3.86
○Thread 19484			3.74	4.31	86.89	2.69	0.01	3.86
○Thread 19485			3.71	4.31	86.19	2.69	0.01	3.86
○Thread 19486			3.70	4.31	85.84	2.69	0.01	3.87
○Thread 19487			3.76	4.31	87.24	2.69	0.01	3.85
○Thread 19488			3.75	4.31	87.01	2.69	0.01	3.87
○Thread 19489			3.74	4.31	86.89	2.69	0.01	3.87
○Thread 19490			3.74	4.31	86.89	2.69	0.01	3.86
○Thread 19491			3.70	4.31	85.97	2.69	0.01	3.86
○Thread 19492			3.74	4.31	86.89	2.69	0.01	3.86
○Thread 19493			3.74	4.31	86.90	2.69	0.01	3.86
○Thread 19494			3.76	4.31	87.36	2.69	0.01	3.86
○Thread 19495			3.76	4.31	87.25	2.69	0.01	3.87
○Thread 19496			3.76	4.31	87.25	2.69	0.01	3.86
○Thread 19497			3.77	4.31	87.60	2.69	0.01	3.86
○Thread 19498			3.65	4.31	84.70	2.69	0.01	3.87
○Thread 19499			3.70	4.31	85.97	2.69	0.01	3.87
○Thread 19500			3.64	4.31	84.58	2.69	0.01	3.86
○Thread 19501			3.38	4.31	78.55	2.69	0.01	3.86
○Thread 19502			3.28	4.31	76.23	2.69	0.01	3.87

▶Scalability - 1x64

Number processes: 1 Number nodes: 1 Run Command: <executable> -m meta-llama-3.1-8b-instruct-Q4_0.gguf -t <OMP_NUM_THREADS> -b 2048 -ub 512 -npp 128 -ntg 0 -npl 16 -c 16384 --seed 0 --output-format jsonlMPI Command: mpirun -n <number_processes> --bind-to none --report-bindings Run Directory: /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-18-66/176-131-5415/llama.cpp/run/oneview_runs/multicore/armclang/oneview_run_1761317305OMP_NUM_THREADS: 64OMP_PROC_BIND: spreadOMP_DISPLAY_AFFINITY: TRUEOMP_AFFINITY_FORMAT: 'OMP: pid %P tid %i thread %n bound to OS proc set {%A}'OMP_DISPLAY_ENV: TRUEOMP_PLACES: threads

ID	Observed Processes	Observed Threads	Time(s)	Elapsed Time (s)	Active Time (%)	Start (after process) (s)	End (before process) (s)	Maximum Time on the Same CPU (s)
►Node ip-172-31-18-66+	1	64	4.29
►Process 19534+		64	4.29
○Thread 19534			4.29	6.63	64.69	0.00	0.00	3.91
○Thread 19601			3.38	3.93	86.05	2.69	0.01	3.48
○Thread 19602			3.37	3.93	85.80	2.69	0.01	3.48
○Thread 19603			3.34	3.93	85.16	2.69	0.01	3.48
○Thread 19604			3.38	3.93	86.18	2.69	0.01	3.46
○Thread 19605			3.29	3.93	83.89	2.69	0.01	3.46
○Thread 19606			3.35	3.93	85.42	2.69	0.01	3.48
○Thread 19607			3.29	3.93	83.89	2.69	0.01	3.46
○Thread 19608			3.36	3.93	85.67	2.69	0.01	3.48
○Thread 19609			3.34	3.93	85.17	2.69	0.01	3.48
○Thread 19610			3.39	3.93	86.31	2.69	0.01	3.47
○Thread 19611			3.34	3.93	85.17	2.69	0.01	3.48
○Thread 19612			3.34	3.93	85.04	2.69	0.01	3.48
○Thread 19613			3.37	3.93	85.81	2.69	0.01	3.48
○Thread 19614			3.36	3.93	85.68	2.69	0.01	3.45
○Thread 19615			3.34	3.93	85.17	2.69	0.01	3.48
○Thread 19616			3.35	3.93	85.43	2.69	0.01	3.46
○Thread 19617			3.29	3.93	83.77	2.69	0.01	3.47
○Thread 19618			3.33	3.93	84.92	2.69	0.01	3.48
○Thread 19619			3.27	3.93	83.27	2.69	0.01	3.47
○Thread 19620			3.31	3.93	84.41	2.69	0.01	3.47
○Thread 19621			3.30	3.93	84.16	2.69	0.01	3.47
○Thread 19622			3.31	3.93	84.29	2.69	0.01	3.46
○Thread 19623			3.35	3.93	85.31	2.69	0.01	3.48
○Thread 19624			3.38	3.93	86.07	2.69	0.01	3.47
○Thread 19625			3.33	3.93	84.80	2.69	0.01	3.48
○Thread 19626			3.31	3.93	84.29	2.69	0.01	3.48
○Thread 19627			3.31	3.93	84.42	2.69	0.01	3.47
○Thread 19628			3.32	3.93	84.68	2.69	0.01	3.47
○Thread 19629			3.33	3.93	84.93	2.69	0.01	3.47
○Thread 19630			3.33	3.93	84.94	2.69	0.01	3.47
○Thread 19631			3.33	3.93	84.94	2.69	0.01	3.48
○Thread 19632			3.33	3.93	84.82	2.69	0.01	3.46
○Thread 19633			3.31	3.93	84.43	2.69	0.01	3.48
○Thread 19634			3.34	3.93	85.07	2.69	0.01	3.46
○Thread 19635			3.29	3.93	83.80	2.69	0.01	3.45
○Thread 19636			3.36	3.93	85.71	2.69	0.01	3.47
○Thread 19637			3.33	3.93	84.82	2.70	0.01	3.48
○Thread 19638			3.34	3.93	85.20	2.70	0.01	3.48
○Thread 19639			3.33	3.93	84.82	2.70	0.01	3.47
○Thread 19640			3.34	3.93	85.08	2.70	0.01	3.46
○Thread 19641			3.34	3.93	85.08	2.70	0.01	3.46
○Thread 19642			3.37	3.93	85.85	2.70	0.01	3.46
○Thread 19643			3.34	3.93	85.08	2.70	0.01	3.48
○Thread 19644			3.32	3.93	84.70	2.70	0.01	3.47
○Thread 19645			3.32	3.93	84.70	2.70	0.01	3.44
○Thread 19646			3.37	3.93	85.98	2.70	0.01	3.47
○Thread 19647			3.33	3.93	84.96	2.70	0.01	3.47
○Thread 19648			3.32	3.93	84.71	2.70	0.01	3.47
○Thread 19649			3.35	3.93	85.47	2.70	0.01	3.47
○Thread 19650			3.31	3.93	84.46	2.70	0.01	3.48
○Thread 19651			3.34	3.93	85.09	2.70	0.01	3.47
○Thread 19652			3.34	3.93	85.22	2.70	0.01	3.47
○Thread 19653			3.32	3.93	84.59	2.70	0.01	3.46
○Thread 19654			3.30	3.92	84.20	2.70	0.01	3.45
○Thread 19655			3.33	3.92	84.97	2.70	0.01	3.48
○Thread 19656			3.38	3.92	86.12	2.70	0.01	3.47
○Thread 19657			3.36	3.92	85.61	2.70	0.01	3.45
○Thread 19658			3.35	3.92	85.36	2.70	0.01	3.45
○Thread 19659			3.31	3.92	84.34	2.70	0.01	3.48
○Thread 19660			3.35	3.92	85.49	2.70	0.01	3.48
○Thread 19661			3.36	3.92	85.74	2.70	0.01	3.48
○Thread 19662			3.34	3.92	85.11	2.70	0.01	3.48
○Thread 19663			3.33	3.92	84.85	2.70	0.01	3.48

Report Configuration