OV - - OMP Regions

ID
▼1x6–
▼isix06.benchmarkcenter.megware.com–
○process 2871605
▼1x72–
▼isix06.benchmarkcenter.megware.com–
○process 2876776
▼1x96–
▼isix06.benchmarkcenter.megware.com–
○process 2892249
▼1x120–
▼isix06.benchmarkcenter.megware.com–
○process 2907747
▼1x128–
▼isix06.benchmarkcenter.megware.com–
○process 2923267
▼1x144–
▼isix06.benchmarkcenter.megware.com–
○process 2938796
▼1x168–
▼isix06.benchmarkcenter.megware.com–
○process 2954354
▼1x192–
▼isix06.benchmarkcenter.megware.com–
○process 2969927

							requested parallelism	walltime sum (s)	nb instances	any sync average per thread time (s)	any wait average per thread time (s)	parallelism overhead (%)	local speedup if perfectly balanced	global speedup if perfectly balanced
start addr	function name	source location	level	ancestor thread num	invoker	parallel or teams	1x6	1x72	1x96	1x120	1x128	1x144	1x168	1x192	1x6	1x72	1x96	1x120	1x128	1x144	1x168	1x192	1x6	1x72	1x96	1x120	1x128	1x144	1x168	1x192	1x6	1x72	1x96	1x120	1x128	1x144	1x168	1x192	1x6	1x72	1x96	1x120	1x128	1x144	1x168	1x192	1x6	1x72	1x96	1x120	1x128	1x144	1x168	1x192	1x6	1x72	1x96	1x120	1x128	1x144	1x168	1x192	1x6	1x72	1x96	1x120	1x128	1x144	1x168	1x192
libggml-cpu.so:0x30d9c	ggml_graph_compute	ggml-cpu.c:3148	0	0	runtime	parallel	6	72	96	120	128	144	168	192	23.825	7.419	7.094	6.674	6.620	6.815	6.086	5.056	132	132	132	132	132	132	132	132	3.243	2.940	3.062	2.818	2.979	3.159	2.801	2.424	3.240	2.939	3.059	2.815	2.977	3.156	2.799	2.422	13.6	39.6	43.2	42.2	45.0	46.4	46.0	47.9	1.158	1.657	1.760	1.731	1.818	1.864	1.853	1.921	1.141	1.424	1.462	1.440	1.466	1.487	1.463	1.520
(null):(nil)		:0	0	0	runtime	parallel	6	72	96	120	128	144	168	192	1.328	0.406	0.420	0.364	0.393	0.353	0.374	0.166	4.10 E3	4.10 E3	4.10 E3	4.10 E3	4.10 E3	4.10 E3	4.10 E3	4.10 E3	0.367	0.188	0.129	0.112	0.109	98.9 E-3	0.132	48.9 E-3	0.366	0.188	0.128	0.111	0.108	97.8 E-3	0.131	48.3 E-3	27.6	46.4	30.6	30.8	27.7	28.1	35.4	29.5	1.381	1.864	1.442	1.446	1.383	1.390	1.548	1.418	1.014	1.019	1.013	1.012	1.012	1.010	1.015	1.007
libggml-cpu.so:0x64e9f	ggml_backend_amx_convert_weight(ggml_tensor, void const, u...	mmq.cpp:2337	0	0	runtime	parallel	6	72	96	120	128	144	168	192	0.421	0.140	0.148	0.150	0.156	0.161	0.165	0.176	225	225	225	225	225	225	225	225	62.1 E-3	46.9 E-3	54.9 E-3	61.5 E-3	53.0 E-3	65.7 E-3	73.1 E-3	77.5 E-3	62.1 E-3	46.9 E-3	54.9 E-3	61.5 E-3	53.0 E-3	65.7 E-3	73.1 E-3	77.5 E-3	14.7	33.4	37.2	41.0	33.9	40.8	44.3	44.2	1.173	1.503	1.592	1.694	1.513	1.690	1.796	1.791	1.002	1.005	1.006	1.007	1.006	1.007	1.008	1.011

Report Configuration

▶PrOMPT Topology

OpenMP Regions

▶Filters