OV - Compare Functions

Functions

▶<unknown>: 0 - 396.04 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run icx_default							Run aocc_9							Run icx_5

241	0.02	0.00	0.01	40	0.04	0.00	29	0.00	0.00	0.00	1	0.00	0.00	481	0.01	0.00	0.01	20	0.00	0.00	637	0.04	0.00	0.02	56	0.04	0.00
313	0.05	0.01	0.02	73	0.03	0.00	264	0.05	0.01	0.03	59	0.08	0.01	266	0.02	0.00	0.01	38	0.02	0.00	99	0.00	0.00	0.01	10	0.00	0.00
263	0.02	0.00	0.01	34	0.01	0.00	37	0.00	0.00	0.01	6	0.00	0.00	35	0.00	0.00	0.01	8	0.00	0.00	11	0.00	0.00	0.00	1	0.00	0.00
243	0.01	0.00	0.01	27	0.02	0.00	301	0.00	0.00	0.00	2	0.00	0.00	246	0.01	0.00	0.01	24	0.02	0.00	75	0.01	0.00	0.01	18	0.02	0.00
265	0.06	0.01	0.03	61	0.07	0.01	262	0.04	0.00	0.02	52	0.04	0.00	7	0.01	0.00	0.01	24	0.02	0.00	749	0.00	0.00	0.00	2	0.00	0.00
26	0.00	0.00	0.00	1	0.00	0.00	192	0.00	0.00	0.01	1	0.00	0.00	-1	0.00	0.00	0.00	2	0.00	0.00	425	0.00	0.00	0.01	1	0.00	0.00
35	0.00	0.00	0.00	1	0.00	0.00	68	0.00	0.00	0.01	2	0.00	0.00	36	0.00	0.00	0.01	4	0.00	0.00	495	0.00	0.00	0.01	3	0.00	0.00
302	0.00	0.00	0.00	2	0.00	0.00	236	0.03	0.00	0.01	47	0.04	0.00	242	0.00	0.00	0.00	2	0.00	0.00	71	0.00	0.00	0.00	2	0.00	0.00
-1	0.00	0.00	0.01	3	0.00	0.00	339	0.00	0.00	0.00	1	0.00	0.00	358	0.00	0.00	0.01	1	0.00	0.00	109	0.00	0.00	0.01	8	0.00	0.00
334	0.07	0.01	0.02	79	0.05	0.01	-1	0.00	0.00	0.01	1	0.00	0.00	344	0.00	0.00	0.00	3	0.00	0.00	721	0.00	0.00	0.00	2	0.00	0.00
34	0.00	0.00	0.01	7	0.00	0.00	287	0.05	0.01	0.03	68	0.05	0.00	291	0.04	0.00	0.03	54	0.04	0.01	653	0.00	0.00	0.00	2	0.00	0.00
478	0.01	0.00	0.01	22	0.01	0.00	240	0.01	0.00	0.02	23	0.03	0.00	305	0.00	0.00	0.01	5	0.00	0.00	117	0.00	0.00	0.00	1	0.00	0.00
288	0.05	0.01	0.02	63	0.06	0.00	9	0.01	0.00	0.01	22	0.02	0.00	337	0.07	0.01	0.03	73	0.06	0.01	430	0.02	0.00	0.01	36	0.03	0.00
6	0.01	0.00	0.01	19	0.01	0.00	312	0.06	0.01	0.03	72	0.04	0.00	268	0.06	0.01	0.05	63	0.34	0.01	509	0.04	0.01	0.02	64	0.07	0.00
10901	0.00	0.00	0.01	9	0.00	0.00	476	0.00	0.00	0.01	11	0.07	0.00	244	0.02	0.00	0.02	32	0.09	0.00	669	0.04	0.01	0.02	65	0.04	0.00
10851	0.00	0.00	0.01	1	0.00	0.00	10876	0.00	0.00	0.00	2	0.00	0.00	316	0.08	0.01	0.03	80	0.05	0.01	438	0.02	0.00	0.01	38	0.02	0.00
10876	0.00	0.00	0.01	8	0.00	0.00	10901	0.01	0.00	0.01	17	0.00	0.00	10901	0.01	0.00	0.01	12	0.00	0.00	10901	0.00	0.00	0.01	8	0.00	0.00
11119	0.00	0.00	0.00	1	0.00	0.00	10851	0.00	0.00	0.01	1	0.00	0.00	10851	0.00	0.00	0.01	1	0.00	0.00	10876	0.00	0.00	0.00	1	0.00	0.00
10899	0.00	0.00	0.01	2	0.00	0.00	1946	0.39	0.05	0.09	95	0.13	0.01	11125	0.00	0.00	0.00	2	0.00	0.00	10833	0.00	0.00	0.00	1	0.00	0.00
11125	0.00	0.00	0.00	1	0.00	0.00	3629	0.00	0.00	0.00	1	0.00	0.00	11115	0.00	0.00	0.00	1	0.00	0.00	11125	0.00	0.00	0.01	3	0.00	0.00
14	0.00	0.00	0.01	1	0.00	0.00	686	0.00	0.00	0.00	1	0.00	0.00	10899	0.00	0.00	0.00	2	0.16	0.00	11119	0.00	0.00	0.01	1	0.00	0.00
1946	0.39	0.05	0.09	96	0.14	0.02	1333	0.00	0.00	0.00	1	0.00	0.00	10876	0.00	0.00	0.01	2	0.00	0.00	10899	0.00	0.00	0.00	2	0.00	0.00
1089	0.00	0.00	0.01	1	0.00	0.00	1089	0.00	0.00	0.00	1	0.00	0.00	1946	0.40	0.05	0.09	95	0.14	0.02	10879	0.00	0.00	0.01	2	0.00	0.00
3689	0.05	0.01	0.03	70	0.11	0.00	1326	0.00	0.00	0.00	1	0.00	0.00	686	0.00	0.00	0.00	1	0.00	0.00	1946	0.38	0.05	0.09	95	0.13	0.02
1122	0.00	0.00	0.01	1	0.00	0.00	1324	0.00	0.00	0.00	1	0.00	0.00	1089	0.00	0.00	0.00	1	0.00	0.00	3621	0.00	0.00	0.00	1	0.00	0.00
1101	0.00	0.00	0.00	1	0.00	0.00	1317	0.00	0.00	0.00	1	0.00	0.00	3621	0.00	0.00	0.00	1	0.00	0.00	1089	0.00	0.00	0.00	1	0.00	0.00
686	0.00	0.00	0.01	1	0.00	0.00	3631	0.00	0.00	0.01	1	0.00	0.00	3631	0.00	0.00	0.01	1	0.00	0.00	686	0.00	0.00	0.00	1	0.00	0.00
1489	0.00	0.00	0.00	1	0.00	0.00	1489	0.00	0.00	0.01	3	0.00	0.00	1324	0.00	0.00	0.00	1	0.00	0.00	1333	0.00	0.00	0.00	1	0.00	0.00
1318	0.00	0.00	0.01	1	0.00	0.00	3605	0.00	0.00	0.01	1	0.00	0.00	1335	0.00	0.00	0.00	1	0.00	0.00	1101	0.00	0.00	0.00	2	0.00	0.00
1326	0.00	0.00	0.01	1	0.00	0.00	2381	0.00	0.00	0.00	1	0.00	0.00	1101	0.00	0.00	0.01	1	0.00	0.00	1326	0.00	0.00	0.00	1	0.00	0.00
3695	0.00	0.00	0.01	3	0.36	0.01	1335	0.00	0.00	0.00	1	0.00	0.00	1326	0.00	0.00	0.00	1	0.00	0.00	883	0.00	0.00	0.00	1	0.00	0.00
3604	0.00	0.00	0.01	1	0.00	0.00	2047	0.00	0.00	0.00	1	0.00	0.00	1333	0.00	0.00	0.00	1	0.00	0.00	1318	0.00	0.00	0.00	1	0.00	0.00
3605	0.00	0.00	0.01	1	0.00	0.00	1909	0.00	0.00	0.01	2	0.00	0.00	1318	0.00	0.00	0.01	1	0.00	0.00	1122	0.00	0.00	0.00	1	0.00	0.00
1324	0.00	0.00	0.01	1	0.00	0.00	1927	0.00	0.00	0.00	1	0.00	0.00	1493	0.00	0.00	0.00	3	0.00	0.00	1489	0.00	0.00	0.01	3	0.00	0.00
2486	0.00	0.00	0.00	1	0.00	0.00	1921	0.00	0.00	0.01	1	0.00	0.00	3695	0.00	0.00	0.04	2	1.33	0.02	3604	0.00	0.00	0.01	1	0.00	0.00
1401	0.00	0.00	0.00	3	0.00	0.00	2073	0.00	0.00	0.01	1	0.00	0.00	3605	0.00	0.00	0.02	1	0.00	0.00	1317	0.00	0.00	0.00	1	0.00	0.00
1405	0.00	0.00	0.00	1	0.00	0.00	2045	0.02	0.00	0.01	40	0.02	0.00	3604	0.00	0.00	0.00	1	0.00	0.00	3605	0.00	0.00	0.03	1	0.00	0.00
1039	0.00	0.00	0.01	3	0.00	0.00	2090	0.00	0.00	0.04	2	1.82	0.03	3689	0.06	0.01	0.03	73	0.07	0.00	3456	0.00	0.00	0.04	1	0.00	0.00
807	0.00	0.00	0.00	1	0.00	0.00	2089	0.02	0.00	0.03	29	0.26	0.00	2486	0.00	0.00	0.01	2	0.00	0.00	3302	0.00	0.00	0.00	1	0.00	0.00
86	0.00	0.00	0.00	4	0.00	0.00	1948	0.06	0.01	0.03	72	0.05	0.00	1401	0.00	0.00	0.00	3	0.00	0.00	3305	0.05	0.01	0.02	67	0.03	0.00
1386	0.10	0.01	0.47	27	4.02	0.10	1643	0.00	0.00	0.01	1	0.00	0.00	1406	0.00	0.00	0.00	1	0.00	0.00	3188	0.00	0.00	0.00	1	0.00	0.00
1874	0.00	0.00	0.01	1	0.00	0.00	1715	0.00	0.00	0.01	1	0.00	0.00	1039	0.00	0.00	0.00	2	0.00	0.00	3397	0.01	0.00	0.01	13	0.02	0.00
2487	44.64	5.37	6.12	96	3.47	0.58	1680	0.00	0.00	0.00	1	0.00	0.00	86	0.00	0.00	0.01	6	0.00	0.00	3455	0.03	0.00	0.02	47	0.08	0.00
979	0.00	0.00	0.00	1	0.00	0.00	1675	0.00	0.00	0.02	1	0.00	0.00	820	0.00	0.00	0.00	1	0.00	0.00	3275	0.00	0.00	0.01	1	0.00	0.00
1385	36.79	4.43	4.97	96	4.47	0.53	1476	0.00	0.00	0.00	1	0.00	0.00	2487	46.37	5.43	5.73	96	4.00	0.56	3436	0.00	0.00	0.00	1	0.00	0.00
2233	0.00	0.00	0.01	4	0.00	0.00	-1	0.00	0.00	0.00	1	0.00	0.00	1386	0.05	0.01	0.17	24	1.83	0.03	3412	0.02	0.00	0.01	41	0.03	0.00
45	0.00	0.00	0.01	1	0.00	0.00	1683	0.00	0.00	0.00	1	0.00	0.00	979	0.00	0.00	0.00	1	0.00	0.00	3135	0.00	0.00	0.01	1	0.00	0.00
568	0.00	0.00	0.01	1	0.00	0.00	1639	0.00	0.00	0.01	1	0.00	0.00	1385	38.11	4.46	5.26	95	1.42	0.17	2822	0.00	0.00	0.00	1	0.00	0.00
772	0.00	0.00	0.01	1	0.00	0.00	1164	0.00	0.00	0.01	1	0.00	0.00	1874	0.00	0.00	0.01	1	0.00	0.00	2770	0.00	0.00	0.01	1	0.00	0.00
38	0.00	0.00	0.00	1	0.00	0.00	2356	0.00	0.00	0.01	2	0.00	0.00	47	0.00	0.00	0.00	1	0.00	0.00	2885	0.00	0.00	0.00	1	0.00	0.00
2484	0.00	0.00	0.01	1	0.00	0.00	1092	0.00	0.00	0.00	3	0.14	0.00	289	0.00	0.00	0.00	1	0.00	0.00	222	0.00	0.00	0.00	1	0.00	0.00
196	0.00	0.00	0.01	1	0.00	0.00	1397	0.00	0.00	0.01	2	0.00	0.00	46	0.00	0.00	0.00	1	0.00	0.00	2875	0.00	0.00	0.00	1	0.00	0.00
2989	0.00	0.00	0.01	1	0.00	0.00	2924	0.10	0.01	0.04	84	0.06	0.01	2	0.00	0.00	0.01	1	0.00	0.00	2879	0.00	0.00	0.00	1	0.00	0.00
2965	0.00	0.00	0.01	1	0.00	0.00	2915	0.00	0.00	0.00	1	0.00	0.00	190	0.00	0.00	0.00	1	0.00	0.00	2356	0.00	0.00	0.00	1	0.00	0.00
2499	0.00	0.00	0.01	1	0.00	0.00	1111	81.78	9.57	10.22	96	6.20	0.97	2989	0.00	0.00	0.00	1	0.00	0.00	2029	0.00	0.00	0.00	1	0.00	0.00
2053	0.00	0.00	0.01	1	0.00	0.00	1114	0.00	0.00	0.00	1	0.00	0.00	2499	0.00	0.00	0.00	1	0.00	0.00	1088	0.00	0.00	0.00	1	0.00	0.00
2052	0.00	0.00	0.01	1	0.00	0.00	1116	2.15	0.25	0.33	96	0.33	0.04	2041	0.00	0.00	0.02	1	0.00	0.00	1092	0.00	0.00	0.01	2	0.00	0.00
1802	0.00	0.00	0.01	1	0.00	0.00	1104	0.00	0.00	0.00	1	0.00	0.00	1990	0.00	0.00	0.02	1	0.00	0.00	1096	0.00	0.00	0.01	3	0.00	0.00
1824	0.00	0.00	0.01	1	0.00	0.00	1982	0.00	0.00	0.01	1	0.00	0.00	744	0.00	0.00	0.00	1	0.00	0.00	2044	0.00	0.00	0.01	3	0.00	0.00
2049	0.00	0.00	0.01	1	0.00	0.00	1991	0.00	0.00	0.00	1	0.00	0.00	1991	0.00	0.00	0.00	1	0.00	0.00	1972	0.00	0.00	0.00	1	0.00	0.00
-1	0.00	0.00	0.01	1	0.00	0.00	1098	0.00	0.00	0.01	3	0.00	0.00	1993	0.00	0.00	0.00	1	0.00	0.00	1111	78.39	9.81	10.71	96	5.88	1.03
2098	0.00	0.00	0.02	1	0.00	0.00	138	0.00	0.00	0.00	1	0.00	0.00	2088	0.00	0.00	0.01	1	0.00	0.00	1114	0.00	0.00	0.00	2	0.00	0.00
746	0.00	0.00	0.01	1	0.00	0.00	47	0.00	0.00	0.00	1	0.00	0.00	2050	0.00	0.00	0.00	1	0.00	0.00	1116	2.05	0.26	0.36	96	0.36	0.05
12557	0.00	0.00	0.00	1	0.00	0.00	2948	0.00	0.00	0.00	1	0.00	0.00	1803	0.00	0.00	0.01	1	0.00	0.00	2399	0.00	0.00	0.00	1	0.00	0.00
12563	0.00	0.00	0.00	1	0.00	0.00	2848	0.00	0.00	0.00	1	0.00	0.00	561	0.00	0.00	0.03	1	0.00	0.00	1982	0.00	0.00	0.00	1	0.00	0.00
12565	0.00	0.00	0.01	3	0.00	0.00	2989	0.00	0.00	0.00	1	0.00	0.00	38	0.00	0.00	0.00	1	0.00	0.00	2924	0.09	0.01	0.03	84	0.05	0.01
12553	0.00	0.00	0.01	3	0.00	0.00	553	0.00	0.00	0.03	1	0.00	0.00	645	0.00	0.00	0.00	1	0.00	0.00	1098	0.00	0.00	0.01	6	0.00	0.00
636	0.10	0.01	0.04	90	0.07	0.01	370	0.00	0.00	0.00	1	0.00	0.00	12563	0.00	0.00	0.00	1	0.00	0.00	47	0.00	0.00	0.00	2	0.00	0.00
3188	0.00	0.00	0.01	8	0.01	0.00	40	0.00	0.00	0.01	1	0.00	0.00	12553	0.00	0.00	0.00	3	0.00	0.00	2891	0.00	0.00	0.00	1	0.00	0.00
3344	10.12	1.22	1.66	96	2.89	0.27	12553	0.00	0.00	0.00	2	0.00	0.00	12565	0.00	0.00	0.00	1	0.00	0.00	2	0.00	0.00	0.00	1	0.00	0.00
3045	0.00	0.00	0.00	2	0.00	0.00	11317	0.00	0.00	0.00	1	0.00	0.00	636	0.07	0.01	0.03	77	0.05	0.01	2766	0.00	0.00	0.01	1	0.00	0.00
3349	6.71	0.81	1.22	96	2.43	0.28	11316	0.00	0.00	0.00	1	0.00	0.00	3188	0.00	0.00	0.01	8	0.00	0.00	2989	0.00	0.00	0.01	1	0.00	0.00
3038	0.00	0.00	0.00	2	0.00	0.00	12565	0.00	0.00	0.01	3	0.00	0.00	3045	0.00	0.00	0.01	2	0.00	0.00	12557	0.00	0.00	0.01	1	0.00	0.00
3350	0.17	0.02	0.11	93	0.14	0.02	12557	0.00	0.00	0.00	1	0.00	0.00	3046	0.00	0.00	0.00	2	0.00	0.00	12565	0.00	0.00	0.00	2	0.00	0.00
3345	0.14	0.02	0.04	90	0.07	0.01	3188	0.01	0.00	0.01	11	0.01	0.00	3349	4.11	0.48	0.63	96	1.38	0.08	12553	0.00	0.00	0.01	2	0.00	0.00
							3344	9.83	1.15	1.48	96	3.13	0.18	3344	9.59	1.12	1.30	96	3.58	0.13	56	0.00	0.00	0.01	2	0.00	0.00
							3046	0.00	0.00	0.00	1	0.00	0.00	3350	0.14	0.02	0.05	90	0.09	0.01	957	0.00	0.00	0.01	2	0.00	0.00
							3349	4.49	0.53	0.74	96	1.60	0.12	3345	0.13	0.02	0.05	89	0.08	0.01	1050	0.00	0.00	0.01	1	0.00	0.00
							3038	0.00	0.00	0.00	1	0.00	0.00								397	0.00	0.00	0.01	1	0.00	0.00
							3350	0.14	0.02	0.05	88	0.12	0.01								1036	0.00	0.00	0.01	8	0.01	0.00
							3345	0.13	0.02	0.04	90	0.07	0.01								3188	0.00	0.00	0.01	5	0.00	0.00
																					3039	0.00	0.00	0.01	2	0.00	0.00
																					3344	9.79	1.23	1.59	96	2.80	0.27
																					3349	6.28	0.79	1.21	96	2.21	0.27
																					3038	0.00	0.00	0.01	3	0.00	0.00
																					3350	0.17	0.02	0.10	92	0.14	0.02
																					3345	0.14	0.02	0.06	92	0.08	0.01

▶sgemm.cpp: 138 - 1.49 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default							Run icx_default							Run aocc_9							Run icx_5
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 205-206 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 220-220 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 805-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 853-855 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 205-206 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 220-221 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 805-821 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 827-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 853-855 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 205-206 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 220-221 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 805-855 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044
411	0.45	0.05	0.09	96	0.21	0.02	409	0.46	0.05	0.08	96	0.17	0.02	414	0.58	0.07	0.09	96	0.30	0.01

▶ops.cpp: 8690 - 1.21 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run icx_default							Run aocc_9	Run icx_5
		/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/cmath: 1583-1583 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 370-387 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 486-503 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 671-688 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 736-751 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-389 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8690-8706 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939								/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/cmath: 1583-1583 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 392-393 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 508-509 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 693-694 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 756-757 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8690-8706 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939
	332	0.11	0.01	0.04	90	0.06	0.01		707	1.10	0.14	0.17	96	0.40	0.02

▶quants.c: 1011 - 1.05 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run icx_default	Run aocc_9	Run icx_5
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1011-1013 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1066-1077
			771	1.05	0.13	0.15	96	0.47	0.01

▶vec.cpp: 331 - 0.21 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run icx_default	Run aocc_9	Run icx_5
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-9232/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 331-337
			505	0.21	0.03	0.05	96	0.13	0.01

▶Old Layout

Functions

Name	Module	Coverage (%)	Inclusive Time w.r.t. Wall Time(s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (coverage)	Deviation (time)
Name	Module	orig_default	icx_default	aocc_9	icx_5	orig_default	icx_default	aocc_9	icx_5	orig_default	icx_default	aocc_9	icx_5	orig_default	icx_default	aocc_9	icx_5	orig_default	icx_default	aocc_9	icx_5	orig_default	icx_default	aocc_9	icx_5
kmp_flag_64<false, true>::wait(kmp_info, int, void)	libiomp5.so	NA	81.78	NA	78.39	NA	9.57	NA	9.81	NA	10.22	NA	10.71	NA	96	NA	96	NA	6.20	NA	5.88	NA	0.97	NA	1.03
__kmp_hardware_timestamp	libomp.so	44.64	NA	46.37	NA	5.37	NA	5.43	NA	6.12	NA	5.73	NA	96	NA	96	NA	3.47	NA	4.00	NA	0.58	NA	0.56	NA
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libomp.so	36.79	NA	38.11	NA	4.43	NA	4.46	NA	4.97	NA	5.26	NA	96	NA	95	NA	4.47	NA	1.42	NA	0.53	NA	0.17	NA
mkl_blas_def_sgemm_kernel_0_zen	libmkl_def.so.2	10.12	9.83	9.59	9.79	1.22	1.15	1.12	1.23	1.66	1.48	1.30	1.59	96	96	96	96	2.89	3.13	3.58	2.80	0.27	0.18	0.13	0.27
mkl_blas_def_sgemm_scopy_right16_bdz	libmkl_def.so.2	6.71	4.49	4.11	6.28	0.81	0.53	0.48	0.79	1.22	0.74	0.63	1.21	96	96	96	96	2.43	1.60	1.38	2.21	0.28	0.12	0.08	0.27
kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check()	libiomp5.so	NA	2.15	NA	2.05	NA	0.25	NA	0.26	NA	0.33	NA	0.36	NA	96	NA	96	NA	0.33	NA	0.36	NA	0.04	NA	0.05
__GI___sched_yield	libc.so.6	0.39	0.39	0.40	0.38	0.05	0.05	0.05	0.05	0.09	0.09	0.09	0.09	96	95	95	95	0.14	0.13	0.14	0.13	0.02	0.01	0.02	0.02
void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<4>(long, long, long, long)	libggml-cpu.so	0.45	0.46	0.58	NA	0.05	0.05	0.07	NA	0.09	0.08	0.09	NA	96	96	96	NA	0.21	0.17	0.30	NA	0.02	0.02	0.01	NA
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	NA	NA	NA	1.10	NA	NA	NA	0.14	NA	NA	NA	0.17	NA	NA	NA	96	NA	NA	NA	0.40	NA	NA	NA	0.02
ggml_vec_dot_q8_0_q8_0	libggml-cpu.so	NA	NA	NA	1.05	NA	NA	NA	0.13	NA	NA	NA	0.15	NA	NA	NA	96	NA	NA	NA	0.47	NA	NA	NA	0.01
mkl_blas_def_sgemm_scopy_right4_bdz	libmkl_def.so.2	0.17	0.14	0.14	0.17	0.02	0.02	0.02	0.02	0.11	0.05	0.05	0.10	93	88	90	92	0.14	0.12	0.09	0.14	0.02	0.01	0.01	0.02
mkl_blas_def_sgemm_mscale	libmkl_def.so.2	0.14	0.13	0.13	0.14	0.02	0.02	0.02	0.02	0.04	0.04	0.05	0.06	90	90	89	92	0.07	0.07	0.08	0.08	0.01	0.01	0.01	0.01
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	0.07	0.11	0.07	NA	0.01	0.01	0.01	NA	0.02	0.04	0.03	NA	79	90	73	NA	0.05	0.06	0.06	NA	0.01	0.01	0.01	NA
ggml_vec_dot_f16	libggml-cpu.so	NA	NA	NA	0.21	NA	NA	NA	0.03	NA	NA	NA	0.05	NA	NA	NA	96	NA	NA	NA	0.13	NA	NA	NA	0.01
ggml_compute_forward_rope_f32(ggml_compute_params const, ggml_tensor, bool)	libggml-cpu.so	0.05	0.06	0.08	NA	0.01	0.01	0.01	NA	0.02	0.03	0.03	NA	73	72	80	NA	0.03	0.04	0.05	NA	0.00	0.00	0.01	NA
__kmp_yield	libiomp5.so	NA	0.10	NA	0.09	NA	0.01	NA	0.01	NA	0.04	NA	0.03	NA	84	NA	84	NA	0.06	NA	0.05	NA	0.01	NA	0.01
ggml_vec_swiglu_f32	libggml-cpu.so	0.06	0.05	0.06	NA	0.01	0.01	0.01	NA	0.03	0.03	0.05	NA	61	59	63	NA	0.07	0.08	0.34	NA	0.01	0.01	0.01	NA
f64xsubf128	libm.so.6	0.10	NA	0.07	NA	0.01	NA	0.01	NA	0.04	NA	0.03	NA	90	NA	77	NA	0.07	NA	0.05	NA	0.01	NA	0.01	NA
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libomp.so	0.10	NA	0.05	NA	0.01	NA	0.01	NA	0.47	NA	0.17	NA	27	NA	24	NA	4.02	NA	1.83	NA	0.10	NA	0.03	NA
ggml_compute_forward_rms_norm	libggml-cpu.so	0.05	0.05	0.04	NA	0.01	0.01	0.00	NA	0.02	0.03	0.03	NA	63	68	54	NA	0.06	0.05	0.04	NA	0.00	0.00	0.01	NA
__memcpy_avx512_unaligned_erms	libc.so.6	0.05	NA	0.06	NA	0.01	NA	0.01	NA	0.03	NA	0.03	NA	70	NA	73	NA	0.11	NA	0.07	NA	0.00	NA	0.00	NA
__libm_sse2_sincosf_l9	binary	NA	0.06	NA	0.05	NA	0.01	NA	0.01	NA	0.03	NA	0.02	NA	72	NA	67	NA	0.05	NA	0.03	NA	0.00	NA	0.00
ggml_vec_dot_f16	libggml-cpu.so	0.02	0.04	0.02	0.00	0.00	0.00	0.00	0.00	0.01	0.02	0.01	0.01	34	52	38	3	0.01	0.04	0.02	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_add_non_quantized	libggml-cpu.so	0.02	0.03	0.02	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.02	0.01	40	47	32	1	0.04	0.04	0.09	0.00	0.00	0.00	0.00	0.00
__intel_avx_rep_memcpy	binary	NA	0.02	NA	0.03	NA	0.00	NA	0.00	NA	0.03	NA	0.02	NA	29	NA	47	NA	0.26	NA	0.08	NA	0.00	NA	0.00
ggml_compute_forward_mul	libggml-cpu.so	0.01	0.01	0.01	NA	0.00	0.00	0.00	NA	0.01	0.02	0.01	NA	27	23	24	NA	0.02	0.03	0.02	NA	0.00	0.00	0.00	NA
ggml_compute_forward_rope_f32	libggml-cpu.so	NA	NA	NA	0.04	NA	NA	NA	0.01	NA	NA	NA	0.02	NA	NA	NA	65	NA	NA	NA	0.04	NA	NA	NA	0.00
__libm_expf_l9	binary	NA	0.02	NA	0.02	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	40	NA	41	NA	0.02	NA	0.03	NA	0.00	NA	0.00
ggml_vec_swiglu_f32	libggml-cpu.so	NA	NA	NA	0.04	NA	NA	NA	0.01	NA	NA	NA	0.02	NA	NA	NA	64	NA	NA	NA	0.07	NA	NA	NA	0.00
ggml_compute_forward_rms_norm	libggml-cpu.so	NA	NA	NA	0.04	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	56	NA	NA	NA	0.04	NA	NA	NA	0.00
ggml_cpu_fp32_to_fp16	libggml-cpu.so	0.01	0.01	0.01	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	19	22	24	NA	0.01	0.02	0.02	NA	0.00	0.00	0.00	NA
quantize_row_q8_0	libggml-cpu.so	0.01	0.00	0.01	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	22	11	20	NA	0.01	0.07	0.00	NA	0.00	0.00	0.00	NA
ggml_compute_forward_add_non_quantized	libggml-cpu.so	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	36	NA	NA	NA	0.03	NA	NA	NA	0.00
mm_cleanup_thread_cbk	libmkl_core.so.2	0.00	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	9	17	12	8	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_mul	libggml-cpu.so	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	38	NA	NA	NA	0.02	NA	NA	NA	0.00
mkl_blas_def_xsgemm_bdz	libmkl_def.so.2	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	8	11	8	5	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.00
ggml_graph_compute_thread	libggml-cpu.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	7	6	8	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_cpu_fp32_to_fp16	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	18	NA	NA	NA	0.02	NA	NA	NA	0.00
__intel_avx_rep_memset	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.04	NA	0.04	NA	2	NA	1	NA	1.82	NA	0.00	NA	0.03	NA	0.00
__libm_roundf_y8	binary	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	13	NA	NA	NA	0.02	NA	NA	NA	0.00
dequantize_row_q8_0	libggml-base.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.03	0.03	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
__memcmp_evex_movbe	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.02	0.03	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__memset_avx512_unaligned_erms	libc.so.6	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.04	NA	3	NA	2	NA	0.36	NA	1.33	NA	0.01	NA	0.02	NA
mkl_serv_allocate	libmkl_core.so.2	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.01	0.00	8	2	2	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
llama_vocab::impl::~impl()	libllama.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.02	0.02	0.02	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
sched_yield@plt	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	4	NA	6	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
mkl_blas_sgemm_omp_get_prototype	libmkl_intel_thread.so.2	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	0.01	3	2	3	2	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_mul_mat	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	10	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_compute_forward_set_rows	libggml-cpu.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	2	2	5	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
mkl_blas_sgemm_omp_driver_v1.extracted.38	libmkl_intel_thread.so.2	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.00	0.00	3	3	1	2	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	3	NA	6	NA	0.00	NA	0.00	NA	0.00	NA	0.00
quantize_row_q8_0_ref	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	8	NA	NA	NA	0.01	NA	NA	NA	0.00
ggml_graph_compute_thread	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	8	NA	NA	NA	0.00	NA	NA	NA	0.00
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::compare(char const*) const	libstdc++.so.6.0.29	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__memcpy_sse2_unaligned	libc.so.6	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.01	1	3	NA	3	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
unknown_function	libggml-cpu.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.00	NA	3	1	2	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
llama_vocab::impl::load(llama_model_loader&, LLM_KV const&)	libllama.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.00	0.01	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
int __kmp_barrier_template<false>(barrier_type, int, int, unsigned long, void, void ()(void, void)) [clone .isra.33]	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	3	NA	3	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
mm_account_ptr_by_tid	libmkl_core.so.2	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.00	0.00	2	NA	2	2	0.00	NA	0.16	0.00	0.00	NA	0.00	0.00
mkl_blas_sgemm_mscale	libmkl_core.so.2	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	1	NA	2	3	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
mkl_blas_def_sgemm_blk_info_bdz	libmkl_def.so.2	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	2	1	NA	3	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.02	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
ggml_graph_compute.omp_outlined	libggml-cpu.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	1	NA	4	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__kmp_enter_single	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	3	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
_int_malloc	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	0.00	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
_IO_fread	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	0.00	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	3	NA	2	NA	0.14	NA	0.00	NA	0.00	NA	0.00
__memchr_evex	libc.so.6	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.00	0.01	1	NA	1	1	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
__strlen_evex	libc.so.6	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.01	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
std::_Hashtable<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, unsigned char>, s...	libllama.so	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.01	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
ggml_compute_forward_glu	libggml-cpu.so	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	3	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
_int_free	libc.so.6	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.00	0.00	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
mkl_blas_def_sgemm_copyat_bdz	libmkl_def.so.2	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	2	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__GI___pthread_create	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	0.00	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
malloc_consolidate	libc.so.6	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.01	0.00	1	NA	1	1	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
__kmp_api_omp_get_num_threads	libomp.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	4	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
ggml_graph_compute.extracted	libggml-cpu.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	2	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
_dl_lookup_symbol_x	ld-linux-x86-64.so.2	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	1	1	2	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00
__GI___pthread_getspecific	libc.so.6	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.00	1	NA	1	2	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
mkl_blas_def_sgemm_copybn_bdz	libmkl_def.so.2	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	2	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
__memcpy_sse2_unaligned_erms	libc.so.6	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	3	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
mkl_serv_cbwr_get	libmkl_core.so.2	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
__kmp_invoke_microtask	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	1	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
_intel_fast_memcpy	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__kmp_finish_implicit_task	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	2	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__GI___libc_malloc	libc.so.6	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00
.plt.sec@start	libstdc++.so.6.0.29	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00
mkl_blas_sgemm_2D_bsrc	libmkl_intel_thread.so.2	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	1	1	NA	1	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
kmp_flag_native<unsigned long long, (flag_type)1, true>::done_check()	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__kmp_join_barrier(int)	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	3	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_invoke_task_func	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	3	NA	NA	NA	0.00	NA	NA	NA	0.00
dequantize_row_q8_0	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
std::__detail::_Map_base<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, int>, st...	libllama.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
expf	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmp_api_omp_get_num_threads	libiomp5.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
unicode_cpt_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, unsigned long&)	libllama.so	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
__GI___libc_free	libc.so.6	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
ggml_cpu_extra_compute_forward	libggml-cpu.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
unknown_function	libllama.so	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA
ggml_compute_forward_mul_mat	libggml-cpu.so	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA
mkl_blas_sgemm_omp_driver_v1.extracted	libmkl_intel_thread.so.2	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__kmp_yield	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
std::basic_ostream<char, std::char_traits<char> >& std::__ostream_insert<char, std::char_traits<char> >(std::basic_ostream<char, std::char_traits<char> >&, char const*, long)	libstdc++.so.6.0.29	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__kmp_launch_thread	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
unlink_chunk.constprop.0	libc.so.6	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__libm_log2_l9	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__kmp_enter_single	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__rawmemchr_evex	libc.so.6	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00
__GI___pthread_mutex_lock	libc.so.6	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	0.00	1	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
mkl_blas_sgemm_get_bufs_size	libmkl_core.so.2	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	1	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
_ZN11llama_vocab4impl4loadER18llama_model_loaderRK6LLM_KV.A	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
mkl_serv_deallocate	libmkl_core.so.2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
mkl_blas_def_sgemm_getbufs_bdz	libmkl_def.so.2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_vec_dot_q8_0_q8_0	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
_ZNSt10_HashtableINSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEESt4pairIKS5_hESaIS8_ENSt8__detail10_Select1stESt8equal_toIS5_ESt4hashIS5_ENSA_18_Mod_range_hashingENSA_20_Default_ranged_hashENSA_20_Prime_rehash_policyENSA_17_Hashtable_traitsILb1ELb0EL...	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_get_glu_op	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
quantize_row_q8_0_ref	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long)	libstdc++.so.6.0.29	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_compute_forward_glu	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_compute_forward_set_rows	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00
__strcmp_evex	libc.so.6	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_append(char const*, unsigned long)	libstdc++.so.6.0.29	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__tls_get_addr	ld-linux-x86-64.so.2	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
unicode_cpts_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
powf	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
.plt.sec@start	libmkl_intel_thread.so.2	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_nrows	libggml-base.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
mkl_serv_check_ptr_and_warn	libmkl_intel_thread.so.2	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmp_fork_barrier(int, int)	libiomp5.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__libm_sse2_sincosf	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__GI___clone_internal	libc.so.6	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml::cpu::repack::extra_buffer_type::get_tensor_traits(ggml_tensor const*)	libggml-cpu.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmp_fork_call	libiomp5.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_gallocr_reserve_n	libggml-base.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_construct(unsigned long, char)	libstdc++.so.6.0.29	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmp_invoke_microtask	libiomp5.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmpc_global_thread_num	libiomp5.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_blck_size	libggml-base.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
std::_Hash_bytes(void const*, unsigned long, unsigned long)	libstdc++.so.6.0.29	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
__kmpc_single	libomp.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
__kmp_fork_barrier(int, int)	libomp.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
do_lookup_x	ld-linux-x86-64.so.2	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
replace_all(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<...	libllama.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
llamafile_sgemm	libggml-cpu.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
gguf_get_arr_str	libggml-base.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
strcmp	ld-linux-x86-64.so.2	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
mkl_blas_sgemm_blk_info_bdz	libmkl_core.so.2	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
check_match	ld-linux-x86-64.so.2	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
std::ostream::sentry::sentry(std::ostream&)	libstdc++.so.6.0.29	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
bool gguf_reader::read<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >(std::vector<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::allocato...	libggml-base.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__kmpc_barrier	libomp.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
gguf_kv_to_str[abi:cxx11](gguf_context const*, int)	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::find(char, unsigned long) const	libstdc++.so.6.0.29	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
ggml_type_size	libggml-base.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__kmp_join_barrier(int)	libomp.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
ggml_backend_blas_graph_compute(ggml_backend, ggml_cgraph)	libggml-blas.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
operator new(unsigned long)	libstdc++.so.6.0.29	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
std::pair<std::__detail::_Node_iterator<std::pair<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<c...	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
llama_decode_text(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__kmp_get_global_thread_id_reg	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
llama_batch_init	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_launch_thread	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_barrier	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
_IO_file_xsgetn	libc.so.6	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_task_team_sync	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_is_empty	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
llama_decode_text	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__svml_logf4	binary	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
_ZNSt8__detail9_Map_baseINSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEESt4pairIKS6_iESaIS9_ENS_10_Select1stESt8equal_toIS6_ESt4hashIS6_ENS_18_Mod_range_hashingENS_20_Default_ranged_hashENS_20_Prime_rehash_policyENS_17_Hashtable_traitsILb1ELb0ELb1EEEL...	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
mkl_serv_cpu_detect	libmkl_core.so.2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_backend_cpu_get_extra_buffer_types()	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
_ZN11llama_vocab4implD2Ev.A	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
roundf	binary	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
_ZNKSt10_HashtableISt4pairINSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEES6_ES0_IKS7_iESaIS9_ENSt8__detail10_Select1stESt8equal_toIS7_EN11llama_vocab4impl9pair_hashENSB_18_Mod_range_hashingENSB_20_Default_ranged_hashENSB_20_Prime_rehash_policyENSB_17...	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::reserve(unsigned long)	libstdc++.so.6.0.29	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_get_type_traits_cpu	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00

	orig_default	icx_default	aocc_9	icx_5
Uncheck all modules
libomp.so	81.53 %	0.00 %	84.54 %
libiomp5.so
libmkl_def.so.2	17.14 %	14.60 %	13.97 %	16.39 %
libggml-cpu.so	0.75 %	0.84 %	0.93 %	2.55 %
libc.so.6	0.45 %	0.40 %	0.47 %	0.39 %
binary
libm.so.6	0.10 %	0.00 %	0.07 %
libmkl_core.so.2	0.01 %	0.01 %	0.01 %	0.01 %
libllama.so	0.01 %	0.01 %	0.01 %	0.00 %
libggml-base.so	0.00 %	0.00 %	0.00 %	0.01 %
libmkl_intel_thread.so.2	0.00 %	0.00 %	0.00 %	0.00 %
libstdc++.so.6.0.29	0.00 %	0.00 %	0.00 %	0.00 %
ld-linux-x86-64.so.2	0.00 %	0.00 %	0.00 %	0.00 %
libggml-blas.so	0.00 %

Report Configuration

Functions

▶<unknown>: 0 - 396.04 %

▶sgemm.cpp: 138 - 1.49 %

▶ops.cpp: 8690 - 1.21 %

▶quants.c: 1011 - 1.05 %

▶vec.cpp: 331 - 0.21 %

▶Old Layout

▶Filters

Functions