OV - Compare Functions

Functions

▶<unknown>: 0 - 397.02 %

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_4							Run icx_3

34	0.00	0.00	0.01	7	0.00	0.00	29	0.00	0.00	0.00	1	0.00	0.00	314	0.04	0.01	0.03	58	0.05	0.00	495	0.00	0.00	0.00	1	0.00	0.00
313	0.03	0.00	0.02	47	0.03	0.00	262	0.02	0.00	0.02	33	0.02	0.00	264	0.01	0.00	0.01	29	0.01	0.00	637	0.02	0.00	0.02	36	0.04	0.00
265	0.03	0.00	0.02	44	0.04	0.00	312	0.04	0.00	0.03	59	0.04	0.00	27	0.00	0.00	0.00	1	0.00	0.00	99	0.00	0.00	0.01	10	0.00	0.00
35	0.00	0.00	0.01	4	0.00	0.00	264	0.03	0.00	0.01	41	0.02	0.00	244	0.02	0.00	0.02	41	0.03	0.00	669	0.03	0.00	0.01	55	0.02	0.00
355	0.00	0.00	0.01	1	0.00	0.00	68	0.00	0.00	0.00	1	0.00	0.00	35	0.00	0.00	0.01	9	0.01	0.00	553	0.00	0.00	0.00	1	0.00	0.00
334	0.05	0.01	0.03	68	0.04	0.00	301	0.00	0.00	0.01	1	0.00	0.00	196	0.00	0.00	0.00	1	0.00	0.00	653	0.00	0.00	0.00	1	0.00	0.00
302	0.00	0.00	0.01	1	0.00	0.00	236	0.02	0.00	0.02	35	0.03	0.00	7	0.00	0.00	0.00	7	0.00	0.00	75	0.01	0.00	0.01	12	0.00	0.00
6	0.00	0.00	0.01	9	0.00	0.00	37	0.00	0.00	0.01	9	0.00	0.00	-1	0.00	0.00	0.00	1	0.00	0.00	438	0.01	0.00	0.01	21	0.02	0.00
241	0.02	0.00	0.01	35	0.02	0.00	476	0.00	0.00	0.01	10	0.00	0.00	240	0.00	0.00	0.00	2	0.00	0.00	109	0.00	0.00	0.01	6	0.00	0.00
263	0.02	0.00	0.01	33	0.01	0.00	9	0.01	0.00	0.01	13	0.02	0.00	36	0.00	0.00	0.00	5	0.00	0.00	749	0.00	0.00	0.00	1	0.00	0.00
243	0.01	0.00	0.01	20	0.02	0.00	287	0.02	0.00	0.02	26	0.02	0.00	242	0.03	0.00	0.02	38	0.03	0.00	582	0.00	0.00	0.00	1	0.00	0.00
26	0.00	0.00	0.01	2	0.00	0.00	413	0.04	0.00	0.01	83	0.03	0.00	266	0.03	0.00	0.02	44	0.03	0.00	509	0.02	0.00	0.02	38	0.07	0.00
341	0.00	0.00	0.00	2	0.00	0.00	332	0.05	0.01	0.02	61	0.04	0.00	289	0.03	0.00	0.02	40	0.04	0.00	430	0.02	0.00	0.02	36	0.03	0.00
195	0.00	0.00	0.00	1	0.00	0.00	240	0.01	0.00	0.01	18	0.02	0.00	335	0.07	0.01	0.02	77	0.04	0.00	10899	0.00	0.00	0.00	2	0.00	0.00
269	0.00	0.00	0.00	1	0.00	0.00	10901	0.00	0.00	0.01	7	0.00	0.00	479	0.00	0.00	0.01	9	0.00	0.00	10876	0.00	0.00	0.01	2	0.00	0.00
415	0.04	0.00	0.01	77	0.03	0.00	10926	0.00	0.00	0.01	1	0.00	0.00	416	0.04	0.01	0.01	84	0.03	0.00	10879	0.00	0.00	0.01	1	0.00	0.00
478	0.01	0.00	0.01	11	0.01	0.00	10876	0.00	0.00	0.01	3	0.02	0.00	10901	0.00	0.00	0.00	6	0.00	0.00	10901	0.00	0.00	0.01	9	0.00	0.00
288	0.03	0.00	0.03	40	0.04	0.00	10851	0.00	0.00	0.00	1	0.00	0.00	11125	0.00	0.00	0.01	1	0.00	0.00	11125	0.00	0.00	0.00	1	0.00	0.00
10901	0.01	0.00	0.01	18	0.00	0.00	10899	0.00	0.00	0.01	2	0.00	0.00	10876	0.00	0.00	0.00	5	0.00	0.00	1946	0.40	0.05	0.09	95	0.13	0.02
10851	0.00	0.00	0.00	1	0.00	0.00	1946	0.39	0.04	0.09	96	0.13	0.02	10899	0.00	0.00	0.00	1	0.00	0.00	2252	0.00	0.00	0.00	1	0.00	0.00
10876	0.00	0.00	0.01	3	0.00	0.00	686	0.00	0.00	0.00	1	0.00	0.00	10805	0.00	0.00	0.00	1	0.00	0.00	1089	0.00	0.00	0.00	1	0.00	0.00
10883	0.00	0.00	0.01	1	0.00	0.00	1087	0.00	0.00	0.00	1	0.00	0.00	11119	0.00	0.00	0.00	1	0.00	0.00	1333	0.00	0.00	0.00	1	0.00	0.00
11125	0.00	0.00	0.00	1	0.00	0.00	3631	0.00	0.00	0.00	1	0.00	0.00	3631	0.00	0.00	0.01	1	0.00	0.00	1101	0.00	0.00	0.00	1	0.00	0.00
10899	0.00	0.00	0.00	1	0.00	0.00	883	0.00	0.00	0.00	1	0.00	0.00	1101	0.00	0.00	0.00	1	0.00	0.00	1326	0.00	0.00	0.01	1	0.00	0.00
1946	0.40	0.05	0.09	95	0.13	0.01	1335	0.00	0.00	0.00	1	0.00	0.00	686	0.00	0.00	0.01	1	0.00	0.00	1122	0.00	0.00	0.00	1	0.00	0.00
2252	0.00	0.00	0.00	1	0.00	0.00	1101	0.00	0.00	0.00	2	0.00	0.00	1946	0.41	0.05	0.09	96	0.13	0.02	1318	0.00	0.00	0.00	1	0.00	0.00
3631	0.00	0.00	0.01	1	0.00	0.00	1326	0.00	0.00	0.01	1	0.00	0.00	1089	0.00	0.00	0.01	1	0.00	0.00	1324	0.00	0.00	0.00	1	0.00	0.00
1324	0.00	0.00	0.02	1	0.00	0.00	1122	0.00	0.00	0.00	1	0.00	0.00	3695	0.00	0.00	0.01	1	0.00	0.00	1489	0.00	0.00	0.00	1	0.00	0.00
1101	0.00	0.00	0.00	1	0.00	0.00	1318	0.00	0.00	0.01	1	0.00	0.00	1324	0.00	0.00	0.01	2	0.16	0.00	3605	0.00	0.00	0.03	1	0.00	0.00
686	0.00	0.00	0.01	1	0.00	0.00	1493	0.00	0.00	0.00	1	0.00	0.00	1333	0.00	0.00	0.01	1	0.00	0.00	1335	0.00	0.00	0.00	1	0.00	0.00
1326	0.00	0.00	0.00	1	0.00	0.00	1489	0.00	0.00	0.00	1	0.00	0.00	3604	0.00	0.00	0.01	1	0.00	0.00	3689	0.00	0.00	0.01	1	0.00	0.00
1318	0.00	0.00	0.00	1	0.00	0.00	3605	0.00	0.00	0.03	1	0.00	0.00	1326	0.00	0.00	0.01	1	0.00	0.00	3435	0.00	0.00	0.01	1	0.00	0.00
3689	0.01	0.00	0.01	30	0.01	0.00	2381	0.00	0.00	0.00	1	0.00	0.00	1489	0.00	0.00	0.01	2	0.00	0.00	3482	0.00	0.00	0.00	1	0.00	0.00
3695	0.00	0.00	0.02	2	0.52	0.01	1324	0.00	0.00	0.01	1	0.00	0.00	1317	0.00	0.00	0.01	1	0.00	0.00	3583	0.02	0.00	0.01	35	0.02	0.00
3604	0.00	0.00	0.00	1	0.00	0.00	2049	0.00	0.00	0.00	1	0.00	0.00	1318	0.00	0.00	0.01	1	0.00	0.00	3568	0.01	0.00	0.01	11	0.06	0.00
2380	0.00	0.00	0.00	1	0.00	0.00	2045	0.01	0.00	0.01	26	0.01	0.00	3689	0.02	0.00	0.02	30	0.02	0.00	3624	0.01	0.00	0.01	19	0.16	0.00
3605	0.00	0.00	0.02	1	0.00	0.00	2090	0.01	0.00	0.04	3	1.33	0.02	3605	0.00	0.00	0.02	1	0.00	0.00	3605	0.00	0.00	0.00	1	0.00	0.00
2486	0.00	0.00	0.00	3	0.00	0.00	2089	0.01	0.00	0.01	20	0.05	0.00	1129	0.00	0.00	0.01	1	0.00	0.00	3480	0.03	0.00	0.02	54	0.04	0.00
941	0.00	0.00	0.00	1	0.00	0.00	1948	0.03	0.00	0.02	51	0.04	0.00	1335	0.00	0.00	0.00	1	0.00	0.00	3625	0.00	0.00	0.04	2	1.37	0.02
1401	0.00	0.00	0.01	4	0.00	0.00	1643	0.00	0.00	0.01	1	0.00	0.00	2487	45.88	5.41	6.16	96	3.00	0.58	2875	0.00	0.00	0.03	1	0.00	0.00
1405	0.00	0.00	0.00	2	0.00	0.00	1715	0.00	0.00	0.01	1	0.00	0.00	1284	0.00	0.00	0.00	2	0.00	0.00	2995	0.00	0.00	0.00	1	0.00	0.00
1386	0.09	0.01	0.44	21	5.04	0.10	635	0.00	0.00	0.00	1	0.00	0.00	1406	0.00	0.00	0.00	3	0.00	0.00	2885	0.00	0.00	0.02	1	0.00	0.00
1018	0.00	0.00	0.00	1	0.00	0.00	1675	0.00	0.00	0.01	1	0.00	0.00	1385	37.64	4.44	5.03	95	2.28	0.27	2822	0.00	0.00	0.00	1	0.00	0.00
1385	37.65	4.40	4.94	95	2.48	0.28	1476	0.00	0.00	0.00	1	0.00	0.00	86	0.00	0.00	0.01	7	0.00	0.00	2877	0.00	0.00	0.00	1	0.00	0.00
1039	0.00	0.00	0.00	1	0.00	0.00	1642	0.00	0.00	0.01	1	0.00	0.00	1401	0.00	0.00	0.00	1	0.00	0.00	2879	0.00	0.00	0.00	1	0.00	0.00
86	0.00	0.00	0.01	5	0.00	0.00	1639	0.00	0.00	0.01	1	0.00	0.00	1039	0.00	0.00	0.00	2	0.00	0.00	2029	0.00	0.00	0.00	2	0.00	0.00
1284	0.00	0.00	0.00	1	0.00	0.00	2356	0.00	0.00	0.00	1	0.00	0.00	1386	0.08	0.01	0.43	22	4.76	0.10	1088	0.00	0.00	0.00	1	0.00	0.00
1406	0.00	0.00	0.00	1	0.00	0.00	2029	0.00	0.00	0.01	4	0.00	0.00	1405	0.00	0.00	0.01	4	0.00	0.00	1092	0.00	0.00	0.01	4	0.00	0.00
1874	0.00	0.00	0.00	1	0.00	0.00	1092	0.00	0.00	0.01	5	0.09	0.00	941	0.00	0.00	0.01	4	0.00	0.00	1397	0.00	0.00	0.01	2	0.00	0.00
979	0.00	0.00	0.00	1	0.00	0.00	1397	0.00	0.00	0.01	3	0.00	0.00	2233	0.00	0.00	0.01	3	0.02	0.00	2924	0.09	0.01	0.03	84	0.06	0.01
2487	45.62	5.33	5.97	96	3.06	0.57	1104	0.00	0.00	0.00	2	0.00	0.00	81	0.00	0.00	0.01	1	0.00	0.00	2915	0.00	0.00	0.00	2	0.00	0.00
2233	0.00	0.00	0.00	1	0.00	0.00	1111	81.06	9.44	10.28	96	5.74	1.01	196	0.00	0.00	0.01	1	0.00	0.00	1111	80.42	9.38	10.20	96	5.62	0.99
285	0.00	0.00	0.00	1	0.00	0.00	1114	0.00	0.00	0.00	1	0.00	0.00	2766	0.00	0.00	0.01	1	0.00	0.00	1984	0.00	0.00	0.00	1	0.00	0.00
31	0.00	0.00	0.00	1	0.00	0.00	1116	2.09	0.24	0.34	96	0.32	0.04	2989	0.00	0.00	0.01	1	0.00	0.00	1116	2.05	0.24	0.35	96	0.36	0.05
81	0.00	0.00	0.00	1	0.00	0.00	1167	0.00	0.00	0.01	1	0.00	0.00	12553	0.00	0.00	0.01	1	0.00	0.00	1201	0.00	0.00	0.01	1	0.00	0.00
82	0.00	0.00	0.00	2	0.15	0.00	1982	0.00	0.00	0.01	3	0.00	0.00	12565	0.00	0.00	0.00	2	0.00	0.00	1098	0.00	0.00	0.01	3	0.00	0.00
259	0.00	0.00	0.00	1	0.00	0.00	2916	0.00	0.00	0.00	1	0.00	0.00	12557	0.00	0.00	0.00	1	0.00	0.00	46	0.00	0.00	0.00	1	0.00	0.00
190	0.00	0.00	0.01	1	0.00	0.00	1984	0.00	0.00	0.00	1	0.00	0.00	1802	0.00	0.00	0.01	1	0.00	0.00	190	0.00	0.00	0.01	1	0.00	0.00
2	0.00	0.00	0.00	1	0.00	0.00	1096	0.00	0.00	0.00	1	0.00	0.00	2052	0.00	0.00	0.02	1	0.00	0.00	2484	0.00	0.00	0.00	1	0.00	0.00
2499	0.00	0.00	0.00	1	0.00	0.00	1098	0.00	0.00	0.01	4	0.00	0.00	2049	0.00	0.00	0.01	1	0.00	0.00	2912	0.00	0.00	0.00	1	0.00	0.00
2912	0.00	0.00	0.00	1	0.00	0.00	2924	0.11	0.01	0.04	88	0.07	0.01	2050	0.00	0.00	0.01	1	0.00	0.00	2766	0.00	0.00	0.01	1	0.00	0.00
2766	0.00	0.00	0.00	1	0.00	0.00	1201	0.00	0.00	0.01	2	0.00	0.00	2145	0.00	0.00	0.01	1	0.00	0.00	2989	0.00	0.00	0.00	1	0.00	0.00
2989	0.00	0.00	0.01	1	0.00	0.00	2355	0.00	0.00	0.00	1	0.00	0.00	743	0.00	0.00	0.01	1	0.00	0.00	1231	0.00	0.00	0.00	1	0.00	0.00
12553	0.00	0.00	0.00	2	0.00	0.00	138	0.00	0.00	0.00	1	0.00	0.00	2098	0.00	0.00	0.02	1	0.00	0.00	1050	0.00	0.00	0.03	1	0.00	0.00
12565	0.00	0.00	0.01	1	0.00	0.00	190	0.00	0.00	0.01	1	0.00	0.00	2109	0.00	0.00	0.01	1	0.00	0.00	44	0.00	0.00	0.01	2	0.00	0.00
2145	0.00	0.00	0.00	1	0.00	0.00	2766	0.00	0.00	0.01	1	0.00	0.00	63	0.00	0.00	0.01	1	0.00	0.00	543	0.00	0.00	0.00	1	0.00	0.00
747	0.00	0.00	0.00	1	0.00	0.00	2499	0.00	0.00	0.00	1	0.00	0.00	570	0.00	0.00	0.02	3	0.58	0.01	1036	0.01	0.00	0.01	11	0.06	0.00
2052	0.00	0.00	0.02	1	0.00	0.00	12557	0.00	0.00	0.00	1	0.00	0.00	636	0.03	0.00	0.03	48	0.04	0.00	12565	0.00	0.00	0.00	4	0.00	0.00
2049	0.00	0.00	0.00	1	0.00	0.00	11316	0.00	0.00	0.00	1	0.00	0.00	3188	0.01	0.00	0.01	11	0.02	0.00	12553	0.00	0.00	0.01	3	0.00	0.00
2107	0.00	0.00	0.00	1	0.00	0.00	12565	0.00	0.00	0.01	2	0.00	0.00	3349	9.83	1.16	1.70	96	3.61	0.43	3188	0.01	0.00	0.02	12	0.02	0.00
2053	0.00	0.00	0.00	1	0.00	0.00	12553	0.00	0.00	0.01	6	0.00	0.00	3040	0.00	0.00	0.00	1	0.00	0.00	3349	9.85	1.15	1.65	96	3.66	0.42
-1	0.00	0.00	0.00	1	0.00	0.00	12563	0.00	0.00	0.01	2	0.00	0.00	3344	5.11	0.60	0.84	96	1.30	0.12	3045	0.00	0.00	0.01	3	0.00	0.00
2098	0.00	0.00	0.03	1	0.00	0.00	553	0.00	0.00	0.04	1	0.00	0.00	2907	0.00	0.00	0.00	1	0.00	0.00	3344	5.11	0.60	0.84	96	1.35	0.12
2106	0.00	0.00	0.00	1	0.00	0.00	462	0.00	0.00	0.00	1	0.00	0.00	3350	0.13	0.01	0.10	81	0.14	0.02	3038	0.00	0.00	0.01	1	0.00	0.00
568	0.00	0.00	0.04	2	1.26	0.02	65	0.00	0.00	0.00	1	0.00	0.00	3345	0.09	0.01	0.04	81	0.06	0.01	3350	0.13	0.01	0.09	81	0.14	0.02
35	0.00	0.00	0.01	1	0.00	0.00	3188	0.01	0.00	0.01	18	0.00	0.00								3345	0.08	0.01	0.05	79	0.07	0.01
636	0.06	0.01	0.03	72	0.04	0.00	3045	0.00	0.00	0.01	3	0.00	0.00
3045	0.00	0.00	0.01	5	0.00	0.00	3344	5.14	0.60	0.79	96	1.72	0.11
3188	0.01	0.00	0.01	22	0.02	0.00	3349	10.15	1.18	1.69	96	3.76	0.44
3345	0.07	0.01	0.04	75	0.05	0.01	3350	0.13	0.01	0.07	83	0.13	0.01
3350	0.13	0.01	0.10	82	0.13	0.01	3345	0.09	0.01	0.04	80	0.07	0.01
3349	9.94	1.16	1.64	96	3.67	0.43
3040	0.00	0.00	0.00	1	0.00	0.00
3038	0.00	0.00	0.00	1	0.00	0.00
3046	0.00	0.00	0.00	1	0.00	0.00
3344	5.28	0.62	0.84	96	1.33	0.13

▶sgemm.cpp: 138 - 1.35 %

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_4							Run icx_3
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/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/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044
411	0.44	0.05	0.08	96	0.22	0.02	409	0.49	0.06	0.08	96	0.16	0.02	412	0.43	0.05	0.07	96	0.17	0.02

▶quants.c: 1011 - 1.14 %

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_4	Run icx_3
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/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/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1066-1077 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
			771	1.14	0.13	0.15	96	0.45	0.01

▶ops.cpp: 8690 - 0.34 %

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_4	Run icx_3
				/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/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-389 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/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/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 392-393 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 508-509 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 693-694 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 756-757 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8690-8706 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939
			707	0.34	0.04	0.08	95	0.11	0.01

▶vec.cpp: 331 - 0.15 %

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_4	Run icx_3
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-631-1812/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/176-631-1812/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 331-337
			505	0.15	0.02	0.03	90	0.06	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_4	icx_3	orig_default	icx_default	aocc_4	icx_3	orig_default	icx_default	aocc_4	icx_3	orig_default	icx_default	aocc_4	icx_3	orig_default	icx_default	aocc_4	icx_3	orig_default	icx_default	aocc_4	icx_3
kmp_flag_64<false, true>::wait(kmp_info, int, void)	libiomp5.so	NA	81.06	NA	80.42	NA	9.44	NA	9.38	NA	10.28	NA	10.20	NA	96	NA	96	NA	5.74	NA	5.62	NA	1.01	NA	0.99
__kmp_hardware_timestamp	libomp.so	45.62	NA	45.88	NA	5.33	NA	5.41	NA	5.97	NA	6.16	NA	96	NA	96	NA	3.06	NA	3.00	NA	0.57	NA	0.58	NA
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libomp.so	37.65	NA	37.64	NA	4.40	NA	4.44	NA	4.94	NA	5.03	NA	95	NA	95	NA	2.48	NA	2.28	NA	0.28	NA	0.27	NA
mkl_blas_def_sgemm_scopy_right16_bdz	libmkl_def.so.2	9.94	10.15	9.83	9.85	1.16	1.18	1.16	1.15	1.64	1.69	1.70	1.65	96	96	96	96	3.67	3.76	3.61	3.66	0.43	0.44	0.43	0.42
mkl_blas_def_sgemm_kernel_0_zen	libmkl_def.so.2	5.28	5.14	5.11	5.11	0.62	0.60	0.60	0.60	0.84	0.79	0.84	0.84	96	96	96	96	1.33	1.72	1.30	1.35	0.13	0.11	0.12	0.12
kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check()	libiomp5.so	NA	2.09	NA	2.05	NA	0.24	NA	0.24	NA	0.34	NA	0.35	NA	96	NA	96	NA	0.32	NA	0.36	NA	0.04	NA	0.05
__GI___sched_yield	libc.so.6	0.40	0.39	0.41	0.40	0.05	0.04	0.05	0.05	0.09	0.09	0.09	0.09	95	96	96	95	0.13	0.13	0.13	0.13	0.01	0.02	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	0.44	0.49	0.43	NA	0.05	0.06	0.05	NA	0.08	0.08	0.07	NA	96	96	96	NA	0.22	0.16	0.17	NA	0.02	0.02	0.02	NA
ggml_vec_dot_q8_0_q8_0	libggml-cpu.so	NA	NA	NA	1.14	NA	NA	NA	0.13	NA	NA	NA	0.15	NA	NA	NA	96	NA	NA	NA	0.45	NA	NA	NA	0.01
mkl_blas_def_sgemm_scopy_right4_bdz	libmkl_def.so.2	0.13	0.13	0.13	0.13	0.01	0.01	0.01	0.01	0.10	0.07	0.10	0.09	82	83	81	81	0.13	0.13	0.14	0.14	0.01	0.01	0.02	0.02
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	NA	NA	NA	0.34	NA	NA	NA	0.04	NA	NA	NA	0.08	NA	NA	NA	95	NA	NA	NA	0.11	NA	NA	NA	0.01
mkl_blas_def_sgemm_mscale	libmkl_def.so.2	0.07	0.09	0.09	0.08	0.01	0.01	0.01	0.01	0.04	0.04	0.04	0.05	75	80	81	79	0.05	0.07	0.06	0.07	0.01	0.01	0.01	0.01
__kmp_yield	libiomp5.so	NA	0.11	NA	0.09	NA	0.01	NA	0.01	NA	0.04	NA	0.03	NA	88	NA	84	NA	0.07	NA	0.06	NA	0.01	NA	0.01
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	0.05	0.05	0.07	NA	0.01	0.01	0.01	NA	0.03	0.02	0.02	NA	68	61	77	NA	0.04	0.04	0.04	NA	0.00	0.00	0.00	NA
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libomp.so	0.09	NA	0.08	NA	0.01	NA	0.01	NA	0.44	NA	0.43	NA	21	NA	22	NA	5.04	NA	4.76	NA	0.10	NA	0.10	NA
ggml_vec_dot_f16	libggml-cpu.so	NA	NA	NA	0.15	NA	NA	NA	0.02	NA	NA	NA	0.03	NA	NA	NA	90	NA	NA	NA	0.06	NA	NA	NA	0.01
void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<2>(long, long, long, long)	libggml-cpu.so	0.04	0.04	0.04	NA	0.00	0.00	0.01	NA	0.01	0.01	0.01	NA	77	83	84	NA	0.03	0.03	0.03	NA	0.00	0.00	0.00	NA
ggml_compute_forward_rope_f32(ggml_compute_params const, ggml_tensor, bool)	libggml-cpu.so	0.03	0.04	0.04	NA	0.00	0.00	0.01	NA	0.02	0.03	0.03	NA	47	59	58	NA	0.03	0.04	0.05	NA	0.00	0.00	0.00	NA
f64xsubf128	libm.so.6	0.06	NA	0.03	NA	0.01	NA	0.00	NA	0.03	NA	0.03	NA	72	NA	48	NA	0.04	NA	0.04	NA	0.00	NA	0.00	NA
ggml_vec_swiglu_f32	libggml-cpu.so	0.03	0.03	0.03	NA	0.00	0.00	0.00	NA	0.02	0.01	0.02	NA	44	41	44	NA	0.04	0.02	0.03	NA	0.00	0.00	0.00	NA
ggml_compute_forward_rms_norm	libggml-cpu.so	0.03	0.02	0.03	NA	0.00	0.00	0.00	NA	0.03	0.02	0.02	NA	40	26	40	NA	0.04	0.02	0.04	NA	0.00	0.00	0.00	NA
ggml_compute_forward_add_non_quantized	libggml-cpu.so	0.02	0.02	0.03	NA	0.00	0.00	0.00	NA	0.01	0.02	0.02	NA	35	35	38	NA	0.02	0.03	0.03	NA	0.00	0.00	0.00	NA
__libm_sse2_sincosf_l9	binary	NA	0.03	NA	0.03	NA	0.00	NA	0.00	NA	0.02	NA	0.02	NA	51	NA	54	NA	0.04	NA	0.04	NA	0.00	NA	0.00
ggml_vec_dot_f16	libggml-cpu.so	0.02	0.02	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.02	0.01	0.00	33	33	29	1	0.01	0.02	0.01	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_mul	libggml-cpu.so	0.01	0.01	0.02	NA	0.00	0.00	0.00	NA	0.01	0.01	0.02	NA	20	18	41	NA	0.02	0.02	0.03	NA	0.00	0.00	0.00	NA
__memcpy_avx512_unaligned_erms	libc.so.6	0.01	NA	0.02	0.00	0.00	NA	0.00	0.00	0.01	NA	0.02	0.01	30	NA	30	1	0.01	NA	0.02	0.00	0.00	NA	0.00	0.00
mkl_blas_def_xsgemm_bdz	libmkl_def.so.2	0.01	0.01	0.01	0.01	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.02	22	18	11	12	0.02	0.00	0.02	0.02	0.00	0.00	0.00	0.00
__libm_expf_l9	binary	NA	0.01	NA	0.02	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	26	NA	35	NA	0.01	NA	0.02	NA	0.00	NA	0.00
ggml_compute_forward_rope_f32	libggml-cpu.so	NA	NA	NA	0.03	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	55	NA	NA	NA	0.02	NA	NA	NA	0.00
ggml_compute_forward_rms_norm	libggml-cpu.so	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	36	NA	NA	NA	0.04	NA	NA	NA	0.00
ggml_vec_swiglu_f32	libggml-cpu.so	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	38	NA	NA	NA	0.07	NA	NA	NA	0.00
ggml_compute_forward_add_non_quantized	libggml-cpu.so	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	36	NA	NA	NA	0.03	NA	NA	NA	0.00
__intel_avx_rep_memcpy	binary	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	20	NA	19	NA	0.05	NA	0.16	NA	0.00	NA	0.00
mm_cleanup_thread_cbk	libmkl_core.so.2	0.01	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.00	0.01	18	7	6	9	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_cpu_fp32_to_fp16	libggml-cpu.so	0.00	0.01	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.00	NA	9	13	7	NA	0.00	0.02	0.00	NA	0.00	0.00	0.00	NA
quantize_row_q8_0	libggml-cpu.so	0.01	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	11	10	9	NA	0.01	0.00	0.00	NA	0.00	0.00	0.00	NA
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	9	9	NA	0.00	0.00	0.01	NA	0.00	0.00	0.00	NA
ggml_compute_forward_mul	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	21	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	0.04	0.04	0.02	NA	2	1	3	NA	1.26	0.00	0.58	NA	0.02	0.00	0.01	NA
__intel_avx_rep_memset	binary	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.04	NA	0.04	NA	3	NA	2	NA	1.33	NA	1.37	NA	0.02	NA	0.02
__memcmp_evex_movbe	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.02	0.03	0.02	0.03	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
quantize_row_q8_0_ref	libggml-base.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	11	NA	NA	NA	0.06	NA	NA	NA	0.00
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	0.01	0.00	0.01	3	3	5	2	0.00	0.02	0.00	0.00	0.00	0.00	0.00	0.00
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	12	NA	NA	NA	0.00	NA	NA	NA	0.00
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	0.00	0.01	0.01	0.01	2	6	1	3	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	0.03	0.01	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	0.01	NA	0.01	NA	5	NA	7	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
mkl_blas_def_sgemm_copyat_bdz	libmkl_def.so.2	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	0.01	5	3	NA	3	0.00	0.00	NA	0.00	0.00	0.00	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	11	NA	NA	NA	0.06	NA	NA	NA	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	0.01	NA	0.01	NA	5	NA	4	NA	0.09	NA	0.00	NA	0.00	NA	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
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	1	2	2	4	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_graph_compute.omp_outlined	libggml-cpu.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	4	NA	5	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	0.00	0.01	0.01	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long)	libstdc++.so.6.0.29	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
_int_free	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.02	0.01	0.01	0.00	1	1	2	1	0.00	0.00	0.16	0.00	0.00	0.00	0.00	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	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.02	NA	0.02	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__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	4	NA	3	NA	0.00	NA	0.00	NA	0.00	NA	0.00
std::_Hash_bytes(void const*, unsigned long, unsigned long)	libstdc++.so.6.0.29	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	0.01	1	1	NA	1	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
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	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
malloc_consolidate	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.00	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	0.02	NA	0.01	NA	2	NA	1	NA	0.52	NA	0.00	NA	0.01	NA	0.00	NA
__kmp_launch_thread	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	4	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
_ZN11llama_vocab4implD2Ev.A	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.03	NA	NA	NA	1	NA	NA	NA	0.00	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	6	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	0.03	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
mm_account_ptr_by_tid	libmkl_core.so.2	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	1	2	1	2	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	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
__kmp_join_barrier(int)	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	2	NA	4	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__kmp_api_omp_get_num_threads	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	3	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
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	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
__GI___pthread_getspecific	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	1	2	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
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	0.01	NA	0.00	NA	4	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::compare(char const*) const	libstdc++.so.6.0.29	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_invoke_task_func	libomp.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_api_omp_get_num_threads	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	1	NA	3	NA	0.00	NA	0.02	NA	0.00	NA	0.00	NA
_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	0.02	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__strlen_evex	libc.so.6	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
ggml_compute_forward_mul_mat	libggml-cpu.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.00	0.00	NA	2	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
__memcpy_sse2_unaligned	libc.so.6	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.00	NA	1	2	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00
__kmp_fork_barrier(int, int)	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	3	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	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_enter_single	libiomp5.so	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	NA	NA
__kmpc_single	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	2	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_compute_forward_set_rows	libggml-cpu.so	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	NA
ggml_compute_forward_glu	libggml-cpu.so	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	2	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
__kmp_invoke_microtask	libomp.so	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	NA	NA
__GI___libc_free	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
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	0.01	0.00	1	NA	1	1	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
llama_vocab::impl::load(llama_model_loader&, LLM_KV const&)	libllama.so	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
__memchr_evex	libc.so.6	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__kmp_finish_implicit_task	libomp.so	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	NA
__kmp_enter_single	libomp.so	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	NA
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
__kmp_fork_barrier(int, int)	libiomp5.so	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	NA
mkl_blas_sgemm_omp_driver_v1.extracted	libmkl_intel_thread.so.2	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_resume_if_soft_paused	libiomp5.so	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
__GI___pthread_mutex_lock	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
mkl_serv_cbwr_get	libmkl_core.so.2	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
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	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
__kmp_invoke_microtask	libiomp5.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_type_size	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
mkl_blas_def_sgemm_blk_info_bdz	libmkl_def.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
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_replace_aux(unsigned long, unsigned long, unsigned long, char)	libstdc++.so.6.0.29	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	1	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
__GI___mmap	libc.so.6	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	1	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
_dl_fixup	ld-linux-x86-64.so.2	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	2	NA	NA	NA	0.15	NA	NA	NA	0.00	NA	NA	NA
mkl_blas_sgemm_2D_bsrc	libmkl_intel_thread.so.2	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_malloc	libc.so.6	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
__GI___pthread_create	libc.so.6	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
ggml::cpu::repack::extra_buffer_type::get_tensor_traits(ggml_tensor const*)	libggml-cpu.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
mkl_blas_def_sgemm_freebufs_bdz	libmkl_def.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
_dl_relocate_object	ld-linux-x86-64.so.2	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	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
create_thread	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_backend_sched_graph_compute_async	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
__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
gguf_kv_to_str[abi:cxx11](gguf_context const*, int)	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
ggml_is_contiguous	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
ggml_graph_compute.extracted	libggml-cpu.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
__kmp_join_barrier(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
_IO_file_xsgetn	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
__kmpc_bound_num_threads	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
__kmp_hardware_timestamp	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
mkl_serv_cpuiszen	libmkl_core.so.2	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
kmp_flag_native<unsigned long long, (flag_type)1, true>::done_check()	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
__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
__kmp_init_implicit_task	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
__kmp_finish_implicit_task	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_powf_l9	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
__memcpy_sse2_unaligned_erms	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
unicode_cpt_from_utf8	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
expf	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
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	1	NA	NA	NA	0.00	NA	NA	NA	0.00
_intel_fast_memcpy	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
__libm_logf_l9	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
_ZNSt10_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
gguf_free	libggml-base.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::ostream::sentry::sentry(std::ostream&)	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_compute_forward_rope	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
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
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	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
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	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_rope_yarn_corr_dims	libggml-base.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
do_lookup_x	ld-linux-x86-64.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
mkl_blas_def_sgemm_copybn_bdz	libmkl_def.so.2	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_launch_thread	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_data_to_str[abi:cxx11](gguf_type, void const*, int)	libllama.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
llamafile_sgemm	libggml-cpu.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	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
__kmp_yield	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
unicode_cpt_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, unsigned long&)	libllama.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
__GI___clone3	libc.so.6	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
memset	ld-linux-x86-64.so.2	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
unicode_cpt_to_utf8[abi:cxx11](unsigned int)	libllama.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
__GI___open64_nocancel	ld-linux-x86-64.so.2	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
unknown_function	libllama.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_compute_forward_add	libggml-cpu.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
.plt.sec@start	libstdc++.so.6.0.29	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
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	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
mm_get_tinfo	libmkl_core.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
ggml_nrows	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
open_path	ld-linux-x86-64.so.2	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
unicode_cpts_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.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
mkl_blas_def_sgemm_pst	libmkl_def.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_get_bufs_size	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
.plt.sec@start	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
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	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
unlink_chunk.constprop.0	libc.so.6	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
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	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
__GI___pthread_mutex_unlock_usercnt	libc.so.6	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
ggml_is_contiguous_1	libggml-base.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
operator new(unsigned long)	libstdc++.so.6.0.29	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
unknown_function	libggml-cpu.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

	orig_default	icx_default	aocc_4	icx_3
Uncheck all modules
libomp.so	83.38 %	0.00 %	83.62 %
libiomp5.so
libmkl_def.so.2	15.43 %	15.52 %	15.17 %	15.17 %
libggml-cpu.so	0.68 %	0.73 %	0.72 %	1.75 %
libc.so.6	0.42 %	0.40 %	0.44 %	0.40 %
binary
libm.so.6	0.06 %	0.00 %	0.03 %
libmkl_core.so.2	0.01 %	0.01 %	0.01 %	0.01 %
libllama.so	0.01 %	0.01 %	0.01 %	0.01 %
libggml-base.so	0.00 %	0.01 %	0.00 %	0.01 %
libstdc++.so.6.0.29	0.00 %	0.00 %	0.00 %	0.00 %
libmkl_intel_thread.so.2	0.00 %	0.01 %	0.00 %	0.00 %
ld-linux-x86-64.so.2	0.00 %	0.00 %	0.00 %	0.00 %

Report Configuration

Functions

▶<unknown>: 0 - 397.02 %

▶sgemm.cpp: 138 - 1.35 %

▶quants.c: 1011 - 1.14 %

▶ops.cpp: 8690 - 0.34 %

▶vec.cpp: 331 - 0.15 %

▶Old Layout

▶Filters

Functions