OV - Compare Functions

Functions

▶quants.c: 44 - 210.88 %

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_10							Run icx_3
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/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/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 44-47 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 108-109 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 129-131 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1013-1013 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1033-1042 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/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/176-976-6240/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/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 44-47 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 108-109 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 129-131 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/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/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1033-1042 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/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/176-976-6240/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/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 44-47 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 108-109 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 129-131 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1013-1013 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1033-1042 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1066-1077
486	70.45	6.23	8.11	96	21.96	1.95	484	70.20	6.22	8.13	96	22.00	1.96	489	70.23	6.25	8.18	96	21.71	1.95

▶<unknown>: 0 - 115.89 %

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_10							Run icx_3

2487	15.04	1.33	3.05	96	11.92	1.04	1681	0.00	0.00	0.00	1	0.00	0.00	481	0.05	0.00	0.02	56	0.05	0.00	457	0.00	0.00	0.01	1	0.00	0.00
1283	0.00	0.00	0.00	1	0.00	0.00	635	0.00	0.00	0.00	1	0.00	0.00	36	0.00	0.00	0.01	1	0.00	0.00	3135	0.00	0.00	0.01	1	0.00	0.00
1401	0.03	0.00	0.05	34	0.10	0.01	1639	0.00	0.00	0.01	1	0.00	0.00	266	0.05	0.00	0.04	32	0.07	0.01	2995	0.00	0.00	0.01	1	0.00	0.00
1385	12.25	1.08	2.63	96	9.78	0.85	1642	0.00	0.00	0.01	1	0.00	0.00	147	0.00	0.00	0.00	1	0.00	0.00	2770	0.00	0.00	0.01	1	0.00	0.00
86	0.00	0.00	0.00	2	0.00	0.00	1715	0.00	0.00	0.00	1	0.00	0.00	35	0.08	0.01	0.03	76	0.06	0.01	2885	0.00	0.00	0.01	1	0.00	0.00
1003	0.00	0.00	0.00	1	0.00	0.00	1675	0.00	0.00	0.02	1	0.00	0.00	246	0.01	0.00	0.02	19	0.04	0.00	2877	0.00	0.00	0.01	1	0.00	0.00
1386	0.71	0.06	2.27	88	3.11	0.27	1476	0.00	0.00	0.01	1	0.00	0.00	271	0.00	0.00	0.00	1	0.00	0.00	2875	0.00	0.00	0.02	1	0.00	0.00
807	0.01	0.00	0.01	9	0.00	0.00	1643	0.00	0.00	0.00	1	0.00	0.00	7	0.01	0.00	0.01	9	0.02	0.00	2879	0.00	0.00	0.01	1	0.00	0.00
1301	0.00	0.00	0.01	3	0.00	0.00	1689	0.00	0.00	0.00	1	0.00	0.00	-1	0.00	0.00	0.01	6	0.02	0.00	1164	0.00	0.00	0.01	2	0.00	0.00
1018	0.00	0.00	0.01	7	0.00	0.00	2	0.00	0.00	0.01	3	0.00	0.00	301	0.00	0.00	0.00	1	0.00	0.00	1088	0.02	0.00	0.02	25	0.04	0.00
34	0.08	0.01	0.03	67	0.06	0.01	2355	0.00	0.00	0.00	1	0.00	0.00	300	0.00	0.00	0.01	3	0.00	0.00	1092	0.08	0.01	0.13	35	0.30	0.03
313	0.06	0.01	0.02	63	0.05	0.00	1088	0.02	0.00	0.06	24	0.13	0.01	244	0.01	0.00	0.07	9	0.23	0.02	1098	0.18	0.02	0.08	78	0.21	0.02
265	0.01	0.00	0.05	9	0.17	0.01	1092	0.07	0.01	0.12	33	0.28	0.02	298	0.00	0.00	0.00	1	0.00	0.00	2924	0.03	0.00	0.02	34	0.04	0.00
355	0.00	0.00	0.00	2	0.00	0.00	1098	0.20	0.02	0.08	86	0.21	0.02	242	0.01	0.00	0.01	13	0.02	0.00	1096	0.00	0.00	0.01	1	0.00	0.00
288	0.01	0.00	0.02	9	0.04	0.00	2044	0.00	0.00	0.01	2	0.00	0.00	358	0.00	0.00	0.00	2	0.00	0.00	1111	27.24	2.47	5.50	96	20.40	1.83
4	0.00	0.00	0.00	1	0.00	0.00	1111	27.02	2.40	5.38	96	21.38	1.87	66	0.00	0.00	0.01	4	0.00	0.00	1984	0.01	0.00	0.01	8	0.02	0.00
-1	0.01	0.00	0.01	8	0.02	0.00	1114	0.04	0.00	0.04	22	0.14	0.01	272	0.00	0.00	0.01	4	0.00	0.00	1116	0.88	0.08	0.21	96	0.66	0.06
30	0.00	0.00	0.00	1	0.00	0.00	1116	0.77	0.07	0.20	96	0.57	0.05	268	0.00	0.00	0.03	1	0.00	0.00	2399	0.00	0.00	0.01	5	0.00	0.00
6	0.00	0.00	0.01	3	0.00	0.00	1164	0.00	0.00	0.01	1	0.00	0.00	291	0.00	0.00	0.01	5	0.05	0.00	1972	0.00	0.00	0.01	3	0.00	0.00
241	0.01	0.00	0.04	15	0.09	0.01	1972	0.00	0.00	0.00	4	0.00	0.00	314	0.01	0.00	0.01	14	0.00	0.00	1187	0.00	0.00	0.01	7	0.00	0.00
299	0.00	0.00	0.00	1	0.00	0.00	1982	0.00	0.00	0.01	1	0.00	0.00	198	0.02	0.00	0.01	26	0.02	0.00	1114	0.04	0.00	0.05	23	0.15	0.01
297	0.00	0.00	0.01	1	0.00	0.00	1984	0.00	0.00	0.01	8	0.00	0.00	305	0.01	0.00	0.01	11	0.02	0.00	2	0.00	0.00	0.01	1	0.00	0.00
263	0.05	0.00	0.03	31	0.08	0.01	1187	0.01	0.00	0.01	14	0.02	0.00	413	0.00	0.00	0.00	1	0.00	0.00	2484	0.00	0.00	0.01	1	0.00	0.00
243	0.01	0.00	0.02	14	0.05	0.00	2399	0.00	0.00	0.01	6	0.00	0.00	337	0.08	0.01	0.04	45	0.10	0.01	2989	0.00	0.00	0.02	1	0.00	0.00
341	0.01	0.00	0.01	8	0.02	0.00	2356	0.00	0.00	0.01	1	0.00	0.00	344	0.01	0.00	0.01	15	0.03	0.00	2499	0.00	0.00	0.01	1	0.00	0.00
144	0.00	0.00	0.01	2	0.00	0.00	2924	0.03	0.00	0.02	38	0.04	0.00	316	0.09	0.01	0.03	73	0.06	0.01	60	0.00	0.00	0.01	1	0.00	0.00
269	0.00	0.00	0.00	2	0.00	0.00	1096	0.00	0.00	0.01	3	0.00	0.00	3637	0.00	0.00	0.00	1	0.00	0.00	153	0.01	0.00	0.01	10	0.00	0.00
239	0.01	0.00	0.01	10	0.00	0.00	190	0.00	0.00	0.00	1	0.00	0.00	1338	0.00	0.00	0.00	1	0.00	0.00	1327	0.00	0.00	0.02	1	0.00	0.00
65	0.00	0.00	0.00	3	0.00	0.00	2962	0.00	0.00	0.00	1	0.00	0.00	689	0.00	0.00	0.01	1	0.00	0.00	513	0.00	0.00	0.01	1	0.00	0.00
302	0.00	0.00	0.01	7	0.00	0.00	2989	0.00	0.00	0.00	1	0.00	0.00	1321	0.00	0.00	0.00	1	0.00	0.00	1329	0.00	0.00	0.01	1	0.00	0.00
311	0.00	0.00	0.01	7	0.00	0.00	60	0.00	0.00	0.00	1	0.00	0.00	437	0.00	0.00	0.00	1	0.00	0.00	1321	0.00	0.00	0.01	1	0.00	0.00
478	0.08	0.01	0.02	70	0.05	0.00	153	0.00	0.00	0.01	5	0.00	0.00	3701	0.00	0.00	0.03	2	0.20	0.02	689	0.00	0.00	0.02	1	0.00	0.00
195	0.01	0.00	0.01	24	0.01	0.00	3637	0.00	0.00	0.00	1	0.00	0.00	1320	0.00	0.00	0.00	1	0.00	0.00	3611	0.00	0.00	0.02	1	0.00	0.00
334	0.08	0.01	0.05	39	0.13	0.01	1336	0.00	0.00	0.00	1	0.00	0.00	3695	0.03	0.00	0.03	38	0.05	0.00	1949	0.08	0.01	0.04	55	0.09	0.01
190	0.00	0.00	0.00	1	0.00	0.00	689	0.00	0.00	0.01	1	0.00	0.00	3611	0.00	0.00	0.01	1	0.00	0.00	1356	0.00	0.00	0.01	1	0.00	0.00
2	0.00	0.00	0.00	1	0.00	0.00	1320	0.00	0.00	0.01	1	0.00	0.00	3610	0.00	0.00	0.00	1	0.00	0.00	957	0.00	0.00	0.01	8	0.00	0.00
2766	0.00	0.00	0.00	1	0.00	0.00	1327	0.00	0.00	0.01	1	0.00	0.00	1949	0.11	0.01	0.06	60	0.12	0.01	41	0.00	0.00	0.01	1	0.00	0.00
2989	0.00	0.00	0.01	1	0.00	0.00	641	0.00	0.00	0.00	1	0.00	0.00	348	0.00	0.00	0.01	1	0.00	0.00	75	0.00	0.00	0.01	3	0.00	0.00
742	0.00	0.00	0.00	1	0.00	0.00	1321	0.00	0.00	0.00	1	0.00	0.00	2487	15.04	1.34	3.11	96	11.77	1.03	56	0.00	0.00	0.01	3	0.00	0.00
1802	0.00	0.00	0.02	1	0.00	0.00	3695	0.00	0.00	0.00	1	0.00	0.00	1401	0.02	0.00	0.03	27	0.06	0.00	387	0.00	0.00	0.01	5	0.02	0.00
2053	0.00	0.00	0.00	1	0.00	0.00	3610	0.00	0.00	0.01	1	0.00	0.00	789	0.00	0.00	0.01	4	0.00	0.00	397	0.00	0.00	0.01	8	0.00	0.00
2052	0.00	0.00	0.01	1	0.00	0.00	3611	0.00	0.00	0.01	1	0.00	0.00	1385	12.55	1.12	2.67	96	9.71	0.85	44	0.01	0.00	0.01	10	0.00	0.00
2145	0.00	0.00	0.00	1	0.00	0.00	1949	0.09	0.01	0.04	50	0.10	0.01	979	0.00	0.00	0.01	1	0.00	0.00	399	0.00	0.00	0.01	5	0.00	0.00
-1	0.00	0.00	0.01	1	0.00	0.00	1914	0.00	0.00	0.01	3	0.00	0.00	86	0.01	0.00	0.01	13	0.03	0.00	543	0.00	0.00	0.01	3	0.00	0.00
2098	0.00	0.00	0.02	1	0.00	0.00	1916	0.00	0.00	0.01	1	0.00	0.00	1284	0.00	0.00	0.00	1	0.00	0.00	261	0.00	0.00	0.00	2	0.00	0.00
2106	0.00	0.00	0.00	1	0.00	0.00	1906	0.00	0.00	0.01	2	0.00	0.00	1406	0.00	0.00	0.00	1	0.00	0.00	68	0.00	0.00	0.01	1	0.00	0.00
3637	0.00	0.00	0.01	1	0.00	0.00	1909	0.00	0.00	0.01	1	0.00	0.00	1386	0.70	0.06	2.14	88	2.95	0.26	43	0.00	0.00	0.01	3	0.00	0.00
1016	0.00	0.00	0.00	1	0.00	0.00	2055	0.00	0.00	0.01	2	0.00	0.00	807	0.01	0.00	0.01	15	0.00	0.00	1036	0.09	0.01	0.03	78	0.06	0.01
1336	0.00	0.00	0.00	1	0.00	0.00	1921	0.00	0.00	0.01	3	0.00	0.00	1301	0.00	0.00	0.01	4	0.00	0.00	46	0.00	0.00	0.01	8	0.00	0.00
689	0.00	0.00	0.02	1	0.00	0.00	2079	0.00	0.00	0.00	1	0.00	0.00	1018	0.01	0.00	0.01	9	0.00	0.00	-1	0.00	0.00	0.00	1	0.00	0.00
1320	0.00	0.00	0.01	1	0.00	0.00	2089	0.06	0.01	0.03	56	0.06	0.00	153	0.00	0.00	0.01	6	0.00	0.00	37	0.00	0.00	0.01	1	0.00	0.00
1327	0.00	0.00	0.00	1	0.00	0.00	1810	0.00	0.00	0.01	3	0.00	0.00	97	0.00	0.00	0.00	2	0.00	0.00	391	0.00	0.00	0.01	6	0.02	0.00
3701	0.00	0.00	0.01	2	0.04	0.00	2054	0.00	0.00	0.01	7	0.00	0.00	61	0.00	0.00	0.00	1	0.00	0.00	3584	0.01	0.00	0.01	10	0.00	0.00
646	0.00	0.00	0.00	1	0.00	0.00	1908	0.00	0.00	0.00	1	0.00	0.00	290	0.00	0.00	0.00	3	0.00	0.00	3625	0.01	0.00	0.05	2	0.31	0.03
1321	0.00	0.00	0.00	1	0.00	0.00	1948	0.03	0.00	0.02	46	0.03	0.00	636	0.03	0.00	0.02	36	0.04	0.00	3540	0.00	0.00	0.01	3	0.00	0.00
3695	0.02	0.00	0.03	26	0.05	0.00	2045	0.00	0.00	0.01	7	0.02	0.00	51	0.00	0.00	0.01	1	0.00	0.00	3535	0.00	0.00	0.01	3	0.00	0.00
3611	0.00	0.00	0.02	1	0.00	0.00	2090	0.01	0.00	0.08	3	0.49	0.04	72	0.00	0.00	0.00	6	0.00	0.00	3583	0.01	0.00	0.01	12	0.03	0.00
3610	0.00	0.00	0.00	1	0.00	0.00	2049	0.01	0.00	0.01	14	0.00	0.00	41	0.00	0.00	0.01	5	0.00	0.00	3568	0.04	0.00	0.02	51	0.03	0.00
1949	0.10	0.01	0.05	53	0.12	0.01	2073	0.03	0.00	0.01	40	0.02	0.00	39	0.00	0.00	0.01	6	0.02	0.00	3482	0.01	0.00	0.01	9	0.00	0.00
71	0.00	0.00	0.01	4	0.00	0.00	1993	0.00	0.00	0.00	1	0.00	0.00	69	0.01	0.00	0.01	11	0.03	0.00	3477	0.01	0.00	0.01	9	0.02	0.00
31	0.00	0.00	0.00	2	0.00	0.00	2004	0.00	0.00	0.01	2	0.00	0.00	63	0.00	0.00	0.00	3	0.00	0.00	3231	0.00	0.00	0.00	1	0.00	0.00
68	0.01	0.00	0.01	10	0.00	0.00	1887	0.00	0.00	0.00	1	0.00	0.00	38	0.00	0.00	0.01	2	0.00	0.00	3437	0.00	0.00	0.00	1	0.00	0.00
62	0.00	0.00	0.00	2	0.00	0.00	2047	0.00	0.00	0.01	5	0.00	0.00	70	0.00	0.00	0.01	1	0.00	0.00	3227	0.00	0.00	0.01	4	0.00	0.00
60	0.00	0.00	0.01	3	0.00	0.00	260	0.00	0.00	0.01	3	0.00	0.00	259	0.00	0.00	0.01	3	0.00	0.00	3435	0.00	0.00	0.00	2	0.00	0.00
35	0.00	0.00	0.00	2	0.00	0.00	55	0.00	0.00	0.01	1	0.00	0.00	61	0.00	0.00	0.01	2	0.00	0.00	3448	0.00	0.00	0.00	2	0.00	0.00
649	0.00	0.00	0.00	1	0.00	0.00	76	0.00	0.00	0.01	5	0.00	0.00	36	0.00	0.00	0.01	3	0.00	0.00	3543	0.00	0.00	0.01	2	0.00	0.00
50	0.00	0.00	0.00	2	0.00	0.00	95	0.00	0.00	0.00	1	0.00	0.00	2	0.00	0.00	0.01	1	0.00	0.00	3480	0.04	0.00	0.02	42	0.05	0.00
69	0.00	0.00	0.01	1	0.00	0.00	43	0.00	0.00	0.01	8	0.00	0.00	190	0.00	0.00	0.01	1	0.00	0.00	3450	0.00	0.00	0.01	7	0.00	0.00
40	0.00	0.00	0.01	8	0.00	0.00	65	0.00	0.00	0.01	3	0.00	0.00	2499	0.00	0.00	0.01	1	0.00	0.00	3443	0.00	0.00	0.01	4	0.00	0.00
-1	0.00	0.00	0.00	2	0.00	0.00	74	0.00	0.00	0.01	1	0.00	0.00	121	0.00	0.00	0.00	1	0.00	0.00	3438	0.00	0.00	0.01	5	0.00	0.00
257	0.00	0.00	0.01	7	0.02	0.00	36	0.00	0.00	0.01	1	0.00	0.00	1982	0.00	0.00	0.00	1	0.00	0.00	3605	0.04	0.00	0.02	43	0.04	0.00
38	0.00	0.00	0.00	1	0.00	0.00	42	0.00	0.00	0.00	1	0.00	0.00	2041	0.00	0.00	0.01	1	0.00	0.00	3624	0.08	0.01	0.04	69	0.08	0.01
153	0.01	0.00	0.01	9	0.02	0.00	45	0.00	0.00	0.01	7	0.00	0.00	1990	0.00	0.00	0.01	1	0.00	0.00	3587	0.00	0.00	0.01	5	0.00	0.00
60	0.00	0.00	0.00	1	0.00	0.00	73	0.01	0.00	0.01	9	0.00	0.00	1986	0.00	0.00	0.00	1	0.00	0.00	419	0.00	0.00	0.01	5	0.00	0.00
304	0.00	0.00	0.00	1	0.00	0.00	234	0.01	0.00	0.01	10	0.02	0.00	748	0.00	0.00	0.00	1	0.00	0.00	11	0.00	0.00	0.00	2	0.00	0.00
290	0.00	0.00	0.00	1	0.00	0.00	264	0.01	0.00	0.08	4	0.39	0.04	2059	0.00	0.00	0.00	1	0.00	0.00	422	0.01	0.00	0.01	14	0.02	0.00
636	0.04	0.00	0.03	48	0.05	0.00	37	0.09	0.01	0.03	82	0.06	0.01	2050	0.00	0.00	0.00	1	0.00	0.00	427	0.00	0.00	0.00	1	0.00	0.00
							268	0.00	0.00	0.01	1	0.00	0.00	1822	0.00	0.00	0.00	1	0.00	0.00	-1	0.00	0.00	0.01	2	0.00	0.00
							353	0.00	0.00	0.01	1	0.00	0.00	1803	0.00	0.00	0.00	1	0.00	0.00	495	0.00	0.00	0.01	4	0.00	0.00
							7	0.00	0.00	0.01	1	0.00	0.00								109	0.07	0.01	0.02	66	0.05	0.00
							332	0.08	0.01	0.04	40	0.12	0.01								653	0.00	0.00	0.01	4	0.00	0.00
							301	0.01	0.00	0.01	10	0.02	0.00								651	0.00	0.00	0.00	1	0.00	0.00
							148	0.00	0.00	0.01	1	0.00	0.00								509	0.01	0.00	0.03	4	0.14	0.01
							297	0.00	0.00	0.01	2	0.00	0.00								637	0.00	0.00	0.02	3	0.10	0.01
							298	0.00	0.00	0.00	2	0.00	0.00								75	0.01	0.00	0.01	11	0.00	0.00
							262	0.05	0.00	0.05	31	0.11	0.01								530	0.00	0.00	0.01	3	0.00	0.00
							192	0.02	0.00	0.01	34	0.02	0.00								749	0.06	0.01	0.02	64	0.05	0.00
							339	0.00	0.00	0.01	2	0.00	0.00								539	0.00	0.00	0.00	2	0.00	0.00
							310	0.00	0.00	0.01	3	0.03	0.00								541	0.00	0.00	0.00	2	0.00	0.00
							-1	0.00	0.00	0.01	4	0.00	0.00								117	0.00	0.00	0.00	4	0.00	0.00
							236	0.01	0.00	0.01	13	0.00	0.00								544	0.00	0.00	0.00	1	0.00	0.00
							69	0.00	0.00	0.01	4	0.00	0.00								270	0.00	0.00	0.01	1	0.00	0.00
							9	0.00	0.00	0.01	4	0.00	0.00								216	0.00	0.00	0.01	2	0.00	0.00
							287	0.01	0.00	0.01	15	0.00	0.00								553	0.00	0.00	0.01	1	0.00	0.00
							240	0.02	0.00	0.02	25	0.04	0.00								597	0.00	0.00	0.01	2	0.00	0.00
							312	0.08	0.01	0.03	65	0.07	0.01								599	0.00	0.00	0.01	3	0.00	0.00
							476	0.06	0.01	0.02	59	0.05	0.00								305	0.01	0.00	0.01	23	0.02	0.00
																					669	0.06	0.01	0.02	63	0.05	0.00
																					438	0.01	0.00	0.02	9	0.04	0.00
																					721	0.01	0.00	0.01	12	0.02	0.00
																					582	0.00	0.00	0.00	2	0.00	0.00
																					430	0.01	0.00	0.04	6	0.14	0.01
																					740	0.00	0.00	0.00	3	0.00	0.00
																					575	0.00	0.00	0.00	3	0.00	0.00

▶quants.c: 1011 - 69.92 %

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_10	Run icx_3
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/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/176-976-6240/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/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1066-1077
			771	69.92	6.34	8.31	96	21.50	1.96

▶sgemm.cpp: 138 - 1.64 %

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_10							Run icx_3
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/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/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044
411	0.57	0.05	0.08	96	0.20	0.02	409	0.56	0.05	0.08	96	0.17	0.02	414	0.51	0.05	0.08	96	0.18	0.02

▶ggml-cpu.c: 533 - 1.27 %

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_10							Run icx_3
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1136-1147 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1171 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1177-1177 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1198 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1207-1212 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1221-1234 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1242-1260 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1267-1276 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1297 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1304-1328 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1339-1339 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1345-1345 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1352-1358 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1365-1379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1397							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-534 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1147 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1171 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1177-1177 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1198 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1207-1234 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1242-1260 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1267-1276 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1295 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1304-1328 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1339-1339 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1345-1345 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1352-1358 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1365-1379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1397							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1136-1147 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1171 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1184-1187 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1198 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1207-1212 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1221-1234 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1242-1260 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1267-1276 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1297 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1304-1328 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1339-1339 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1345-1345 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1352-1358 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1365-1379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1397							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-534 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1147 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1171 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1177-1177 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1198 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1207-1234 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1242-1260 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1267-1276 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1295 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1304-1328 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1339-1339 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1345-1345 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1352-1358 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1365-1379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1397
26	0.29	0.03	0.06	96	0.14	0.01	29	0.29	0.03	0.06	96	0.14	0.01	27	0.24	0.02	0.06	94	0.12	0.01	99	0.44	0.04	0.08	95	0.19	0.02

▶ops.cpp: 8690 - 0.24 %

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_10	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/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8690-8706 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 392-393 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 508-509 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 693-694 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 756-757 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/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/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-389 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404
			707	0.24	0.02	0.09	46	0.35	0.03

▶vec.cpp: 331 - 0.16 %

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_10	Run icx_3
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-6240/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/176-976-6240/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 331-337
			505	0.16	0.01	0.07	37	0.20	0.02

▶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_10	icx_3	orig_default	icx_default	aocc_10	icx_3	orig_default	icx_default	aocc_10	icx_3	orig_default	icx_default	aocc_10	icx_3	orig_default	icx_default	aocc_10	icx_3	orig_default	icx_default	aocc_10	icx_3
ggml_vec_dot_q8_0_q8_0	libggml-cpu.so	70.45	70.20	70.23	0.06	6.23	6.22	6.25	0.01	8.11	8.13	8.18	0.02	96	96	96	64	21.96	22.00	21.71	0.05	1.95	1.96	1.95	0.00
ggml_vec_dot_q8_0_q8_0	libggml-cpu.so	NA	NA	NA	69.92	NA	NA	NA	6.34	NA	NA	NA	8.31	NA	NA	NA	96	NA	NA	NA	21.50	NA	NA	NA	1.96
kmp_flag_64<false, true>::wait(kmp_info, int, void)	libiomp5.so	NA	27.02	NA	27.24	NA	2.40	NA	2.47	NA	5.38	NA	5.50	NA	96	NA	96	NA	21.38	NA	20.40	NA	1.87	NA	1.83
__kmp_hardware_timestamp	libomp.so	15.04	NA	15.04	NA	1.33	NA	1.34	NA	3.05	NA	3.11	NA	96	NA	96	NA	11.92	NA	11.77	NA	1.04	NA	1.03	NA
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libomp.so	12.25	NA	12.55	NA	1.08	NA	1.12	NA	2.63	NA	2.67	NA	96	NA	96	NA	9.78	NA	9.71	NA	0.85	NA	0.85	NA
kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check()	libiomp5.so	NA	0.77	NA	0.88	NA	0.07	NA	0.08	NA	0.20	NA	0.21	NA	96	NA	96	NA	0.57	NA	0.66	NA	0.05	NA	0.06
void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<4>(long, long, long, long)	libggml-cpu.so	0.57	0.56	0.51	NA	0.05	0.05	0.05	NA	0.08	0.08	0.08	NA	96	96	96	NA	0.20	0.17	0.18	NA	0.02	0.02	0.02	NA
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libomp.so	0.71	NA	0.70	NA	0.06	NA	0.06	NA	2.27	NA	2.14	NA	88	NA	88	NA	3.11	NA	2.95	NA	0.27	NA	0.26	NA
ggml_compute_forward_mul_mat	libggml-cpu.so	0.29	0.29	0.24	NA	0.03	0.03	0.02	NA	0.06	0.06	0.06	NA	96	96	94	NA	0.14	0.14	0.12	NA	0.01	0.01	0.01	NA
ggml_compute_forward_mul_mat	libggml-cpu.so	NA	NA	NA	0.44	NA	NA	NA	0.04	NA	NA	NA	0.08	NA	NA	NA	95	NA	NA	NA	0.19	NA	NA	NA	0.02
__GI___sched_yield	libc.so.6	0.10	0.09	0.11	0.08	0.01	0.01	0.01	0.01	0.05	0.04	0.06	0.04	53	50	60	55	0.12	0.10	0.12	0.09	0.01	0.01	0.01	0.01
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libiomp5.so	NA	0.20	NA	0.18	NA	0.02	NA	0.02	NA	0.08	NA	0.08	NA	86	NA	78	NA	0.21	NA	0.21	NA	0.02	NA	0.02
ggml_graph_compute_thread	libggml-cpu.so	0.08	0.09	0.08	NA	0.01	0.01	0.01	NA	0.03	0.03	0.03	NA	67	82	76	NA	0.06	0.06	0.06	NA	0.01	0.01	0.01	NA
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	NA	NA	NA	0.24	NA	NA	NA	0.02	NA	NA	NA	0.09	NA	NA	NA	46	NA	NA	NA	0.35	NA	NA	NA	0.03
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	0.08	0.08	0.08	0.00	0.01	0.01	0.01	0.00	0.05	0.04	0.04	0.00	39	40	45	3	0.13	0.12	0.10	0.00	0.01	0.01	0.01	0.00
ggml_compute_forward_rope_f32(ggml_compute_params const, ggml_tensor, bool)	libggml-cpu.so	0.06	0.08	0.09	NA	0.01	0.01	0.01	NA	0.02	0.03	0.03	NA	63	65	73	NA	0.05	0.07	0.06	NA	0.00	0.01	0.01	NA
quantize_row_q8_0	libggml-cpu.so	0.08	0.06	0.05	NA	0.01	0.01	0.00	NA	0.02	0.02	0.02	NA	70	59	56	NA	0.05	0.05	0.05	NA	0.00	0.00	0.00	NA
ggml_vec_dot_f16	libggml-cpu.so	NA	NA	NA	0.16	NA	NA	NA	0.01	NA	NA	NA	0.07	NA	NA	NA	37	NA	NA	NA	0.20	NA	NA	NA	0.02
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libiomp5.so	NA	0.07	NA	0.08	NA	0.01	NA	0.01	NA	0.12	NA	0.13	NA	33	NA	35	NA	0.28	NA	0.30	NA	0.02	NA	0.03
ggml_vec_dot_f16	libggml-cpu.so	0.05	0.05	0.05	0.00	0.00	0.00	0.00	0.00	0.03	0.05	0.04	0.01	31	31	32	4	0.08	0.11	0.07	0.00	0.01	0.01	0.01	0.00
__intel_avx_rep_memcpy	binary	NA	0.06	NA	0.08	NA	0.01	NA	0.01	NA	0.03	NA	0.04	NA	56	NA	69	NA	0.06	NA	0.08	NA	0.00	NA	0.01
quantize_row_q8_0_ref	libggml-base.so	NA	NA	NA	0.09	NA	NA	NA	0.01	NA	NA	NA	0.03	NA	NA	NA	78	NA	NA	NA	0.06	NA	NA	NA	0.01
kmp_flag_native<unsigned long long, (flag_type)1, true>::done_check()	libiomp5.so	NA	0.04	NA	0.04	NA	0.00	NA	0.00	NA	0.04	NA	0.05	NA	22	NA	23	NA	0.14	NA	0.15	NA	0.01	NA	0.01
f64xsubf128	libm.so.6	0.04	NA	0.03	NA	0.00	NA	0.00	NA	0.03	NA	0.02	NA	48	NA	36	NA	0.05	NA	0.04	NA	0.00	NA	0.00	NA
__libm_sse2_sincosf_l9	binary	NA	0.03	NA	0.04	NA	0.00	NA	0.00	NA	0.02	NA	0.02	NA	46	NA	42	NA	0.03	NA	0.05	NA	0.00	NA	0.00
ggml::cpu::repack::extra_buffer_type::get_tensor_traits(ggml_tensor const*)	libggml-cpu.so	0.01	0.02	0.02	0.01	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	24	34	26	23	0.01	0.02	0.02	0.02	0.00	0.00	0.00	0.00
ggml_graph_compute_thread	libggml-cpu.so	NA	NA	NA	0.07	NA	NA	NA	0.01	NA	NA	NA	0.02	NA	NA	NA	66	NA	NA	NA	0.05	NA	NA	NA	0.00
_intel_fast_memcpy	binary	NA	0.03	NA	0.04	NA	0.00	NA	0.00	NA	0.01	NA	0.02	NA	40	NA	43	NA	0.02	NA	0.04	NA	0.00	NA	0.00
__kmp_yield	libiomp5.so	NA	0.03	NA	0.03	NA	0.00	NA	0.00	NA	0.02	NA	0.02	NA	38	NA	34	NA	0.04	NA	0.04	NA	0.00	NA	0.00
ggml_compute_forward_rope_f32	libggml-cpu.so	NA	NA	NA	0.06	NA	NA	NA	0.01	NA	NA	NA	0.02	NA	NA	NA	63	NA	NA	NA	0.05	NA	NA	NA	0.00
__memcpy_avx512_unaligned_erms	libc.so.6	0.02	0.00	0.03	NA	0.00	0.00	0.00	NA	0.03	0.00	0.03	NA	26	1	38	NA	0.05	0.00	0.05	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	0.03	NA	0.02	NA	0.00	NA	0.00	NA	0.05	NA	0.03	NA	34	NA	27	NA	0.10	NA	0.06	NA	0.01	NA	0.00	NA
ggml_compute_forward_mul	libggml-cpu.so	0.01	0.02	0.01	0.00	0.00	0.00	0.00	0.00	0.02	0.02	0.02	0.00	14	25	19	1	0.05	0.04	0.04	0.00	0.00	0.00	0.00	0.00
__libm_roundf_y8	binary	NA	NA	NA	0.04	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	51	NA	NA	NA	0.03	NA	NA	NA	0.00
__kmp_barrier	libiomp5.so	NA	0.02	NA	0.02	NA	0.00	NA	0.00	NA	0.06	NA	0.02	NA	24	NA	25	NA	0.13	NA	0.04	NA	0.01	NA	0.00
ggml_compute_forward_add_non_quantized	libggml-cpu.so	0.01	0.01	0.01	NA	0.00	0.00	0.00	NA	0.04	0.01	0.07	NA	15	13	9	NA	0.09	0.00	0.23	NA	0.01	0.00	0.02	NA
ggml_vec_swiglu_f32	libggml-cpu.so	0.01	0.01	0.00	NA	0.00	0.00	0.00	NA	0.05	0.08	0.03	NA	9	4	1	NA	0.17	0.39	0.00	NA	0.01	0.04	0.00	NA
ggml_cpu_extra_compute_forward	libggml-cpu.so	0.01	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	10	10	13	5	0.00	0.02	0.02	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_rms_norm	libggml-cpu.so	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.00	0.02	0.01	0.01	0.01	9	15	5	3	0.04	0.00	0.05	0.00	0.00	0.00	0.00	0.00
ggml_is_empty	libggml-base.so	0.01	0.01	0.01	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	10	9	11	NA	0.00	0.00	0.03	NA	0.00	0.00	0.00	NA
ggml_compute_forward_set_rows	libggml-cpu.so	0.00	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.00	7	10	11	1	0.00	0.02	0.02	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_glu	libggml-cpu.so	0.01	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.00	8	2	15	2	0.02	0.00	0.03	0.00	0.00	0.00	0.00	0.00
__tls_get_addr	ld-linux-x86-64.so.2	0.01	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	9	5	6	10	0.02	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_row_size	libggml-base.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	8	7	5	8	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__intel_avx_rep_memset	binary	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.08	NA	0.05	NA	3	NA	2	NA	0.49	NA	0.31	NA	0.04	NA	0.03
ggml_compute_forward_rope	libggml-cpu.so	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	7	3	14	1	0.00	0.03	0.00	0.00	0.00	0.00	0.00	0.00
ggml_type_size	libggml-base.so	0.00	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	1	8	6	10	0.00	0.00	0.02	0.00	0.00	0.00	0.00	0.00
__kmpc_barrier	libomp.so	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	9	NA	15	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__libm_powf_l9	binary	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	14	NA	10	NA	0.00	NA	0.00	NA	0.00	NA	0.00
unknown_function	libggml-cpu.so	0.01	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	8	4	6	2	0.02	0.00	0.02	0.00	0.00	0.00	0.00	0.00
__kmpc_barrier	libiomp5.so	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	14	NA	7	NA	0.02	NA	0.00	NA	0.00	NA	0.00
__libm_expf_l9	binary	NA	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	7	NA	12	NA	0.02	NA	0.03	NA	0.00	NA	0.00
sched_yield@plt	libomp.so	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	2	NA	13	NA	0.00	NA	0.03	NA	0.00	NA	0.00	NA
ggml_cpu_fp32_to_fp16	libggml-cpu.so	0.00	0.00	0.01	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	3	4	9	NA	0.00	0.00	0.02	NA	0.00	0.00	0.00	NA
__kmp_resume_if_soft_paused	libiomp5.so	NA	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	8	NA	8	NA	0.00	NA	0.02	NA	0.00	NA	0.00
__kmp_get_global_thread_id_reg	libomp.so	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	7	NA	9	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
ggml_rope_yarn_corr_dims	libggml-base.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.00	7	3	3	2	0.02	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__libm_logf_l9	binary	NA	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	7	NA	9	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_can_repeat	libggml-base.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.00	NA	4	5	6	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_backend_cpu_get_extra_buffer_types()	libggml-cpu.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.00	3	4	4	4	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__libm_log2_l9	binary	NA	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	5	NA	9	NA	0.00	NA	0.02	NA	0.00	NA	0.00
ggml_cpu_extra_compute_forward	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	14	NA	NA	NA	0.02	NA	NA	NA	0.00
ggml_compute_forward_glu	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	0.02	NA	NA	NA	0.00
ggml_compute_forward_add_non_quantized	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.04	NA	NA	NA	6	NA	NA	NA	0.14	NA	NA	NA	0.01
_IO_fread	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	0.02	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__kmp_task_team_sync	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	6	NA	5	NA	0.00	NA	0.00	NA	0.00	NA	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	11	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_compute_forward_mul	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	9	NA	NA	NA	0.04	NA	NA	NA	0.00
__memset_avx512_unaligned_erms	libc.so.6	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.03	NA	2	NA	2	NA	0.04	NA	0.20	NA	0.00	NA	0.02	NA
__memcmp_evex_movbe	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.02	0.01	0.01	0.02	1	1	1	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	0.01	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_vec_swiglu_f32	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.03	NA	NA	NA	4	NA	NA	NA	0.14	NA	NA	NA	0.01
ggml_is_contiguous	libggml-base.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	3	3	2	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
llamafile_sgemm	libggml-cpu.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	2	1	2	3	0.00	0.00	0.00	0.00	0.00	0.00	0.00	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	8	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	8	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_task_team_sync	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	3	NA	4	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
ggml_compute_forward_add	libggml-cpu.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	2	1	4	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_get_glu_op	libggml-base.so	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	1	1	3	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__kmp_get_global_thread_id_reg	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	4	NA	3	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__libm_exp2f_z0	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	2	NA	5	NA	0.00	NA	0.00	NA	0.00	NA	0.00
roundf	binary	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	7	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_is_contiguous_1	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	6	NA	NA	NA	0.02	NA	NA	NA	0.00
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	0.02	0.01	0.00	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_nrows	libggml-base.so	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	2	NA	3	1	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
ggml_is_contiguous_1	libggml-base.so	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	2	NA	3	1	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
ggml_backend_cpu_repack_buffer_type()	libggml-cpu.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.00	0.01	2	1	1	2	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_reshape	libggml-cpu.so	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.01	0.00	1	NA	3	2	0.00	NA	0.00	0.00	0.00	NA	0.00	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	NA	0.00	0.00	0.00	NA	0.00	0.01	0.00	NA	0.02	1	1	NA	1	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
_int_free	libc.so.6	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.02	1	1	NA	1	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
ggml_are_same_shape	libggml-base.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	1	1	1	3	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_blck_size	libggml-base.so	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	1	2	3	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00
ggml_is_contiguous	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	5	NA	NA	NA	0.02	NA	NA	NA	0.00
ggml_compute_forward_rms_norm	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	3	NA	NA	NA	0.10	NA	NA	NA	0.01
unlink_chunk.constprop.0	libc.so.6	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.00	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_compute_forward_permute	libggml-cpu.so	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	1	2	NA	2	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
powf	binary	NA	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
malloc_consolidate	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	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__svml_logf4_l9	binary	NA	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
logf	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	4	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_can_repeat	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	5	NA	NA	NA	0.00	NA	NA	NA	0.00
floorf	binary	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	5	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	0.00	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
__memchr_evex	libc.so.6	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.00	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
std::_Hash_bytes(void const*, unsigned long, unsigned long)	libstdc++.so.6.0.29	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
__log2_finite	libm.so.6	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
__kmpc_global_thread_num	libomp.so	NA	NA	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
ggml_get_type_traits	libggml-base.so	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.01	2	1	NA	1	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
__svml_logf4	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	3	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__kmp_join_barrier(int)	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	3	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
.plt.sec@start	libstdc++.so.6.0.29	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	1	NA	1	1	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
do_lookup_x	ld-linux-x86-64.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
ggml_get_type_traits_cpu	libggml-cpu.so	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00	0.01	NA	0.00	1	1	NA	2	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
__libm_floorf_y8	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	2	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_compute_forward_set_rows	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	4	NA	NA	NA	0.00	NA	NA	NA	0.00
.plt.sec@start	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
log2	binary	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
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	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
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	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
ggml_compute_forward_view	libggml-cpu.so	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.00	NA	NA	2	1	NA	NA	0.00	0.00	NA	NA	0.00	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	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
unknown_function	libggml-base.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
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	NA	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
expf	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__kmpc_global_thread_num	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_compute_forward_add	libggml-cpu.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
__libm_floor_y8	binary	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
__libm_expf_e7	binary	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
_ZN11llama_vocab4implD2Ev.A	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
ggml_rope_yarn_corr_dims	libggml-base.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
unknown_function	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::_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
__GI___libc_malloc	libc.so.6	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::_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	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
ceilf	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_invoke_task_func	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	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
unicode_utf8_to_byte(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	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
gguf_kv_to_str[abi:cxx11](gguf_context const*, int)	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
_dl_fixup	ld-linux-x86-64.so.2	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
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >* std::__uninitialized_copy<false>::__uninit_copy<__gnu_cxx::__normal_iterator<std::__cxx11::basic_string<char, std::char_traits<char>, st...	binary	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
_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	0.01	NA	NA	NA	1	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
_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	0.01	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	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_compute_forward_dup	libggml-cpu.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
__vfscanf_internal	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
gguf_get_arr_str	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
ggml_graph_plan	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
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	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
strcmp	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
__GI___nptl_stack_list_add	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
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
__kmp_init_implicit_task	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_resume_if_soft_paused	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
std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long)	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
_intel_fast_memset	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
__kmp_finish_implicit_task	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
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::find(char const*, unsigned long, unsigned long) const	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
__libm_ceilf_y8	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
exp2f	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
ggml_dup_tensor	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
__kmp_enter_single	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
__vfprintf_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
unicode_cpt_to_utf8[abi:cxx11](unsigned 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
__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_launch_thread	libomp.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
llama_batch_allocr::clear()	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
ggml_compute_forward_dup	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
__kmp_finish_implicit_task	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
ggml_compute_forward_cpy	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
(anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::mnpack(long, long, long, long)	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
__GI_getenv	libc.so.6	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
_dl_lookup_symbol_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
__GI___libc_free	libc.so.6	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::__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>, std::alloca...	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
ggml_graph_compute.omp_outlined	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
llama_vocab::impl::token_to_piece(int, char*, int, int, bool) const	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
__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
ggml_compute_forward_get_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
_int_malloc	libc.so.6	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
__GI_____strtol_l_internal	libc.so.6	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
gguf_read_emplace_helper<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >	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
_ZN13llama_context6decodeERK11llama_batch.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
_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
std::ostream::sentry::sentry(std::ostream&)	libstdc++.so.6.0.29	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
floor	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
unicode_cpt_from_utf8	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_backend_cpu_repack_buffer_type	libggml-cpu.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

	orig_default	icx_default	aocc_10	icx_3
Uncheck all modules
libggml-cpu.so	71.73 %	71.51 %	71.44 %	71.03 %
libiomp5.so
libomp.so	28.04 %	0.00 %	28.33 %
libc.so.6	0.13 %	0.10 %	0.15 %	0.09 %
binary	0.00 %	0.16 %	0.00 %	0.24 %
libggml-base.so	0.03 %	0.02 %	0.03 %	0.13 %
libm.so.6	0.04 %	0.00 %	0.03 %
libllama.so	0.01 %	0.01 %	0.01 %	0.01 %
ld-linux-x86-64.so.2	0.01 %	0.00 %	0.01 %	0.01 %
libstdc++.so.6.0.29	0.00 %	0.00 %	0.00 %	0.00 %

Report Configuration

Functions

▶quants.c: 44 - 210.88 %

▶<unknown>: 0 - 115.89 %

▶quants.c: 1011 - 69.92 %

▶sgemm.cpp: 138 - 1.64 %

▶ggml-cpu.c: 533 - 1.27 %

▶ops.cpp: 8690 - 0.24 %

▶vec.cpp: 331 - 0.16 %

▶Old Layout

▶Filters

Functions