OV - Compare Functions

Functions

▶sgemm.cpp: 138 - 196.37 %

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_3							Run icx_5
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044
411	65.38	6.14	8.42	96	21.69	2.05	409	65.32	6.15	8.36	96	21.81	2.06	412	65.66	6.14	8.36	96	21.75	2.04

▶<unknown>: 0 - 120.44 %

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_3							Run icx_5

2486	0.00	0.00	0.01	3	0.00	0.00	1642	0.00	0.00	0.01	1	0.00	0.00	1018	0.00	0.00	0.01	4	0.00	0.00	3135	0.00	0.00	0.02	1	0.00	0.00
1401	0.02	0.00	0.03	28	0.04	0.00	1715	0.00	0.00	0.01	1	0.00	0.00	1401	0.02	0.00	0.02	26	0.04	0.00	2770	0.00	0.00	0.00	1	0.00	0.00
789	0.00	0.00	0.00	1	0.00	0.00	1675	0.00	0.00	0.02	1	0.00	0.00	1405	0.00	0.00	0.01	1	0.00	0.00	2885	0.00	0.00	0.02	1	0.00	0.00
1297	0.00	0.00	0.01	1	0.00	0.00	631	0.00	0.00	0.00	1	0.00	0.00	1385	14.19	1.33	3.91	96	9.64	0.89	2822	0.00	0.00	0.00	1	0.00	0.00
86	0.00	0.00	0.01	2	0.00	0.00	1643	0.00	0.00	0.00	1	0.00	0.00	1003	0.00	0.00	0.00	2	0.00	0.00	2875	0.00	0.00	0.01	1	0.00	0.00
1385	14.38	1.35	3.74	96	9.66	0.89	1476	0.00	0.00	0.03	1	0.00	0.00	807	0.01	0.00	0.01	14	0.01	0.00	2877	0.00	0.00	0.00	1	0.00	0.00
941	0.00	0.00	0.00	2	0.00	0.00	1164	0.00	0.00	0.00	1	0.00	0.00	1301	0.00	0.00	0.01	4	0.00	0.00	1164	0.00	0.00	0.00	3	0.00	0.00
1003	0.00	0.00	0.01	2	0.00	0.00	2	0.00	0.00	0.00	1	0.00	0.00	2486	0.00	0.00	0.00	2	0.00	0.00	1420	0.00	0.00	0.00	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	786	0.00	0.00	0.00	3	0.00	0.00	1096	0.00	0.00	0.01	1	0.00	0.00
1386	0.81	0.08	2.31	91	2.94	0.27	1088	0.03	0.00	0.05	31	0.09	0.01	789	0.00	0.00	0.00	2	0.00	0.00	2029	0.00	0.00	0.01	2	0.00	0.00
1018	0.00	0.00	0.01	4	0.00	0.00	1092	0.07	0.01	0.09	34	0.24	0.02	1039	0.00	0.00	0.00	2	0.00	0.00	1088	0.01	0.00	0.02	20	0.04	0.00
807	0.01	0.00	0.01	11	0.02	0.00	1098	0.21	0.02	0.08	88	0.19	0.02	941	0.00	0.00	0.00	1	0.00	0.00	1092	0.06	0.01	0.11	35	0.21	0.02
1301	0.00	0.00	0.01	6	0.00	0.00	2924	0.03	0.00	0.02	37	0.03	0.00	86	0.01	0.00	0.01	13	0.02	0.00	1098	0.15	0.02	0.08	76	0.22	0.02
2487	17.66	1.66	4.72	96	11.78	1.09	1104	0.00	0.00	0.00	1	0.00	0.00	979	0.00	0.00	0.00	1	0.00	0.00	2924	0.01	0.00	0.01	15	0.03	0.00
34	0.07	0.01	0.02	70	0.05	0.00	1111	31.44	2.96	8.26	96	21.13	1.96	1284	0.00	0.00	0.00	1	0.00	0.00	2915	0.00	0.00	0.01	2	0.00	0.00
265	0.05	0.00	0.14	8	0.62	0.06	1114	0.03	0.00	0.06	17	0.18	0.02	2487	17.53	1.64	4.50	96	11.82	1.09	1111	18.19	1.92	3.84	96	7.59	0.79
4	0.00	0.00	0.00	3	0.00	0.00	1187	0.01	0.00	0.01	10	0.02	0.00	1386	0.82	0.08	2.39	88	3.07	0.28	1114	0.03	0.00	0.06	19	0.15	0.02
269	0.00	0.00	0.00	1	0.00	0.00	2399	0.00	0.00	0.00	6	0.00	0.00	1402	0.00	0.00	0.01	2	0.00	0.00	1116	0.59	0.06	0.19	96	0.31	0.03
65	0.00	0.00	0.01	5	0.00	0.00	1972	0.00	0.00	0.01	1	0.00	0.00	1406	0.00	0.00	0.01	2	0.00	0.00	2399	0.01	0.00	0.01	15	0.00	0.00
355	0.01	0.00	0.01	11	0.00	0.00	2044	0.00	0.00	0.00	1	0.00	0.00	312	0.01	0.00	0.01	10	0.02	0.00	1984	0.00	0.00	0.00	4	0.00	0.00
35	0.00	0.00	0.01	2	0.00	0.00	1116	0.95	0.09	0.24	96	0.58	0.05	266	0.06	0.01	0.14	7	0.71	0.07	1972	0.00	0.00	0.01	5	0.00	0.00
288	0.01	0.00	0.04	11	0.11	0.01	190	0.00	0.00	0.00	1	0.00	0.00	35	0.07	0.01	0.03	70	0.05	0.00	1187	0.01	0.00	0.01	14	0.01	0.00
268	0.00	0.00	0.00	2	0.00	0.00	2484	0.00	0.00	0.00	1	0.00	0.00	269	0.00	0.00	0.00	1	0.00	0.00	2499	0.00	0.00	0.00	1	0.00	0.00
302	0.01	0.00	0.01	9	0.00	0.00	2499	0.00	0.00	0.00	1	0.00	0.00	289	0.01	0.00	0.01	9	0.00	0.00	2	0.00	0.00	0.00	1	0.00	0.00
301	0.00	0.00	0.00	2	0.00	0.00	60	0.00	0.00	0.00	1	0.00	0.00	302	0.00	0.00	0.00	1	0.00	0.00	2766	0.00	0.00	0.01	1	0.00	0.00
6	0.01	0.00	0.02	13	0.04	0.00	153	0.01	0.00	0.01	10	0.02	0.00	303	0.01	0.00	0.01	16	0.00	0.00	2989	0.00	0.00	0.00	1	0.00	0.00
195	0.02	0.00	0.02	25	0.03	0.00	3637	0.00	0.00	0.01	1	0.00	0.00	-1	0.00	0.00	0.01	6	0.00	0.00	60	0.00	0.00	0.00	1	0.00	0.00
298	0.00	0.00	0.01	2	0.00	0.00	1338	0.00	0.00	0.00	1	0.00	0.00	240	0.01	0.00	0.01	16	0.01	0.00	153	0.01	0.00	0.01	11	0.01	0.00
297	0.00	0.00	0.01	4	0.00	0.00	689	0.00	0.00	0.01	1	0.00	0.00	36	0.00	0.00	0.00	1	0.00	0.00	1076	0.00	0.00	0.00	1	0.00	0.00
243	0.02	0.00	0.01	22	0.02	0.00	1321	0.00	0.00	0.00	1	0.00	0.00	5	0.00	0.00	0.01	3	0.03	0.00	1336	0.00	0.00	0.01	1	0.00	0.00
26	0.09	0.01	0.03	82	0.06	0.01	1327	0.00	0.00	0.00	1	0.00	0.00	298	0.00	0.00	0.00	2	0.00	0.00	1329	0.00	0.00	0.00	1	0.00	0.00
341	0.00	0.00	0.01	4	0.03	0.00	1320	0.00	0.00	0.00	1	0.00	0.00	242	0.02	0.00	0.06	13	0.20	0.02	1320	0.00	0.00	0.01	1	0.00	0.00
144	0.00	0.00	0.00	1	0.00	0.00	3695	0.00	0.00	0.00	1	0.00	0.00	342	0.00	0.00	0.01	6	0.02	0.00	1327	0.00	0.00	0.01	1	0.00	0.00
299	0.00	0.00	0.01	3	0.00	0.00	1336	0.00	0.00	0.01	1	0.00	0.00	296	0.00	0.00	0.01	2	0.00	0.00	591	0.00	0.00	0.00	1	0.00	0.00
239	0.00	0.00	0.01	6	0.00	0.00	3611	0.00	0.00	0.02	1	0.00	0.00	145	0.00	0.00	0.00	2	0.00	0.00	918	0.00	0.00	0.00	1	0.00	0.00
-1	0.00	0.00	0.01	4	0.03	0.00	1949	0.11	0.01	0.06	66	0.12	0.01	356	0.00	0.00	0.01	8	0.00	0.00	1321	0.00	0.00	0.00	1	0.00	0.00
311	0.00	0.00	0.01	6	0.00	0.00	1914	0.00	0.00	0.01	2	0.00	0.00	411	0.00	0.00	0.01	8	0.00	0.00	3695	0.00	0.00	0.00	1	0.00	0.00
241	0.04	0.00	0.07	22	0.25	0.02	1916	0.01	0.00	0.01	15	0.02	0.00	270	0.01	0.00	0.01	9	0.00	0.00	689	0.00	0.00	0.01	1	0.00	0.00
410	0.00	0.00	0.01	7	0.00	0.00	2047	0.01	0.00	0.01	11	0.02	0.00	244	0.03	0.00	0.04	28	0.09	0.01	3611	0.00	0.00	0.00	1	0.00	0.00
2	0.00	0.00	0.01	1	0.00	0.00	1911	0.00	0.00	0.00	2	0.00	0.00	66	0.00	0.00	0.01	8	0.00	0.00	1949	0.05	0.01	0.03	57	0.05	0.01
2912	0.00	0.00	0.01	1	0.00	0.00	2055	0.00	0.00	0.01	3	0.00	0.00	196	0.02	0.00	0.01	29	0.04	0.00	3369	0.00	0.00	0.01	4	0.00	0.00
190	0.00	0.00	0.01	1	0.00	0.00	1921	0.00	0.00	0.01	4	0.03	0.00	7	0.01	0.00	0.02	16	0.03	0.00	3364	0.00	0.00	0.00	1	0.00	0.00
2766	0.00	0.00	0.01	1	0.00	0.00	2079	0.01	0.00	0.02	6	0.06	0.01	2912	0.00	0.00	0.00	1	0.00	0.00	3302	0.02	0.00	0.02	40	0.02	0.00
2989	0.00	0.00	0.01	1	0.00	0.00	2089	0.00	0.00	0.01	7	0.02	0.00	2484	0.00	0.00	0.01	1	0.00	0.00	3305	0.10	0.01	0.04	86	0.06	0.01
2115	0.00	0.00	0.01	1	0.00	0.00	1948	0.10	0.01	0.03	84	0.07	0.01	122	0.00	0.00	0.00	1	0.00	0.00	3268	0.01	0.00	0.01	12	0.02	0.00
2145	0.00	0.00	0.01	1	0.00	0.00	1810	0.00	0.00	0.00	1	0.00	0.00	2891	0.00	0.00	0.00	1	0.00	0.00	3273	0.00	0.00	0.01	10	0.00	0.00
2053	0.00	0.00	0.01	1	0.00	0.00	1906	0.00	0.00	0.01	1	0.00	0.00	2499	0.00	0.00	0.00	1	0.00	0.00	3456	0.02	0.00	0.04	20	0.07	0.01
1802	0.00	0.00	0.01	1	0.00	0.00	1908	0.00	0.00	0.00	1	0.00	0.00	2989	0.00	0.00	0.00	1	0.00	0.00	3262	0.00	0.00	0.00	2	0.00	0.00
2106	0.00	0.00	0.01	1	0.00	0.00	1909	0.00	0.00	0.01	2	0.00	0.00	2115	0.00	0.00	0.00	1	0.00	0.00	3266	0.00	0.00	0.01	2	0.00	0.00
2109	0.00	0.00	0.01	1	0.00	0.00	2049	0.03	0.00	0.02	35	0.04	0.00	53	0.00	0.00	0.00	1	0.00	0.00	3259	0.00	0.00	0.01	3	0.00	0.00
2052	0.00	0.00	0.02	1	0.00	0.00	2045	0.03	0.00	0.02	37	0.03	0.00	2145	0.00	0.00	0.02	1	0.00	0.00	3418	0.01	0.00	0.01	11	0.01	0.00
742	0.00	0.00	0.01	1	0.00	0.00	2090	0.01	0.00	0.04	10	0.14	0.01	2046	0.00	0.00	0.00	1	0.00	0.00	3413	0.05	0.01	0.02	57	0.05	0.00
2098	0.00	0.00	0.02	1	0.00	0.00	2054	0.02	0.00	0.02	29	0.03	0.00	2052	0.00	0.00	0.03	1	0.00	0.00	3184	0.01	0.00	0.01	14	0.01	0.00
2107	0.00	0.00	0.01	1	0.00	0.00	1999	0.00	0.00	0.00	2	0.00	0.00	748	0.00	0.00	0.00	1	0.00	0.00	3397	0.20	0.02	0.06	90	0.11	0.01
3637	0.00	0.00	0.01	1	0.00	0.00	1993	0.00	0.00	0.01	6	0.00	0.00	2053	0.00	0.00	0.00	1	0.00	0.00	3455	0.04	0.00	0.04	51	0.05	0.01
1338	0.00	0.00	0.01	1	0.00	0.00	2004	0.01	0.00	0.01	12	0.02	0.00	2098	0.00	0.00	0.01	1	0.00	0.00	3412	0.03	0.00	0.01	41	0.03	0.00
689	0.00	0.00	0.02	1	0.00	0.00	1887	0.01	0.00	0.01	14	0.02	0.00	1802	0.00	0.00	0.00	1	0.00	0.00	3436	0.01	0.00	0.01	19	0.02	0.00
963	0.00	0.00	0.01	1	0.00	0.00	1927	0.00	0.00	0.01	6	0.00	0.00	3469	0.00	0.00	0.00	1	0.00	0.00	3307	0.01	0.00	0.01	20	0.02	0.00
1321	0.00	0.00	0.01	1	0.00	0.00	260	0.01	0.00	0.01	10	0.02	0.00	3637	0.00	0.00	0.00	1	0.00	0.00	3275	0.02	0.00	0.01	38	0.02	0.00
1327	0.00	0.00	0.01	1	0.00	0.00	55	0.00	0.00	0.01	5	0.00	0.00	1338	0.00	0.00	0.00	1	0.00	0.00	3188	0.01	0.00	0.01	25	0.02	0.00
3701	0.00	0.00	0.01	5	0.02	0.00	76	0.00	0.00	0.01	5	0.00	0.00	689	0.00	0.00	0.01	1	0.00	0.00	13	0.00	0.00	0.01	9	0.00	0.00
1320	0.00	0.00	0.01	1	0.00	0.00	45	0.00	0.00	0.01	7	0.00	0.00	1321	0.00	0.00	0.00	1	0.00	0.00	11	0.00	0.00	0.00	1	0.00	0.00
1336	0.00	0.00	0.01	1	0.00	0.00	43	0.01	0.00	0.01	12	0.00	0.00	1327	0.00	0.00	0.00	1	0.00	0.00	422	0.01	0.00	0.01	12	0.00	0.00
3695	0.00	0.00	0.03	1	0.00	0.00	203	0.00	0.00	0.00	1	0.00	0.00	3701	0.01	0.00	0.01	10	0.02	0.00	427	0.00	0.00	0.01	1	0.00	0.00
3611	0.00	0.00	0.02	1	0.00	0.00	65	0.00	0.00	0.01	7	0.00	0.00	3695	0.01	0.00	0.03	5	0.10	0.01	425	0.00	0.00	0.00	2	0.00	0.00
3610	0.00	0.00	0.01	1	0.00	0.00	622	0.00	0.00	0.00	1	0.00	0.00	1320	0.00	0.00	0.00	1	0.00	0.00	-1	0.00	0.00	0.01	8	0.02	0.00
1949	0.11	0.01	0.05	67	0.12	0.01	689	0.00	0.00	0.01	1	0.00	0.00	3611	0.00	0.00	0.02	1	0.00	0.00	109	0.07	0.01	0.03	71	0.05	0.01
71	0.01	0.00	0.01	14	0.02	0.00	74	0.00	0.00	0.01	3	0.00	0.00	1949	0.14	0.01	0.04	69	0.12	0.01	653	0.00	0.00	0.00	6	0.00	0.00
31	0.00	0.00	0.00	1	0.00	0.00	36	0.00	0.00	0.00	3	0.00	0.00	32	0.00	0.00	0.00	2	0.00	0.00	651	0.00	0.00	0.01	6	0.02	0.00
720	0.00	0.00	0.01	1	0.00	0.00	42	0.00	0.00	0.00	4	0.00	0.00	51	0.00	0.00	0.01	2	0.00	0.00	509	0.03	0.00	0.11	8	0.41	0.04
60	0.00	0.00	0.00	2	0.00	0.00	67	0.00	0.00	0.00	3	0.00	0.00	72	0.00	0.00	0.01	4	0.00	0.00	637	0.01	0.00	0.04	9	0.10	0.01
37	0.00	0.00	0.01	8	0.00	0.00	73	0.01	0.00	0.01	23	0.02	0.00	41	0.00	0.00	0.00	7	0.00	0.00	514	0.00	0.00	0.01	2	0.00	0.00
35	0.00	0.00	0.01	2	0.00	0.00	234	0.01	0.00	0.01	15	0.02	0.00	39	0.00	0.00	0.00	3	0.00	0.00	101	0.00	0.00	0.00	1	0.00	0.00
69	0.00	0.00	0.01	1	0.00	0.00	264	0.06	0.01	0.14	11	0.63	0.06	69	0.01	0.00	0.01	10	0.02	0.00	495	0.00	0.00	0.00	1	0.00	0.00
695	0.00	0.00	0.01	1	0.00	0.00	148	0.00	0.00	0.00	1	0.00	0.00	-1	0.00	0.00	0.01	1	0.00	0.00	75	0.04	0.00	0.03	43	0.04	0.00
68	0.00	0.00	0.01	7	0.00	0.00	353	0.01	0.00	0.01	10	0.00	0.00	36	0.00	0.00	0.00	1	0.00	0.00	544	0.00	0.00	0.00	1	0.00	0.00
257	0.00	0.00	0.01	7	0.00	0.00	268	0.00	0.00	0.01	6	0.00	0.00	63	0.00	0.00	0.01	1	0.00	0.00	530	0.00	0.00	0.00	3	0.00	0.00
38	0.00	0.00	0.01	6	0.00	0.00	296	0.00	0.00	0.01	5	0.00	0.00	258	0.01	0.00	0.01	14	0.03	0.00	270	0.00	0.00	0.01	3	0.00	0.00
95	0.00	0.00	0.01	1	0.00	0.00	-1	0.00	0.00	0.01	4	0.00	0.00	711	0.00	0.00	0.00	1	0.00	0.00	597	0.00	0.00	0.01	1	0.00	0.00
153	0.00	0.00	0.01	8	0.00	0.00	267	0.00	0.00	0.01	3	0.00	0.00	61	0.00	0.00	0.01	3	0.00	0.00	741	0.00	0.00	0.00	1	0.00	0.00
61	0.00	0.00	0.01	2	0.00	0.00	7	0.00	0.00	0.00	4	0.00	0.00	38	0.00	0.00	0.01	3	0.00	0.00	539	0.00	0.00	0.01	3	0.00	0.00
290	0.00	0.00	0.01	6	0.02	0.00	301	0.01	0.00	0.01	16	0.02	0.00	59	0.00	0.00	0.01	1	0.00	0.00	740	0.00	0.00	0.01	4	0.00	0.00
636	0.16	0.01	0.04	90	0.08	0.01	300	0.00	0.00	0.01	2	0.00	0.00	153	0.01	0.00	0.01	12	0.02	0.00	117	0.00	0.00	0.00	5	0.00	0.00
							69	0.00	0.00	0.01	4	0.00	0.00	290	0.00	0.00	0.01	3	0.03	0.00	71	0.00	0.00	0.01	2	0.00	0.00
							298	0.00	0.00	0.01	2	0.00	0.00	636	0.11	0.01	0.04	86	0.07	0.01	540	0.00	0.00	0.01	2	0.00	0.00
							192	0.04	0.00	0.02	47	0.04	0.00								419	0.00	0.00	0.01	5	0.00	0.00
							68	0.00	0.00	0.01	1	0.00	0.00								430	0.03	0.00	0.07	30	0.14	0.01
							310	0.00	0.00	0.01	8	0.00	0.00								599	0.00	0.00	0.01	6	0.00	0.00
							37	0.09	0.01	0.03	77	0.06	0.01								555	0.01	0.00	0.01	9	0.02	0.00
							236	0.04	0.00	0.08	22	0.30	0.03								553	0.00	0.00	0.01	5	0.00	0.00
							339	0.00	0.00	0.01	6	0.00	0.00								305	0.02	0.00	0.01	35	0.02	0.00
							240	0.03	0.00	0.03	28	0.06	0.01								438	0.02	0.00	0.03	20	0.06	0.01
							287	0.01	0.00	0.04	13	0.09	0.01								721	0.01	0.00	0.02	8	0.04	0.00
							9	0.02	0.00	0.01	24	0.02	0.00								515	0.00	0.00	0.00	8	0.00	0.00
							408	0.00	0.00	0.01	7	0.00	0.00								582	0.00	0.00	0.01	6	0.00	0.00
																					749	0.07	0.01	0.03	75	0.05	0.01
																					216	0.00	0.00	0.01	4	0.00	0.00
																					575	0.00	0.00	0.01	10	0.00	0.00
																					957	0.01	0.00	0.01	15	0.00	0.00
																					41	0.00	0.00	0.01	9	0.02	0.00
																					37	0.00	0.00	0.01	4	0.00	0.00
																					56	0.00	0.00	0.01	1	0.00	0.00
																					387	0.00	0.00	0.01	5	0.00	0.00
																					397	0.01	0.00	0.01	27	0.01	0.00
																					44	0.01	0.00	0.01	11	0.00	0.00
																					-1	0.00	0.00	0.00	9	0.00	0.00
																					543	0.00	0.00	0.01	3	0.00	0.00
																					261	0.00	0.00	0.00	3	0.00	0.00
																					68	0.00	0.00	0.01	4	0.00	0.00
																					43	0.00	0.00	0.01	7	0.00	0.00
																					46	0.00	0.00	0.01	8	0.00	0.00
																					77	0.00	0.00	0.01	7	0.02	0.00
																					399	0.01	0.00	0.01	11	0.00	0.00
																					391	0.00	0.00	0.01	5	0.00	0.00

▶quants.c: 1011 - 76.56 %

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_3	Run icx_5
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/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/176-976-8784/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/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
			771	76.56	8.06	9.12	96	8.49	0.90

▶ops.cpp: 8690 - 1.90 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run icx_default							Run aocc_3	Run icx_5
		/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/cmath: 1583-1583 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 370-387 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 486-503 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 671-688 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 736-751 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-389 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8690-8706 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130								/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/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 392-393 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 508-509 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 693-694 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 756-757 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8690-8706 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
	332	0.32	0.03	0.08	66	0.17	0.02		707	1.57	0.17	0.34	74	0.84	0.09

▶quants.c: 293 - 1.07 %

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_3							Run icx_5
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 293-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 386-386 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 293-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 386-386 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 293-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 386-386 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404
478	0.37	0.03	0.08	96	0.15	0.01	476	0.36	0.03	0.07	93	0.17	0.02	479	0.35	0.03	0.07	94	0.17	0.02

▶ops.cpp: 6210 - 0.82 %

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_3							Run icx_5
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6320-6331 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6338-6379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6389-6447 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6456-6484 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6258-6276 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6285-6285 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6296-6303 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6320-6379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6385-6393 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6399-6484 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6229 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6320-6331 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6338-6379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6389-6484 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490							/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6258-6276 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6285-6288 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6296-6303 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6320-6379 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6385-6393 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6399-6447 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6456-6484 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490
313	0.22	0.02	0.05	96	0.11	0.01	312	0.21	0.02	0.05	95	0.11	0.01	314	0.20	0.02	0.04	92	0.11	0.01	669	0.20	0.02	0.05	95	0.10	0.01

▶ggml-cpu.c: 533 - 0.82 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	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_3							Run icx_5
		/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/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/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1397
	29	0.12	0.01	0.04	89	0.08	0.01	27	0.11	0.01	0.04	84	0.07	0.01	99	0.59	0.06	0.10	96	0.18	0.02

▶ops.cpp: 8692 - 0.63 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default							Run icx_default	Run aocc_3							Run icx_5
	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/cmath: 1583-1583 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 375-387 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-503 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 673-688 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 740-751 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8692-8692 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8700-8700 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130								/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/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 375-387 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-503 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 677-688 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 740-751 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8692-8692 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8700-8700 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
334	0.32	0.03	0.09	67	0.20	0.02		335	0.31	0.03	0.11	64	0.19	0.02

▶vec.cpp: 331 - 0.58 %

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_3	Run icx_5
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 331-337 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
			505	0.58	0.06	0.19	66	0.30	0.03

▶ggml-quants.c: 199 - 0.36 %

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_3	Run icx_5
				/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-quants.c: 199-222
			1036	0.36	0.04	0.07	96	0.15	0.02

▶vec.cpp: 304 - 0.32 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default							Run icx_default	Run aocc_3							Run icx_5
	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-325 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/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/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-325 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
263	0.14	0.01	0.04	63	0.09	0.01		264	0.18	0.02	0.06	63	0.13	0.01

▶vec.cpp: 207 - 0.13 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default	Run icx_default							Run aocc_3	Run icx_5
		/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 207-207 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-325 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/176-976-8784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
	262	0.13	0.01	0.05	61	0.11	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_3	icx_5	orig_default	icx_default	aocc_3	icx_5	orig_default	icx_default	aocc_3	icx_5	orig_default	icx_default	aocc_3	icx_5	orig_default	icx_default	aocc_3	icx_5	orig_default	icx_default	aocc_3	icx_5
void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<4>(long, long, long, long)	libggml-cpu.so	65.38	65.32	65.66	NA	6.14	6.15	6.14	NA	8.42	8.36	8.36	NA	96	96	96	NA	21.69	21.81	21.75	NA	2.05	2.06	2.04	NA
ggml_vec_dot_q8_0_q8_0	libggml-cpu.so	NA	NA	NA	76.56	NA	NA	NA	8.06	NA	NA	NA	9.12	NA	NA	NA	96	NA	NA	NA	8.49	NA	NA	NA	0.90
kmp_flag_64<false, true>::wait(kmp_info, int, void)	libiomp5.so	NA	31.44	NA	18.19	NA	2.96	NA	1.92	NA	8.26	NA	3.84	NA	96	NA	96	NA	21.13	NA	7.59	NA	1.96	NA	0.79
__kmp_hardware_timestamp	libomp.so	17.66	NA	17.53	NA	1.66	NA	1.64	NA	4.72	NA	4.50	NA	96	NA	96	NA	11.78	NA	11.82	NA	1.09	NA	1.09	NA
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libomp.so	14.38	NA	14.19	NA	1.35	NA	1.33	NA	3.74	NA	3.91	NA	96	NA	96	NA	9.66	NA	9.64	NA	0.89	NA	0.89	NA
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libomp.so	0.81	NA	0.82	NA	0.08	NA	0.08	NA	2.31	NA	2.39	NA	91	NA	88	NA	2.94	NA	3.07	NA	0.27	NA	0.28	NA
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	NA	NA	NA	1.57	NA	NA	NA	0.17	NA	NA	NA	0.34	NA	NA	NA	74	NA	NA	NA	0.84	NA	NA	NA	0.09
kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check()	libiomp5.so	NA	0.95	NA	0.59	NA	0.09	NA	0.06	NA	0.24	NA	0.19	NA	96	NA	96	NA	0.58	NA	0.31	NA	0.05	NA	0.03
quantize_row_q8_0	libggml-cpu.so	0.37	0.36	0.35	0.00	0.03	0.03	0.03	0.00	0.08	0.07	0.07	0.00	96	93	94	1	0.15	0.17	0.17	0.00	0.01	0.02	0.02	0.00
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	0.32	0.32	0.31	0.00	0.03	0.03	0.03	0.00	0.09	0.08	0.11	0.01	67	66	64	10	0.20	0.17	0.19	0.00	0.02	0.02	0.02	0.00
ggml_compute_forward_rope_f32(ggml_compute_params const, ggml_tensor, bool)	libggml-cpu.so	0.22	0.21	0.20	0.01	0.02	0.02	0.02	0.00	0.05	0.05	0.04	0.01	96	95	92	9	0.11	0.11	0.11	0.02	0.01	0.01	0.01	0.00
ggml_compute_forward_mul_mat	libggml-cpu.so	NA	NA	NA	0.59	NA	NA	NA	0.06	NA	NA	NA	0.10	NA	NA	NA	96	NA	NA	NA	0.18	NA	NA	NA	0.02
ggml_vec_dot_f16	libggml-cpu.so	NA	NA	NA	0.58	NA	NA	NA	0.06	NA	NA	NA	0.19	NA	NA	NA	66	NA	NA	NA	0.30	NA	NA	NA	0.03
ggml_vec_dot_f16	libggml-cpu.so	0.14	0.13	0.18	0.00	0.01	0.01	0.02	0.00	0.04	0.05	0.06	0.00	63	61	63	1	0.09	0.11	0.13	0.00	0.01	0.01	0.01	0.00
__GI___sched_yield	libc.so.6	0.11	0.11	0.14	0.05	0.01	0.01	0.01	0.01	0.05	0.06	0.04	0.03	67	66	69	57	0.12	0.12	0.12	0.05	0.01	0.01	0.01	0.01
quantize_row_q8_0_ref	libggml-base.so	NA	NA	NA	0.36	NA	NA	NA	0.04	NA	NA	NA	0.07	NA	NA	NA	96	NA	NA	NA	0.15	NA	NA	NA	0.02
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libiomp5.so	NA	0.21	NA	0.15	NA	0.02	NA	0.02	NA	0.08	NA	0.08	NA	88	NA	76	NA	0.19	NA	0.22	NA	0.02	NA	0.02
ggml_compute_forward_mul_mat	libggml-cpu.so	0.09	0.12	0.11	NA	0.01	0.01	0.01	NA	0.03	0.04	0.04	NA	82	89	84	NA	0.06	0.08	0.07	NA	0.01	0.01	0.01	NA
f64xsubf128	libm.so.6	0.16	NA	0.11	NA	0.01	NA	0.01	NA	0.04	NA	0.04	NA	90	NA	86	NA	0.08	NA	0.07	NA	0.01	NA	0.01	NA
ggml_graph_compute_thread	libggml-cpu.so	0.07	0.09	0.07	NA	0.01	0.01	0.01	NA	0.02	0.03	0.03	NA	70	77	70	NA	0.05	0.06	0.05	NA	0.00	0.01	0.00	NA
ggml_compute_forward_rope_f32	libggml-cpu.so	NA	NA	NA	0.20	NA	NA	NA	0.02	NA	NA	NA	0.05	NA	NA	NA	95	NA	NA	NA	0.10	NA	NA	NA	0.01
__libm_sse2_sincosf_l9	binary	NA	0.10	NA	0.10	NA	0.01	NA	0.01	NA	0.03	NA	0.04	NA	84	NA	86	NA	0.07	NA	0.06	NA	0.01	NA	0.01
__libm_roundf_y8	binary	NA	NA	NA	0.20	NA	NA	NA	0.02	NA	NA	NA	0.06	NA	NA	NA	90	NA	NA	NA	0.11	NA	NA	NA	0.01
ggml_vec_swiglu_f32	libggml-cpu.so	0.05	0.06	0.06	NA	0.00	0.01	0.01	NA	0.14	0.14	0.14	NA	8	11	7	NA	0.62	0.63	0.71	NA	0.06	0.06	0.07	NA
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libiomp5.so	NA	0.07	NA	0.06	NA	0.01	NA	0.01	NA	0.09	NA	0.11	NA	34	NA	35	NA	0.24	NA	0.21	NA	0.02	NA	0.02
ggml_compute_forward_add_non_quantized	libggml-cpu.so	0.04	0.04	0.02	0.00	0.00	0.00	0.00	0.00	0.07	0.08	0.06	0.00	22	22	13	2	0.25	0.30	0.20	0.00	0.02	0.03	0.02	0.00
ggml::cpu::repack::extra_buffer_type::get_tensor_traits(ggml_tensor const*)	libggml-cpu.so	0.02	0.04	0.02	0.02	0.00	0.00	0.00	0.00	0.02	0.02	0.01	0.01	25	47	29	35	0.03	0.04	0.04	0.02	0.00	0.00	0.00	0.00
__libm_powf_l9	binary	NA	0.03	NA	0.05	NA	0.00	NA	0.01	NA	0.02	NA	0.02	NA	35	NA	57	NA	0.04	NA	0.05	NA	0.00	NA	0.00
ggml_vec_dot_q8_0_q8_0	libggml-cpu.so	NA	NA	NA	0.07	NA	NA	NA	0.01	NA	NA	NA	0.03	NA	NA	NA	75	NA	NA	NA	0.05	NA	NA	NA	0.01
ggml_graph_compute_thread	libggml-cpu.so	NA	NA	NA	0.07	NA	NA	NA	0.01	NA	NA	NA	0.03	NA	NA	NA	71	NA	NA	NA	0.05	NA	NA	NA	0.01
ggml_compute_forward_mul	libggml-cpu.so	0.02	0.03	0.03	0.00	0.00	0.00	0.00	0.00	0.01	0.03	0.04	0.01	22	28	28	1	0.02	0.06	0.09	0.00	0.00	0.01	0.01	0.00
kmp_flag_native<unsigned long long, (flag_type)1, true>::done_check()	libiomp5.so	NA	0.03	NA	0.03	NA	0.00	NA	0.00	NA	0.06	NA	0.06	NA	17	NA	19	NA	0.18	NA	0.15	NA	0.02	NA	0.02
__libm_expf_l9	binary	NA	0.03	NA	0.03	NA	0.00	NA	0.00	NA	0.02	NA	0.01	NA	37	NA	41	NA	0.03	NA	0.03	NA	0.00	NA	0.00
__intel_avx_rep_memcpy	binary	NA	0.00	NA	0.04	NA	0.00	NA	0.00	NA	0.01	NA	0.04	NA	7	NA	51	NA	0.02	NA	0.05	NA	0.00	NA	0.01
ggml_cpu_fp32_to_fp16	libggml-cpu.so	0.01	0.02	0.01	0.00	0.00	0.00	0.00	0.00	0.02	0.01	0.02	0.01	13	24	16	9	0.04	0.02	0.03	0.00	0.00	0.00	0.00	0.00
ggml_cpu_fp32_to_fp16	libggml-cpu.so	NA	NA	NA	0.04	NA	NA	NA	0.00	NA	NA	NA	0.03	NA	NA	NA	43	NA	NA	NA	0.04	NA	NA	NA	0.00
__kmp_barrier	libiomp5.so	NA	0.03	NA	0.01	NA	0.00	NA	0.00	NA	0.05	NA	0.02	NA	31	NA	20	NA	0.09	NA	0.04	NA	0.01	NA	0.00
__kmp_yield	libiomp5.so	NA	0.03	NA	0.01	NA	0.00	NA	0.00	NA	0.02	NA	0.01	NA	37	NA	15	NA	0.03	NA	0.03	NA	0.00	NA	0.00
int __kmp_barrier_template<false>(barrier_type, int, int, unsigned long, void, void ()(void, void)) [clone .isra.33]	libomp.so	0.02	NA	0.02	NA	0.00	NA	0.00	NA	0.03	NA	0.02	NA	28	NA	26	NA	0.04	NA	0.04	NA	0.00	NA	0.00	NA
ggml_vec_swiglu_f32	libggml-cpu.so	NA	NA	NA	0.03	NA	NA	NA	0.00	NA	NA	NA	0.11	NA	NA	NA	8	NA	NA	NA	0.41	NA	NA	NA	0.04
ggml_compute_forward_rms_norm	libggml-cpu.so	0.01	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.04	0.04	0.01	0.00	11	13	9	3	0.11	0.09	0.00	0.00	0.01	0.01	0.00	0.00
__libm_logf_l9	binary	NA	0.02	NA	0.01	NA	0.00	NA	0.00	NA	0.02	NA	0.01	NA	29	NA	20	NA	0.03	NA	0.02	NA	0.00	NA	0.00
ggml_compute_forward_add_non_quantized	libggml-cpu.so	NA	NA	NA	0.03	NA	NA	NA	0.00	NA	NA	NA	0.07	NA	NA	NA	30	NA	NA	NA	0.14	NA	NA	NA	0.01
__libm_log2_l9	binary	NA	0.01	NA	0.02	NA	0.00	NA	0.00	NA	0.01	NA	0.02	NA	11	NA	40	NA	0.02	NA	0.02	NA	0.00	NA	0.00
__intel_avx_rep_memset	binary	NA	0.01	NA	0.02	NA	0.00	NA	0.00	NA	0.04	NA	0.04	NA	10	NA	20	NA	0.14	NA	0.07	NA	0.01	NA	0.01
ggml_cpu_extra_compute_forward	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	0.01	6	15	16	5	0.00	0.02	0.01	0.00	0.00	0.00	0.00	0.00
ggml_is_empty	libggml-base.so	0.00	0.01	0.01	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	7	23	10	NA	0.00	0.02	0.02	NA	0.00	0.00	0.00	NA
ggml_compute_forward_set_rows	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	0.00	9	16	16	1	0.00	0.02	0.00	0.00	0.00	0.00	0.00	0.00
__tls_get_addr	ld-linux-x86-64.so.2	0.00	0.01	0.01	0.01	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	8	10	12	11	0.00	0.02	0.02	0.01	0.00	0.00	0.00	0.00
roundf	binary	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	38	NA	NA	NA	0.02	NA	NA	NA	0.00
ggml_rope_yarn_corr_dims	libggml-base.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	14	3	0.00	0.02	0.03	0.00	0.00	0.00	0.00	0.00
llamafile_sgemm	libggml-cpu.so	0.01	0.01	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	11	10	8	4	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_can_repeat	libggml-base.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	14	5	4	7	0.02	0.00	0.00	0.02	0.00	0.00	0.00	0.00
ggml_type_size	libggml-base.so	0.00	0.01	0.00	0.01	0.00	0.00	0.00	0.00	0.01	0.01	0.00	0.01	6	12	3	11	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
logf	binary	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	15	NA	12	NA	0.02	NA	0.02	NA	0.00	NA	0.00
__svml_logf4_l9	binary	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	14	NA	14	NA	0.02	NA	0.01	NA	0.00	NA	0.00
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	6	8	10	5	0.00	0.00	0.02	0.00	0.00	0.00	0.00	0.00
ggml_compute_forward_mul	libggml-cpu.so	NA	NA	NA	0.02	NA	NA	NA	0.00	NA	NA	NA	0.03	NA	NA	NA	20	NA	NA	NA	0.06	NA	NA	NA	0.01
__kmpc_barrier	libomp.so	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	11	NA	14	NA	0.02	NA	0.01	NA	0.00	NA	0.00	NA
__svml_logf4	binary	NA	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	1	NA	25	NA	0.00	NA	0.02	NA	0.00	NA	0.00
ggml_is_empty	libggml-base.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	27	NA	NA	NA	0.01	NA	NA	NA	0.00
ggml_compute_forward_glu	libggml-cpu.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	4	6	6	6	0.03	0.00	0.02	0.00	0.00	0.00	0.00	0.00
__kmpc_barrier	libiomp5.so	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	10	NA	14	NA	0.02	NA	0.01	NA	0.00	NA	0.00
ggml_compute_forward_add	libggml-cpu.so	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.00	1	6	9	8	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
unknown_function	libggml-cpu.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	4	4	6	8	0.03	0.00	0.00	0.02	0.00	0.00	0.00	0.00
(anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::mnpack(long, long, long, long)	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	7	8	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	0.01	0.01	0.01	0.00	5	4	8	5	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_blck_size	libggml-base.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.01	0.01	8	4	3	7	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_row_size	libggml-base.so	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.00	0.01	NA	7	7	8	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00
_intel_fast_memcpy	binary	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	19	NA	NA	NA	0.02	NA	NA	NA	0.00
__kmp_task_team_sync	libiomp5.so	NA	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	6	NA	15	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__memcpy_avx512_unaligned_erms	libc.so.6	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.03	0.00	0.03	0.00	1	1	5	1	0.00	0.00	0.10	0.00	0.00	0.00	0.01	0.00
ggml_compute_forward_rms_norm	libggml-cpu.so	NA	NA	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.04	NA	NA	NA	9	NA	NA	NA	0.10	NA	NA	NA	0.01
__memset_avx512_unaligned_erms	libc.so.6	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	5	NA	10	NA	0.02	NA	0.02	NA	0.00	NA	0.00	NA
sched_yield@plt	libomp.so	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	2	NA	13	NA	0.00	NA	0.02	NA	0.00	NA	0.00	NA
powf	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	4	NA	10	NA	0.03	NA	0.00	NA	0.00	NA	0.00
__libm_exp2f_z0	binary	NA	0.00	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	3	NA	11	NA	0.00	NA	0.01	NA	0.00	NA	0.00
ggml_compute_forward_reshape	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	4	5	2	3	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	15	NA	NA	NA	0.00	NA	NA	NA	0.00
__libm_floorf_y8	binary	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	NA	NA
ggml_is_contiguous	libggml-base.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	2	7	3	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	0.01	NA	0.00	0.01	2	NA	1	9	0.00	NA	0.00	0.02	0.00	NA	0.00	0.00
ggml_get_type_traits_cpu	libggml-cpu.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	3	4	3	1	0.00	0.00	0.03	0.00	0.00	0.00	0.00	0.00
__log2_finite	libm.so.6	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	6	NA	3	NA	0.02	NA	0.03	NA	0.00	NA	0.00	NA
__memcmp_evex_movbe	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.02	0.02	0.02	0.00	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	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	12	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	6	NA	4	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
_intel_fast_memset	binary	NA	0.01	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	6	NA	NA	NA	0.06	NA	NA	NA	0.01	NA	NA
ggml_can_repeat	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	0.00	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	0.02	NA	NA	NA	8	NA	NA	NA	0.04	NA	NA	NA	0.00
_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	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_get_type_traits	libggml-base.so	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	3	2	4	0.00	0.00	0.00	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	0.03	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
unknown_function	libggml-base.so	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.00	NA	NA	1	9	NA	NA	0.00	0.00	NA	NA	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
__kmp_get_global_thread_id_reg	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	4	NA	4	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
llama_vocab::impl::load(llama_model_loader&, LLM_KV const&)	libllama.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.03	0.00	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_get_glu_op	libggml-base.so	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	5	2	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00
ggml_compute_forward_dup	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	0.01	2	3	1	2	0.00	0.00	0.00	0.00	0.00	0.00	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	0.00	0.00	0.00	0.01	1	1	2	4	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
ggml_is_contiguous_1	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	3	1	4	NA	0.00	0.00	0.00	NA	0.00	0.00	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	0.01	0.01	0.02	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_compute_forward_get_rows	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	6	NA	NA	NA	0.02	NA	NA	NA	0.00
__libm_sse2_sincosf	binary	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	NA	NA
__libm_ceilf_y8	binary	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	NA	NA
_int_free	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__GI___libc_malloc	libc.so.6	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
__kmp_get_global_thread_id_reg	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	5	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	6	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	6	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_invoke_microtask	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	3	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
ggml_compute_forward_get_rows	libggml-cpu.so	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.00	NA	2	2	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	NA	0.00	0.00	NA	NA	0.01	0.01	NA	NA	3	2	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA
malloc_consolidate	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	0.00	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
unlink_chunk.constprop.0	libc.so.6	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.00	0.01	1	1	1	1	0.00	0.00	0.00	0.00	0.00	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	0.00	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	5	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_resume_if_soft_paused	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	2	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__kmp_enter_single	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	2	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__strlen_evex	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_are_same_shape	libggml-base.so	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.01	NA	NA	1	3	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	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	0.00	0.00	1	NA	1	1	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
ggml_compute_forward_view	libggml-cpu.so	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	0.01	2	NA	NA	2	0.00	NA	NA	0.00	0.00	NA	NA	0.00
__kmp_launch_thread	libiomp5.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	2	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
log2	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
__kmpc_global_thread_num	libiomp5.so	NA	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
exp2f	binary	NA	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	0.00	NA	0.00	NA	0.00
__kmp_resume_if_soft_paused	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	4	NA	NA	NA	0.00	NA	NA	NA	0.00
_ZNKSt10_HashtableISt4pairINSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEES6_ES0_IKS7_iESaIS9_ENSt8__detail10_Select1stESt8equal_toIS7_EN11llama_vocab4impl9pair_hashENSB_18_Mod_range_hashingENSB_20_Default_ranged_hashENSB_20_Prime_rehash_policyENSB_17...	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.02	NA	NA	NA	1	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	4	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	0.02	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
OmptReturnAddressGuard::OmptReturnAddressGuard(int, void*)	libomp.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	3	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
__kmpc_global_thread_num	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::ostream::sentry::sentry(std::ostream&)	libstdc++.so.6.0.29	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
__kmp_invoke_task_func	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	2	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
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	2	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
__GI___libc_free	libc.so.6	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.00	0.00	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
bool gguf_read_emplace_helper<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >(gguf_reader const&, std::vector<gguf_kv, std::allocator<gguf_kv> >&, std::__cxx11::basic_string<c...	libggml-base.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
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	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
__libm_expf_e7	binary	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	2	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long)	libstdc++.so.6.0.29	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	0.01	1	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
ggml_graph_compute.extracted	libggml-cpu.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_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	3	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
__kmp_barrier	libomp.so	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	NA
__kmp_fork_barrier(int, int)	libomp.so	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	NA
ggml_compute_forward_cpy	libggml-cpu.so	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	NA
unicode_utf8_to_byte(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
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	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
_dl_lookup_symbol_x	ld-linux-x86-64.so.2	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	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	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA
std::_Hash_bytes(void const*, unsigned long, unsigned long)	libstdc++.so.6.0.29	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA
expf	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	2	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
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
floorf	binary	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
.plt.sec@start	libstdc++.so.6.0.29	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	0.00	1	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
do_lookup_x	ld-linux-x86-64.so.2	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
floor	binary	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
__kmp_invoke_microtask	libiomp5.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
_ZN11llama_vocab4implD2Ev.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::_Rb_tree<ggml_backend_buffer_type, std::pair<ggml_backend_buffer_type const, ggml_context>, std::_Select1st<std::pair<ggml_backend_buffer_type const, ggml_context> >, std::less<ggml_backend_buffer_type>, std::allocator...	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
_dl_addr	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
check_match	ld-linux-x86-64.so.2	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
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
__kmp_launch_thread	libomp.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::reserve(unsigned long)	libstdc++.so.6.0.29	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
gguf_data_to_str[abi:cxx11](gguf_type, void const*, int)	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_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
__kmp_join_barrier(int)	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
operator delete(void*)	libstdc++.so.6.0.29	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
__kmp_task_team_setup	libomp.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
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	0.01	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	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
unicode_cpt_to_utf8[abi:cxx11](unsigned int)	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
_IO_str_init_static_internal	libc.so.6	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
__memchr_evex	libc.so.6	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::vector<gguf_kv, std::allocator<gguf_kv> >::~vector()	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
_dl_relocate_object_no_relro	ld-linux-x86-64.so.2	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
gguf_find_tensor	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
.plt.sec@start	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
gguf_free	libggml-base.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
std::_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	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmp_fork_barrier(int, int)	libiomp5.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__kmp_invoke_task_func	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
ceilf	binary	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_mul_mat	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
_IO_default_xsputn	libc.so.6	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__GI___isoc99_sscanf	libc.so.6	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__GI___pthread_cond_signal	libc.so.6	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
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	1	NA	NA	NA	0.00	NA	NA	NA	0.00
__kmp_join_barrier(int)	libiomp5.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	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
__kmp_api_omp_get_thread_num	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
_int_malloc	libc.so.6	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
_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
_ZN11llama_vocab4impl4loadER18llama_model_loaderRK6LLM_KV.A	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
ggml_graph_plan	libggml-cpu.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00

	orig_default	icx_default	aocc_3	icx_5
Uncheck all modules
libggml-cpu.so	66.78 %	66.80 %	67.08 %	79.87 %
libomp.so	32.89 %	0.00 %	32.60 %
libiomp5.so
binary
libggml-base.so	0.03 %	0.05 %	0.03 %	0.43 %
libc.so.6	0.13 %	0.12 %	0.15 %	0.06 %
libm.so.6	0.16 %	0.00 %	0.11 %
libllama.so	0.01 %	0.01 %	0.01 %	0.01 %
ld-linux-x86-64.so.2	0.01 %	0.01 %	0.01 %	0.01 %
libstdc++.so.6.0.29	0.00 %	0.00 %	0.00 %	0.00 %

Report Configuration

Functions

▶sgemm.cpp: 138 - 196.37 %

▶<unknown>: 0 - 120.44 %

▶quants.c: 1011 - 76.56 %

▶ops.cpp: 8690 - 1.90 %

▶quants.c: 293 - 1.07 %

▶ops.cpp: 6210 - 0.82 %

▶ggml-cpu.c: 533 - 0.82 %

▶ops.cpp: 8692 - 0.63 %

▶vec.cpp: 331 - 0.58 %

▶ggml-quants.c: 199 - 0.36 %

▶vec.cpp: 304 - 0.32 %

▶vec.cpp: 207 - 0.13 %

▶Old Layout

▶Filters

Functions