OV - Compare Functions

Functions

▶kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 119 - 189.12 %

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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 119-131 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 682-682							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 119-131 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 682-682							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 119-131 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 682-682							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 119-131 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 682-682
565	46.43	2.46	2.26	95	4.88	0.21	555	47.41	2.48	2.25	95	4.79	0.20	565	47.49	2.39	2.26	95	5.02	0.21	559	47.79	2.43	2.27	95	4.55	0.20

▶<unknown>: 0 - 141.49 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	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 gcc_default							Run armclang_3							Run gcc_5

67	0.00	0.00	0.01	3	0.00	0.00	278	0.00	0.00	0.00	2	0.00	0.00	345	0.00	0.00	0.01	3	0.00	0.00	488	0.00	0.00	0.01	3	0.00	0.00
13	0.00	0.00	0.00	1	0.00	0.00	493	0.00	0.00	0.01	2	0.01	0.00	487	0.00	0.00	0.00	1	0.00	0.00	-1	0.06	0.00	0.02	38	0.06	0.00
480	0.00	0.00	0.00	2	0.00	0.00	307	0.01	0.00	0.01	8	0.01	0.00	480	0.00	0.00	0.00	1	0.00	0.00	497	0.00	0.00	0.00	2	0.00	0.00
34	0.00	0.00	0.00	1	0.00	0.00	14	0.00	0.00	0.00	1	0.00	0.00	69	0.00	0.00	0.00	2	0.00	0.00	311	0.01	0.00	0.01	8	0.00	0.00
39	0.00	0.00	0.00	1	0.00	0.00	18	0.00	0.00	0.00	1	0.00	0.00	-1	0.04	0.00	0.01	30	0.04	0.00	310	0.00	0.00	0.01	3	0.00	0.00
149	0.00	0.00	0.01	1	0.00	0.00	547	0.00	0.00	0.00	1	0.00	0.00	451	0.00	0.00	0.01	2	0.00	0.00	319	0.00	0.00	0.01	1	0.00	0.00
306	0.00	0.00	0.01	1	0.00	0.00	-1	0.05	0.00	0.01	36	0.05	0.00	504	0.00	0.00	0.00	2	0.00	0.00	198	0.00	0.00	0.00	1	0.00	0.00
474	0.00	0.00	0.00	1	0.00	0.00	342	0.00	0.00	0.00	1	0.00	0.00	316	0.01	0.00	0.01	5	0.00	0.00	346	0.00	0.00	0.01	4	0.00	0.00
-1	0.04	0.00	0.01	30	0.04	0.00	552	0.00	0.00	0.00	2	0.01	0.00	563	0.00	0.00	0.01	1	0.00	0.00	471	0.00	0.00	0.01	1	0.00	0.00
316	0.00	0.00	0.01	2	0.00	0.00	472	0.00	0.00	0.01	3	0.01	0.00	8	0.00	0.00	0.00	1	0.00	0.00	282	0.00	0.00	0.01	2	0.00	0.00
345	0.00	0.00	0.01	2	0.00	0.00	66	0.00	0.00	0.01	1	0.00	0.00	10	0.09	0.00	0.05	47	0.16	0.01	95	0.01	0.00	0.01	5	0.00	0.00
244	0.00	0.00	0.01	4	0.00	0.00	197	0.00	0.00	0.00	3	0.00	0.00	12	0.01	0.00	0.05	2	0.65	0.03	281	0.00	0.00	0.01	1	0.00	0.00
562	0.00	0.00	0.01	1	0.00	0.00	15	0.01	0.00	0.01	6	0.00	0.00	510	0.00	0.00	0.01	1	0.00	0.00	556	0.00	0.00	0.00	1	0.00	0.00
8	0.00	0.00	0.00	1	0.00	0.00	476	0.00	0.00	0.00	2	0.01	0.00	927	2.63	0.13	0.21	95	1.11	0.05	66	0.00	0.00	0.00	1	0.00	0.00
9	0.00	0.00	0.00	1	0.00	0.00	276	0.32	0.02	0.04	90	0.21	0.01	822	0.16	0.01	0.03	70	0.12	0.00	15	0.01	0.00	0.00	6	0.00	0.00
10	0.08	0.00	0.04	41	0.12	0.01	277	0.00	0.00	0.01	2	0.00	0.00	934	0.06	0.00	0.02	23	0.14	0.01	479	0.00	0.00	0.01	1	0.00	0.00
11	0.00	0.00	0.00	1	0.00	0.00	745	1.50	0.08	0.13	96	0.50	0.02	467	0.00	0.00	0.00	1	0.00	0.00	476	0.00	0.00	0.00	2	0.00	0.00
12	0.01	0.00	0.04	2	0.45	0.02	26	0.00	0.00	0.01	3	0.00	0.00	1131	0.00	0.00	0.00	1	0.00	0.00	276	0.32	0.02	0.03	90	0.16	0.01
510	0.00	0.00	0.02	1	0.00	0.00	280	30.61	1.60	2.95	96	7.07	0.26	740	0.00	0.00	0.00	1	0.00	0.00	277	0.00	0.00	0.00	1	0.00	0.00
927	2.68	0.14	0.25	94	1.10	0.05	281	0.01	0.00	0.01	9	0.04	0.00	1115	0.00	0.00	0.01	1	0.00	0.00	280	30.06	1.53	3.05	96	7.03	0.26
822	0.14	0.01	0.02	62	0.11	0.00	740	0.00	0.00	0.00	1	0.00	0.00	707	0.00	0.00	0.00	1	0.00	0.00	281	0.01	0.00	0.01	5	0.05	0.00
934	0.06	0.00	0.04	28	0.16	0.01	213	0.00	0.00	0.00	1	0.00	0.00	1122	0.00	0.00	0.00	1	0.00	0.00	26	0.00	0.00	0.01	2	0.00	0.00
824	0.05	0.00	0.02	32	0.07	0.00	98	0.00	0.00	0.00	1	0.00	0.00	1124	0.00	0.00	0.01	1	0.00	0.00	745	1.51	0.08	0.12	96	0.55	0.02
1114	0.00	0.00	0.00	1	0.00	0.00	96	0.00	0.00	0.00	1	0.00	0.00	824	0.07	0.00	0.01	46	0.06	0.00	61	0.00	0.00	0.00	1	0.00	0.00
1689	0.61	0.03	0.07	94	0.30	0.01	510	0.00	0.00	0.02	1	0.00	0.00	1689	0.60	0.03	0.05	96	0.25	0.01	1293	0.08	0.00	0.06	42	0.17	0.01
1115	0.00	0.00	0.00	1	0.00	0.00	822	0.13	0.01	0.02	61	0.12	0.01	1	0.05	0.00	0.02	33	0.08	0.00	927	2.43	0.12	0.18	96	0.73	0.03
707	0.00	0.00	0.00	1	0.00	0.00	935	0.00	0.00	0.01	1	0.00	0.00	284	0.00	0.00	0.01	1	0.00	0.00	822	0.14	0.01	0.03	68	0.11	0.00
1122	0.00	0.00	0.00	1	0.00	0.00	1114	0.00	0.00	0.00	1	0.00	0.00	438	0.00	0.00	0.00	1	0.00	0.00	934	0.06	0.00	0.02	35	0.08	0.00
1124	0.00	0.00	0.00	1	0.00	0.00	1303	0.00	0.00	0.00	1	0.00	0.00	1902	0.36	0.02	0.10	82	0.38	0.02	1115	0.00	0.00	0.00	1	0.00	0.00
1131	0.00	0.00	0.01	1	0.00	0.00	1293	0.09	0.00	0.03	49	0.10	0.01	492	0.00	0.00	0.01	1	0.00	0.00	1300	0.00	0.00	0.00	1	0.00	0.00
1133	0.00	0.00	0.02	1	0.00	0.00	927	2.58	0.13	0.20	96	0.72	0.03	773	0.00	0.00	0.01	2	0.00	0.00	824	0.07	0.00	0.02	42	0.07	0.00
1	0.05	0.00	0.01	32	0.06	0.00	1295	0.01	0.00	0.03	3	0.32	0.02	842	0.00	0.00	0.01	2	0.00	0.00	1114	0.00	0.00	0.01	1	0.00	0.00
1902	0.33	0.02	0.09	80	0.32	0.01	1115	0.00	0.00	0.01	1	0.00	0.00	838	0.30	0.01	0.04	86	0.17	0.01	510	0.00	0.00	0.02	1	0.00	0.00
527	0.06	0.00	0.03	21	0.15	0.01	934	0.07	0.00	0.02	39	0.08	0.00	527	0.06	0.00	0.04	19	0.24	0.01	1122	0.00	0.00	0.02	1	0.00	0.00
529	1.83	0.10	0.18	96	0.65	0.03	1131	0.00	0.00	0.02	1	0.00	0.00	529	1.81	0.09	0.18	96	0.65	0.03	1124	0.00	0.00	0.01	1	0.00	0.00
425	0.01	0.00	0.01	5	0.01	0.00	1300	0.00	0.00	0.01	1	0.00	0.00	306	0.02	0.00	0.01	13	0.03	0.00	1131	0.01	0.00	0.03	1	0.00	0.00
492	0.00	0.00	0.01	2	0.00	0.00	1993	0.00	0.00	0.01	3	0.00	0.00	1282	0.02	0.00	0.01	18	0.04	0.00	1295	0.02	0.00	0.06	3	0.62	0.03
850	0.00	0.00	0.01	2	0.00	0.00	707	0.00	0.00	0.00	1	0.00	0.00	844	0.11	0.01	0.02	51	0.11	0.01	32	0.00	0.00	0.00	1	0.00	0.00
1282	0.03	0.00	0.01	19	0.04	0.00	1122	0.00	0.00	0.00	1	0.00	0.00	425	0.00	0.00	0.01	3	0.00	0.00	1814	0.00	0.00	0.01	1	0.00	0.00
838	0.27	0.01	0.07	90	0.23	0.01	348	0.00	0.00	0.00	1	0.00	0.00	1242	0.03	0.00	0.01	23	0.04	0.00	1832	0.00	0.00	0.01	1	0.00	0.00
438	0.00	0.00	0.00	4	0.00	0.00	824	0.06	0.00	0.02	38	0.08	0.00	855	27.23	1.37	2.65	96	6.72	0.27	1696	0.01	0.00	0.03	1	0.00	0.00
834	0.09	0.01	0.02	59	0.07	0.00	1133	0.00	0.00	0.01	1	0.00	0.00	834	0.07	0.00	0.02	42	0.07	0.00	1907	0.00	0.00	0.02	1	0.00	0.00
436	0.00	0.00	0.00	1	0.00	0.00	470	0.00	0.00	0.01	1	0.00	0.00	61	0.00	0.00	0.00	1	0.00	0.00	729	0.00	0.00	0.00	1	0.00	0.00
319	0.00	0.00	0.00	1	0.00	0.00	1611	0.00	0.00	0.01	1	0.00	0.00	3284	0.00	0.00	0.00	1	0.00	0.00	1818	0.00	0.00	0.00	1	0.00	0.00
844	0.09	0.00	0.04	48	0.10	0.00	326	0.00	0.00	0.01	1	0.00	0.00	1	0.00	0.00	0.00	1	0.00	0.00	1880	0.00	0.00	0.01	1	0.00	0.00
773	0.00	0.00	0.01	2	0.00	0.00	1594	0.01	0.00	0.03	1	0.00	0.00	3480	0.00	0.00	0.01	1	0.00	0.00	1695	0.00	0.00	0.00	1	0.00	0.00
1242	0.04	0.00	0.01	25	0.06	0.00	1762	0.00	0.00	0.02	1	0.00	0.00	3016	0.00	0.00	0.00	1	0.00	0.00	760	0.00	0.00	0.00	1	0.00	0.00
855	27.86	1.48	2.84	96	6.72	0.27	1726	0.00	0.00	0.02	1	0.00	0.00	-1	0.42	0.02	0.07	93	0.27	0.01	631	0.00	0.00	0.02	1	0.00	0.00
306	0.01	0.00	0.01	10	0.01	0.00	638	0.00	0.00	0.00	1	0.00	0.00	2948	0.32	0.02	0.04	92	0.18	0.01	-1	0.00	0.00	0.00	1	0.00	0.00
62	0.00	0.00	0.00	1	0.00	0.00	1761	0.00	0.00	0.00	1	0.00	0.00	1981	0.00	0.00	0.00	1	0.00	0.00	54	0.00	0.00	0.00	1	0.00	0.00
3001	0.00	0.00	0.02	1	0.00	0.00	1768	0.00	0.00	0.00	1	0.00	0.00	2922	0.00	0.00	0.00	1	0.00	0.00	50	0.00	0.00	0.00	1	0.00	0.00
3480	0.00	0.00	0.00	1	0.00	0.00	645	0.00	0.00	0.01	1	0.00	0.00	2925	0.18	0.01	0.03	70	0.13	0.01	677	0.00	0.00	0.00	1	0.00	0.00
3016	0.00	0.00	0.00	1	0.00	0.00	1799	0.00	0.00	0.00	1	0.00	0.00	88	0.00	0.00	0.00	1	0.00	0.00	85	0.00	0.00	0.00	2	0.01	0.00
-1	0.43	0.02	0.06	91	0.27	0.01	-1	0.00	0.00	0.01	1	0.00	0.00	261	0.00	0.00	0.00	3	0.01	0.00	82	0.00	0.00	0.01	2	0.01	0.00
1981	0.00	0.00	0.01	1	0.00	0.00	692	0.00	0.00	0.02	1	0.00	0.00	598	0.01	0.00	0.01	4	0.06	0.00	589	0.00	0.00	0.00	3	0.00	0.00
3032	0.00	0.00	0.00	2	0.00	0.00	1858	0.00	0.00	0.02	1	0.00	0.00	75	0.00	0.00	0.01	2	0.10	0.00	378	0.27	0.01	0.04	84	0.17	0.01
2948	0.25	0.01	0.04	84	0.17	0.01	3284	0.00	0.00	0.00	1	0.00	0.00	35	0.00	0.00	0.00	1	0.00	0.00	350	0.00	0.00	0.00	2	0.00	0.00
2155	0.01	0.00	0.01	5	0.00	0.00	3424	0.00	0.00	0.00	1	0.00	0.00	66	0.00	0.00	0.00	2	0.00	0.00	348	0.00	0.00	0.00	2	0.00	0.00
2925	0.17	0.01	0.03	71	0.15	0.01	1	0.00	0.00	0.00	1	0.00	0.00	42	0.00	0.00	0.00	1	0.00	0.00	263	0.00	0.00	0.00	1	0.00	0.00
2922	0.01	0.00	0.01	6	0.00	0.00	284	0.00	0.00	0.00	1	0.00	0.00	643	0.00	0.00	0.00	1	0.00	0.00	338	0.17	0.01	0.03	68	0.13	0.01
39	0.00	0.00	0.01	1	0.00	0.00	263	0.00	0.00	0.01	4	0.01	0.00	-1	0.00	0.00	0.00	1	0.00	0.00	284	0.00	0.00	0.00	1	0.00	0.00
261	0.00	0.00	0.00	1	0.00	0.00	350	0.01	0.00	0.01	8	0.00	0.00	786	0.00	0.00	0.00	1	0.00	0.00	3001	0.00	0.00	0.00	1	0.00	0.00
64	0.00	0.00	0.01	1	0.00	0.00	378	0.30	0.02	0.03	89	0.17	0.01	2032	0.00	0.00	0.02	1	0.00	0.00	2999	0.00	0.00	0.00	1	0.00	0.00
598	0.00	0.00	0.01	2	0.00	0.00	338	0.19	0.01	0.03	73	0.14	0.01	769	0.00	0.00	0.00	1	0.00	0.00	3284	0.00	0.00	0.00	1	0.00	0.00
555	0.00	0.00	0.01	1	0.00	0.00	623	0.00	0.00	0.01	3	0.00	0.00	1940	0.00	0.00	0.00	1	0.00	0.00	290	0.00	0.00	0.00	1	0.00	0.00
73	0.00	0.00	0.01	1	0.00	0.00	53	0.00	0.00	0.00	1	0.00	0.00	1939	0.01	0.00	0.02	1	0.00	0.00
75	0.01	0.00	0.01	7	0.00	0.00	-1	0.00	0.00	0.00	1	0.00	0.00	1987	0.00	0.00	0.01	1	0.00	0.00
787	0.00	0.00	0.01	1	0.00	0.00	581	0.00	0.00	0.01	1	0.00	0.00	1998	0.00	0.00	0.00	1	0.00	0.00
2033	0.00	0.00	0.01	1	0.00	0.00	88	0.00	0.00	0.00	2	0.01	0.00	1931	0.00	0.00	0.01	1	0.00	0.00
1941	0.00	0.00	0.00	1	0.00	0.00	79	0.00	0.00	0.00	1	0.00	0.00	-1	0.00	0.00	0.01	1	0.00	0.00
1776	0.00	0.00	0.00	1	0.00	0.00								2000	0.00	0.00	0.00	1	0.00	0.00
1988	0.00	0.00	0.01	1	0.00	0.00								1753	0.00	0.00	0.01	1	0.00	0.00
1987	0.00	0.00	0.00	1	0.00	0.00
1996	0.00	0.00	0.00	1	0.00	0.00
770	0.00	0.00	0.00	1	0.00	0.00
1940	0.01	0.00	0.04	1	0.00	0.00
1932	0.00	0.00	0.02	1	0.00	0.00
1754	0.00	0.00	0.02	1	0.00	0.00

▶quants.c: 2466 - 52.93 %

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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2466-2466 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2481-2495 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2506-2558 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2565-2590 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2600-2616 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2650-2660 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2666-2668 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2675-2675 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2683-2684 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2693-2699 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2709-2758 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2769-2812 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2821-2821 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2923-2923 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 1122-1122 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 1234-1234 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 1682-1682 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 3139-3139 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 4144-4144 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10238-10238 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12569-12569 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12710-12710 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12893-12893 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 16570-16570 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 17409-17409 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 21097-21097 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 21435-21435 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 21999-21999 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25296-25296 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25379-25379 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25654-25654 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 28759-28759 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2466-2466 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2481-2506 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2569-2575 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2600-2615 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2653-2654 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2675-2676 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2683-2683 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2693-2698 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2709-2758 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2765-2812 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2821-2821 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2923-2923 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2466-2466 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2481-2495 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2506-2558 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2565-2590 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2619-2660 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2666-2668 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2835-2853 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2859-2868 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2874-2895 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2901-2916 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2923-2923 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 1122-1122 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 1234-1234 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 1682-1682 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 3139-3139 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 4144-4144 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10238-10238 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12569-12569 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12710-12710 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12893-12893 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 16570-16570 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 17409-17409 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 21097-21097 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 21435-21435 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 21999-21999 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25296-25296 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25379-25379 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25654-25654 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 28759-28759 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2466-2466 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2481-2506 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2572-2575 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2600-2615 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2653-2654 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2675-2676 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2683-2683 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2693-2702 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2709-2758 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2765-2814 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2821-2821 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2923-2923 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51
431	13.48	0.71	0.62	96	0.56	0.01	432	12.88	0.67	0.59	96	0.71	0.02	431	13.71	0.69	0.61	96	0.60	0.01	436	12.86	0.65	0.59	96	0.69	0.02

▶ops.cpp: 6210 - 3.08 %

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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6261-6279 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6285-6303 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6312 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6333-6361 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6367-6379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6385-6393 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6407-6416 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6422-6432 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6438-6484 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6321-6379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6385-6395 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6402-6484 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6261-6279 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6285-6303 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6312 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6333-6361 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6367-6379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6385-6393 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6407-6416 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6422-6432 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6438-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6484 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6218-6231
318	0.85	0.04	0.08	96	0.30	0.01	275	0.89	0.05	0.07	96	0.30	0.01	318	0.81	0.04	0.08	96	0.31	0.01	274	0.54	0.03	0.05	94	0.26	0.01

▶ops.cpp: 8692 - 2.99 %

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	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 gcc_default							Run armclang_3	Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 282-357 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 403-474 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 638-662 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 704-725 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8692-8692 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8700-8702 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8730 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8742-8749 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8886 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8892-8908 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/cmath: 2544-2544 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 282-357 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 403-474 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 638-661 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 703-725 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8691-8706 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8853 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8908 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/cmath: 2544-2544 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 402-474 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 638-661 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 706-725 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8691-8706 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8749 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8847 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8862 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8908 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/cmath: 2544-2544 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51
338	0.98	0.05	0.08	88	0.35	0.02	335	1.00	0.05	0.10	86	0.40	0.02		339	1.01	0.05	0.08	86	0.34	0.01

▶vec.cpp: 369 - 1.44 %

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	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 gcc_default							Run armclang_3	Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 369-369 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 402-405 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 957-957 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1008-1034							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 370-370 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 405-405 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1009-1023 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 370-370 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 405-405 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1009-1023 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034
270	0.84	0.04	0.26	16	0.78	0.03	268	0.31	0.02	0.11	16	0.47	0.02		269	0.29	0.01	0.13	16	0.65	0.03

▶ops.cpp: 8691 - 1.02 %

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)	ASM Fct ID
Run orig_default	Run gcc_default	Run armclang_3							Run gcc_5
			/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 375-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-503 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 677-688 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 740-751 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8692-8692 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8700-8702 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8712-8720 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8727-8730 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8742-8749 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8755-8819 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8834 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8847 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8859-8862 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8868-8873 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8881-8886 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8892-8908 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8920-8920 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8926-8927 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8936-8939 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/cmath: 2544-2544 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51
		338	1.02	0.05	0.09	88	0.41	0.02

▶vec.cpp: 207 - 0.99 %

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 gcc_default							Run armclang_3	Run gcc_5
		/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 207-207 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 220-279 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 207-207 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 220-279 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337
	266	0.48	0.03	0.06	85	0.25	0.01		267	0.50	0.03	0.05	86	0.23	0.01

▶ggml-cpu.c: 533 - 0.71 %

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 gcc_default	Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1147 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1167 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1177-1177 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1207-1212 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1221-1234 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1267-1276 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1297 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1304-1309 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1339-1339 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1345-1345 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1352-1358 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1397 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 682-682 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1436-1444 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1454-1465 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1474-1475 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1483-1539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1552-1560 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1567-1579 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1585-1601 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1623-1628 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1635-1642 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1784 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1792-2038 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2047-2047 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2055-2055 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2061-2077 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2083-2096 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2862-2897								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1147 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1167 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1177-1177 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1207-1212 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1221-1234 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1267-1276 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1297 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1304-1309 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1339-1339 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1345-1345 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1352-1358 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1397 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 682-682 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1436-1444 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1454-1465 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1474-1475 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1483-1539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1552-1560 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1567-1579 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1585-1601 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1623-1628 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1635-1642 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1784 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1792-2038 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2047-2047 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2055-2055 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2061-2077 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2083-2096 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2862-2897
30	0.09	0.00	0.01	54	0.07	0.00		30	0.05	0.00	0.01	31	0.07	0.00
38	0.35	0.02	0.06	73	0.30	0.01		38	0.22	0.01	0.04	59	0.24	0.01

▶kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 21 - 0.70 %

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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 21-27 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 67-75 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 92-96 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 111-142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 151-258 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 264-271 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 282-292 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 299-340 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/kai_common.h: 136-136							/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 898-898 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 2943-2943 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 3174-3174 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 6853-6853 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 7154-7154 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 9945-9945 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10568-10568 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10805-10805 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12531-12531 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 15594-15594 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 16191-16191 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 17374-17374 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 17537-17537 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 22034-22034 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 22069-22069 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 22134-22134 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 24797-24797 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 24809-24809 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 21-27 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 67-75 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 90-97 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 120-120 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 262-271 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 289-292 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 332-340							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 21-27 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 67-75 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 92-96 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 111-142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 151-258 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 264-271 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 282-292 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 299-340 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/kai_common.h: 136-136							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 21-27 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 67-75 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 90-97 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 262-274 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 289-292 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 332-340 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 898-898 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 2943-2943 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 3174-3174 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 6853-6853 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 7154-7154 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 9945-9945 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10568-10568 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10805-10805 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12531-12531 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 15594-15594 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 16191-16191 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 17374-17374 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 17537-17537 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 22034-22034 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 22069-22069 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 22134-22134 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 24797-24797 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 24809-24809
506	0.18	0.01	0.23	4	0.74	0.04	495	0.16	0.01	0.18	4	0.63	0.02	506	0.18	0.01	0.21	4	0.57	0.02	499	0.18	0.01	0.20	4	0.63	0.02

▶kleidiai.cpp: 445 - 0.61 %

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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 445-445 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 533-539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 547-547							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 445-445 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 532-547							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 445-445 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 533-539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 547-547							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 445-445 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 532-540 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 547-547
471	0.28	0.01	0.04	80	0.21	0.01	468	0.05	0.00	0.01	38	0.04	0.00	471	0.22	0.01	0.04	68	0.21	0.01	472	0.06	0.00	0.01	37	0.06	0.00

▶ops.cpp: 6235 - 0.60 %

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 gcc_default	Run armclang_3	Run gcc_5
				/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6235-6247
			275	0.60	0.03	0.05	94	0.22	0.01

▶vec.cpp: 304 - 0.60 %

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)	ASM Fct ID
Run orig_default	Run gcc_default	Run armclang_3							Run gcc_5
			/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 304-304 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-325 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51
		268	0.60	0.03	0.06	86	0.30	0.01

▶binary-ops.cpp: 18 - 0.53 %

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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 518-518 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 537-541 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 42-45 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 54-65 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 84-95 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 101-101 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 110-110 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 121-139 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 152-154 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/common.h: 61-68 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 518-519 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 536-541 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 42-45 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 54-65 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 84-101 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 122-139 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 152-154 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/common.h: 59-68 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 518-518 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 537-541 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 42-45 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 54-65 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 84-95 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 101-101 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 110-110 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 121-139 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 152-154 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/common.h: 61-68 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 518-518 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 536-541 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 42-45 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 54-65 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 84-101 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 122-139 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 152-154 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/common.h: 58-68 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51
248	0.22	0.01	0.05	71	0.22	0.01	246	0.05	0.00	0.03	26	0.12	0.01	248	0.18	0.01	0.06	59	0.23	0.01	247	0.09	0.00	0.04	22	0.24	0.01

▶vec.cpp: 221 - 0.42 %

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	ASM Fct ID
Run orig_default							Run gcc_default	Run armclang_3	Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 221-223 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-279 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 336-337
268	0.42	0.02	0.05	83	0.22	0.01

▶ggml-cpu.c: 3228 - 0.37 %

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	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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3231 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3231 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3231 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3231 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404
10	0.09	0.00	0.02	41	0.12	0.01	13	0.10	0.01	0.03	48	0.13	0.01	10	0.10	0.01	0.03	46	0.14	0.01	13	0.07	0.00	0.02	42	0.08	0.00

▶binary-ops.cpp: 10 - 0.35 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 518-518 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 537-541 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 42-45 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 54-65 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 84-95 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 101-101 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 110-110 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 121-146 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/common.h: 61-68 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 518-519 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 536-541 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 42-45 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 54-65 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 84-101 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 122-146 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/common.h: 59-68 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 518-518 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 537-541 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 42-45 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 54-65 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 84-95 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 101-101 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 110-110 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 121-146 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/common.h: 61-68 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 518-518 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 536-541 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 42-45 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 54-65 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 84-101 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 122-146 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/common.h: 58-68 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51
246	0.09	0.00	0.05	22	0.23	0.01	244	0.05	0.00	0.04	15	0.19	0.01	246	0.10	0.00	0.05	22	0.33	0.01	245	0.12	0.01	0.04	23	0.30	0.01

▶ops.cpp: 4304 - 0.33 %

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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 638-661 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4304-4306 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4314-4338 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4351-4355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4362-4365							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 638-661 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4304-4343 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4351-4355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4362-4365							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 677-688 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4304-4306 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4314-4338 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4351-4355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4362-4365							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 638-661 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4304-4343 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4351-4355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4362-4365
293	0.12	0.01	0.05	25	0.31	0.01	293	0.10	0.01	0.04	16	0.26	0.01	293	0.05	0.00	0.03	18	0.14	0.01	297	0.06	0.00	0.03	17	0.13	0.01

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 36 - 0.32 %

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 gcc_default							Run armclang_3	Run gcc_5
		/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/kai_common.h: 143-143 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 36-36 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 80-95 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 102-158								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/kai_common.h: 143-143 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 36-36 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 80-95 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 101-158
	510	0.17	0.01	0.68	1	0.00	0.00		514	0.16	0.01	0.63	1	0.00	0.00

▶vec.cpp: 370 - 0.25 %

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)	ASM Fct ID
Run orig_default	Run gcc_default	Run armclang_3							Run gcc_5
			/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 369-369 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 390-391 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 402-405 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 957-957 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1045-1063 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1072-1072
		270	0.25	0.01	0.10	16	0.46	0.02

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 80 - 0.24 %

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 gcc_default	Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 80-95 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 102-158								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 80-95 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 102-158
521	0.13	0.01	0.53	1	0.00	0.00		521	0.11	0.01	0.45	1	0.00	0.00

▶ggml-cpu.c: 1424 - 0.16 %

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 gcc_default							Run armclang_3	Run gcc_5
		/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1424-1429 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1436-1445 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1454-1465 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1474-1476 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1483-1539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1552-1560 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1567-1579 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1585-1601 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1623-1628 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1634-1642 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1784 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1792-2040 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2047-2047 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2055-2055 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2061-2076 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2085-2096 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2862-2873 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2898 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 137-137								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1424-1429 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1436-1445 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1454-1465 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1474-1476 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1483-1539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1552-1560 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1567-1579 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1585-1601 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1623-1628 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1634-1642 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1784 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1792-2040 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2047-2047 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2055-2055 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2061-2076 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2085-2096 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2862-2873 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2898 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 137-137
	33	0.09	0.00	0.02	50	0.08	0.00		33	0.07	0.00	0.02	43	0.07	0.00

▶ops.cpp: 6310 - 0.14 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run armclang_3	Run gcc_5
				/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6310-6314 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6321-6379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6385-6395 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6402-6484 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6490-6490
			277	0.14	0.01	0.02	64	0.12	0.01

▶ggml.c: 1432 - 0.13 %

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 gcc_default							Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1432-1432 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1438-1438							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1432-1438							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1432-1432 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1438-1438							/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1432-1438
72	0.06	0.00	0.02	31	0.09	0.00	85	0.01	0.00	0.01	9	0.04	0.00	72	0.04	0.00	0.02	26	0.09	0.00	81	0.02	0.00	0.01	13	0.00	0.00

▶ggml-cpu.c: 1125 - 0.12 %

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 gcc_default							Run armclang_3	Run gcc_5
		/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1147 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1171 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1177-1177 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1207-1234 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1267-1276 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1297 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1304-1309 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1339-1339 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1345-1345 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1352-1397								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1147 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1171 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1177-1177 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1207-1234 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1267-1276 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1297 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1304-1309 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1339-1339 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1345-1345 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1352-1397
	32	0.06	0.00	0.01	40	0.06	0.00		32	0.06	0.00	0.02	38	0.05	0.00

▶ops.cpp: 5524 - 0.10 %

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 gcc_default	Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 5524-5526 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 5542-5563 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 5571-5585								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 5524-5526 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 5542-5563 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 5571-5585
307	0.06	0.00	0.02	39	0.08	0.00		307	0.04	0.00	0.01	26	0.04	0.00

▶kleidiai.cpp: 96 - 0.07 %

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	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 gcc_default	Run armclang_3							Run gcc_5
	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/std_function.h: 247-247 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/std_function.h: 589-591 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/variant: 1626-1626 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/variant: 1814-1817 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 96-96 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 302-321 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 327-340 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 348-381 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/build/_deps/kleidiai_download-src/kai/kai_common.h: 143-143								/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/std_function.h: 247-247 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/std_function.h: 589-591 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/variant: 1626-1626 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/variant: 1814-1817 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/armclang_3/_deps/kleidiai_download-src/kai/kai_common.h: 143-143 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 96-96 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 302-321 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 327-340 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 348-381
475	0.03	0.00	0.01	23	0.03	0.00		475	0.04	0.00	0.01	23	0.05	0.00

▶traits.cpp: 12 - 0.06 %

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 gcc_default							Run armclang_3							Run gcc_5
		/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_iterator.h: 1068-1068 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 12-23							/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1068-1068 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1102-1102 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 12-17 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 23-23							/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_iterator.h: 1068-1068 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 12-23
	242	0.03	0.00	0.01	20	0.03	0.00	244	0.01	0.00	0.01	9	0.04	0.00	243	0.02	0.00	0.01	16	0.05	0.00

▶kleidiai.cpp: 92 - 0.04 %

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 gcc_default							Run armclang_3	Run gcc_5
		/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/invoke.h: 61-61 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/std_function.h: 589-591 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 92-92 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 302-321 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 327-376 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 382-382 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/kai_common.h: 143-143 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/variant: 1626-1626 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/variant: 1814-1814								/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/invoke.h: 61-61 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/std_function.h: 247-247 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/std_function.h: 589-591 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 92-92 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 302-321 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 327-376 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 382-382 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/gcc_5/_deps/kleidiai_download-src/kai/kai_common.h: 143-143 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/variant: 1626-1626 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/variant: 1814-1814
	465	0.02	0.00	0.01	19	0.03	0.00		468	0.02	0.00	0.01	16	0.01	0.00

▶kleidiai.cpp: 56 - 0.04 %

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 gcc_default							Run armclang_3	Run gcc_5
		/usr/include/stdlib.h: 363-363 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 56-75 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 82-82 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 445-445 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 551-552 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 562-569 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kernels.h: 19-20								/usr/include/stdlib.h: 363-363 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 56-75 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 82-82 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 445-445 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 551-552 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 562-569 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kernels.h: 19-20
	459	0.02	0.00	0.01	17	0.03	0.00		463	0.01	0.00	0.01	10	0.05	0.00

▶ggml-cpu.cpp: 38 - 0.03 %

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 gcc_default							Run armclang_3	Run gcc_5
		/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/new_allocator.h: 172-172 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/new_allocator.h: 191-191 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 99-99 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 368-369 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 388-388 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp: 38-38 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp: 49-64 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/vector.tcc: 114-123
	95	0.03	0.00	0.01	20	0.04	0.00

▶ops.cpp: 1358 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	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 gcc_default	Run armclang_3							Run gcc_5
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 80-80 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1358-1399 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1410-1424 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1431-1440 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1469-1472								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 80-80 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1358-1399 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1410-1424 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1431-1440 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1469-1472
274	0.01	0.00	0.01	8	0.04	0.00		274	0.01	0.00	0.01	9	0.00	0.00

▶ops.cpp: 19 - 0.01 %

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 gcc_default							Run armclang_3	Run gcc_5
		/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 19-40 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 50-54 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 60-73 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 85-187 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 194-229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 236-244 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 251-281 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 288-296 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 304-304 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 314-318 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 324-337 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 349-486 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 493-528 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 535-543 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 550-580 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 587-595 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 602-632 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 639-647 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 655-655 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 665-667 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 675-688 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 698-798 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 807-842 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 849-857 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 864-894 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 901-909 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 916-946 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 953-961 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 968-998 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1005-1013 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1021-1021 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1031-1033 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1041-1084 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1091-1099 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1107-1107 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1117-1127 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1135-1148 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1158-1173 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1179-1190 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1199-1237 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1244-1252 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1266-1306 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1314-1323 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 1342-1349 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 518-519 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 536-541 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/176-138-2040/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51
	277	0.01	0.00	0.01	8	0.04	0.00

▶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	gcc_default	armclang_3	gcc_5	orig_default	gcc_default	armclang_3	gcc_5	orig_default	gcc_default	armclang_3	gcc_5	orig_default	gcc_default	armclang_3	gcc_5	orig_default	gcc_default	armclang_3	gcc_5	orig_default	gcc_default	armclang_3	gcc_5
kai_run_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm	libggml-cpu.so	46.43	47.41	47.49	47.79	2.46	2.48	2.39	2.43	2.26	2.25	2.26	2.27	95	95	95	95	4.88	4.79	5.02	4.55	0.21	0.20	0.21	0.20
gomp_team_barrier_wait_end	libgomp.so.1.0.0	NA	30.61	NA	30.06	NA	1.60	NA	1.53	NA	2.95	NA	3.05	NA	96	NA	96	NA	7.07	NA	7.03	NA	0.26	NA	0.26
kmp_flag_64<false, true>::wait(kmp_info, int, void)	libomp.so	27.86	NA	27.23	NA	1.48	NA	1.37	NA	2.84	NA	2.65	NA	96	NA	96	NA	6.72	NA	6.72	NA	0.27	NA	0.27	NA
ggml_vec_dot_q6_K_q8_K	libggml-cpu.so	13.48	12.88	13.71	12.86	0.71	0.67	0.69	0.65	0.62	0.59	0.61	0.59	96	96	96	96	0.56	0.71	0.60	0.69	0.01	0.02	0.01	0.02
__GI___pthread_mutex_lock	libc.so.6	2.68	2.58	2.63	2.43	0.14	0.13	0.13	0.12	0.25	0.20	0.21	0.18	94	96	95	96	1.10	0.72	1.11	0.73	0.05	0.03	0.05	0.03
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	0.98	1.00	1.02	1.01	0.05	0.05	0.05	0.05	0.08	0.10	0.09	0.08	88	86	88	86	0.35	0.40	0.41	0.34	0.02	0.02	0.02	0.01
kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check()	libomp.so	1.83	NA	1.81	NA	0.10	NA	0.09	NA	0.18	NA	0.18	NA	96	NA	96	NA	0.65	NA	0.65	NA	0.03	NA	0.03	NA
__aarch64_ldadd4_acq_rel	libgomp.so.1.0.0	NA	1.50	NA	1.51	NA	0.08	NA	0.08	NA	0.13	NA	0.12	NA	96	NA	96	NA	0.50	NA	0.55	NA	0.02	NA	0.02
ggml_compute_forward_rope_f32(ggml_compute_params const, ggml_tensor, bool)	libggml-cpu.so	0.85	0.89	0.81	0.14	0.04	0.05	0.04	0.01	0.08	0.07	0.08	0.02	96	96	96	64	0.30	0.30	0.31	0.12	0.01	0.01	0.01	0.01
ggml_vec_dot_f16	libggml-cpu.so	0.42	0.48	0.60	0.50	0.02	0.03	0.03	0.03	0.05	0.06	0.06	0.05	83	85	86	86	0.22	0.25	0.30	0.23	0.01	0.01	0.01	0.01
ggml_vec_swiglu_f32	libggml-cpu.so	0.84	0.31	0.25	0.29	0.04	0.02	0.01	0.01	0.26	0.11	0.10	0.13	16	16	16	16	0.78	0.47	0.46	0.65	0.03	0.02	0.02	0.03
__GI___sched_yield	libc.so.6	0.61	NA	0.60	NA	0.03	NA	0.03	NA	0.07	NA	0.05	NA	94	NA	96	NA	0.30	NA	0.25	NA	0.01	NA	0.01	NA
unknown_function	[vdso]	0.43	NA	0.42	NA	0.02	NA	0.02	NA	0.06	NA	0.07	NA	91	NA	93	NA	0.27	NA	0.27	NA	0.01	NA	0.01	NA
kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon	libggml-cpu.so	0.18	0.16	0.18	0.18	0.01	0.01	0.01	0.01	0.23	0.18	0.21	0.20	4	4	4	4	0.74	0.63	0.57	0.63	0.04	0.02	0.02	0.02
__aarch64_ldadd8_acq_rel	libomp.so	0.33	NA	0.36	NA	0.02	NA	0.02	NA	0.09	NA	0.10	NA	80	NA	82	NA	0.32	NA	0.38	NA	0.01	NA	0.02	NA
gomp_barrier_wait_end	libgomp.so.1.0.0	NA	0.32	NA	0.32	NA	0.02	NA	0.02	NA	0.04	NA	0.03	NA	90	NA	90	NA	0.21	NA	0.16	NA	0.01	NA	0.01
ggml::cpu::kleidiai::extra_buffer_type::get_tensor_traits(ggml_tensor const*)	libggml-cpu.so	0.28	0.05	0.22	0.06	0.01	0.00	0.01	0.00	0.04	0.01	0.04	0.01	80	38	68	37	0.21	0.04	0.21	0.06	0.01	0.00	0.01	0.00
ggml_rope_cache_init(float, float, float const, float, long, float, float, float*, float, float)	libggml-cpu.so	NA	NA	NA	0.60	NA	NA	NA	0.03	NA	NA	NA	0.05	NA	NA	NA	94	NA	NA	NA	0.22	NA	NA	NA	0.01
sincosf	libm.so.6	NA	0.30	NA	0.27	NA	0.02	NA	0.01	NA	0.03	NA	0.04	NA	89	NA	84	NA	0.17	NA	0.17	NA	0.01	NA	0.01
__GI___lll_lock_wait	libc.so.6	0.14	0.13	0.16	0.14	0.01	0.01	0.01	0.01	0.02	0.02	0.03	0.03	62	61	70	68	0.11	0.12	0.12	0.11	0.00	0.01	0.00	0.00
__sincosf_finite	libamath.so	0.25	NA	0.32	NA	0.01	NA	0.02	NA	0.04	NA	0.04	NA	84	NA	92	NA	0.17	NA	0.18	NA	0.01	NA	0.01	NA
ggml_graph_compute_thread	libggml-cpu.so	0.35	NA	0.22	NA	0.02	NA	0.01	NA	0.06	NA	0.04	NA	73	NA	59	NA	0.30	NA	0.24	NA	0.01	NA	0.01	NA
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libomp.so	0.27	NA	0.30	NA	0.01	NA	0.01	NA	0.07	NA	0.04	NA	90	NA	86	NA	0.23	NA	0.17	NA	0.01	NA	0.01	NA
kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0	libggml-cpu.so	0.13	0.17	0.11	0.16	0.01	0.01	0.01	0.01	0.53	0.68	0.45	0.63	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
rope_yarn(float, float, float, long, float, float, float, float*)	libggml-cpu.so	NA	NA	NA	0.54	NA	NA	NA	0.03	NA	NA	NA	0.05	NA	NA	NA	94	NA	NA	NA	0.26	NA	NA	NA	0.01
ggml_compute_forward_mul	libggml-cpu.so	0.22	0.05	0.18	0.09	0.01	0.00	0.01	0.00	0.05	0.03	0.06	0.04	71	26	59	22	0.22	0.12	0.23	0.24	0.01	0.01	0.01	0.01
ggml_cpu_fp32_to_fp16	libggml-cpu.so	0.09	0.10	0.10	0.07	0.00	0.01	0.01	0.00	0.02	0.03	0.03	0.02	41	48	46	42	0.12	0.13	0.14	0.08	0.01	0.01	0.01	0.00
__expf_finite	libm.so.6	NA	0.19	NA	0.17	NA	0.01	NA	0.01	NA	0.03	NA	0.03	NA	73	NA	68	NA	0.14	NA	0.13	NA	0.01	NA	0.01
ggml_compute_forward_add_non_quantized	libggml-cpu.so	0.09	0.05	0.10	0.12	0.00	0.00	0.00	0.01	0.05	0.04	0.05	0.04	22	15	22	23	0.23	0.19	0.33	0.30	0.01	0.01	0.01	0.01
__expf_finite	libamath.so	0.17	NA	0.18	NA	0.01	NA	0.01	NA	0.03	NA	0.03	NA	71	NA	70	NA	0.15	NA	0.13	NA	0.01	NA	0.01	NA
ggml_compute_forward_rms_norm	libggml-cpu.so	0.12	0.10	0.05	0.06	0.01	0.01	0.00	0.00	0.05	0.04	0.03	0.03	25	16	18	17	0.31	0.26	0.14	0.13	0.01	0.01	0.01	0.01
ggml_compute_forward_mul_mat	libggml-cpu.so	0.09	0.06	0.05	0.06	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.02	54	40	31	38	0.07	0.06	0.07	0.05	0.00	0.00	0.00	0.00
__GI___lll_lock_wake	libc.so.6	0.05	0.06	0.07	0.07	0.00	0.00	0.00	0.00	0.02	0.02	0.01	0.02	32	38	46	42	0.07	0.08	0.06	0.07	0.00	0.00	0.00	0.00
__GI___pthread_mutex_unlock_usercnt	libc.so.6	0.06	0.07	0.06	0.06	0.00	0.00	0.00	0.00	0.04	0.02	0.02	0.02	28	39	23	35	0.16	0.08	0.14	0.08	0.01	0.00	0.01	0.00
__kmp_hyper_barrier_gather(barrier_type, kmp_info, int, int, void ()(void, void), void*)	libomp.so	0.09	NA	0.11	NA	0.00	NA	0.01	NA	0.04	NA	0.02	NA	48	NA	51	NA	0.10	NA	0.11	NA	0.00	NA	0.01	NA
unknown_function	libggml-cpu.so	0.04	0.05	0.04	0.06	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.02	30	36	30	38	0.04	0.05	0.04	0.06	0.00	0.00	0.00	0.00
__memcpy	libastring.so	0.08	NA	0.09	NA	0.00	NA	0.00	NA	0.04	NA	0.05	NA	41	NA	47	NA	0.12	NA	0.16	NA	0.01	NA	0.01	NA
__GI___memcpy_sve	libc.so.6	NA	0.09	NA	0.08	NA	0.00	NA	0.00	NA	0.03	NA	0.06	NA	49	NA	42	NA	0.10	NA	0.17	NA	0.01	NA	0.01
__kmp_barrier	libomp.so	0.09	NA	0.07	NA	0.01	NA	0.00	NA	0.02	NA	0.02	NA	59	NA	42	NA	0.07	NA	0.07	NA	0.00	NA	0.00	NA
ggml_graph_compute_thread	libggml-cpu.so	NA	0.09	NA	0.07	NA	0.00	NA	0.00	NA	0.02	NA	0.02	NA	50	NA	43	NA	0.08	NA	0.07	NA	0.00	NA	0.00
ggml_is_empty	libggml-base.so	0.06	0.01	0.04	0.02	0.00	0.00	0.00	0.00	0.02	0.01	0.02	0.01	31	9	26	13	0.09	0.04	0.09	0.00	0.00	0.00	0.00	0.00
kmp_flag_native<unsigned long long, (flag_type)1, true>::done_check()	libomp.so	0.06	NA	0.06	NA	0.00	NA	0.00	NA	0.03	NA	0.04	NA	21	NA	19	NA	0.15	NA	0.24	NA	0.01	NA	0.01	NA
ggml_compute_forward_set_rows	libggml-cpu.so	0.06	0.01	0.04	0.01	0.00	0.00	0.00	0.00	0.02	0.01	0.01	0.01	39	8	26	8	0.08	0.01	0.04	0.00	0.00	0.00	0.00	0.00
@plt_start@	libomp.so	0.05	NA	0.05	NA	0.00	NA	0.00	NA	0.01	NA	0.02	NA	32	NA	33	NA	0.06	NA	0.08	NA	0.00	NA	0.00	NA
__kmp_yield	libomp.so	0.04	NA	0.03	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	25	NA	23	NA	0.06	NA	0.04	NA	0.00	NA	0.00	NA
ggml::cpu::kleidiai::tensor_traits::compute_forward_q4_0(ggml_compute_params, ggml_tensor)	libggml-cpu.so	0.03	NA	0.04	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	23	NA	23	NA	0.03	NA	0.05	NA	0.00	NA	0.00	NA
ggml_cpu_extra_compute_forward	libggml-cpu.so	0.00	0.03	0.01	0.02	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.01	4	20	9	16	0.00	0.03	0.04	0.05	0.00	0.00	0.00	0.00
__kmp_now_nsec	libomp.so	0.03	NA	0.02	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	19	NA	18	NA	0.04	NA	0.04	NA	0.00	NA	0.00	NA
ggml::cpu::kleidiai::tensor_traits::compute_forward_q4_0(ggml_compute_params, ggml_tensor) [clone .isra.0]	libggml-cpu.so	NA	0.02	NA	0.02	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	19	NA	16	NA	0.03	NA	0.01	NA	0.00	NA	0.00
ggml_backend_cpu_kleidiai_buffer_type	libggml-cpu.so	NA	0.02	0.00	0.01	NA	0.00	0.00	0.00	NA	0.01	0.01	0.01	NA	17	2	10	NA	0.03	0.00	0.05	NA	0.00	0.00	0.00
ggml_backend_cpu_get_extra_buffer_types()	libggml-cpu.so	NA	0.03	0.00	0.01	NA	0.00	0.00	0.00	NA	0.01	0.00	0.01	NA	20	2	5	NA	0.04	0.00	0.00	NA	0.00	0.00	0.00
__kmpc_barrier	libomp.so	0.01	NA	0.02	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	10	NA	13	NA	0.01	NA	0.03	NA	0.00	NA	0.00	NA
__GI___memset_generic	libc.so.6	NA	0.01	NA	0.02	NA	0.00	NA	0.00	NA	0.03	NA	0.06	NA	3	NA	3	NA	0.32	NA	0.62	NA	0.02	NA	0.03
ggml_compute_forward_add	libggml-cpu.so	0.01	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.00	0.01	0.01	8	2	9	2	0.04	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__memset	libastring.so	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.04	NA	0.05	NA	2	NA	2	NA	0.45	NA	0.65	NA	0.02	NA	0.03	NA
gomp_team_barrier_wait	libgomp.so.1.0.0	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	9	NA	5	NA	0.04	NA	0.05	NA	0.00	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	0.02	0.01	0.02	1	1	1	1	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	0.00	0.01	0.00	7	2	2	2	0.00	0.01	0.10	0.01	0.00	0.00	0.00	0.00
quantize_row_q8_K_ref	libggml-base.so	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.01	0.01	0.01	0.02	2	3	4	1	0.00	0.00	0.06	0.00	0.00	0.00	0.00	0.00
llama_vocab::impl::load(llama_model_loader&, LLM_KV const&)	libllama.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.02	0.02	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_barrier	libggml-cpu.so	0.00	0.01	NA	0.01	0.00	0.00	NA	0.00	0.00	0.01	NA	0.00	1	6	NA	6	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
__GI___libc_malloc	libc.so.6	0.00	0.00	0.00	0.01	0.00	0.00	0.00	0.00	0.01	0.02	0.00	0.03	1	1	1	1	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	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.04	NA	0.02	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
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	0.00	0.01	0.01	2	1	3	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	NA	0.01	NA	0.01	NA	0.00	NA	0.00	NA	0.03	NA	0.03	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__powf_finite	libm.so.6	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	8	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_compute_forward_dup	libggml-cpu.so	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	8	NA	1	NA	0.04	NA	0.00	NA	0.00	NA	0.00
std::__detail::_Map_base<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, int>, st...	libllama.so	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
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	0.02	0.02	NA	1	1	1	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA
ggml_compute_forward_rope	libggml-cpu.so	0.00	NA	0.01	0.00	0.00	NA	0.00	0.00	0.01	NA	0.01	0.01	2	NA	5	1	0.00	NA	0.00	0.00	0.00	NA	0.00	0.00
ggml_kleidiai_select_kernels(cpu_feature, ggml_tensor const*)	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	3	1	2	0.00	0.01	0.00	0.00	0.00	0.00	0.00	0.00
llama_kv_cache::set_input_kq_mask(ggml_tensor, llama_ubatch const, bool) const	libllama.so	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.01	0.02	0.00	0.00	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__kmp_get_global_thread_id_reg	libomp.so	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	5	NA	3	NA	0.01	NA	0.00	NA	0.00	NA	0.00	NA
_int_free	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	0.02	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
__fs_pow_1	libamath.so	0.01	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	6	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
_int_malloc	libc.so.6	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
kai_get_lhs_packed_offset_lhs_quant_pack_qsi8d32p4x8sb_f32_neon	libggml-cpu.so	NA	0.00	0.00	0.00	NA	0.00	0.00	0.00	NA	0.01	0.00	0.00	NA	2	2	2	NA	0.01	0.00	0.00	NA	0.00	0.00	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	0.01	0.01	0.00	1	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00	0.00	0.00
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	0.01	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
GOMP_barrier	libgomp.so.1.0.0	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	3	NA	2	NA	0.00	NA	0.00	NA	0.00	NA	0.00
__log2_finite	libm.so.6	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	4	NA	1	NA	0.01	NA	0.00	NA	0.00	NA	0.00
dequantize_row_q4_0	libggml-base.so	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	0.00	1	1	NA	3	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
__kmp_resume_if_soft_paused	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	4	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
ggml_cpu_get_sve_cnt	libggml-cpu.so	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.01	NA	0.00	3	1	NA	1	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00
__GI___libc_free	libc.so.6	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.02	0.01	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA
__ieee754_log2	libamath.so	0.01	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	5	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
ggml_rope_yarn_corr_dims	libggml-base.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	1	NA	3	NA	0.00	NA	0.01	NA	0.00	NA	0.00	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::find(char const*, unsigned long, unsigned long) const	libstdc++.so.6.0.33	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
unknown_function	libllama.so	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	0.01	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
std::_Function_handler<void (unsigned long, unsigned long, unsigned long, unsigned long, void const, void const, float, unsigned long, unsigned long, float, float), void ()(unsigned long, unsigned long, unsigned long, unsigned long, void const*, voi...	libggml-cpu.so	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	1	3	NA	NA	0.00	0.00	NA	NA	0.00	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	2	NA	2	NA	0.00	NA	0.00	NA	0.00	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, unsigned char>, s...	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
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	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
llama_vocab::~llama_vocab()	libllama.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml::cpu::repack::extra_buffer_type::get_tensor_traits(ggml_tensor const*)	libggml-cpu.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	3	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
ggml_compute_forward_get_rows	libggml-cpu.so	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	0.01	1	NA	NA	3	0.00	NA	NA	0.00	0.00	NA	NA	0.00
unlink_chunk.constprop.0	libc.so.6	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
kai_get_rhs_packed_offset_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm	libggml-cpu.so	0.00	0.00	NA	0.00	0.00	0.00	NA	0.00	0.01	0.00	NA	0.00	1	2	NA	1	0.00	0.01	NA	0.00	0.00	0.00	NA	0.00
std::ostream::put(char)	libstdc++.so.6.0.33	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.02	NA	NA	0.00	1	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
ggml_is_contiguous_1	libggml-base.so	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	2	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
unknown_function	libggml-base.so	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
std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long)	libstdc++.so.6.0.33	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
_IO_file_xsgetn	libc.so.6	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	NA
gomp_barrier_wait	libgomp.so.1.0.0	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	2	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
std::_Function_handler<unsigned long (unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long), unsigned long (*)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long)>::_M_invoke(s...	libggml-cpu.so	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	2	NA	1	NA	0.01	NA	0.00	NA	0.00	NA	0.00
__GI_memchr	libc.so.6	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00
syscall	libc.so.6	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
__kmp_invoke_task_func	libomp.so	0.00	NA	0.00	NA	0.00	NA	0.00	NA	0.01	NA	0.01	NA	2	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
ggml_are_same_shape	libggml-base.so	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.01	NA	NA	0.01	1	NA	NA	2	0.00	NA	NA	0.01	0.00	NA	NA	0.00
__kmp_join_barrier(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
gguf_get_arr_str	libggml-base.so	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00
do_lookup_x	ld-linux-aarch64.so.1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00
@plt_start@	libstdc++.so.6.0.33	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	1	1	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA
ggml_type_size	libggml-base.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
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.6.0.33	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
__exp2f_finite	libamath.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
__memchr	libastring.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
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	0.00	NA	0.00	NA	1	NA	1	NA	0.00	NA	0.00	NA	0.00	NA	0.00	NA
llama_kv_cache::apply_ubatch(llama_kv_cache::slot_info const&, llama_ubatch const&)	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
__logf_finite	libm.so.6	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
std::_Hash_bytes(void const*, unsigned long, unsigned long)	libstdc++.so.6.0.33	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
bool std::operator==<char, std::char_traits<char>, std::allocator<char> >(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, char const*)	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
void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_construct<char>(char, char*, std::forward_iterator_tag) [clone .isra.0]	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
replace_all(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::__cxx11::basic_string<...	libllama.so	NA	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::cpu::kleidiai::tensor_traits::compute_forward(ggml_compute_params, ggml_tensor)	libggml-cpu.so	0.00	NA	NA	0.00	0.00	NA	NA	0.00	0.00	NA	NA	0.01	1	NA	NA	1	0.00	NA	NA	0.00	0.00	NA	NA	0.00
__fs_log_1	libamath.so	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	NA
__kmp_fork_barrier(int, int)	libomp.so	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
unicode_cpt_flags_array()	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
_IO_sgetn	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
unicode_cpts_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
kai_get_dst_offset_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm	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
ggml_get_type_traits	libggml-base.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
ggml_new_tensor_impl	libggml-base.so	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA
__vfscanf_internal	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
__kmpc_global_thread_num	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
ggml_is_contiguous_n	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
operator new(unsigned long)	libstdc++.so.6.0.33	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
llama_vocab::impl::token_to_piece(int, char*, int, int, bool) const	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
llama_kv_cache::prepare(std::vector<llama_ubatch, std::allocator<llama_ubatch> > const&)	libllama.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
std::_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	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
std::ostream::sentry::sentry(std::ostream&)	libstdc++.so.6.0.33	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
main	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
ggml_blck_size	libggml-base.so	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00
std::_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	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_is_numa	libggml-cpu.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
unicode_utf8_to_byte(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::push_back(char)	libstdc++.so.6.0.33	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
_dl_relocate_object_no_relro	ld-linux-aarch64.so.1	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__GI___strlen_asimd	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
__GI___pthread_mutex_unlock	libc.so.6	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
__aarch64_cas8_sync	libgomp.so.1.0.0	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
llama_hparams::is_masked_swa(unsigned int, llama_swa_type, int, 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
_dl_fixup	ld-linux-aarch64.so.1	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
gomp_init_task	libgomp.so.1.0.0	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_get_type_traits_cpu	libggml-cpu.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
kai_get_mr_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm	libggml-cpu.so	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
__GI_____strtol_l_internal	libc.so.6	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA
ggml_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
__memmove	libastring.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_nrows	libggml-base.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
_dl_lookup_symbol_x	ld-linux-aarch64.so.1	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_compute.omp_outlined	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
ggml_is_contiguous	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
__bcmp	libastring.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
llama_vocab::impl::~impl()	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
ggml_backend_cpu_repack_buffer_type()	libggml-cpu.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.01	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
llama_decode_text(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
__kmpc_single	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_enter_single	libomp.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA
unicode_cpt_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, unsigned long&)	libllama.so	0.00	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA	1	NA	NA	NA	0.00	NA	NA	NA	0.00	NA	NA	NA

Report Configuration

Functions

▶kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 119 - 189.12 %

▶<unknown>: 0 - 141.49 %

▶quants.c: 2466 - 52.93 %

▶ops.cpp: 6210 - 3.08 %

▶ops.cpp: 8692 - 2.99 %

▶vec.cpp: 369 - 1.44 %

▶ops.cpp: 8691 - 1.02 %

▶vec.cpp: 207 - 0.99 %

▶ggml-cpu.c: 533 - 0.71 %

▶kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 21 - 0.70 %

▶kleidiai.cpp: 445 - 0.61 %

▶ops.cpp: 6235 - 0.60 %

▶vec.cpp: 304 - 0.60 %

▶binary-ops.cpp: 18 - 0.53 %

▶vec.cpp: 221 - 0.42 %

▶ggml-cpu.c: 3228 - 0.37 %

▶binary-ops.cpp: 10 - 0.35 %

▶ops.cpp: 4304 - 0.33 %

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 36 - 0.32 %

▶vec.cpp: 370 - 0.25 %

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 80 - 0.24 %

▶ggml-cpu.c: 1424 - 0.16 %

▶ops.cpp: 6310 - 0.14 %

▶ggml.c: 1432 - 0.13 %

▶ggml-cpu.c: 1125 - 0.12 %

▶ops.cpp: 5524 - 0.10 %

▶kleidiai.cpp: 96 - 0.07 %

▶traits.cpp: 12 - 0.06 %

▶kleidiai.cpp: 92 - 0.04 %

▶kleidiai.cpp: 56 - 0.04 %

▶ggml-cpu.cpp: 38 - 0.03 %

▶ops.cpp: 1358 - 0.02 %

▶ops.cpp: 19 - 0.01 %

▶Old Layout

▶Filters

Functions