OV - Compare Loops

Loops

▶mmq.cpp: 1140 - 38.89 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5							Run aocc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1140-1142 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1150-1151						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1140-1142 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1150-1151						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1140-1142 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1150-1151						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1140-1142 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1150-1151
567	0.85	0.34	4.78	100	100	2332.33	704	0.57	0.24	3.90	100	100	512.43	497	0.81	0.34	4.81	100	100	2307.19	653	0.67	0.24	4.01	100	100	2965.08
566	0.91	0.51	7.24	100	100	387.79	705	0.63	0.23	3.77	100	100	3054.79	496	1.06	0.46	6.46	100	100	384.65	652	0.68	0.23	3.91	100	100	540.52

Sum on 2 analyzed binary loops (libggml-cpu.so - 567, libggml-cpu.so - 566)							Sum on 2 analyzed binary loops (libggml-cpu.so - 704, libggml-cpu.so - 705)							Sum on 2 analyzed binary loops (libggml-cpu.so - 497, libggml-cpu.so - 496)							Sum on 2 analyzed binary loops (libggml-cpu.so - 653, libggml-cpu.so - 652)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
Loop Computation Issues							Loop Computation Issues							Loop Computation Issues							Loop Computation Issues
Presence of a large number of scalar integer instructions						1	Presence of a large number of scalar integer instructions							Presence of a large number of scalar integer instructions						1	Presence of a large number of scalar integer instructions
Low iteration count						0	Low iteration count							Low iteration count						1	Low iteration count
Control Flow Issues							Control Flow Issues							Control Flow Issues							Control Flow Issues
Low iteration count							Low iteration count							Low iteration count						1	Low iteration count
Data Access Issues							Data Access Issues							Data Access Issues							Data Access Issues
Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access							Presence of constant non-unit stride data access						1
Presence of indirect access						1	Presence of indirect access						1	Presence of indirect access							Presence of indirect access						1
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of more than 4 paths						0	Presence of more than 4 paths						0	Presence of more than 4 paths						1	Presence of more than 4 paths						0
Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						0	Presence of constant non-unit stride data access						1
Presence of indirect access						1	Presence of indirect access						1	Presence of indirect access						0	Presence of indirect access						1

▶vec.h: 491 - 4.19 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5							Run aocc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497
2263	0.19	0.08	1.14	0	0	179.6	2437	0.10	0.06	0.93	0	0	190.28	2208	0.16	0.08	1.15	0	0	203.89	2015	0.17	0.06	0.97	0	0	204.95

Sum on 1 analyzed binary loop (libggml-cpu.so - 2263)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2437)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2208)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2015)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
Control Flow Issues							Control Flow Issues							Control Flow Issues							Control Flow Issues
Presence of 2 to 4 paths							Presence of 2 to 4 paths						1	Presence of 2 to 4 paths							Presence of 2 to 4 paths						1
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of 2 to 4 paths							Presence of 2 to 4 paths						1	Presence of 2 to 4 paths							Presence of 2 to 4 paths						1

▶vec.cpp: 311 - 2.72 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5							Run aocc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316
1140	0.07	0.03	0.41	0	0	274.68	1232	0.14	0.06	0.91	0	0	204.17	1146	0.07	0.03	0.42	0	0	188.63	1247	0.13	0.06	0.98	0	0	196.21

Sum on 1 analyzed binary loop (libggml-cpu.so - 1140)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1232)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1146)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1247)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
Control Flow Issues							Control Flow Issues							Control Flow Issues							Control Flow Issues
Presence of 2 to 4 paths						1	Presence of 2 to 4 paths							Presence of 2 to 4 paths						1	Presence of 2 to 4 paths
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of 2 to 4 paths						1	Presence of 2 to 4 paths							Presence of 2 to 4 paths						1	Presence of 2 to 4 paths

▶<unknown>: 0 - 1.95 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5							Run aocc_6
Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions
2134	0.01	0.00	0.00	0	0	0	1282	0.01	0.00	0.00	0	0	0	2396	0.00	0.00	0.00	0	0	0	2492	0.01	0.00	0.00	0	0	0
1023	0.01	0.00	0.00	0	0	0	1279	0.01	0.00	0.00	0	0	0	1192	0.00	0.00	0.00	0	0	0	2263	0.00	0.00	0.00	0	0	0
2291	0.01	0.00	0.00	0	0	0	2842	0.01	0.00	0.00	0	0	0	2298	0.02	0.00	0.00	0	0	0	2291	0.00	0.00	0.00	0	0	0
2298	0.01	0.00	0.00	0	0	0	2638	0.01	0.00	0.00	0	0	0	2295	0.00	0.00	0.00	0	0	0	527	0.00	0.00	0.00	0	0	0
2415	0.01	0.00	0.00	0	0	0	2640	0.01	0.00	0.00	0	0	0	2399	0.00	0.00	0.00	0	0	0	2402	0.03	0.00	0.00	0	0	0
2289	0.01	0.00	0.00	0	0	0	2450	0.01	0.00	0.00	0	0	0	2513	0.00	0.00	0.00	0	0	0	1000	0.00	0.00	0.00	0	0	0
2395	0.01	0.00	0.00	0	0	0	2628	0.01	0.00	0.00	0	0	0	2293	0.02	0.00	0.00	0	0	0	2403	0.01	0.00	0.00	0	0	0
2294	0.02	0.00	0.00	0	0	0	2634	0.01	0.00	0.00	0	0	0	2302	0.02	0.00	0.00	0	0	0	2395	0.00	0.00	0.00	0	0	0
2504	0.01	0.00	0.00	0	0	0	2739	0.01	0.00	0.00	0	0	0	1910	0.02	0.00	0.02	0	0	13.19	1118	0.01	0.00	0.00	0	0	0
1189	0.01	0.00	0.00	0	0	0	816	0.06	0.01	0.10	0	0	94.69	360	0.01	0.00	0.00	0	0	42.67	2257	0.00	0.00	0.00	0	0	0
1955	0.03	0.00	0.02	0	0	7.23	695	0.01	0.00	0.02	0	0	765.61	1654	0.07	0.01	0.10	0	0	159.38	2489	0.00	0.00	0.00	0	0	0
709	0.01	0.00	0.00	0	0	0	1399	0.01	0.00	0.00	0	0	0	2324	0.00	0.00	0.00	0	0	NA	1615	0.02	0.00	0.02	0	0	856.99
372	0.00	0.00	0.00	0	0	NA	107	0.00	0.00	0.00	0	0	NA	352	0.00	0.00	0.00	0	0	151.72	2019	0.02	0.00	0.02	0	0	153.07
1610	0.06	0.01	0.09	0	0	172.69	1969	0.01	0.00	0.00	0	0	0	750	0.03	0.00	0.03	0	0	219.12	83	0.00	0.00	0.00	0	0	NA
427	0.01	0.00	0.01	0	0	0	377	0.00	0.00	0.00	0	0	0	491	0.02	0.00	0.03	0	0	606.87	1804	0.02	0.00	0.07	0	0	226.6
434	0.00	0.00	0.00	0	0	NA	108	0.01	0.00	0.04	0	0	32.55	614	0.04	0.00	0.07	0	0	105.78	874	0.04	0.00	0.04	0	0	205.11
1351	0.00	0.00	0.00	0	0	0	1759	0.01	0.00	0.01	0	0	1540.77	50	0.00	0.00	0.00	0	0	NA	355	0.00	0.00	0.00	0	0	NA
1605	0.00	0.00	0.00	0	0	2510.95	2105	0.02	0.00	0.06	0	0	444.43	6	0.04	0.01	0.10	0	0	0	319	0.01	0.00	0.00	0	0	38.16
576	0.01	0.00	0.01	0	0	287.52	1966	0.01	0.00	0.01	0	0	0	1649	0.00	0.00	0.00	0	0	2474.88	84	0.02	0.00	0.04	0	0	110.66
146	0.01	0.00	0.03	0	0	44.83	700	0.03	0.00	0.01	0	0	366.36	2193	0.01	0.00	0.01	0	0	58.39	1614	0.01	0.00	0.00	0	0	1804.93
2250	0.01	0.00	0.02	0	0	50.48	407	0.00	0.00	0.00	0	0	NA	345	0.01	0.00	0.01	0	0	10.84	1992	0.01	0.00	0.01	0	0	157.41
2265	0.02	0.00	0.03	0	0	7.17	2441	0.03	0.00	0.02	0	0	151.91	503	0.05	0.00	0.05	0	0	1500.31	1715	0.02	0.00	0.01	0	0	0
833	0.04	0.00	0.04	0	0	194.06	2410	0.01	0.00	0.01	0	0	195.31	502	0.01	0.00	0.01	0	0	404.58	648	0.01	0.00	0.01	0	0	98.77
565	0.02	0.00	0.02	0	0	540.6	914	0.04	0.00	0.04	0	0	227.02	51	0.02	0.00	0.03	0	0	17.7	649	0.04	0.00	0.06	0	0	688.01
1863	0.02	0.00	0.06	0	0	226.51	1758	0.06	0.01	0.10	0	0	184.1	2210	0.03	0.00	0.03	0	0	6.53	782	0.05	0.00	0.07	0	0	139.01
719	0.04	0.00	0.06	0	0	124.03	701	0.06	0.00	0.07	0	0	889.74	1890	0.02	0.00	0.05	0	0	238.23	643	0.01	0.00	0.02	0	0	616.2
575	0.05	0.00	0.07	0	0	1037.22	918	0.01	0.00	0.00	0	0	0								741	0.00	0.00	0.00	0	0	0
							838	0.01	0.00	0.00	0	0	0								321	0.00	0.00	0.00	0	0	NA
																					963	0.00	0.00	0.00	0	0	0

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count

▶mmq.cpp: 303 - 1.79 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5							Run aocc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 651-663 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 816-818 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 825-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 651-663 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 816-818 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 825-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 651-663 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 816-818 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 825-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 651-663 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 816-818 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 825-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392
659	0.06	0.03	0.39	90.91	38.76	0	384	0.05	0.03	0.44	90.91	38.76	0	594	0.06	0.03	0.44	90.91	38.76	0	326	0.07	0.03	0.52	90.91	38.76	0

Sum on 1 analyzed binary loop (libggml-cpu.so - 659)							Sum on 1 analyzed binary loop (libggml-cpu.so - 384)							Sum on 1 analyzed binary loop (libggml-cpu.so - 594)							Sum on 1 analyzed binary loop (libggml-cpu.so - 326)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
Loop Computation Issues							Loop Computation Issues							Loop Computation Issues							Loop Computation Issues
Presence of a large number of scalar integer instructions						1	Presence of a large number of scalar integer instructions						1	Presence of a large number of scalar integer instructions						1	Presence of a large number of scalar integer instructions						1
Data Access Issues							Data Access Issues							Data Access Issues							Data Access Issues
Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1
Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1
More than 20% of the loads are accessing the stack						1	More than 20% of the loads are accessing the stack						1	More than 20% of the loads are accessing the stack						1	More than 20% of the loads are accessing the stack						1
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1
Inefficient Vectorization							Inefficient Vectorization							Inefficient Vectorization							Inefficient Vectorization
Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1

▶ops.cpp: 6220 - 1.44 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5							Run aocc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6222 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6222 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions
1888	0.07	0.04	0.56	15.56	9.17	122.56	2113	0.05	0.03	0.47	1.96	6.62	250.15	1885	0.06	0.03	0.41	15.56	9.17	163.11

Sum on 1 analyzed binary loop (libggml-cpu.so - 1888)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2113)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1885)							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis						Count	Analysis						Count	Analysis						Count	Analysis	Count
Loop Computation Issues							Loop Computation Issues							Loop Computation Issues
Presence of expensive FP instructions						1	Presence of expensive FP instructions						1	Presence of expensive FP instructions						1
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1
Control Flow Issues							Control Flow Issues							Control Flow Issues
Presence of calls						1	Presence of calls						1	Presence of calls						1
Data Access Issues							Data Access Issues							Data Access Issues
More than 20% of the loads are accessing the stack						1	More than 20% of the loads are accessing the stack						1	More than 20% of the loads are accessing the stack						1
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of calls						1	Presence of calls						1	Presence of calls						1

▶ops.cpp: 8885 - 1.28 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5							Run aocc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
2254	0.09	0.02	0.27	0	6.25	0.34	2419	0.09	0.02	0.36	0	6.25	0.24	2199	0.09	0.02	0.27	0	6.25	0.34	1997	0.10	0.02	0.37	0	6.25	0.07

Sum on 1 analyzed binary loop (libggml-cpu.so - 2254)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2419)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2199)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1997)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
Loop Computation Issues							Loop Computation Issues							Loop Computation Issues							Loop Computation Issues
Presence of a large number of scalar integer instructions						1	Presence of a large number of scalar integer instructions						1	Presence of a large number of scalar integer instructions						1	Presence of a large number of scalar integer instructions						1
Data Access Issues							Data Access Issues							Data Access Issues							Data Access Issues
Presence of indirect access						1	Presence of indirect access						1	Presence of indirect access						1	Presence of indirect access						1
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of indirect access						1	Presence of indirect access						1	Presence of indirect access						1	Presence of indirect access						1

▶quants.c: 298 - 0.70 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5							Run aocc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404
3016	1.17	0.01	0.18	59.66	29.26	456.09	3307	1.04	0.01	0.18	58.33	28.75	511.87	2984	1.09	0.01	0.16	60.7	29.66	489.16	2730	1.03	0.01	0.18	60.7	29.66	508.19

Sum on 1 analyzed binary loop (libggml-cpu.so - 3016)							Sum on 1 analyzed binary loop (libggml-cpu.so - 3307)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2984)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2730)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
Loop Computation Issues							Loop Computation Issues							Loop Computation Issues							Loop Computation Issues
Presence of expensive FP instructions						1	Presence of expensive FP instructions						1	Presence of expensive FP instructions						1	Presence of expensive FP instructions						1
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						0	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						0	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						0
Control Flow Issues							Control Flow Issues							Control Flow Issues							Control Flow Issues
Presence of 2 to 4 paths						1	Presence of 2 to 4 paths						0	Presence of 2 to 4 paths						1	Presence of 2 to 4 paths						1
Presence of more than 4 paths						0	Presence of more than 4 paths						1	Presence of more than 4 paths						0	Presence of more than 4 paths						0
Data Access Issues							Data Access Issues							Data Access Issues							Data Access Issues
More than 10% of the vector loads instructions are unaligned						1	More than 10% of the vector loads instructions are unaligned						1	More than 10% of the vector loads instructions are unaligned						1	More than 10% of the vector loads instructions are unaligned						1
Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of 2 to 4 paths						1	Presence of 2 to 4 paths						0	Presence of 2 to 4 paths						1	Presence of 2 to 4 paths						1
Presence of more than 4 paths						0	Presence of more than 4 paths						1	Presence of more than 4 paths						0	Presence of more than 4 paths						0
Inefficient Vectorization							Inefficient Vectorization							Inefficient Vectorization							Inefficient Vectorization
Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1

▶ops.cpp: 6210 - 0.70 %

ASM Loop ID	GFLOP/s	ASM Loop ID	GFLOP/s	ASM Loop ID	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default		Run aocc_default		Run icx_5		Run aocc_6
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
						1808	0.07	0.04	0.70	2.27	7.95	223.11

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 1 analyzed binary loop (libggml-cpu.so - 1808)
Analysis	Count	Analysis	Count	Analysis	Count	Analysis						Count
						Loop Computation Issues
						Presence of expensive FP instructions						1
						Presence of a large number of scalar integer instructions						1
						Control Flow Issues
						Presence of calls						1
						Presence of more than 4 paths						1
						Data Access Issues
						More than 20% of the loads are accessing the stack						1
						Vectorization Roadblocks
						Presence of calls						1
						Presence of more than 4 paths						1
						Inefficient Vectorization
						Use of masked instructions						1

▶vec.h: 1084 - 0.46 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5							Run aocc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1115-1115 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373
1147	0.06	0.01	0.11	100	100	2677.48	1236	0.06	0.01	0.11	98	98.13	3028.94	1153	0.07	0.01	0.10	100	100	2832.04	1257	0.07	0.01	0.13	98	98.13	2706.91

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count

▶ggml-cpu.c: 3204 - 0.36 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run orig_default							Run aocc_default							Run icx_5		Run aocc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3207						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3207						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-004-0874/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3207
6	0.04	0.01	0.11	100	100	0	5	0.04	0.01	0.13	100	100	0.99			5	0.03	0.01	0.12	100	100	1.16

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis						Count	Analysis						Count	Analysis	Count	Analysis						Count

Report Configuration

Loops

▶mmq.cpp: 1140 - 38.89 %

▶vec.h: 491 - 4.19 %

▶vec.cpp: 311 - 2.72 %

▶<unknown>: 0 - 1.95 %

▶mmq.cpp: 303 - 1.79 %

▶ops.cpp: 6220 - 1.44 %

▶ops.cpp: 8885 - 1.28 %

▶quants.c: 298 - 0.70 %

▶ops.cpp: 6210 - 0.70 %

▶vec.h: 1084 - 0.46 %

▶ggml-cpu.c: 3204 - 0.36 %