OV - Compare Loops

Loops

▶sgemm.cpp: 138 - 197.98 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_8						Run icx_1
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-821 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 827-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 826-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-821					Loop Source Regions
2364	0.07	0.05	0.49	0	0	2688	0.08	0.05	0.57	0	0	1978	0.06	0.03	0.36	0	0
2373	8.32	6.10	65.93	0	0	2702	8.33	6.04	65.28	0	0	1987	8.28	6.03	65.33	0	0

Sum on 2 analyzed binary loops (libggml-cpu.so - 2364, libggml-cpu.so - 2373)						Sum on 2 analyzed binary loops (libggml-cpu.so - 2688, libggml-cpu.so - 2702)						Sum on 2 analyzed binary loops (libggml-cpu.so - 1978, libggml-cpu.so - 1987)						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

▶quants.c: 1066 - 76.31 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_8		Run icx_1
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1066-1073 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
						4223	8.30	7.22	76.31	88.89	20.14

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 - 4223)
Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count
						Loop Computation Issues
						Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
						Data Access Issues
						Presence of indirect access					1
						Presence of special instructions executing on a single port					1
						Vectorization Roadblocks
						Presence of indirect access					1
						Inefficient Vectorization
						Presence of special instructions executing on a single port					1

▶<unknown>: 0 - 1.13 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_8						Run icx_1
Loop Source Regions						Loop Source Regions						Loop Source Regions						Loop Source Regions
2640	0.00	0.00	0.00	0	0	2395	0.01	0.00	0.00	0	0	1075	0.00	0.00	0.00	0	0	4515	0.00	0.00	0.00	0	0
1126	0.00	0.00	0.00	0	0	2289	0.00	0.00	0.00	0	0	2300	0.00	0.00	0.00	0	0	4524	0.00	0.00	0.00	0	0
2513	0.00	0.00	0.00	0	0	2294	0.01	0.00	0.00	0	0	2392	0.02	0.00	0.00	0	0	4518	0.02	0.00	0.00	0	0
2638	0.00	0.00	0.00	0	0	2504	0.00	0.00	0.00	0	0	324	0.00	0.00	0.00	0	0	4335	0.00	0.00	0.00	0	0
2741	0.01	0.00	0.00	0	0	1947	0.02	0.00	0.00	0	0	2492	0.00	0.00	0.00	0	0	729	0.02	0.00	0.05	0	0
765	0.09	0.00	0.01	0	0	1948	0.00	0.00	0.00	0	0	2305	0.01	0.00	0.00	0	0	3862	0.01	0.00	0.00	0	0
484	0.02	0.00	0.00	0	0	444	0.07	0.00	0.02	0	0	767	0.09	0.00	0.01	0	0	1768	0.04	0.00	0.01	0	0
90	0.01	0.00	0.01	0	0	114	0.02	0.00	0.02	0	0	64	0.01	0.00	0.00	0	0	759	0.03	0.00	0.01	0	0
398	0.07	0.00	0.01	0	0	124	0.02	0.01	0.07	0	0	1259	0.02	0.00	0.02	0	0	115	0.02	0.01	0.08	0	0
85	0.01	0.00	0.00	0	0	108	0.01	0.00	0.00	0	0	1431	0.02	0.00	0.03	0	0	3825	0.01	0.00	0.02	0	0
1704	0.01	0.00	0.00	0	0	2099	0.02	0.00	0.03	0	0	1426	0.01	0.00	0.00	0	0	3812	0.01	0.00	0.00	0	0
5	0.01	0.00	0.01	0	0	6	0.01	0.00	0.01	0	0	1	0.01	0.00	0.00	0	0	125	0.02	0.00	0.01	0	0
1462	0.04	0.01	0.09	0	0	1418	0.03	0.00	0.01	0	0	1181	0.00	0.00	0.00	0	0	1023	0.01	0.00	0.00	0	0
1456	0.01	0.00	0.02	0	0	1707	0.01	0.00	0.01	0	0	5	0.01	0.00	0.01	0	0	3808	0.00	0.00	0.00	0	0
87	0.01	0.00	0.00	0	0	873	0.07	0.00	0.02	0	0	1087	0.00	0.00	0.00	0	0	127	0.02	0.00	0.03	0	0
358	0.00	0.00	0.00	0	0	558	0.01	0.00	0.00	0	0	435	0.03	0.00	0.01	0	0	144	0.02	0.01	0.08	0	0
1196	0.00	0.00	0.00	0	0	2111	0.00	0.00	0.00	0	0	69	0.01	0.00	0.02	0	0	654	0.01	0.00	0.01	0	0
1195	0.03	0.00	0.01	0	0	1412	0.00	0.00	0.00	0	0	1976	0.01	0.00	0.00	0	0	2710	0.02	0.00	0.00	0	0
99	0.02	0.01	0.06	0	0	401	0.01	0.00	0.00	0	0	1452	0.01	0.00	0.00	0	0	3142	0.02	0.00	0.05	0	0
1709	0.01	0.00	0.03	0	0	1734	0.02	0.01	0.06	0	0	78	0.03	0.01	0.06	0	0	3	0.02	0.00	0.02	0	0
1730	0.01	0.00	0.00	0	0	112	0.01	0.00	0.00	0	0	66	0.01	0.00	0.00	0	0	119	0.01	0.00	0.00	0	0
						113	0.00	0.00	0.00	0	0	355	0.04	0.00	0.01	0	0	121	0.01	0.00	0.00	0	0
												317	0.01	0.00	0.01	0	0	3118	0.02	0.00	0.02	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

▶vec.h: 508 - 0.78 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_8		Run icx_1
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-389 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 508-509 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
						3822	0.16	0.07	0.78	85.05	20.79

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 - 3822)
Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count
						Loop Computation Issues
						Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
						Data Access Issues
						Presence of indirect access					1
						Presence of special instructions executing on a single port					1
						Vectorization Roadblocks
						Presence of indirect access					1
						Inefficient Vectorization
						Presence of special instructions executing on a single port					1

▶vec.cpp: 331 - 0.71 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_8		Run icx_1
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 331-332 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
						1754	0.16	0.07	0.71	5.88	8.82

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 - 1754)
Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count
						Loop Computation Issues
						Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
						Data Access Issues
						Presence of indirect access					1
						Vectorization Roadblocks
						Presence of indirect access					1

▶vec.h: 491 - 0.50 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_8						Run icx_1
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497					Loop Source Regions
1723	0.05	0.02	0.17	100	75	2109	0.07	0.01	0.16	100	75	1445	0.06	0.02	0.17	100	75

Sum on 1 analyzed binary loop (libggml-cpu.so - 1723)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2109)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1445)						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

▶quants.c: 298 - 0.44 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_8						Run icx_1
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355					Loop Source Regions
2527	0.04	0.01	0.15	58.66	28.88	2918	0.04	0.01	0.15	59.66	29.26	2115	0.04	0.01	0.14	60.7	29.66

Sum on 1 analyzed binary loop (libggml-cpu.so - 2527)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2918)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2115)						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					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
Presence of 2 to 4 paths					1	Presence of 2 to 4 paths					1	Presence of 2 to 4 paths					1
Data Access Issues						Data Access Issues						Data Access Issues
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
Presence of 2 to 4 paths					1	Presence of 2 to 4 paths					1	Presence of 2 to 4 paths					1
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

▶vec.cpp: 311 - 0.38 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_8						Run icx_1
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316					Loop Source Regions
761	0.05	0.01	0.13	100	66.67	866	0.05	0.01	0.13	100	66.67	759	0.05	0.01	0.12	100	66.67

Sum on 1 analyzed binary loop (libggml-cpu.so - 761)						Sum on 1 analyzed binary loop (libggml-cpu.so - 866)						Sum on 1 analyzed binary loop (libggml-cpu.so - 759)						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
Low iteration count						Low iteration count					1	Low iteration count
Control Flow Issues						Control Flow Issues						Control Flow Issues
Low iteration count						Low iteration count					1	Low iteration count

▶ops.cpp: 6210 - 0.12 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_8						Run icx_1
Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz17.benchmarkcenter.megware.com/176-976-6329/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions
				1262	0.04	0.01	0.12	5.56	7.29

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 - 1262)						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
				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
				Presence of special instructions executing on a single port					1
				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
				Presence of special instructions executing on a single port					1
				Use of masked instructions					1

Report Configuration

Loops

▶sgemm.cpp: 138 - 197.98 %

▶quants.c: 1066 - 76.31 %

▶<unknown>: 0 - 1.13 %

▶vec.h: 508 - 0.78 %

▶vec.cpp: 331 - 0.71 %

▶vec.h: 491 - 0.50 %

▶quants.c: 298 - 0.44 %

▶vec.cpp: 311 - 0.38 %

▶ops.cpp: 6210 - 0.12 %