OV - Compare Loops

Loops

▶quants.c: 108 - 362.96 %

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	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 gcc_default							Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 108-109 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 129-131 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1033-1042 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 108-109 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 129-131 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1033-1042 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130						Loop Source Regions	/cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 628-628 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 108-108 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1033-1035 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/fmaintrin.h: 65-65 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 463-463 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 929-929 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 1329-1329						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 108-109 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 129-131 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1033-1042 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 108-109 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 129-131 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1033-1042 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130						Loop Source Regions	/cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 628-628 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 108-108 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 1033-1035 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/fmaintrin.h: 65-65 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 463-463 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 929-929 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 1329-1329
2866	56.92	37.42	61.72	0	0	54.14	2537	57.34	37.65	61.76	0	0	53.84	1989	52.07	33.64	58.45	0	0	60.31	2159	57.26	37.70	61.85	0	0	53.82	5766	56.87	37.54	61.71	0	0	53.96	1950	50.89	32.98	57.47	0	0	59.81

Sum on 1 analyzed binary loop (libggml-cpu.so - 2866)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2537)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1989)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2159)							Sum on 1 analyzed binary loop (libggml-cpu.so - 5766)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1950)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count

▶sgemm.cpp: 138 - 0.84 %

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	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 gcc_default		Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-821 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 827-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-821 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 826-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 138-138 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-821 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 827-846 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 966-966 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1044-1044						Loop Source Regions
2625	0.13	0.07	0.12	0	0	208.39	2364	0.14	0.07	0.12	0	0	200.87			2021	0.13	0.07	0.11	0	0	108.06	5300	0.13	0.07	0.11	0	0	224.01
2639	0.14	0.07	0.12	0	0	98.81	2373	0.15	0.08	0.13	0	0	91.5			2012	0.07	0.02	0.04	0	0	290.25	5326	0.13	0.07	0.11	0	0	103.91

Sum on 2 analyzed binary loops (libggml-cpu.so - 2625, libggml-cpu.so - 2639)							Sum on 2 analyzed binary loops (libggml-cpu.so - 2364, libggml-cpu.so - 2373)							No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 2 analyzed binary loops (libggml-cpu.so - 2021, libggml-cpu.so - 2012)							Sum on 2 analyzed binary loops (libggml-cpu.so - 5300, libggml-cpu.so - 5326)							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	Analysis						Count	Analysis	Count

▶sgemm.cpp: 818 - 0.37 %

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	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 gcc_default							Run aocc_7		Run icx_3		Run gcc_3
Loop Source Regions		Loop Source Regions		Loop Source Regions	/cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 628-628 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/xmmintrin.h: 204-204 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/f16cintrin.h: 48-48 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-819 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/emmintrin.h: 595-595 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/fmaintrin.h: 65-65 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 346-346 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 463-463 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 698-698 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 929-929						Loop Source Regions		Loop Source Regions		Loop Source Regions	/cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 628-628 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/xmmintrin.h: 204-204 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/f16cintrin.h: 48-48 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 818-819 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/llamafile/sgemm.cpp: 1038-1038 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/emmintrin.h: 595-595 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/fmaintrin.h: 65-65 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 346-346 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 463-463 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 698-698 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 929-929
				1618	0.11	0.05	0.10	0	0	263.21					1579	0.10	0.05	0.09	0	0	280.09
				1626	0.11	0.05	0.09	0	0	129.76					1587	0.10	0.05	0.09	0	0	129.7

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 2 analyzed binary loops (libggml-cpu.so - 1618, libggml-cpu.so - 1626)							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 2 analyzed binary loops (libggml-cpu.so - 1579, libggml-cpu.so - 1587)
Analysis	Count	Analysis	Count	Analysis						Count	Analysis	Count	Analysis	Count	Analysis						Count

▶<unknown>: 0 - 0.27 %

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	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 gcc_default							Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions
1197	0.01	0.00	0.00	0	0	0	2842	0.01	0.00	0.00	0	0	0	2810	0.02	0.00	0.00	0	0	0	1956	0.00	0.00	0.00	0	0	NA	4698	0.01	0.00	0.00	0	0	0	3133	0.01	0.00	0.00	0	0	0
2405	0.01	0.00	0.00	0	0	0	2640	0.01	0.00	0.00	0	0	0	2914	0.01	0.00	0.00	0	0	0	2417	0.01	0.00	0.00	0	0	0	3847	0.00	0.00	0.00	0	0	NA	1559	0.02	0.00	0.00	0	0	0
2299	0.01	0.00	0.00	0	0	0	2741	0.02	0.00	0.00	0	0	0	2573	0.01	0.00	0.00	0	0	0	2687	0.03	0.00	0.00	0	0	0	4100	0.01	0.00	0.00	0	0	9.51	2835	0.01	0.00	0.00	0	0	0
2404	0.01	0.00	0.00	0	0	0	2992	0.04	0.00	0.00	0	0	0	3308	0.01	0.00	0.00	0	0	0	1203	0.02	0.00	0.00	0	0	0	758	0.00	0.00	0.00	0	0	NA	3109	0.01	0.00	0.00	0	0	0
2208	0.01	0.00	0.00	0	0	0	1303	0.01	0.00	0.00	0	0	0	2943	0.03	0.00	0.00	0	0	0	315	0.02	0.00	0.00	0	0	0	13	0.01	0.00	0.00	0	0	0	2896	0.02	0.00	0.00	0	0	0
2516	0.01	0.00	0.00	0	0	0	317	0.00	0.00	0.00	0	0	NA	474	0.00	0.00	0.00	0	0	NA	64	0.01	0.00	0.00	0	0	2.65	245	0.02	0.00	0.01	0	0	0	2662	0.04	0.00	0.00	0	0	0
349	0.01	0.00	0.00	0	0	0	913	0.01	0.00	0.00	0	0	0	376	0.05	0.00	0.00	0	0	363.82	1271	0.02	0.00	0.00	0	0	117.87	806	0.03	0.00	0.00	0	0	0	72	0.03	0.01	0.01	0	0	0
2304	0.01	0.00	0.00	0	0	0	83	0.02	0.00	0.00	0	0	180.98	753	0.04	0.00	0.00	0	0	142.04	1580	0.00	0.00	0.00	0	0	NA	258	0.00	0.00	0.00	0	0	NA	1404	0.02	0.00	0.00	0	0	2340.2
1936	0.03	0.00	0.00	0	0	0	358	0.01	0.00	0.00	0	0	0	91	0.00	0.00	0.00	0	0	NA	1466	0.00	0.00	0.00	0	0	NA	5306	0.02	0.00	0.01	0	0	3240.97	1396	0.00	0.00	0.00	0	0	NA
2063	0.01	0.00	0.00	0	0	0	90	0.02	0.00	0.00	0	0	0	1087	0.00	0.00	0.00	0	0	NA	2010	0.01	0.00	0.00	0	0	857.56	4191	0.01	0.00	0.00	0	0	106.79	1411	0.02	0.00	0.00	0	0	433.98
23	0.01	0.00	0.00	0	0	0	85	0.01	0.00	0.00	0	0	3.97	466	0.05	0.00	0.00	0	0	507.44	1094	0.01	0.00	0.00	0	0	2048.71	243	0.01	0.00	0.00	0	0	0	1047	0.00	0.00	0.00	0	0	NA
114	0.02	0.00	0.00	0	0	0	1874	0.00	0.00	0.00	0	0	NA	88	0.01	0.00	0.00	0	0	0	1095	0.02	0.00	0.00	0	0	2572.79	4174	0.01	0.00	0.00	0	0	166.38	732	0.04	0.01	0.01	0	0	708.83
106	0.01	0.00	0.00	0	0	333.18	0	0.01	0.00	0.00	0	0	0	1088	0.05	0.00	0.00	0	0	706.03	71	0.01	0.00	0.00	0	0	0	237	0.01	0.00	0.00	0	0	233.77	89	0.01	0.00	0.00	0	0	0
2047	0.01	0.00	0.00	0	0	237.93	2366	0.02	0.00	0.01	0	0	3359.85	70	0.02	0.00	0.01	0	0	0	5	0.02	0.00	0.00	0	0	23.65	3406	0.04	0.00	0.00	0	0	47.16	726	0.02	0.00	0.00	0	0	123.52
124	0.06	0.02	0.03	0	0	50.55	1709	0.03	0.00	0.00	0	0	105.59	1437	0.00	0.00	0.00	0	0	NA	1440	0.03	0.00	0.00	0	0	7.32	239	0.02	0.00	0.00	0	0	4.13	5	0.03	0.00	0.00	0	0	23.75
108	0.03	0.00	0.00	0	0	1.7	1456	0.03	0.00	0.00	0	0	124.12	1449	0.02	0.00	0.00	0	0	13.68	2149	0.06	0.02	0.03	0	0	1.04	4179	0.02	0.00	0.00	0	0	358.37	1581	0.02	0.00	0.00	0	0	3950.76
6	0.01	0.00	0.00	0	0	5.29	87	0.01	0.00	0.00	0	0	0	55	0.02	0.00	0.00	0	0	5.74	62	0.01	0.00	0.00	0	0	224.58	2858	0.01	0.00	0.00	0	0	1519.37	1048	0.01	0.00	0.00	0	0	4658.03
1409	0.00	0.00	0.00	0	0	NA	5	0.01	0.00	0.00	0	0	4.33	5	0.02	0.00	0.00	0	0	6.78	1445	0.02	0.00	0.00	0	0	140.58								66	0.03	0.00	0.01	0	0	227.68
1681	0.02	0.00	0.00	0	0	67.94	1196	0.00	0.00	0.00	0	0	NA	66	0.02	0.00	0.00	0	0	0	69	0.02	0.00	0.00	0	0	0								57	0.02	0.00	0.00	0	0	5.05
1708	0.05	0.01	0.02	0	0	277.71	1704	0.05	0.00	0.00	0	0	7.94	1446	0.03	0.00	0.00	0	0	202.68	1193	0.01	0.00	0.00	0	0	0								430	0.00	0.00	0.00	0	0	NA
2064	0.01	0.00	0.00	0	0	190.43	1730	0.01	0.00	0.00	0	0	158.56	1444	0.03	0.00	0.00	0	0	2179.32	66	0.01	0.00	0.00	0	0	0								3139	0.01	0.00	0.00	0	0	0
556	0.03	0.00	0.00	0	0	641.98								1620	0.03	0.00	0.00	0	0	3839.13	1274	0.06	0.01	0.02	0	0	370.49
102	0.04	0.01	0.01	0	0	157.79								64	0.03	0.01	0.01	0	0	116.96	2015	0.02	0.00	0.00	0	0	4535.57
1415	0.05	0.00	0.00	0	0	1062.47								331	0.03	0.00	0.00	0	0	0
399	0.01	0.00	0.00	0	0	0								57	0.01	0.00	0.00	0	0	113.66
112	0.02	0.00	0.00	0	0	0
2629	0.02	0.00	0.00	0	0	4303.28
2052	0.03	0.00	0.00	0	0	239.97

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.							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	Analysis						Count	Analysis						Count

▶vec.h: 491 - 0.22 %

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	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 gcc_default							Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-491 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 935-935 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 11216-11216 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14192-14192 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 15160-15160						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-491 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 935-935 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 11216-11216 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14192-14192 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 15160-15160
2062	0.27	0.02	0.04	100	75	1564.38	1723	0.22	0.02	0.04	100	75	1781.82	1433	0.22	0.02	0.04	100	70	1583.82	1459	0.25	0.03	0.04	100	75	1606.01	4189	0.22	0.02	0.03	100	75	1486.96	1394	0.24	0.02	0.03	100	70	1616.69

Sum on 1 analyzed binary loop (libggml-cpu.so - 2062)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1723)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1433)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1459)							Sum on 1 analyzed binary loop (libggml-cpu.so - 4189)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1394)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
Data Access Issues							Data Access Issues							Data Access Issues							Data Access Issues							Data Access Issues							Data Access Issues
Presence of constant non-unit stride data access							Presence of constant non-unit stride data access							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							Presence of constant non-unit stride data access						1
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of constant non-unit stride data access							Presence of constant non-unit stride data access							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							Presence of constant non-unit stride data access						1

▶vec.cpp: 311 - 0.19 %

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	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 gcc_default							Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-311 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14192-14192 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 15160-15160						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-311 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14192-14192 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 15160-15160
864	0.18	0.02	0.04	100	66.67	752.21	761	0.17	0.02	0.03	100	66.67	1005.58	722	0.20	0.02	0.04	100	66.67	990.43	758	0.19	0.02	0.03	100	66.67	878.66	1779	0.24	0.02	0.04	100	66.67	700.95	698	0.13	0.01	0.02	100	66.67	968.8

Sum on 1 analyzed binary loop (libggml-cpu.so - 864)							Sum on 1 analyzed binary loop (libggml-cpu.so - 761)							Sum on 1 analyzed binary loop (libggml-cpu.so - 722)							Sum on 1 analyzed binary loop (libggml-cpu.so - 758)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1779)							Sum on 1 analyzed binary loop (libggml-cpu.so - 698)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
Loop Computation Issues							Loop Computation Issues							Loop Computation Issues							Loop Computation Issues							Loop Computation Issues							Loop Computation Issues
Low iteration count						1	Low iteration count							Low iteration count							Low iteration count							Low iteration count						1	Low iteration count
Control Flow Issues							Control Flow Issues							Control Flow Issues							Control Flow Issues							Control Flow Issues							Control Flow Issues
Low iteration count						1	Low iteration count							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							Data Access Issues							Data Access Issues
Presence of constant non-unit stride data access							Presence of constant non-unit stride data access							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							Presence of constant non-unit stride data access						1
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of constant non-unit stride data access							Presence of constant non-unit stride data access							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							Presence of constant non-unit stride data access						1

▶quants.c: 298 - 0.15 %

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	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 gcc_default							Run aocc_7		Run icx_3							Run gcc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/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/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/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/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 79-79 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 86-86 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 1046-1046 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-298 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 319-321 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/xmmintrin.h: 184-184 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/xmmintrin.h: 240-240 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/xmmintrin.h: 793-793 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/pmmintrin.h: 71-71 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 186-186 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 296-296 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 320-320 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 475-475 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 526-526 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 905-905 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 935-935 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 1066-1066 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 1329-1329 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 1472-1472						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/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/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 79-79 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 86-86 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx2intrin.h: 1046-1046 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-298 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 319-321 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/xmmintrin.h: 184-184 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/xmmintrin.h: 240-240 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/xmmintrin.h: 793-793 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/pmmintrin.h: 71-71 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 186-186 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 296-296 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 320-320 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 475-475 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 526-526 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 905-905 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 935-935 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 1066-1066 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avxintrin.h: 1329-1329
2855	0.08	0.02	0.03	60.7	29.66	0.43	2527	0.08	0.02	0.03	58.66	28.88	0.46	1982	0.07	0.02	0.03	66.67	31.25	0.46			5745	0.09	0.02	0.03	60.7	29.66	0.5	1943	0.08	0.02	0.03	59.65	29.28	0

Sum on 1 analyzed binary loop (libggml-cpu.so - 2855)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2527)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1982)							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 - 5745)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1943)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis	Count	Analysis						Count	Analysis						Count
Loop Computation Issues							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	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	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							Control Flow Issues
Presence of 2 to 4 paths						1	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						0
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 more than 4 paths						1
Data Access Issues							Data Access Issues							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			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							Vectorization Roadblocks
Presence of 2 to 4 paths						1	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						0
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 more than 4 paths						1
Inefficient Vectorization							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	Presence of special instructions executing on a single port						1

▶ggml-cpu.c: 1664 - 0.12 %

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	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 gcc_default							Run aocc_7		Run icx_3		Run gcc_3
Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2891						Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2891
				71	0.16	0.04	0.08	0	9.38	3.79					73	0.08	0.03	0.05	0	9.56	19.34

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 - 71)							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 - 73)
Analysis	Count	Analysis	Count	Analysis						Count	Analysis	Count	Analysis	Count	Analysis						Count
				Control Flow Issues											Control Flow Issues
				Presence of calls						1					Presence of calls						1
				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
				Vectorization Roadblocks											Vectorization Roadblocks
				Presence of calls						1					Presence of calls						1
				Presence of more than 4 paths						1					Presence of more than 4 paths						1

▶ggml-cpu.c: 533 - 0.12 %

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	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	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 gcc_default		Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2891						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2891						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-534 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2891						Loop Source Regions
		99	0.08	0.03	0.05	0	9.58	25.47			78	0.11	0.03	0.05	0	9.56	17.69	262	0.08	0.01	0.02	0	9.82	50.77

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 - 99)							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 - 78)							Sum on 1 analyzed binary loop (libggml-cpu.so - 262)							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	Analysis						Count	Analysis	Count
		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
		Presence of more than 4 paths						1			Presence of more than 4 paths						1	Presence of more than 4 paths						1

▶ggml-cpu.c: 1193 - 0.07 %

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	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	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 gcc_default		Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194						Loop Source Regions
		82	0.09	0.03	0.05	0	12.5	53.36			63	0.09	0.01	0.01	0	12.5	131.51	233	0.07	0.01	0.01	0	12.5	123.73

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 - 82)							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 - 63)							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	Analysis						Count	Analysis	Count
		Control Flow Issues									Control Flow Issues
		Presence of calls						1			Presence of calls						1
		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
		Vectorization Roadblocks									Vectorization Roadblocks
		Presence of calls						1			Presence of calls						1

▶ops.cpp: 6220 - 0.04 %

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	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	ASM Loop ID	GFLOP/s
Run orig_default		Run aocc_default							Run gcc_default		Run aocc_7		Run icx_3							Run gcc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions
		1462	0.07	0.01	0.02	6.67	7.5	369.05					3433	0.07	0.01	0.02	15.56	9.17	288.08

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 - 1462)							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 - 3433)							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	Analysis						Count	Analysis	Count
		Loop Computation Issues											Loop Computation Issues
		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
		Presence of a large number of scalar integer instructions						1					Presence of a large number of scalar integer instructions						0
		Control Flow Issues											Control Flow Issues
		Presence of calls						1					Presence of calls						1
		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
		Vectorization Roadblocks											Vectorization Roadblocks
		Presence of calls						1					Presence of calls						1

▶ops.cpp: 6210 - 0.03 %

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	ASM Loop ID	GFLOP/s	ASM Loop ID	GFLOP/s	ASM Loop ID	GFLOP/s
Run orig_default		Run aocc_default		Run gcc_default							Run aocc_7		Run icx_3		Run gcc_3
Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions		Loop Source Regions		Loop Source Regions
				759	0.07	0.02	0.03	19.23	9.74	163.9

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 - 759)							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	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

▶vec.h: 1084 - 0.01 %

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	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 gcc_default		Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1115-1115 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions
871	0.22	0.00	0.00	100	100	4099.26	765	0.20	0.00	0.00	98	98.13	4609.13			766	0.17	0.00	0.00	98	98.13	5283.19	1793	0.23	0.00	0.00	100	100	3681.88

Sum on 1 analyzed binary loop (libggml-cpu.so - 871)							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.							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	Analysis						Count	Analysis	Count
Loop Computation Issues
Presence of expensive FP instructions						1
Control Flow Issues
Presence of 2 to 4 paths						1
Data Access Issues
More than 10% of the vector loads instructions are unaligned						1
Vectorization Roadblocks
Presence of 2 to 4 paths						1
Inefficient Vectorization
Use of masked instructions						1

▶binary-ops.cpp: 10 - 0.01 %

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	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 gcc_default		Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
442	0.11	0.00	0.00	0	6.25	289.66	398	0.12	0.00	0.00	0	6.25	226.14			353	0.21	0.00	0.00	0	6.25	120.08	901	0.15	0.00	0.00	0	6.25	164.71	372	0.10	0.00	0.00	100	50	259.45

Sum on 1 analyzed binary loop (libggml-cpu.so - 442)							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.							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	Analysis						Count	Analysis						Count
Loop Computation Issues
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1

▶vec.cpp: 372 - 0.00 %

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	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 gcc_default							Run aocc_7		Run icx_3		Run gcc_3
Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1101-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-372 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 9376-9376 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 9402-9402 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 10660-10660 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13204-13204 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13607-13607 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13728-13728 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13788-13788 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13848-13848 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13908-13908 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14113-14113 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14192-14192 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14544-14544 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 15536-15536						Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1101-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-372 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 9376-9376 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 9402-9402 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 10660-10660 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13204-13204 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13607-13607 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13728-13728 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13788-13788 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13848-13848 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 13908-13908 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14113-14113 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14192-14192 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14544-14544 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 15536-15536
				726	0.17	0.00	0.00	100	100	5257.86					700	0.18	0.00	0.00	100	100	4375.96

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 - 726)							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 - 700)
Analysis	Count	Analysis	Count	Analysis						Count	Analysis	Count	Analysis	Count	Analysis						Count
				Loop Computation Issues											Loop Computation Issues
				Presence of expensive FP instructions						1					Presence of expensive FP instructions						1
				Control Flow Issues											Control Flow Issues
				Presence of 2 to 4 paths						1					Presence of 2 to 4 paths						1
				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
				Presence of special instructions executing on a single port						1					Presence of special instructions executing on a single port						1
				Vectorization Roadblocks											Vectorization Roadblocks
				Presence of 2 to 4 paths						1					Presence of 2 to 4 paths						1
				Inefficient Vectorization											Inefficient Vectorization
				Presence of special instructions executing on a single port						1					Presence of special instructions executing on a single port						1
				Use of masked instructions						1					Use of masked instructions						1

▶binary-ops.cpp: 18 - 0.00 %

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	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	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 gcc_default		Run aocc_7							Run icx_3							Run gcc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
		484	0.10	0.00	0.00	0	6.25	190.44			433	0.12	0.00	0.00	0	6.25	194.29	1149	0.08	0.00	0.00	0	6.25	356.35	454	0.06	0.00	0.00	100	50	360.35

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.							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	Analysis						Count	Analysis						Count

▶ops.cpp: 4325 - 0.00 %

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	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	ASM Loop ID	GFLOP/s
Run orig_default		Run aocc_default							Run gcc_default		Run aocc_7		Run icx_3							Run gcc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions
		1195	0.09	0.00	0.00	0	7.81	528.99					2864	0.09	0.00	0.00	0	7.81	554.33

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.		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	Analysis						Count	Analysis	Count

▶sampling.cpp: 125 - 0.00 %

ASM Loop ID	GFLOP/s	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	ASM Loop ID	GFLOP/s
Run orig_default		Run aocc_default		Run gcc_default		Run aocc_7		Run icx_3							Run gcc_3
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-950-2189/intel/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126						Loop Source Regions
								3924	0.07	0.00	0.00	33.33	8.33	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.		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	Analysis						Count	Analysis	Count

Report Configuration

Loops

▶quants.c: 108 - 362.96 %

▶sgemm.cpp: 138 - 0.84 %

▶sgemm.cpp: 818 - 0.37 %

▶<unknown>: 0 - 0.27 %

▶vec.h: 491 - 0.22 %

▶vec.cpp: 311 - 0.19 %

▶quants.c: 298 - 0.15 %

▶ggml-cpu.c: 1664 - 0.12 %

▶ggml-cpu.c: 533 - 0.12 %

▶ggml-cpu.c: 1193 - 0.07 %

▶ops.cpp: 6220 - 0.04 %

▶ops.cpp: 6210 - 0.03 %

▶vec.h: 1084 - 0.01 %

▶binary-ops.cpp: 10 - 0.01 %

▶vec.cpp: 372 - 0.00 %

▶binary-ops.cpp: 18 - 0.00 %

▶ops.cpp: 4325 - 0.00 %

▶sampling.cpp: 125 - 0.00 %