OV - Compare Loops

Loops

▶mmq.cpp: 959 - 160.26 %

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	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 gcc_default		Run aocc_default							Run icx_1							Run gcc_6		Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 959-963 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1091-1095 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1103-1104 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 2096-2101						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 959-963 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1091-1095 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1103-1104 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 2056-2057 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 2096-2101						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 959-963 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1091-1095 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1103-1104 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 2096-2101						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 959-963 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1091-1095 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1103-1104 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 2056-2057 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 2096-2101
659	1.83	2.01	38.97	0	0	636.79			770	1.92	2.04	39.78	0	0	630.58	670	1.75	2.16	39.80	0	0	590.68			771	1.76	2.04	40.49	0	0	628.87
658	0.06	0.03	0.58	0	0	208.41										669	0.07	0.03	0.63	0	0	205.7

Sum on 2 analyzed binary loops (libggml-cpu.so - 659, libggml-cpu.so - 658)							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 - 770)							Sum on 2 analyzed binary loops (libggml-cpu.so - 670, libggml-cpu.so - 669)							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 - 771)
Analysis						Count	Analysis	Count	Analysis						Count	Analysis						Count	Analysis	Count	Analysis						Count
Control Flow Issues									Control Flow Issues							Control Flow Issues									Control Flow Issues
Presence of 2 to 4 paths									Presence of 2 to 4 paths						1	Presence of 2 to 4 paths									Presence of 2 to 4 paths						1
Vectorization Roadblocks									Vectorization Roadblocks							Vectorization Roadblocks									Vectorization Roadblocks
Presence of 2 to 4 paths									Presence of 2 to 4 paths						1	Presence of 2 to 4 paths									Presence of 2 to 4 paths						1

▶mmq.cpp: 2056 - 44.62 %

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	ASM Loop ID	GFLOP/s
Run orig_default		Run gcc_default							Run aocc_default		Run icx_1		Run gcc_6		Run aocc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/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/avx512bwintrin.h: 1050-1050 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512bwintrin.h: 2932-2932 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 2056-2058 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 2096-2101 /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: 9458-9458 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 9491-9491 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 10653-10653 /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: 14192-14192 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 14946-14946 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 15160-15160						Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions
		569	1.79	2.23	44.62	0	0	568.99

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 - 569)							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
		Control Flow Issues
		Presence of 2 to 4 paths						1
		Vectorization Roadblocks
		Presence of 2 to 4 paths						1

▶simd-mappings.h: 130 - 4.39 %

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 gcc_default							Run aocc_default		Run icx_1		Run gcc_6							Run aocc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1093-1093 /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: 13848-13848 /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: 14946-14946						Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1093-1093 /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: 13848-13848 /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: 14946-14946						Loop Source Regions
		575	0.03	0.01	0.15	100	100	57.65					502	0.07	0.05	0.97	100	100	379.64
													499	0.08	0.05	0.97	100	100	165.24
													501	0.08	0.05	1.03	100	100	262.08
													500	0.10	0.06	1.27	100	100	706.02

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.		Sum on 4 analyzed binary loops (libggml-cpu.so - 502, libggml-cpu.so - 499, libggml-cpu.so - 501, libggml-cpu.so - 500)							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
													Data Access Issues
													Presence of constant non-unit stride data access						1
													Presence of indirect access						1
													Vectorization Roadblocks
													Presence of constant non-unit stride data access						1
													Presence of indirect access						1

▶vec.h: 491 - 3.05 %

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	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 gcc_default							Run aocc_default							Run icx_1							Run gcc_6		Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/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/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497
2269	0.07	0.03	0.67	0	0	156.59	1661	0.05	0.04	0.71	100	70	73.8	2437	0.06	0.02	0.48	0	0	162.18	2468	0.05	0.03	0.62	0	0	148.82			2445	0.05	0.03	0.56	0	0	213.53

Sum on 1 analyzed binary loop (libggml-cpu.so - 2269)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1661)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2437)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2468)							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 - 2445)
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
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
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						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

▶<unknown>: 0 - 2.63 %

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 gcc_default							Run aocc_default							Run icx_1							Run gcc_6							Run aocc_3
Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions
2504	0.01	0.00	0.00	0	0	0	2750	0.02	0.00	0.01	0	0	0	2485	0.01	0.00	0.00	0	0	0	2519	0.01	0.00	0.00	0	0	0	2491	0.01	0.00	0.00	0	0	0	2906	0.01	0.00	0.00	0	0	0
2294	0.01	0.00	0.00	0	0	0	2807	0.01	0.00	0.00	0	0	0	2640	0.01	0.00	0.00	0	0	0	2409	0.01	0.00	0.00	0	0	0	1210	0.00	0.00	0.00	0	0	0	2804	0.01	0.00	0.00	0	0	0
1955	0.03	0.01	0.19	100	50	0.98	2808	0.00	0.00	0.00	0	0	0	2741	0.01	0.00	0.00	0	0	0	2412	0.01	0.00	0.00	0	0	0	2563	0.00	0.00	0.00	0	0	0	2647	0.01	0.00	0.00	0	0	0
368	0.00	0.00	0.00	0	0	0	3308	0.00	0.00	0.00	0	0	0	376	0.00	0.00	0.00	0	0	0	1968	0.03	0.01	0.17	100	50	3.67	2675	0.00	0.00	0.00	0	0	0	333	0.00	0.00	0.01	0	0	0
1611	0.02	0.00	0.05	0	0	45.05	3021	0.00	0.00	0.00	0	0	0	765	0.01	0.00	0.04	0	0	800.05	377	0.01	0.00	0.00	0	0	0	2808	0.00	0.00	0.00	0	0	0	765	0.01	0.00	0.04	0	0	55.99
527	0.01	0.00	0.00	0	0	0	2810	0.01	0.00	0.00	0	0	0	396	0.01	0.00	0.03	0	0	0	2031	0.01	0.00	0.08	0	0	111.43	2417	0.00	0.00	0.00	0	0	0	2035	0.01	0.00	0.01	0	0	0
422	0.00	0.00	0.00	0	0	0	2909	0.00	0.00	0.00	0	0	0	108	0.01	0.00	0.01	0	0	0	1765	0.01	0.00	0.04	0	0	34.37	2416	0.00	0.00	0.00	0	0	0	580	0.00	0.00	0.00	0	0	0
526	0.01	0.00	0.00	0	0	0	2914	0.00	0.00	0.00	0	0	0	2105	0.02	0.00	0.08	0	0	207.32	689	0.01	0.00	0.03	0	0	0	2677	0.01	0.00	0.00	0	0	0	397	0.01	0.00	0.02	0	0	0
678	0.01	0.00	0.02	0	0	0	3041	0.01	0.00	0.00	0	0	0	579	0.00	0.00	0.00	0	0	0	423	0.00	0.00	0.00	0	0	0	2575	0.00	0.00	0.00	0	0	0	584	0.00	0.00	0.00	0	0	0
539	0.00	0.00	0.00	0	0	0	1385	0.00	0.00	0.01	0	0	0	2441	0.00	0.00	0.00	0	0	0	687	0.01	0.00	0.06	0	0	0	2568	0.01	0.00	0.00	0	0	0	766	0.02	0.00	0.03	0	0	854.04
538	0.01	0.00	0.00	0	0	0	483	0.01	0.00	0.04	0	0	0	394	0.01	0.00	0.04	0	0	0	1927	0.01	0.00	0.01	0	0	0	2620	0.01	0.00	0.00	0	0	0	395	0.01	0.00	0.03	0	0	0
1773	0.01	0.00	0.01	0	0	0	1676	0.01	0.00	0.01	0	0	24.69	1970	0.01	0.00	0.01	0	0	0	539	0.01	0.00	0.00	0	0	0	332	0.01	0.00	0.01	0	0	0	2449	0.00	0.00	0.00	0	0	3.62
146	0.01	0.00	0.01	0	0	0	577	0.00	0.00	0.00	0	0	0	764	0.01	0.00	0.05	0	0	34.32	660	0.02	0.00	0.08	0	0	646.45	585	0.01	0.00	0.02	0	0	337.09	108	0.00	0.00	0.01	0	0	1.45
2256	0.01	0.00	0.02	0	0	33.85	1663	0.00	0.00	0.00	0	0	62.5	2419	0.03	0.00	0.09	0	0	0.42	540	0.01	0.00	0.01	0	0	0	591	0.00	0.00	0.00	0	0	0	2418	0.01	0.00	0.02	0	0	7.68
676	0.01	0.00	0.06	0	0	0	330	0.00	0.00	0.00	0	0	0	2410	0.01	0.00	0.01	0	0	15.69	146	0.01	0.00	0.01	0	0	0	417	0.01	0.00	0.02	0	0	0	581	0.00	0.00	0.00	0	0	0
656	0.01	0.00	0.06	0	0	720.61	71	0.01	0.00	0.02	0	0	0	580	0.00	0.00	0.00	0	0	0	2456	0.01	0.00	0.04	0	0	12.61	1737	0.01	0.00	0.00	0	0	0	2131	0.02	0.00	0.06	0	0	105.68
2271	0.01	0.00	0.06	0	0	0.63	456	0.00	0.00	0.01	0	0	0	313	0.01	0.00	0.00	0	0	0	2471	0.01	0.00	0.07	0	0	9.49	1375	0.01	0.00	0.01	0	0	0	377	0.00	0.00	0.00	0	0	0
1869	0.01	0.00	0.07	0	0	114.73	485	0.01	0.00	0.03	0	0	0															1644	0.01	0.00	0.01	0	0	0
							988	0.02	0.00	0.07	0	0	103.17															584	0.01	0.00	0.01	0	0	249.27
							555	0.01	0.00	0.02	0	0	0															457	0.00	0.00	0.00	0	0	0
							561	0.00	0.00	0.00	0	0	111.11															1632	0.01	0.00	0.03	0	0	298.3
							1319	0.02	0.00	0.09	0	0	52.91															59	0.01	0.00	0.03	0	0	0
							576	0.02	0.00	0.09	0	0	599.62															494	0.01	0.00	0.04	0	0	0
							468	0.00	0.00	0.00	0	0	0															497	0.01	0.00	0.02	0	0	0
																												594	0.01	0.00	0.04	0	0	54.53
																												593	0.01	0.00	0.03	0	0	692.51
																												964	0.01	0.00	0.06	0	0	212.52
																												586	0.01	0.00	0.02	0	0	210.84
																												583	0.01	0.00	0.02	0	0	347

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 - 2.44 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	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 gcc_default							Run aocc_default							Run icx_1							Run gcc_6							Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326
1616	0.04	0.02	0.44	0	7.81	41.38	1320	0.05	0.02	0.44	0	7.81	42.03	1759	0.06	0.02	0.44	0	7.81	44.13	1770	0.04	0.02	0.39	0	7.81	43.71	1313	0.04	0.02	0.44	0	7.81	43.07	1823	0.04	0.01	0.29	100	31.25	58.67

Sum on 1 analyzed binary loop (libggml-cpu.so - 1616)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1320)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1759)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1770)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1313)							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							Loop Computation Issues							Loop Computation Issues							Loop Computation Issues
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1	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

▶mmq.cpp: 303 - 2.02 %

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	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 gcc_default		Run aocc_default							Run icx_1							Run gcc_6		Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-326 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 557-558 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 617-617 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 624-625 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 636-636 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 644-644 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 792-792 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 557-558 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 617-617 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 624-625 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 632-636 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 644-644 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 792-792 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-326 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 557-558 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 617-617 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 624-625 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 636-636 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 644-644 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 792-792 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 557-558 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 617-617 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 624-625 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 632-636 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 644-644 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 792-792 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392
661	0.04	0.03	0.50	91.67	35.76	0			379	0.05	0.03	0.53	94.96	35.16	0	672	0.04	0.03	0.48	91.89	36.15	0			380	0.04	0.03	0.51	94.96	35.16	0

Sum on 1 analyzed binary loop (libggml-cpu.so - 661)							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 - 379)							Sum on 1 analyzed binary loop (libggml-cpu.so - 672)							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 - 380)
Analysis						Count	Analysis	Count	Analysis						Count	Analysis						Count	Analysis	Count	Analysis						Count
Data Access Issues									Data Access Issues							Data Access Issues									Data Access Issues
Presence of constant non-unit stride data access						1			Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1			Presence of constant non-unit stride data access						1
Presence of indirect access						1			Presence of indirect access						1	Presence of indirect access						1			Presence of indirect access						1
Presence of special instructions executing on a single port						1			Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1			Presence of special instructions executing on a single port						1
More than 20% of the loads are accessing the stack						1			More than 20% of the loads are accessing the stack						1	More than 20% of the loads are accessing the stack						1			More than 20% of the loads are accessing the stack						1
Vectorization Roadblocks									Vectorization Roadblocks							Vectorization Roadblocks									Vectorization Roadblocks
Presence of constant non-unit stride data access						1			Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1			Presence of constant non-unit stride data access						1
Presence of indirect access						1			Presence of indirect access						1	Presence of indirect access						1			Presence of indirect access						1
Inefficient Vectorization									Inefficient Vectorization							Inefficient Vectorization									Inefficient Vectorization
Presence of special instructions executing on a single port						1			Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1			Presence of special instructions executing on a single port						1

▶quants.c: 298 - 1.98 %

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 gcc_default							Run aocc_default							Run icx_1							Run gcc_6							Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355						Loop Source Regions	/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 /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 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/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/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 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-298 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 319-321						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/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/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355						Loop Source Regions	/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 /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 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/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/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 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-298 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 319-321						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 353-355
3022	1.15	0.02	0.31	59.66	29.26	341.18	2212	1.15	0.02	0.33	60	28.75	332.59	3307	1.40	0.02	0.40	58.33	28.75	269.64	3269	1.10	0.02	0.29	60.7	29.66	343.47	2181	1.11	0.02	0.33	59.65	29.28	333.9	3328	1.13	0.02	0.31	60.7	29.66	350.12

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 - 2212)							Sum on 1 analyzed binary loop (libggml-cpu.so - 3307)							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 - 2181)							Sum on 1 analyzed binary loop (libggml-cpu.so - 3328)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
							Loop Computation Issues							Loop Computation Issues														Loop Computation Issues							Loop Computation Issues
							Presence of expensive FP instructions						1	Presence of expensive FP instructions						1								Presence of expensive FP instructions						1	Presence of expensive FP instructions						1
							Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						0	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1								Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						0	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						0
							Control Flow Issues							Control Flow Issues														Control Flow Issues							Control Flow Issues
							Presence of 2 to 4 paths						0	Presence of 2 to 4 paths						0								Presence of 2 to 4 paths						0	Presence of 2 to 4 paths						1
							Presence of more than 4 paths						1	Presence of more than 4 paths						1								Presence of more than 4 paths						1	Presence of more than 4 paths						0
							Data Access Issues							Data Access Issues														Data Access Issues							Data Access Issues
							More than 10% of the vector loads instructions are unaligned						1	More than 10% of the vector loads instructions are unaligned						1								More than 10% of the vector loads instructions are unaligned						1	More than 10% of the vector loads instructions are unaligned						1
							Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1								Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1
							Vectorization Roadblocks							Vectorization Roadblocks														Vectorization Roadblocks							Vectorization Roadblocks
							Presence of 2 to 4 paths						0	Presence of 2 to 4 paths						0								Presence of 2 to 4 paths						0	Presence of 2 to 4 paths						1
							Presence of more than 4 paths						1	Presence of more than 4 paths						1								Presence of more than 4 paths						1	Presence of more than 4 paths						0
							Inefficient Vectorization							Inefficient Vectorization														Inefficient Vectorization							Inefficient Vectorization
							Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1								Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1

▶vec.cpp: 311 - 1.89 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	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 gcc_default							Run aocc_default							Run icx_1							Run gcc_6							Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/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/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/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/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316
1146	0.04	0.02	0.33	0	0	313.85	957	0.05	0.02	0.42	100	66.67	130.52	1233	0.04	0.02	0.30	0	0	270.58	1205	0.04	0.01	0.20	0	0	331.54	944	0.04	0.01	0.26	100	66.67	409.78	1292	0.04	0.02	0.39	0	0	259.5

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 - 957)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1233)							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 - 1292)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
							Data Access Issues							Data Access Issues																					Data Access Issues
							Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access																					Presence of constant non-unit stride data access
							Vectorization Roadblocks							Vectorization Roadblocks																					Vectorization Roadblocks
							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

▶ops.cpp: 6220 - 1.63 %

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	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 gcc_default		Run aocc_default							Run icx_1							Run gcc_6		Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6222 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6222 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6229 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
1894	0.03	0.02	0.36	15.56	9.17	229.65			2113	0.05	0.03	0.52	1.96	6.62	243.36	2064	0.03	0.02	0.32	15.56	9.17	257.53			2139	0.05	0.02	0.43	0	6.25	304.15

Sum on 1 analyzed binary loop (libggml-cpu.so - 1894)							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 - 2113)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2064)							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 - 2139)
Analysis						Count	Analysis	Count	Analysis						Count	Analysis						Count	Analysis	Count	Analysis						Count
Loop Computation Issues									Loop Computation Issues							Loop Computation Issues									Loop Computation Issues
Presence of expensive FP instructions						1			Presence of expensive FP instructions						1	Presence of expensive FP instructions						1			Presence of expensive FP instructions						1
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1			Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1			Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						1
Control Flow Issues									Control Flow Issues							Control Flow Issues									Control Flow Issues
Presence of calls						1			Presence of calls						1	Presence of calls						1			Presence of calls						1
Data Access Issues									Data Access Issues							Data Access Issues									Data Access Issues
Presence of constant non-unit stride data access						0			Presence of constant non-unit stride data access						0	Presence of constant non-unit stride data access						1			Presence of constant non-unit stride data access						0
More than 20% of the loads are accessing the stack						1			More than 20% of the loads are accessing the stack						1	More than 20% of the loads are accessing the stack						1			More than 20% of the loads are accessing the stack						1
Vectorization Roadblocks									Vectorization Roadblocks							Vectorization Roadblocks									Vectorization Roadblocks
Presence of calls						1			Presence of calls						1	Presence of calls						1			Presence of calls						1
Presence of constant non-unit stride data access						0			Presence of constant non-unit stride data access						0	Presence of constant non-unit stride data access						1			Presence of constant non-unit stride data access						0

▶vec.h: 1084 - 1.63 %

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	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 gcc_default		Run aocc_default							Run icx_1							Run gcc_6		Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1115-1115
1153	0.04	0.02	0.37	100	100	1016.65			1237	0.08	0.02	0.45	98	98.13	758.6	1212	0.04	0.02	0.41	100	100	853.94			1302	0.06	0.02	0.40	98	98.13	897.95

Sum on 1 analyzed binary loop (libggml-cpu.so - 1153)							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 - 1237)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1212)							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 - 1302)
Analysis						Count	Analysis	Count	Analysis						Count	Analysis						Count	Analysis	Count	Analysis						Count
Loop Computation Issues									Loop Computation Issues							Loop Computation Issues									Loop Computation Issues
Presence of expensive FP instructions						1			Presence of expensive FP instructions						1	Presence of expensive FP instructions						1			Presence of expensive FP instructions						1
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						1			Presence of 2 to 4 paths						1
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						1	Presence of constant non-unit stride data access									Presence of constant non-unit stride data access						1
Presence of special instructions executing on a single port									Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port									Presence of special instructions executing on a single port						1
Vectorization Roadblocks									Vectorization Roadblocks							Vectorization Roadblocks									Vectorization Roadblocks
Presence of 2 to 4 paths						1			Presence of 2 to 4 paths						1	Presence of 2 to 4 paths						1			Presence of 2 to 4 paths						1
Presence of constant non-unit stride data access						0			Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						0			Presence of constant non-unit stride data access						1
Inefficient Vectorization									Inefficient Vectorization							Inefficient Vectorization									Inefficient Vectorization
Presence of special instructions executing on a single port						0			Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						0			Presence of special instructions executing on a single port						1
Use of masked instructions						1			Use of masked instructions						1	Use of masked instructions						1			Use of masked instructions						1

▶binary-ops.cpp: 18 - 1.60 %

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 gcc_default							Run aocc_default							Run icx_1							Run gcc_6							Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
839	0.03	0.01	0.28	0	6.25	31.65	714	0.03	0.01	0.29	100	50	31.11	915	0.03	0.01	0.23	0	6.25	41.91	877	0.04	0.01	0.26	0	6.25	33.2	698	0.03	0.01	0.28	0	6.25	33.97	916	0.03	0.01	0.26	0	6.25	33.22

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 - 714)							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
							Data Access Issues
							More than 10% of the vector loads instructions are unaligned						1

▶ggml-cpu.c: 3204 - 1.38 %

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 gcc_default							Run aocc_default							Run icx_1							Run gcc_6							Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3207						Loop Source Regions	/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: 9376-9376 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 11216-11216 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3204						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3207						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3207						Loop Source Regions	/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: 9376-9376 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 11216-11216 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3204						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3207
6	0.04	0.01	0.19	100	100	0	5	0.03	0.01	0.28	100	83.33	0	5	0.04	0.01	0.22	100	100	0	6	0.03	0.01	0.18	100	100	0	3	0.04	0.01	0.26	100	83.33	0	5	0.04	0.01	0.24	100	100	1.31

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

▶binary-ops.cpp: 10 - 1.01 %

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	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 gcc_default							Run aocc_default							Run icx_1							Run gcc_6							Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
725	0.03	0.01	0.17	0	6.25	45.8	632	0.02	0.01	0.18	100	50	29.33	817	0.05	0.01	0.18	0	6.25	35.28	741	0.02	0.01	0.17	0	6.25	49.71	626	0.02	0.01	0.19	0	6.25	45.78	818	0.02	0.01	0.12	0	6.25	53.19

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.cpp: 372 - 0.96 %

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 gcc_default							Run aocc_default		Run icx_1		Run gcc_6							Run aocc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-372 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1101-1101 /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/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-372 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1101-1101 /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
		961	0.05	0.02	0.48	100	100	800.88					946	0.04	0.02	0.48	100	100	781.52

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 - 961)							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 - 946)							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
		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
		Presence of constant non-unit stride data access						0					Presence of constant non-unit stride data access						1
		Presence of special instructions executing on a single port						1					Presence of special instructions executing on a single port						1
		Vectorization Roadblocks											Vectorization Roadblocks
		Presence of 2 to 4 paths						1					Presence of 2 to 4 paths						1
		Presence of constant non-unit stride data access						0					Presence of constant non-unit stride data access						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

▶ops.cpp: 6210 - 0.77 %

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	ASM Loop ID	GFLOP/s
Run orig_default		Run gcc_default							Run aocc_default		Run icx_1		Run gcc_6		Run aocc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions
		994	0.07	0.04	0.77	19.61	9.8	277.41

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 - 994)							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
		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

▶ops.cpp: 8885 - 0.75 %

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 gcc_default							Run aocc_default		Run icx_1							Run gcc_6							Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886
2260	0.02	0.01	0.11	0	6.25	0.36	1673	0.03	0.01	0.17	0	6.25	0.53			2460	0.03	0.01	0.13	0	6.25	0.36	1641	0.03	0.01	0.19	0	6.25	0.36	2427	0.03	0.01	0.14	0	6.25	0.62

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: 6238 - 0.58 %

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 gcc_default		Run aocc_default		Run icx_1		Run gcc_6							Run aocc_3
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions
								958	0.04	0.03	0.58	6.25	8.2	204.2

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.		Sum on 1 analyzed binary loop (libggml-cpu.so - 958)							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
								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
								Control Flow Issues
								Presence of calls						1
								Data Access Issues
								More than 20% of the loads are accessing the stack						1
								Vectorization Roadblocks
								Presence of calls						1
								Presence of more than 4 paths						1

▶vec.h: 677 - 0.34 %

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	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 gcc_default		Run aocc_default							Run icx_1		Run gcc_6							Run aocc_3
Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 677-682						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 677-677 /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: 13848-13848						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 677-682
				1760	0.02	0.01	0.11	100	100	37.1			1312	0.02	0.01	0.13	100	100	40.11	1824	0.02	0.01	0.11	100	100	39.55

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: 8817 - 0.27 %

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	ASM Loop ID	GFLOP/s
Run orig_default		Run gcc_default							Run aocc_default		Run icx_1		Run gcc_6		Run aocc_3
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8817-8819						Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions
		1671	0.03	0.01	0.27	0	9.38	57.43

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

▶mmq.cpp: 2096 - 0.23 %

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 gcc_default		Run aocc_default		Run icx_1		Run gcc_6							Run aocc_3
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 2096-2101						Loop Source Regions
								588	0.03	0.01	0.23	42.31	23.56	5436.08

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

▶mmq.cpp: 1093 - 0.20 %

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	ASM Loop ID	GFLOP/s
Run orig_default							Run gcc_default		Run aocc_default		Run icx_1							Run gcc_6		Run aocc_3
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1093-1095 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1103-1104						Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1093-1095 /beegfs/hackathon/users/eoseret/qaas_runs_test/isix06.benchmarkcenter.megware.com/177-703-3988/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1103-1104						Loop Source Regions		Loop Source Regions
655	0.02	0.01	0.10	100	100	50.68					659	0.02	0.01	0.10	100	100	75.24

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

▶mmq.cpp: 959 - 160.26 %

▶mmq.cpp: 2056 - 44.62 %

▶simd-mappings.h: 130 - 4.39 %

▶vec.h: 491 - 3.05 %

▶<unknown>: 0 - 2.63 %

▶ops.cpp: 4325 - 2.44 %

▶mmq.cpp: 303 - 2.02 %

▶quants.c: 298 - 1.98 %

▶vec.cpp: 311 - 1.89 %

▶ops.cpp: 6220 - 1.63 %

▶vec.h: 1084 - 1.63 %

▶binary-ops.cpp: 18 - 1.60 %

▶ggml-cpu.c: 3204 - 1.38 %

▶binary-ops.cpp: 10 - 1.01 %

▶vec.cpp: 372 - 0.96 %

▶ops.cpp: 6210 - 0.77 %

▶ops.cpp: 8885 - 0.75 %

▶ops.cpp: 6238 - 0.58 %

▶vec.h: 677 - 0.34 %

▶ops.cpp: 8817 - 0.27 %

▶mmq.cpp: 2096 - 0.23 %

▶mmq.cpp: 1093 - 0.20 %