OV - Compare Loops

Loops

▶mmq.cpp: 1570 - 49.23 %

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 icx_2		Run aocc_4							Run gcc_6
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1570-1575 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1584-1584 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1590-1597						Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1570-1575 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1584-1584 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1590-1597						Loop Source Regions
		531	13.59	4.56	24.24	0	0	78.81					548	13.08	4.53	24.99	0	0	79.33

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 - 531)							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 - 548)							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: 1573 - 47.50 %

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 aocc_default		Run gcc_default		Run icx_2							Run aocc_4		Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1573-1575 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1584-1584 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1590-1597						Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1573-1575 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1584-1584 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1590-1597						Loop Source Regions		Loop Source Regions
451	11.24	4.21	23.83	0	0	85.42					442	12.89	4.50	23.67	0	0	79.92

Sum on 1 analyzed binary loop (libggml-cpu.so - 451)							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 - 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.
Analysis						Count	Analysis	Count	Analysis	Count	Analysis						Count	Analysis	Count	Analysis	Count

▶mmq.cpp: 1597 - 15.34 %

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	GFLOP/s	ASM Loop ID	GFLOP/s
Run orig_default		Run aocc_default		Run gcc_default							Run icx_2		Run aocc_4		Run gcc_6
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/avx512bwintrin.h: 1021-1021 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512vnniintrin.h: 41-41 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1597-1597 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/avx512fintrin.h: 4037-4037 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 4730-4730 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 7324-7324 /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
				408	10.98	4.15	15.34	87.67	85.7	85.89

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 - 408)							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
				Data Access Issues
				Presence of constant non-unit stride data access						1
				Presence of indirect access						1
				Presence of special instructions executing on a single port						1
				Vectorization Roadblocks
				Presence of constant non-unit stride data access						1
				Presence of indirect access						1
				Inefficient Vectorization
				Presence of special instructions executing on a single port						1

▶mmq.cpp: 1581 - 14.84 %

ASM Loop ID	GFLOP/s	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
Run orig_default		Run aocc_default		Run gcc_default		Run icx_2		Run aocc_4		Run gcc_6
Loop Source Regions		Loop Source Regions		Loop Source Regions		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/avx512bwintrin.h: 1021-1021 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512vnniintrin.h: 41-41 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1581-1581 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1597-1597 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/avx512fintrin.h: 4037-4037 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 4730-4730 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 7324-7324 /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
										387	10.91	4.09	14.84	95.52	62.97	87.73

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.		Sum on 1 analyzed binary loop (libggml-cpu.so - 387)
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
										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 constant non-unit stride data access						1
										Presence of indirect access						1
										Inefficient Vectorization
										Presence of special instructions executing on a single port						1

▶vec.h: 491 - 0.47 %

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	GFLOP/s
Run orig_default							Run aocc_default							Run gcc_default							Run icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497						Loop Source Regions
2188	0.17	0.02	0.12	0	0	1153.98	2437	0.18	0.02	0.08	0	0	881.41	1663	0.16	0.02	0.06	100	70	769.38	2344	0.19	0.02	0.12	0	0	1071.5	2304	0.13	0.02	0.08	0	0	917.75

Sum on 1 analyzed binary loop (libggml-cpu.so - 2188)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2437)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1663)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2344)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2304)							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							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							Presence of 2 to 4 paths						1
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
Vectorization Roadblocks							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						0	Presence of 2 to 4 paths							Presence of 2 to 4 paths						1
Presence of constant non-unit stride data access							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							Presence of constant non-unit stride data access						0

▶mmq.cpp: 303 - 0.43 %

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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 651-663 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 816-818 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 825-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 651-663 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 816-818 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 825-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 651-663 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 816-818 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 825-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 303-330 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 651-663 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 816-818 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 825-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392						Loop Source Regions
638	0.06	0.02	0.12	90.91	38.76	0	384	0.05	0.02	0.11	90.91	38.76	0			648	0.05	0.02	0.09	97.1	54.17	0	399	0.05	0.02	0.11	90.91	38.76	0

Sum on 1 analyzed binary loop (libggml-cpu.so - 638)							Sum on 1 analyzed binary loop (libggml-cpu.so - 384)							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 - 648)							Sum on 1 analyzed binary loop (libggml-cpu.so - 399)							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
Presence of a large number of scalar integer instructions						1	Presence of a large number of scalar integer instructions						1			Presence of a large number of scalar integer instructions							Presence of a large number of scalar integer instructions						1
Data Access Issues							Data Access Issues									Data Access Issues							Data Access Issues
Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1			Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1
Presence of indirect access						0	Presence of indirect access						0			Presence of indirect access						1	Presence of indirect access						0
Presence of expensive instructions: scatter/gather						0	Presence of expensive instructions: scatter/gather						0			Presence of expensive instructions: scatter/gather						1	Presence of expensive instructions: scatter/gather						0
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						0	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						0	Presence of indirect access						0			Presence of indirect access						1	Presence of indirect access						0
Inefficient Vectorization							Inefficient Vectorization									Inefficient Vectorization							Inefficient Vectorization
Presence of expensive instructions: scatter/gather						0	Presence of expensive instructions: scatter/gather						0			Presence of expensive instructions: scatter/gather						1	Presence of expensive instructions: scatter/gather						0
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 - 0.36 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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
1119	0.08	0.01	0.05	0	0	1214.8	1232	0.15	0.02	0.10	0	0	1168.45	959	0.13	0.02	0.06	100	66.67	1790.37	1177	0.08	0.01	0.04	0	0	1258.71	1232	0.17	0.02	0.09	0	0	1325	951	0.06	0.01	0.02	100	66.67	1504.1

Sum on 1 analyzed binary loop (libggml-cpu.so - 1119)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1232)							Sum on 1 analyzed binary loop (libggml-cpu.so - 959)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1177)							Sum on 1 analyzed binary loop (libggml-cpu.so - 1232)							Sum on 1 analyzed binary loop (libggml-cpu.so - 951)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
Control Flow Issues							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							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
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
Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of 2 to 4 paths						1	Presence of 2 to 4 paths							Presence of 2 to 4 paths						0	Presence of 2 to 4 paths						1	Presence of 2 to 4 paths							Presence of 2 to 4 paths
Presence of constant non-unit stride data access						0	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						0	Presence of constant non-unit stride data access							Presence of constant non-unit stride data access

▶ops.cpp: 6220 - 0.14 %

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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6222 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6222 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6229 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions
1836	0.04	0.01	0.04	15.56	9.17	365.83	2113	0.04	0.01	0.04	1.96	6.62	577.43			2001	0.04	0.01	0.03	15.56	9.17	407.77	2015	0.03	0.01	0.04	0	6.25	581.05

Sum on 1 analyzed binary loop (libggml-cpu.so - 1836)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2113)							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 - 2001)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2015)							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
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
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

▶<unknown>: 0 - 0.13 %

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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions
1163	0.00	0.00	0.00	0	0	0	2749	0.00	0.00	0.00	0	0	0	2750	0.00	0.00	0.00	0	0	0	1238	0.01	0.00	0.00	0	0	0	2874	0.00	0.00	0.00	0	0	0	2491	0.01	0.00	0.00	0	0	0
2134	0.00	0.00	0.00	0	0	0	2485	0.00	0.00	0.00	0	0	0	2828	0.00	0.00	0.00	0	0	0	2508	0.01	0.00	0.00	0	0	0	2583	0.00	0.00	0.00	0	0	0	2252	0.02	0.00	0.00	0	0	0
1031	0.00	0.00	0.00	0	0	0	1282	0.00	0.00	0.00	0	0	0	2575	0.00	0.00	0.00	0	0	NA	2401	0.01	0.00	0.00	0	0	0	2287	0.00	0.00	0.00	0	0	NA	1220	0.00	0.00	0.00	0	0	0
2308	0.00	0.00	0.00	0	0	0	2842	0.00	0.00	0.00	0	0	0	1331	0.00	0.00	0.00	0	0	0	2399	0.01	0.00	0.00	0	0	0	2304	0.00	0.00	0.00	0	0	0	1339	0.00	0.00	0.00	0	0	0
1197	0.01	0.00	0.00	0	0	0	2247	0.00	0.00	0.00	0	0	NA	3308	0.00	0.00	0.00	0	0	0	2624	0.01	0.00	0.00	0	0	0	2763	0.00	0.00	0.00	0	0	0	1210	0.00	0.00	0.00	0	0	0
1870	0.00	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	2511	0.01	0.00	0.00	0	0	0	2877	0.01	0.00	0.00	0	0	0	2563	0.00	0.00	0.00	0	0	0
2414	0.01	0.00	0.00	0	0	0	2628	0.00	0.00	0.00	0	0	0	3184	0.00	0.00	0.00	0	0	0	2404	0.01	0.00	0.00	0	0	0	1352	0.00	0.00	0.00	0	0	0	2568	0.00	0.00	0.00	0	0	0
2405	0.00	0.00	0.00	0	0	0	2756	0.00	0.00	0.00	0	0	0	2807	0.00	0.00	0.00	0	0	0	2069	0.00	0.00	0.00	0	0	0	2897	0.00	0.00	0.00	0	0	0	2808	0.00	0.00	0.00	0	0	0
2304	0.01	0.00	0.00	0	0	0	2741	0.01	0.00	0.00	0	0	0	3022	0.00	0.00	0.00	0	0	0	260	0.01	0.00	0.00	0	0	0	2984	0.00	0.00	0.00	0	0	0	2417	0.01	0.00	0.00	0	0	0
2299	0.00	0.00	0.00	0	0	0	703	0.01	0.00	0.00	0	0	0	3041	0.00	0.00	0.00	0	0	0	376	0.01	0.00	0.00	0	0	0	331	0.00	0.00	0.00	0	0	NA	2675	0.00	0.00	0.00	0	0	0
2301	0.01	0.00	0.00	0	0	0	695	0.00	0.00	0.00	0	0	0	2909	0.00	0.00	0.00	0	0	0	716	0.01	0.00	0.00	0	0	0	2285	0.01	0.00	0.00	0	0	227.35	2677	0.01	0.00	0.00	0	0	0
2108	0.00	0.00	0.00	0	0	0	1399	0.00	0.00	0.00	0	0	0	2510	0.00	0.00	0.00	0	0	0	19	0.00	0.00	0.00	0	0	0	722	0.01	0.00	0.00	0	0	353.65	1300	0.01	0.00	0.00	0	0	0
469	0.00	0.00	0.00	0	0	0	528	0.00	0.00	0.00	0	0	303.23	3191	0.00	0.00	0.00	0	0	0	2346	0.00	0.00	0.00	0	0	NA	1735	0.00	0.00	0.00	0	0	NA	2575	0.01	0.00	0.00	0	0	0
2070	0.00	0.00	0.00	0	0	301.48	107	0.00	0.00	0.00	0	0	NA	735	0.00	0.00	0.00	0	0	0	549	0.01	0.00	0.00	0	0	839.39	116	0.00	0.00	0.00	0	0	NA	545	0.00	0.00	0.00	0	0	0
39	0.00	0.00	0.00	0	0	0	1759	0.00	0.00	0.00	0	0	3032.29	1140	0.00	0.00	0.00	0	0	0	6	0.01	0.00	0.00	0	0	0	2309	0.00	0.00	0.00	0	0	28.42	336	0.00	0.00	0.00	0	0	NA
23	0.00	0.00	0.00	0	0	0	705	0.01	0.00	0.00	0	0	454.84	519	0.02	0.00	0.01	0	0	35.07	394	0.01	0.00	0.01	0	0	5.79	392	0.01	0.00	0.00	0	0	0	1648	0.02	0.00	0.00	0	0	14.71
365	0.00	0.00	0.00	0	0	150.74	5	0.01	0.00	0.00	0	0	0	520	0.01	0.00	0.00	0	0	293.78	548	0.01	0.00	0.00	0	0	38.88	723	0.01	0.00	0.00	0	0	75.78	1639	0.01	0.00	0.00	0	0	7604.1
450	0.00	0.00	0.00	0	0	1808.87	707	0.01	0.00	0.00	0	0	104.56	1387	0.00	0.00	0.00	0	0	0	544	0.00	0.00	0.00	0	0	0	721	0.01	0.00	0.00	0	0	25.26	79	0.00	0.00	0.00	0	0	NA
1572	0.00	0.00	0.00	0	0	NA	709	0.01	0.00	0.00	0	0	1653.97	1678	0.01	0.00	0.00	0	0	261.5	2331	0.00	0.00	0.00	0	0	502.2	4	0.02	0.00	0.00	0	0	0	1319	0.00	0.00	0.00	0	0	NA
6	0.01	0.00	0.00	0	0	0	2441	0.00	0.00	0.00	0	0	625.41	1673	0.02	0.00	0.00	0	0	1027.83	1720	0.01	0.00	0.00	0	0	3314.53	724	0.01	0.00	0.00	0	0	171.34	621	0.00	0.00	0.00	0	0	NA
546	0.00	0.00	0.00	0	0	0	2410	0.01	0.00	0.00	0	0	151.61	1665	0.00	0.00	0.00	0	0	54.02	441	0.01	0.00	0.00	0	0	90.4	545	0.01	0.00	0.00	0	0	181.88	1651	0.01	0.00	0.00	0	0	170.78
547	0.01	0.00	0.00	0	0	2110.34	706	0.01	0.00	0.00	0	0	72.2	91	0.00	0.00	0.00	0	0	NA	545	0.01	0.00	0.00	0	0	243.93	712	0.01	0.00	0.00	0	0	0	605	0.01	0.00	0.00	0	0	0
2190	0.01	0.00	0.00	0	0	179	704	0.01	0.00	0.00	0	0	37.9	332	0.00	0.00	0.00	0	0	0								726	0.01	0.00	0.00	0	0	808.35	1377	0.00	0.00	0.00	0	0	0
552	0.01	0.00	0.00	0	0	301.48	377	0.01	0.00	0.00	0	0	0	1382	0.00	0.00	0.00	0	0	0															76	0.00	0.00	0.00	0	0	0
2175	0.00	0.00	0.00	0	0	226.11								1321	0.00	0.00	0.00	0	0	5491.44															971	0.01	0.00	0.00	0	0	862.04
556	0.01	0.00	0.01	0	0	106.4								524	0.01	0.00	0.00	0	0	0															588	0.01	0.00	0.00	0	0	151.81
1811	0.01	0.00	0.00	0	0	239.65								1675	0.02	0.00	0.00	0	0	0.83															587	0.01	0.00	0.00	0	0	303.61
														331	0.01	0.00	0.01	0	0	0															3	0.02	0.00	0.00	0	0	0
														580	0.01	0.00	0.00	0	0	0															581	0.01	0.00	0.00	0	0	0

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

▶ggml-cpu.c: 533 - 0.09 %

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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-534 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-534 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2891						Loop Source Regions
122	0.03	0.00	0.02	0	9.82	4.5	108	0.02	0.00	0.02	0	9.58	16.82			124	0.03	0.00	0.02	0	9.82	13.44	117	0.03	0.00	0.02	0	9.58	14.76

Sum on 1 analyzed binary loop (libggml-cpu.so - 122)							Sum on 1 analyzed binary loop (libggml-cpu.so - 108)							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 - 124)							Sum on 1 analyzed binary loop (libggml-cpu.so - 117)							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							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
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 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						1

▶mmq.cpp: 822 - 0.06 %

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 icx_2		Run aocc_4		Run gcc_6
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/avx512vnniintrin.h: 41-41 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 822-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 9491-9491						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/avx512vnniintrin.h: 41-41 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 822-825 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/amx/mmq.cpp: 1390-1392 /cluster/comp/gcc/14.2.0/lib/gcc/x86_64-pc-linux-gnu/14.2.0/include/avx512fintrin.h: 9491-9491
				455	0.04	0.01	0.03	78.57	69.64	0					409	0.04	0.01	0.03	29.73	31.25	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.		Sum on 1 analyzed binary loop (libggml-cpu.so - 455)							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 - 409)
Analysis	Count	Analysis	Count	Analysis						Count	Analysis	Count	Analysis	Count	Analysis						Count
				Loop Computation Issues											Loop Computation Issues
				Presence of a large number of scalar integer instructions						1					Presence of a large number of scalar integer instructions						1
				Control Flow Issues											Control Flow Issues
				Presence of calls						1					Presence of calls						1
				Data Access Issues											Data Access Issues
				Presence of constant non-unit stride data access						1					Presence of constant non-unit stride data access						1
				Vectorization Roadblocks											Vectorization Roadblocks
				Presence of calls						1					Presence of calls						1
				Presence of constant non-unit stride data access						1					Presence of constant non-unit stride data access						1

▶ggml-cpu.c: 1664 - 0.06 %

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 icx_2		Run aocc_4		Run gcc_6
Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2891
				71	0.04	0.01	0.03	0	8.82	2.75					59	0.04	0.01	0.03	0	9.17	0.55

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.		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 - 59)
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

▶quants.c: 298 - 0.05 %

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	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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-298 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-347 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 298-298 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 304-304 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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
2924	0.33	0.00	0.01	60.7	29.66	801.66	3307	0.30	0.00	0.01	58.33	28.75	877.69	2214	0.67	0.00	0.01	60	28.75	413.37	3143	0.26	0.00	0.01	60.7	29.66	1022.75	3150	0.30	0.00	0.01	60.7	29.66	888.56	2188	0.39	0.00	0.01	59.65	29.28	675.34

Sum on 1 analyzed binary loop (libggml-cpu.so - 2924)							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 - 3143)							Sum on 1 analyzed binary loop (libggml-cpu.so - 3150)							Sum on 1 analyzed binary loop (libggml-cpu.so - 2188)
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						0
Presence of more than 4 paths						0															Presence of more than 4 paths						0	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
More than 10% of the vector loads instructions are unaligned						1															More than 10% of the vector loads instructions are unaligned						1	More than 10% of the vector loads instructions are unaligned						1	More than 10% of the vector loads instructions are unaligned						1
Presence of special instructions executing on a single port						1															Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1
Vectorization Roadblocks																					Vectorization Roadblocks							Vectorization Roadblocks							Vectorization Roadblocks
Presence of 2 to 4 paths						1															Presence of 2 to 4 paths						1	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						0	Presence of more than 4 paths						1
Inefficient Vectorization																					Inefficient Vectorization							Inefficient Vectorization							Inefficient Vectorization
Presence of special instructions executing on a single port						1															Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1	Presence of special instructions executing on a single port						1

▶ops.cpp: 6446 - 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	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	GFLOP/s
Run orig_default		Run aocc_default							Run gcc_default							Run icx_2							Run aocc_4							Run gcc_6
Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6456-6456						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6457						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6457						Loop Source Regions
		2105	0.02	0.00	0.00	72.73	19.13	390.18	990	0.09	0.00	0.02	69.23	36.54	27.02	1968	0.02	0.00	0.01	0	6.25	162.53	2007	0.02	0.00	0.01	0	6.25	165.34

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 - 990)							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
									Data Access Issues
									Presence of constant non-unit stride data access						1
									More than 10% of the vector loads instructions are unaligned						1
									Presence of special instructions executing on a single port						1
									Vectorization Roadblocks
									Presence of constant non-unit stride data access						1
									Inefficient Vectorization
									Presence of special instructions executing on a single port						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 icx_2		Run aocc_4		Run gcc_6
Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245						Loop Source Regions		Loop Source Regions		Loop Source Regions
				996	0.04	0.01	0.03	19.61	9.8	588.56

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 - 996)							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 - 0.03 %

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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130						Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130						Loop Source Regions
2179	0.02	0.00	0.01	0	6.25	6.67	2419	0.02	0.00	0.01	0	6.25	0			2335	0.03	0.00	0.01	0	6.25	0	2292	0.02	0.00	0.01	0	6.25	0

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 - 2419)							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 a large number of scalar integer instructions						1
							Data Access Issues
							Presence of indirect access						1
							Vectorization Roadblocks
							Presence of indirect access						1

▶binary-ops.cpp: 18 - 0.03 %

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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
812	0.16	0.00	0.00	0	6.25	183.12	914	0.20	0.00	0.01	0	6.25	134.05	716	0.28	0.00	0.01	100	50	90.99	848	0.16	0.00	0.00	0	6.25	170.71	914	0.22	0.00	0.01	0	6.25	110.66	705	0.08	0.00	0.00	0	6.25	282.74

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 - 0.03 %

ASM Loop ID	GFLOP/s	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
Run orig_default		Run aocc_default		Run gcc_default		Run icx_2		Run aocc_4		Run gcc_6
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
										965	0.03	0.01	0.03	6.25	8.2	474.82

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		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 - 965)
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: 1084 - 0.02 %

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	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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1113-1116 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1084-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1115-1115 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 372-373						Loop Source Regions
1126	0.19	0.00	0.01	100	100	5009.17	1236	0.13	0.00	0.00	98	98.13	7871.81			1184	0.19	0.00	0.01	100	100	5407.92	1240	0.16	0.00	0.00	98	98.13	6147.9

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.							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 - 0.02 %

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	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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326
1577	0.10	0.00	0.00	0	7.81	462.98	1758	0.15	0.00	0.00	0	7.81	358.82	1322	0.13	0.00	0.00	0	7.81	362.96	1725	0.16	0.00	0.00	0	7.81	343.24	1734	0.02	0.00	0.00	75	18.75	3628.12	1320	0.14	0.00	0.00	0	7.81	355.96

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.							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 - 1320)
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

▶binary-ops.cpp: 10 - 0.02 %

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	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 icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
698	0.06	0.00	0.00	0	6.25	452.22	816	0.09	0.00	0.00	0	6.25	274.3	634	0.20	0.00	0.00	100	50	124.16	712	0.09	0.00	0.00	0	6.25	261.67	826	0.08	0.00	0.00	0	6.25	343.39	633	0.08	0.00	0.00	0	6.25	275.71

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.							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 - 0.01 %

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 aocc_default							Run gcc_default							Run icx_2							Run aocc_4							Run gcc_6
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1046-1046						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_vector.h: 1046-1046						Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126
1936	0.07	0.00	0.00	0	6.25	0	2992	0.07	0.00	0.00	0	6.25	0	2943	0.07	0.00	0.00	0	6.25	0	1963	0.11	0.00	0.00	33.33	8.33	0	3069	0.09	0.00	0.00	0	6.25	0	2881	0.11	0.00	0.00	0	6.25	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

▶traits.cpp: 13 - 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	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 aocc_default		Run gcc_default		Run icx_2		Run aocc_4		Run gcc_6
Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h: 1054-1054 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_iterator.h: 1182-1182 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 13-17						Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions
403	0.02	0.00	0.01	0	12.5	0

Sum on 1 analyzed binary loop (libggml-cpu.so - 403)							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
Control Flow Issues
Presence of 2 to 4 paths						1
Data Access Issues
Presence of constant non-unit stride data access						1
Vectorization Roadblocks
Presence of 2 to 4 paths						1
Presence of constant non-unit stride data access						1

▶ggml-cpu.c: 3204 - 0.01 %

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 icx_2		Run aocc_4		Run gcc_6
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/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3204-3204						Loop Source Regions		Loop Source Regions		Loop Source Regions
				5	0.06	0.00	0.01	100	83.33	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

▶vec.cpp: 372 - 0.01 %

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 icx_2		Run aocc_4		Run gcc_6
Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1101-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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/175-924-9259/intel/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1101-1101 /beegfs/hackathon/users/eoseret/qaas_runs_test/175-924-9259/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
				963	0.16	0.00	0.00	100	100	6425.74					953	0.21	0.00	0.00	100	100	4277.56

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.		Sum on 1 analyzed binary loop (libggml-cpu.so - 953)
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
															Presence of constant non-unit stride data access						1
															Presence of special instructions executing on a single port						1
															Vectorization Roadblocks
															Presence of 2 to 4 paths						1
															Presence of constant non-unit stride data access						1
															Inefficient Vectorization
															Presence of special instructions executing on a single port						1
															Use of masked instructions						1

▶stl_algo.h: 1594 - 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	GFLOP/s
Run orig_default		Run aocc_default		Run gcc_default							Run icx_2		Run aocc_4		Run gcc_6
Loop Source Regions		Loop Source Regions		Loop Source Regions	/cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_heap.h: 262-264 /cluster/comp/gcc/14.2.0/include/c++/14.2.0/bits/stl_algo.h: 1594-1595						Loop Source Regions		Loop Source Regions		Loop Source Regions
				2573	0.04	0.00	0.00	0	7.45	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

▶hashtable.h: 2386 - 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 icx_2		Run aocc_4							Run gcc_6
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/hashtable.h: 2386-2403 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/hashtable_policy.h: 287-287 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/hashtable_policy.h: 434-434 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/hashtable_policy.h: 1255-1255						Loop Source Regions
								2775	0.02	0.00	0.00	0	11.93	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

▶hashtable.h: 1840 - 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	GFLOP/s	ASM Loop ID	GFLOP/s
Run orig_default		Run aocc_default							Run gcc_default		Run icx_2		Run aocc_4		Run gcc_6
Loop Source Regions		Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/char_traits.h: 389-389 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/basic_string.h: 195-195 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/basic_string.h: 6236-6237 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/hashtable.h: 1840-1843 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/hashtable_policy.h: 434-434 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/hashtable_policy.h: 1255-1255 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/hashtable_policy.h: 1600-1600 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/stl_pair.h: 467-467						Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions
		2638	0.02	0.00	0.00	0	11.33	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

▶mmq.cpp: 1570 - 49.23 %

▶mmq.cpp: 1573 - 47.50 %

▶mmq.cpp: 1597 - 15.34 %

▶mmq.cpp: 1581 - 14.84 %

▶vec.h: 491 - 0.47 %

▶mmq.cpp: 303 - 0.43 %

▶vec.cpp: 311 - 0.36 %

▶ops.cpp: 6220 - 0.14 %

▶<unknown>: 0 - 0.13 %

▶ggml-cpu.c: 533 - 0.09 %

▶mmq.cpp: 822 - 0.06 %

▶ggml-cpu.c: 1664 - 0.06 %

▶quants.c: 298 - 0.05 %

▶ops.cpp: 6446 - 0.04 %

▶ops.cpp: 6210 - 0.03 %

▶ops.cpp: 8885 - 0.03 %

▶binary-ops.cpp: 18 - 0.03 %

▶ops.cpp: 6238 - 0.03 %

▶vec.h: 1084 - 0.02 %

▶ops.cpp: 4325 - 0.02 %

▶binary-ops.cpp: 10 - 0.02 %

▶sampling.cpp: 125 - 0.01 %

▶traits.cpp: 13 - 0.01 %

▶ggml-cpu.c: 3204 - 0.01 %

▶vec.cpp: 372 - 0.01 %

▶stl_algo.h: 1594 - 0.00 %

▶hashtable.h: 2386 - 0.00 %

▶hashtable.h: 1840 - 0.00 %