OV - Compare Loops

Loops

▶quants.c: 910 - 22.26 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 910-948 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 910-910 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 928-929 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13617-13617 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16103-16103 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 20765-20765 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30781-30781 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31056-31056 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 34664-34664					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 910-910 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 928-928 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13617-13617 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16065-16065 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16103-16103 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 20765-20765 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30781-30781 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31056-31056 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 34664-34664
2293	0.09	0.07	0.96	10.53	24.67	1955	0.09	0.07	8.00	16.22	25.68	1929	0.09	3.44	13.30	11.11	26.69

Sum on 1 analyzed binary loop (libggml-cpu.so - 2293)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1955)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1929)
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues						Loop Computation Issues
Presence of a large number of scalar integer instructions						Presence of a large number of scalar integer instructions					1	Presence of a large number of scalar integer instructions					1
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
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

▶ops.cpp: 6210 - 0.84 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6413-6413					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6211-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6223-6231
		789	0.01	0.00	0.53	2.33	10.1	794	0.01	0.08	0.31	0	12.76

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 - 789)						Sum on 1 analyzed binary loop (libggml-cpu.so - 794)
Analysis	Count	Analysis					Count	Analysis					Count
		Loop Computation Issues						Loop Computation Issues
		Presence of expensive FP instructions					1	Presence of expensive FP instructions					1
		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
		Presence of more than 4 paths					1	Presence of more than 4 paths					0
		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: 1010 - 0.74 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 1010-1027 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 1010-1010 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 1017-1026 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 1010-1010 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 1017-1026 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51
2292	0.01	0.00	0.05	46.15	55.53	1956	0.00	0.00	0.28	48	59.13	1930	0.01	0.11	0.41	45.28	61.44

Sum on 1 analyzed binary loop (libggml-cpu.so - 2292)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1956)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1930)
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues						Loop Computation Issues
Presence of a large number of scalar integer instructions					1	Presence of a large number of scalar integer instructions						Presence of a large number of scalar integer instructions
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
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

▶ops.cpp: 6238 - 0.65 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
				818	0.03	0.17	0.65	0	14.58

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 - 818)
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
				Control Flow Issues
				Presence of calls					1
				Data Access Issues
				Presence of constant non-unit stride data access					1
				Presence of indirect access					1
				Vectorization Roadblocks
				Presence of calls					1
				Presence of constant non-unit stride data access					1
				Presence of indirect access					1

▶vec.cpp: 385 - 0.36 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1008-1034					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1009-1023 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1009-1023 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034
908	0.02	0.00	0.04	68.18	79.76	766	0.01	0.00	0.14	80	97.59	779	0.01	0.05	0.18	90	98.62

Sum on 1 analyzed binary loop (libggml-cpu.so - 908)						Sum on 1 analyzed binary loop (libggml-cpu.so - 766)						Sum on 1 analyzed binary loop (libggml-cpu.so - 779)
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues						Loop Computation Issues
Presence of expensive FP instructions					1	Presence of expensive FP instructions					1	Presence of expensive FP instructions					1
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
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

▶binary-ops.cpp: 10 - 0.21 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
433	0.01	0.00	0.01	0	12.5	410	0.00	0.00	0.06	25	50	412	0.01	0.03	0.13	25	50

Sum on 1 analyzed binary loop (libggml-cpu.so - 433)						Sum on 1 analyzed binary loop (libggml-cpu.so - 410)						Sum on 1 analyzed binary loop (libggml-cpu.so - 412)
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues						Loop Computation Issues
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
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
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

▶binary-ops.cpp: 18 - 0.20 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
		494	0.00	0.00	0.08	25	50	498	0.01	0.03	0.11	25	50

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 - 494)						Sum on 1 analyzed binary loop (libggml-cpu.so - 498)
Analysis	Count	Analysis					Count	Analysis					Count
		Loop Computation Issues						Loop Computation Issues
		Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
		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 constant non-unit stride data access					1	Presence of constant non-unit stride data access					1

▶<unknown>: 0 - 0.15 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions						Loop Source Regions						Loop Source Regions
2480	0.00	0.00	0.00	0	0	1648	0.00	0.00	0.01	0	0
2473	0.00	0.00	0.00	0	0	3728	0.00	0.00	0.01	0	0
2457	0.00	0.00	0.00	0	0	1626	0.00	0.00	0.01	0	0
2801	0.00	0.00	0.00	0	0	4127	0.00	0.00	0.01	0	0
2634	0.00	0.00	0.00	0	0	2038	0.00	0.00	0.01	0	0
2764	0.00	0.00	0.00	0	0	60	0.00	0.00	0.01	0	0
2650	0.01	0.00	0.00	0	0	1199	0.00	0.00	0.01	0	0
2767	0.01	0.00	0.00	0	0	368	0.00	0.00	0.01	0	0
2633	0.00	0.00	0.00	0	0	620	0.00	0.00	0.01	0	0
2886	0.00	0.00	0.00	0	0	312	0.00	0.00	0.01	0	0
0	0.01	0.00	0.01	0	0
1282	0.01	0.00	0.00	0	0
2268	0.01	0.00	0.00	0	0
901	0.01	0.00	0.00	0	0
538	0.01	0.00	0.01	0	0
396	0.00	0.00	0.00	0	0
66	0.01	0.00	0.00	0	0
1437	0.01	0.00	0.00	0	0
1753	0.01	0.00	0.00	0	0
259	0.00	0.00	0.00	0	0
314	0.01	0.00	0.00	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.
Analysis					Count	Analysis					Count	Analysis	Count

▶basic_string.h: 6237 - 0.15 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/usr/include/c++/11/bits/stl_function.h: 369-369 /usr/include/c++/11/bits/char_traits.h: 374-374 /usr/include/c++/11/bits/char_traits.h: 389-389 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable_policy.h: 1251-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/stl_pair.h: 466-466					Loop Source Regions	/usr/include/c++/11/bits/stl_function.h: 369-369 /usr/include/c++/11/bits/char_traits.h: 374-374 /usr/include/c++/11/bits/char_traits.h: 389-389 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable_policy.h: 1251-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/stl_pair.h: 466-466
		4472	0.01	0.00	0.03	0	25	4199	0.00	0.00	0.01	0	25
		4141	0.01	0.00	0.02	0	25	4210	0.02	0.01	0.06	0	25
								4541	0.01	0.01	0.03	0	25

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 (libllama.so - 4210)
Analysis	Count	Analysis					Count	Analysis					Count
								Control Flow Issues
								Presence of calls					1
								Presence of more than 4 paths					1
								Vectorization Roadblocks
								Presence of calls					1
								Presence of more than 4 paths					1

▶ops.cpp: 4325 - 0.11 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326
1278	0.01	0.00	0.01	94.12	95.59	1132	0.00	0.00	0.05	0	13.28	1153	0.00	0.01	0.06	90.91	75.04

Sum on 1 analyzed binary loop (libggml-cpu.so - 1278)						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
Loop Computation Issues
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
Data Access Issues
Presence of constant non-unit stride data access					1
Vectorization Roadblocks
Presence of constant non-unit stride data access					1

▶vec.cpp: 231 - 0.09 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262					Loop Source Regions
		763	0.01	0.00	0.09	100	100

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 - 763)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis					Count	Analysis	Count
		Data Access Issues
		Presence of constant non-unit stride data access					1
		Vectorization Roadblocks
		Presence of constant non-unit stride data access					1

▶vec.h: 411 - 0.07 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458					Loop Source Regions
		1470	0.00	0.00	0.07	100	100

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 - 1470)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis					Count	Analysis	Count
		Data Access Issues
		Presence of constant non-unit stride data access					1
		Vectorization Roadblocks
		Presence of constant non-unit stride data access					1

▶vec.h: 646 - 0.07 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653
		1131	0.00	0.00	0.03	100	100	1156	0.00	0.00	0.01	100	100
								1489	0.00	0.01	0.03	100	100

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

▶ops.cpp: 6446 - 0.07 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456
		799	0.00	0.00	0.04	37.5	40.63	828	0.00	0.01	0.03	42.55	63.3

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

▶llama-vocab.cpp: 3216 - 0.06 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 3216-3216 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1916 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 195-195 /usr/include/c++/11/bits/basic_string.h: 211-211 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 3216-3216 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1916 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 195-195 /usr/include/c++/11/bits/basic_string.h: 211-211 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245
		3732	0.01	0.00	0.03	0	25	3800	0.01	0.01	0.03	0	25

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

▶hashtable.h: 2386 - 0.05 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable.h: 2386-2391 /usr/include/c++/11/bits/hashtable.h: 2402-2403					Loop Source Regions	/usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable.h: 2386-2391 /usr/include/c++/11/bits/hashtable.h: 2402-2403
		4180	0.02	0.00	0.04	0	25	4246	0.00	0.00	0.01	0	25

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

▶ops.cpp: 8825 - 0.05 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8826					Loop Source Regions
		1463	0.00	0.00	0.05	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.
Analysis	Count	Analysis					Count	Analysis	Count

▶ggml-impl.h: 354 - 0.04 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-49 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 64-66 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 72-75 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 83-83 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 3320-3320 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13947-13947 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 21569-21569
				1905	0.00	0.01	0.04	15.24	14.64

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

▶basic_string.h: 165 - 0.04 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 399-399 /usr/include/c++/11/bits/char_traits.h: 431-431 /usr/include/c++/11/bits/char_traits.h: 437-437 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-impl.cpp: 149-157 /usr/include/c++/11/ostream: 525-525 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 165-165 /usr/include/c++/11/bits/basic_string.h: 187-195 /usr/include/c++/11/bits/basic_string.h: 219-219 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245 /usr/include/c++/11/bits/basic_string.h: 356-356 /usr/include/c++/11/bits/basic_string.h: 6536-6536 /usr/include/c++/11/bits/basic_string.tcc: 215-219 /usr/include/c++/11/bits/basic_string.tcc: 232-232
				1677	0.01	0.01	0.04	0	19.77

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

▶ggml-cpu.c: 3228 - 0.04 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229
				0	0.00	0.01	0.04	92.11	93.09

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

▶ggml-cpu.c: 1126 - 0.04 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1126-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1126-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395
		48	0.00	0.00	0.03	0	24.36	53	0.00	0.00	0.01	0	23.99

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

▶ops.cpp: 6220 - 0.03 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run gcc_default		Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions		Loop Source Regions
1432	0.01	0.00	0.03	0	13.17

Sum on 1 analyzed binary loop (libggml-cpu.so - 1432)						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
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
Control Flow Issues
Presence of calls					1
Data Access Issues
Presence of constant non-unit stride data access					1
Vectorization Roadblocks
Presence of calls					1
Presence of constant non-unit stride data access					1

▶llama-vocab.cpp: 2148 - 0.03 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2148-2166 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2172-2180 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2186-2200 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2206-2220 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2226-2240 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2246-2257 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2263-2275 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2281-2289 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/stl_vector.h: 1046-1046 /usr/include/c++/11/bits/basic_string.h: 6250-6250
				3970	0.01	0.01	0.03	0	18.79

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

▶llama-vocab.cpp: 1575 - 0.02 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 1575-1575 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 1725-1726 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 1732-1736 /usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 437-437 /usr/include/c++/11/bits/unordered_map.h: 389-389 /usr/include/c++/11/bits/hashtable_policy.h: 219-219 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable_policy.h: 1268-1268 /usr/include/c++/11/bits/hashtable.h: 308-308 /usr/include/c++/11/bits/hashtable.h: 795-795 /usr/include/c++/11/bits/hashtable.h: 810-811 /usr/include/c++/11/bits/hashtable.h: 1890-1895 /usr/include/c++/11/bits/hashtable.h: 1902-1910 /usr/include/c++/11/bits/hashtable.h: 1970-1970 /usr/include/c++/11/bits/hashtable.h: 2014-2021 /usr/include/c++/11/bits/hashtable.h: 2029-2029 /usr/include/c++/11/bits/functional_hash.h: 198-198 /usr/include/c++/11/ext/new_allocator.h: 127-127 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 168-168 /usr/include/c++/11/bits/basic_string.h: 187-195 /usr/include/c++/11/bits/basic_string.h: 201-201 /usr/include/c++/11/bits/basic_string.h: 219-219 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245 /usr/include/c++/11/bits/basic_string.h: 255-255 /usr/include/c++/11/bits/basic_string.h: 320-320 /usr/include/c++/11/bits/basic_string.h: 459-459 /usr/include/c++/11/bits/basic_string.h: 490-490 /usr/include/c++/11/bits/basic_string.h: 568-568 /usr/include/c++/11/bits/basic_string.h: 921-921 /usr/include/c++/11/bits/basic_string.h: 927-927 /usr/include/c++/11/bits/stl_pair.h: 353-353					Loop Source Regions
		3907	0.01	0.00	0.02	0	22.55

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

▶quants.c: 49 - 0.02 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-49 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 63-66 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 72-75 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 3320-3320 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 10248-10248 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13947-13947 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16065-16065 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 19789-19789 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 20386-20386 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 21569-21569					Loop Source Regions
		1932	0.00	0.00	0.02	26.25	19.83

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

▶gguf.cpp: 142 - 0.01 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/gguf.cpp: 142-144
				1185	0.00	0.00	0.01	0	9.38

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

▶basic_string.h: 195 - 0.01 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 3216-3216 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1916 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 195-195 /usr/include/c++/11/bits/basic_string.h: 211-211 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245
				3796	0.00	0.00	0.01	0	25

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

▶ggml-impl.h: 192 - 0.01 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 192-192 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 288-297
				300	0.00	0.00	0.01	0	19.79

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

▶alloc_traits.h: 496 - 0.01 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/usr/include/c++/11/bits/stl_uninitialized.h: 1011-1011 /usr/include/c++/11/bits/alloc_traits.h: 496-496 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 921-921 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/unicode.cpp: 799-800 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/src/unicode.cpp: 811-811 /usr/include/c++/11/bits/vector.tcc: 94-97
				4386	0.00	0.00	0.01	0	25

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

▶ggml-cpu.c: 1193 - 0.01 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-2262/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194
				61	0.00	0.00	0.01	0	22.4

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

Report Configuration

Loops

▶quants.c: 910 - 22.26 %

▶ops.cpp: 6210 - 0.84 %

▶quants.c: 1010 - 0.74 %

▶ops.cpp: 6238 - 0.65 %

▶vec.cpp: 385 - 0.36 %

▶binary-ops.cpp: 10 - 0.21 %

▶binary-ops.cpp: 18 - 0.20 %

▶<unknown>: 0 - 0.15 %

▶basic_string.h: 6237 - 0.15 %

▶ops.cpp: 4325 - 0.11 %

▶vec.cpp: 231 - 0.09 %

▶vec.h: 411 - 0.07 %

▶vec.h: 646 - 0.07 %

▶ops.cpp: 6446 - 0.07 %

▶llama-vocab.cpp: 3216 - 0.06 %

▶hashtable.h: 2386 - 0.05 %

▶ops.cpp: 8825 - 0.05 %

▶ggml-impl.h: 354 - 0.04 %

▶basic_string.h: 165 - 0.04 %

▶ggml-cpu.c: 3228 - 0.04 %

▶ggml-cpu.c: 1126 - 0.04 %

▶ops.cpp: 6220 - 0.03 %

▶llama-vocab.cpp: 2148 - 0.03 %

▶llama-vocab.cpp: 1575 - 0.02 %

▶quants.c: 49 - 0.02 %

▶gguf.cpp: 142 - 0.01 %

▶basic_string.h: 195 - 0.01 %

▶ggml-impl.h: 192 - 0.01 %

▶alloc_traits.h: 496 - 0.01 %

▶ggml-cpu.c: 1193 - 0.01 %