OV - Compare Loops

Loops

▶quants.c: 910 - 241.34 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 910-948					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 928-929 /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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 928-932 /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	6.88	7.13	80.01	10.53	24.67	1955	6.81	6.85	80.58	16.22	25.68	1828	6.81	6.84	80.76	8.82	21.32

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 - 1828)
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

▶quants.c: 49 - 0.65 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-72 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /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
2268	0.05	0.02	0.25	46.43	28.94	1932	0.08	0.03	0.40	26.25	19.83

Sum on 1 analyzed binary loop (libggml-cpu.so - 2268)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1932)						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						Loop Computation Issues
Presence of expensive FP instructions					1	Presence of expensive FP instructions					1
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					0
Presence of a large number of scalar integer instructions					0	Presence of a large number of scalar integer instructions					1
Control Flow Issues						Control Flow Issues
Presence of 2 to 4 paths					0	Presence of 2 to 4 paths					1
Data Access Issues						Data Access Issues
Presence of constant non-unit stride data access						Presence of constant non-unit stride data access					1
Vectorization Roadblocks						Vectorization Roadblocks
Presence of 2 to 4 paths					0	Presence of 2 to 4 paths					1
Presence of more than 4 paths					1	Presence of more than 4 paths					0
Presence of constant non-unit stride data access					0	Presence of constant non-unit stride data access					1

▶vec.cpp: 231 - 0.55 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262
901	0.04	0.02	0.17	96	97	763	0.05	0.02	0.18	100	100	749	0.04	0.02	0.19	100	100

Sum on 1 analyzed binary loop (libggml-cpu.so - 901)						Sum on 1 analyzed binary loop (libggml-cpu.so - 763)						Sum on 1 analyzed binary loop (libggml-cpu.so - 749)
Analysis					Count	Analysis					Count	Analysis					Count
Data Access Issues						Data Access Issues						Data Access Issues
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					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

▶vec.h: 411 - 0.49 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458
1753	0.04	0.02	0.19	100	100	1470	0.04	0.01	0.14	100	100	1405	0.03	0.01	0.16	100	100

Sum on 1 analyzed binary loop (libggml-cpu.so - 1753)						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 - 1405)
Analysis					Count	Analysis					Count	Analysis					Count
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

▶ggml-cpu.c: 1125 - 0.49 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1198-1198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395
65	0.04	0.02	0.17	0	23.77	48	0.04	0.01	0.17	0	24.36	45	0.04	0.01	0.15	0	23.99

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.						Sum on 1 analyzed binary loop (libggml-cpu.so - 48)						Sum on 1 analyzed binary loop (libggml-cpu.so - 45)
Analysis					Count	Analysis					Count	Analysis					Count
						Control Flow Issues						Control Flow Issues
						Presence of calls					1	Presence of calls					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

▶ops.cpp: 6210 - 0.41 %

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_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6223-6231
		789	0.05	0.02	0.29	2.33	10.1	765	0.03	0.01	0.12	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)						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
		Presence of a large number of scalar integer instructions					1
		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

▶vec.cpp: 385 - 0.41 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034
908	0.15	0.02	0.20	68.18	79.76	766	0.08	0.01	0.10	80	97.59	752	0.10	0.01	0.11	88.89	97.32

Sum on 1 analyzed binary loop (libggml-cpu.so - 908)						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
Data Access Issues
Presence of constant non-unit stride data access					1
Vectorization Roadblocks
Presence of constant non-unit stride data access					1

▶ggml-cpu.c: 1183 - 0.32 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1183 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194					Loop Source Regions		Loop Source Regions
66	0.06	0.03	0.32	0	25

Sum on 1 analyzed binary loop (libggml-cpu.so - 66)						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
Control Flow Issues
Presence of calls					1
Vectorization Roadblocks
Presence of calls					1

▶ops.cpp: 6220 - 0.25 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions		Loop Source Regions
1432	0.05	0.02	0.25	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

▶ggml-cpu.c: 1193 - 0.22 %

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_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194
		56	0.04	0.01	0.16	0	23.26	53	0.02	0.01	0.06	0	22.4

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 - 56)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis					Count	Analysis					Count
		Control Flow Issues
		Presence of calls					1
		Vectorization Roadblocks
		Presence of calls					1

▶ops.cpp: 6238 - 0.21 %

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_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
				787	0.05	0.02	0.21	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 - 787)
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

▶ggml-cpu.c: 3228 - 0.17 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404
0	0.02	0.00	0.03	86.36	95.61	4	0.01	0.00	0.02	93.18	94.03	1	0.05	0.01	0.12	0	9.23

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 - 0.16 %

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_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 83-83 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /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
				1803	0.03	0.01	0.16	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.		Sum on 1 analyzed binary loop (libggml-cpu.so - 1803)
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
				Vectorization Roadblocks
				Presence of more than 4 paths					1

▶ops.cpp: 4325 - 0.13 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326
1278	0.04	0.00	0.04	94.12	95.59	1132	0.05	0.00	0.05	0	13.28	1091	0.04	0.00	0.05	0	13.28

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

▶<unknown>: 0 - 0.10 %

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_5
Loop Source Regions						Loop Source Regions						Loop Source Regions
2633	0.01	0.00	0.00	0	0	3728	0.00	0.00	0.00	0	0	1650	0.00	0.00	0.00	0	0
2480	0.01	0.00	0.00	0	0	4180	0.01	0.00	0.00	0	0	4232	0.00	0.00	0.00	0	0
2473	0.01	0.00	0.00	0	0	1648	0.00	0.00	0.00	0	0	3794	0.01	0.00	0.00	0	0
1151	0.01	0.00	0.00	0	0	4472	0.00	0.00	0.00	0	0	4520	0.00	0.00	0.00	0	0
2886	0.02	0.00	0.00	0	0	3907	0.00	0.00	0.00	0	0	3935	0.00	0.00	0.00	0	0
2649	0.01	0.00	0.00	0	0	3732	0.01	0.00	0.00	0	0	3939	0.00	0.00	0.00	0	0
2767	0.01	0.00	0.00	0	0	4141	0.01	0.00	0.00	0	0	4347	0.00	0.00	0.00	0	0
2650	0.01	0.00	0.00	0	0	4130	0.01	0.00	0.00	0	0	4198	0.02	0.00	0.00	0	0
2361	0.00	0.00	0.00	0	0	2027	0.00	0.00	0.00	0	0	3966	0.02	0.00	0.00	0	0
1744	0.00	0.00	0.00	0	0	1466	0.01	0.00	0.00	0	0	34	0.01	0.00	0.00	0	0
70	0.01	0.00	0.01	0	0	1471	0.01	0.00	0.00	0	0	35	0.00	0.00	0.00	0	0
1282	0.01	0.00	0.00	0	0	50	0.00	0.00	0.00	0	0	37	0.00	0.00	0.00	0	0
1357	0.01	0.00	0.00	0	0	1131	0.01	0.00	0.00	0	0	106	0.00	0.00	0.00	0	0
1756	0.00	0.00	0.00	0	0	33	0.01	0.00	0.00	0	0	1094	0.01	0.00	0.00	0	0
1024	0.01	0.00	0.00	0	0	32	0.00	0.00	0.00	0	0	1397	0.00	0.00	0.00	0	0
314	0.00	0.00	0.00	0	0	74	0.00	0.00	0.00	0	0	1406	0.00	0.00	0.00	0	0
												47	0.01	0.00	0.00	0	0
												1400	0.00	0.00	0.00	0	0
												54	0.01	0.00	0.01	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-cpu.c: 2879 - 0.10 %

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_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2898					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2898
		60	0.02	0.00	0.05	0	16.48	57	0.02	0.00	0.06	0	16.41

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

▶binary-ops.cpp: 10 - 0.10 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
433	0.04	0.00	0.04	0	12.5	410	0.03	0.00	0.03	25	50	437	0.04	0.00	0.03	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

▶binary-ops.cpp: 18 - 0.08 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
538	0.04	0.00	0.03	0	11.84	494	0.02	0.00	0.01	25	50	507	0.04	0.00	0.04	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

▶ops.cpp: 6446 - 0.07 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6457					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/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/176-414-5784/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/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6457
1437	0.02	0.00	0.03	0	12.5	799	0.01	0.00	0.02	37.5	40.63	795	0.02	0.00	0.02	0	9.46

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: 533 - 0.05 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2093-2096 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2871-2879 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2895-2897					Loop Source Regions		Loop Source Regions
83	0.02	0.00	0.05	0	20.57

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

▶traits.cpp: 13 - 0.04 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 13-17 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_iterator.h: 1102-1102					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 13-17					Loop Source Regions
396	0.02	0.00	0.02	0	25	368	0.01	0.00	0.02	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: 1197 - 0.02 %

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_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1197-1198					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1197-1198					Loop Source Regions
64	0.01	0.00	0.01	0	25	53	0.01	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 - 0.01 %

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_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8826					Loop Source Regions
		1463	0.01	0.00	0.01	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

▶ops.cpp: 8885 - 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_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8885
				1402	0.01	0.00	0.01	0	7.29

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		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: 6407 - 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_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6407-6407
				783	0.01	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: 1291 - 0.01 %

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_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-414-5784/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1291-1297					Loop Source Regions
		57	0.01	0.00	0.01	0	24.22

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 - 241.34 %

▶quants.c: 49 - 0.65 %

▶vec.cpp: 231 - 0.55 %

▶vec.h: 411 - 0.49 %

▶ggml-cpu.c: 1125 - 0.49 %

▶ops.cpp: 6210 - 0.41 %

▶vec.cpp: 385 - 0.41 %

▶ggml-cpu.c: 1183 - 0.32 %

▶ops.cpp: 6220 - 0.25 %

▶ggml-cpu.c: 1193 - 0.22 %

▶ops.cpp: 6238 - 0.21 %

▶ggml-cpu.c: 3228 - 0.17 %

▶ggml-impl.h: 354 - 0.16 %

▶ops.cpp: 4325 - 0.13 %

▶<unknown>: 0 - 0.10 %

▶ggml-cpu.c: 2879 - 0.10 %

▶binary-ops.cpp: 10 - 0.10 %

▶binary-ops.cpp: 18 - 0.08 %

▶ops.cpp: 6446 - 0.07 %

▶ggml-cpu.c: 533 - 0.05 %

▶traits.cpp: 13 - 0.04 %

▶ggml-cpu.c: 1197 - 0.02 %

▶ops.cpp: 8825 - 0.01 %

▶ops.cpp: 8885 - 0.01 %

▶ops.cpp: 6407 - 0.01 %

▶ggml-cpu.c: 1291 - 0.01 %