OV - Compare Loops

Loops

▶quants.c: 910 - 230.25 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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	5.06	5.21	76.07	10.53	24.67	1955	4.92	5.00	77.10	16.22	25.68	1744	4.95	5.00	77.08	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 - 1744)
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

▶vec.h: 411 - 0.54 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458
1753	0.04	0.01	0.19	100	100	1470	0.03	0.01	0.19	100	100	1326	0.04	0.01	0.16	100	100

Sum on 1 analyzed binary loop (libggml-cpu.so - 1753)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1470)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1326)
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.cpp: 231 - 0.50 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262
901	0.02	0.01	0.14	96	97	763	0.04	0.01	0.20	100	100	697	0.03	0.01	0.17	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)						Sum on 1 analyzed binary loop (libggml-cpu.so - 697)
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

▶quants.c: 49 - 0.43 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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	0.03	0.01	0.17	46.43	28.94	1932	0.04	0.02	0.27	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

▶ggml-cpu.c: 1125 - 0.43 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395					Loop Source Regions
65	0.03	0.01	0.20	0	23.77	48	0.04	0.02	0.23	0	24.36

Sum on 1 analyzed binary loop (libggml-cpu.so - 65)						Sum on 1 analyzed binary loop (libggml-cpu.so - 48)						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						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

▶vec.cpp: 385 - 0.27 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1008-1034 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387
908	0.17	0.01	0.15	68.18	79.76	766	0.07	0.00	0.05	80	97.59	700	0.07	0.00	0.07	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

▶ops.cpp: 6210 - 0.25 %

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_6
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6223-6231
		789	0.04	0.01	0.18	2.33	10.1	712	0.03	0.00	0.07	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

▶ggml-cpu.c: 1126 - 0.24 %

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_6
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395
				46	0.04	0.02	0.24	0	23.94

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 - 46)
Analysis	Count	Analysis	Count	Analysis					Count
				Control Flow Issues
				Presence of calls					1
				Vectorization Roadblocks
				Presence of calls					1
				Presence of more than 4 paths					1

▶ggml-cpu.c: 1183 - 0.20 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194					Loop Source Regions		Loop Source Regions
66	0.03	0.01	0.20	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 - 0.18 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions		Loop Source Regions
1432	0.04	0.01	0.18	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

▶ops.cpp: 6238 - 0.17 %

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_6
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
				713	0.03	0.01	0.17	0	17.06

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 - 713)
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
				Presence of 2 to 4 paths					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 2 to 4 paths					1
				Presence of constant non-unit stride data access					1
				Presence of indirect access					1

▶ggml-cpu.c: 1193 - 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_6
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194
		56	0.03	0.01	0.10	0	23.26	52	0.02	0.00	0.05	0	22.77

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 - 0.14 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229
0	0.02	0.00	0.03	86.36	95.61	4	0.01	0.00	0.03	93.18	94.03	5	0.04	0.01	0.08	0	9.16

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 - 5)
Analysis					Count	Analysis					Count	Analysis					Count
												Loop Computation Issues
												Presence of a large number of scalar integer instructions					1
												Control Flow Issues
												Presence of 2 to 4 paths					1
												Data Access Issues
												Presence of constant non-unit stride data access					1
												Vectorization Roadblocks
												Presence of 2 to 4 paths					1
												Presence of constant non-unit stride data access					1

▶<unknown>: 0 - 0.14 %

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_6
Loop Source Regions						Loop Source Regions						Loop Source Regions
2782	0.00	0.00	0.00	0	0	4180	0.01	0.00	0.00	0	0	3727	0.00	0.00	0.00	0	0
2650	0.01	0.00	0.00	0	0	4472	0.01	0.00	0.00	0	0	3635	0.01	0.00	0.00	0	0
2886	0.00	0.00	0.00	0	0	4140	0.00	0.00	0.00	0	0	3450	0.01	0.00	0.00	0	0
2767	0.03	0.00	0.01	0	0	3732	0.02	0.00	0.01	0	0	3369	0.01	0.00	0.00	0	0
2649	0.00	0.00	0.00	0	0	4130	0.00	0.00	0.00	0	0	3979	0.00	0.00	0.00	0	0
2361	0.01	0.00	0.00	0	0	4141	0.00	0.00	0.00	0	0	3699	0.00	0.00	0.00	0	0
1744	0.00	0.00	0.00	0	0	33	0.00	0.00	0.00	0	0	3460	0.00	0.00	0.00	0	0
70	0.00	0.00	0.00	0	0	32	0.01	0.00	0.01	0	0	85	0.01	0.00	0.00	0	0
259	0.01	0.00	0.00	0	0	1195	0.00	0.00	0.00	0	0	48	0.01	0.00	0.00	0	0
1282	0.01	0.00	0.00	0	0	74	0.01	0.00	0.00	0	0	1826	0.00	0.00	0.00	0	0
106	0.00	0.00	0.00	0	0	2038	0.01	0.00	0.00	0	0	1834	0.00	0.00	0.00	0	0
64	0.01	0.00	0.00	0	0	1199	0.01	0.00	0.00	0	0	1111	0.00	0.00	0.00	0	0
1754	0.01	0.00	0.00	0	0	1468	0.01	0.00	0.00	0	0	55	0.00	0.00	0.01	0	0
1756	0.00	0.00	0.00	0	0	1463	0.01	0.00	0.01	0	0	722	0.00	0.00	0.00	0	0
						1466	0.01	0.00	0.00	0	0	1329	0.01	0.00	0.00	0	0
						57	0.00	0.00	0.01	0	0	719	0.01	0.00	0.01	0	0
						50	0.01	0.00	0.00	0	0	20	0.00	0.00	0.00	0	0
						233	0.00	0.00	0.00	0	0
						1131	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

▶ops.cpp: 4325 - 0.09 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326
1278	0.03	0.00	0.02	94.12	95.59	1132	0.05	0.00	0.03	0	13.28	1046	0.04	0.00	0.03	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

▶ggml-cpu.c: 2879 - 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	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_6
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2898
		60	0.01	0.00	0.04	0	16.48	56	0.01	0.00	0.04	0	15.81

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 - 0.07 %

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_6
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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
				1719	0.02	0.00	0.07	15.84	14.85

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 - 0.07 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run gcc_default		Run gcc_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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	0.07	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

▶ops.cpp: 6446 - 0.06 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6457
1437	0.01	0.00	0.02	0	12.5	799	0.01	0.00	0.02	37.5	40.63	730	0.01	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

▶binary-ops.cpp: 10 - 0.06 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
433	0.05	0.00	0.03	0	12.5	410	0.02	0.00	0.01	25	50	400	0.03	0.00	0.02	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 - 0.06 %

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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
538	0.03	0.00	0.02	0	11.84	494	0.02	0.00	0.01	25	50	462	0.03	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

▶traits.cpp: 13 - 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	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_6
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 13-17					Loop Source Regions
396	0.01	0.00	0.03	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

▶ops.cpp: 8885 - 0.02 %

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_6
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/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/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8885
				1331	0.01	0.00	0.02	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

▶ggml-cpu.c: 1197 - 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_6
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-409-6727/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1197-1198					Loop Source Regions
		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

Report Configuration

Loops

▶quants.c: 910 - 230.25 %

▶vec.h: 411 - 0.54 %

▶vec.cpp: 231 - 0.50 %

▶quants.c: 49 - 0.43 %

▶ggml-cpu.c: 1125 - 0.43 %

▶vec.cpp: 385 - 0.27 %

▶ops.cpp: 6210 - 0.25 %

▶ggml-cpu.c: 1126 - 0.24 %

▶ggml-cpu.c: 1183 - 0.20 %

▶ops.cpp: 6220 - 0.18 %

▶ops.cpp: 6238 - 0.17 %

▶ggml-cpu.c: 1193 - 0.15 %

▶ggml-cpu.c: 3228 - 0.14 %

▶<unknown>: 0 - 0.14 %

▶ops.cpp: 4325 - 0.09 %

▶ggml-cpu.c: 2879 - 0.09 %

▶ggml-impl.h: 354 - 0.07 %

▶ggml-cpu.c: 533 - 0.07 %

▶ops.cpp: 6446 - 0.06 %

▶binary-ops.cpp: 10 - 0.06 %

▶binary-ops.cpp: 18 - 0.06 %

▶traits.cpp: 13 - 0.05 %

▶ops.cpp: 8885 - 0.02 %

▶ggml-cpu.c: 1197 - 0.01 %