OV - Compare Loops

Loops

▶quants.c: 910 - 2.10 %

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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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
2293	0.09	0.08	0.21	10.53	24.67	1955	0.09	0.08	0.68	16.22	25.68	1934	0.09	4.34	1.21	16.22	25.68

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 - 1934)
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.cpp: 385 - 0.84 %

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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034
908	0.07	0.03	0.08	68.18	79.76	766	0.06	0.04	0.33	80	97.59	783	0.06	1.55	0.43	88.89	97.32

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 - 783)
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					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 - 0.72 %

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_1
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6223-6231
		789	0.09	0.04	0.39	2.33	10.1	798	0.04	1.16	0.32	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 - 798)
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

▶ops.cpp: 6238 - 0.51 %

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_1
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
				822	0.05	1.84	0.51	0	14.18

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 - 822)
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

▶binary-ops.cpp: 10 - 0.28 %

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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
433	0.04	0.01	0.03	0	12.5	410	0.03	0.01	0.10	25	50	416	0.03	0.53	0.15	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 - 416)
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 - 0.28 %

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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
538	0.04	0.01	0.03	0	11.84	494	0.03	0.01	0.09	25	50	502	0.04	0.60	0.17	25	50

Sum on 1 analyzed binary loop (libggml-cpu.so - 538)						Sum on 1 analyzed binary loop (libggml-cpu.so - 494)						Sum on 1 analyzed binary loop (libggml-cpu.so - 502)
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

▶ops.cpp: 4325 - 0.24 %

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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326
1278	0.04	0.01	0.03	94.12	95.59	1132	0.02	0.01	0.09	0	13.28	1154	0.02	0.42	0.12	90.91	75.04

Sum on 1 analyzed binary loop (libggml-cpu.so - 1278)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1132)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1154)
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						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						Presence of constant non-unit stride data access					1

▶vec.h: 411 - 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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458
1753	0.02	0.01	0.01	100	100	1470	0.02	0.01	0.06	100	100	1499	0.03	0.35	0.10	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 - 1499)
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

▶ggml-cpu.c: 3228 - 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	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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404
0	0.03	0.01	0.02	86.36	95.61	4	0.02	0.01	0.06	93.18	94.03	0	0.01	0.26	0.07	92.11	93.09

Sum on 1 analyzed binary loop (libggml-cpu.so - 0)						Sum on 1 analyzed binary loop (libggml-cpu.so - 4)						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
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

▶vec.cpp: 231 - 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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262
901	0.02	0.00	0.01	96	97	763	0.02	0.01	0.05	100	100	780	0.02	0.30	0.08	100	100

Sum on 1 analyzed binary loop (libggml-cpu.so - 901)						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 - 780)
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

▶ops.cpp: 6220 - 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	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run gcc_default		Run gcc_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions		Loop Source Regions
1432	0.07	0.04	0.10	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

▶<unknown>: 0 - 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_1
Loop Source Regions						Loop Source Regions						Loop Source Regions
2483	0.01	0.00	0.00	0	0	4180	0.00	0.00	0.00	0	0	4261	0.00	0.00	0.00	0	0
2473	0.00	0.00	0.00	0	0	3768	0.00	0.00	0.00	0	0	4575	0.00	0.00	0.00	0	0
1151	0.00	0.00	0.00	0	0	518	0.00	0.00	0.00	0	0	1676	0.00	0.00	0.00	0	0
2457	0.00	0.00	0.00	0	0	3907	0.00	0.00	0.00	0	0	4216	0.02	0.02	0.01	0	0
2634	0.00	0.00	0.00	0	0	4140	0.00	0.00	0.00	0	0	3955	0.00	0.00	0.00	0	0
2650	0.00	0.00	0.00	0	0	4130	0.00	0.00	0.00	0	0	3796	0.00	0.00	0.00	0	0
2480	0.00	0.00	0.00	0	0	3732	0.02	0.00	0.00	0	0	3972	0.01	0.01	0.00	0	0
2767	0.00	0.00	0.00	0	0	4141	0.00	0.00	0.00	0	0	3800	0.02	0.02	0.01	0	0
330	0.00	0.00	0.00	0	0	4472	0.01	0.00	0.00	0	0	1227	0.00	0.00	0.00	0	0
314	0.03	0.00	0.00	0	0	620	0.04	0.00	0.01	0	0	1910	0.00	0.01	0.00	0	0
1744	0.00	0.00	0.00	0	0	56	0.01	0.00	0.00	0	0	65	0.00	0.00	0.00	0	0
2268	0.00	0.00	0.00	0	0	48	0.01	0.00	0.00	0	0	53	0.00	0.00	0.00	0	0
83	0.00	0.00	0.00	0	0	1466	0.00	0.00	0.00	0	0	1496	0.00	0.02	0.01	0	0
65	0.00	0.00	0.00	0	0	368	0.01	0.00	0.00	0	0	1600	0.00	0.00	0.00	0	0
396	0.00	0.00	0.00	0	0	1199	0.01	0.00	0.00	0	0	1494	0.01	0.03	0.01	0	0
1437	0.02	0.00	0.01	0	0	1932	0.00	0.00	0.00	0	0	61	0.00	0.00	0.00	0	0
1282	0.01	0.00	0.00	0	0	1468	0.01	0.00	0.00	0	0
66	0.01	0.00	0.00	0	0
1756	0.01	0.00	0.00	0	0
1754	0.00	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

▶vec.h: 646 - 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_1
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653
		1131	0.01	0.00	0.01	100	100	1157	0.01	0.16	0.04	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 - 0.03 %

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_1
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/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/176-415-7045/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/176-415-7045/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/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456
		799	0.01	0.00	0.01	37.5	40.63	832	0.01	0.07	0.02	37.5	40.63

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 - 0.02 %

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_1
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8826					Loop Source Regions
		1463	0.01	0.00	0.02	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 - 0.02 %

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_1
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 354-361 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 369-377 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-415-7045/llama.cpp/build/llama.cpp/ggml/src/ggml-quants.c: 408-412
				603	0.05	0.06	0.02	39.13	29.21

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 - 2.10 %

▶vec.cpp: 385 - 0.84 %

▶ops.cpp: 6210 - 0.72 %

▶ops.cpp: 6238 - 0.51 %

▶binary-ops.cpp: 10 - 0.28 %

▶binary-ops.cpp: 18 - 0.28 %

▶ops.cpp: 4325 - 0.24 %

▶vec.h: 411 - 0.17 %

▶ggml-cpu.c: 3228 - 0.15 %

▶vec.cpp: 231 - 0.14 %

▶ops.cpp: 6220 - 0.10 %

▶<unknown>: 0 - 0.09 %

▶vec.h: 646 - 0.06 %

▶ops.cpp: 6446 - 0.03 %

▶ops.cpp: 8825 - 0.02 %

▶ggml-impl.h: 354 - 0.02 %