OV - Compare Loops

Loops

▶quants.c: 979 - 183.32 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 979-1002					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 979-979 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 986-1000					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 979-979 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 986-1000
2447	2.24	2.37	60.58	56.25	68.36	1940	2.25	2.29	62.06	58.06	69.56	1949	2.14	2.18	60.68	55.38	70.96

Sum on 1 analyzed binary loop (libggml-cpu.so - 2447)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1940)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1949)
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues						Loop Computation Issues
Presence of a large number of scalar integer instructions					1	Presence of a large number of scalar integer instructions					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: 910 - 3.99 %

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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 910-910 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 910-910 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/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
2450	0.03	0.03	0.68	10.53	49.34	1938	0.06	0.06	1.49	16.22	51.35	1947	0.07	0.07	1.82	16.22	51.35

Sum on 1 analyzed binary loop (libggml-cpu.so - 2450)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1938)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1947)
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

▶<unknown>: 0 - 0.21 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_1
Loop Source Regions						Loop Source Regions						Loop Source Regions
2483	0.01	0.00	0.00	0	0	4180	0.01	0.00	0.00	0	0	3797	0.00	0.00	0.00	0	0
2473	0.00	0.00	0.00	0	0	666	0.00	0.00	0.00	0	0	4368	0.01	0.00	0.00	0	0
2633	0.00	0.00	0.00	0	0	4472	0.00	0.00	0.00	0	0	1677	0.00	0.00	0.00	0	0
2650	0.01	0.00	0.00	0	0	4127	0.01	0.00	0.00	0	0	4197	0.00	0.00	0.00	0	0
2642	0.00	0.00	0.00	0	0	3907	0.01	0.00	0.00	0	0	3801	0.00	0.00	0.00	0	0
2886	0.01	0.00	0.00	0	0	3728	0.00	0.00	0.00	0	0	4247	0.01	0.00	0.00	0	0
2514	0.00	0.00	0.00	0	0	60	0.00	0.00	0.00	0	0	3973	0.00	0.00	0.00	0	0
2765	0.00	0.00	0.00	0	0	56	0.01	0.00	0.00	0	0	4540	0.00	0.00	0.00	0	0
2767	0.01	0.00	0.00	0	0	495	0.02	0.00	0.01	0	0	33	0.00	0.00	0.00	0	0
1401	0.00	0.00	0.00	0	0	92	0.00	0.00	0.00	0	0	1095	0.00	0.00	0.00	0	0
1398	0.01	0.00	0.01	0	0	53	0.01	0.00	0.00	0	0	32	0.00	0.00	0.00	0	0
1904	0.00	0.00	0.00	0	0	59	0.01	0.00	0.00	0	0	1	0.01	0.00	0.01	0	0
82	0.01	0.00	0.00	0	0	1447	0.01	0.00	0.00	0	0	67	0.01	0.00	0.01	0	0
434	0.02	0.00	0.01	0	0	411	0.00	0.00	0.00	0	0	2030	0.01	0.00	0.00	0	0
76	0.00	0.00	0.00	0	0	1450	0.00	0.00	0.00	0	0	416	0.01	0.00	0.00	0	0
2516	0.00	0.00	0.00	0	0	857	0.00	0.00	0.00	0	0	63	0.01	0.00	0.00	0	0
1901	0.01	0.00	0.00	0	0	33	0.01	0.00	0.00	0	0	1169	0.00	0.00	0.00	0	0
96	0.01	0.00	0.00	0	0	32	0.00	0.00	0.00	0	0	64	0.00	0.00	0.00	0	0
551	0.01	0.00	0.00	0	0	74	0.01	0.00	0.00	0	0	98	0.00	0.00	0.00	0	0
400	0.01	0.00	0.01	0	0	918	0.00	0.00	0.00	0	0	504	0.03	0.00	0.01	0	0
						312	0.00	0.00	0.00	0	0	842	0.00	0.00	0.00	0	0
												1503	0.00	0.00	0.00	0	0
												1167	0.02	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

▶vec.cpp: 385 - 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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1008-1034 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1009-1023 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1009-1023 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387
1015	0.28	0.00	0.09	68.18	82.24	767	0.06	0.00	0.02	80	97.68	793	0.06	0.00	0.03	88.89	97.42

Sum on 1 analyzed binary loop (libggml-cpu.so - 1015)						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 - 793)
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues												Loop Computation Issues
Presence of expensive FP instructions					1							Presence of expensive FP instructions					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 constant non-unit stride data access												Presence of constant non-unit stride data access					1

▶quants.c: 49 - 0.12 %

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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-72 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-49 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 63-66 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 72-75 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/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
2427	0.01	0.00	0.04	46.43	57.89	1915	0.02	0.00	0.08	26.25	39.66

Sum on 1 analyzed binary loop (libggml-cpu.so - 2427)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1915)						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					1	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 - 0.11 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262
1007	0.02	0.00	0.03	100	100	764	0.02	0.00	0.04	100	100	790	0.02	0.00	0.04	100	100

Sum on 1 analyzed binary loop (libggml-cpu.so - 1007)						Sum on 1 analyzed binary loop (libggml-cpu.so - 764)						Sum on 1 analyzed binary loop (libggml-cpu.so - 790)
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

▶ops.cpp: 6210 - 0.11 %

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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6413-6413					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6211-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6223-6231
		790	0.02	0.00	0.08	2.33	20.2	808	0.01	0.00	0.04	0	25.52

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 - 790)						Sum on 1 analyzed binary loop (libggml-cpu.so - 808)
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

▶ggml-cpu.c: 1183 - 0.11 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1183 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194					Loop Source Regions		Loop Source Regions
78	0.02	0.00	0.11	0	50

Sum on 1 analyzed binary loop (libggml-cpu.so - 78)						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

▶ggml-cpu.c: 1125 - 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	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1198-1198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1126-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1126-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395
77	0.01	0.00	0.03	0	46.79	51	0.01	0.00	0.03	0	48.72	55	0.01	0.00	0.04	0	47.98

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 - 55)
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

▶vec.h: 411 - 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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458
1900	0.01	0.00	0.03	100	100	1454	0.01	0.00	0.03	100	100	1508	0.03	0.00	0.03	100	100

Sum on 1 analyzed binary loop (libggml-cpu.so - 1900)						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
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: 6220 - 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	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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions		Loop Source Regions
1565	0.03	0.00	0.06	0	26.34

Sum on 1 analyzed binary loop (libggml-cpu.so - 1565)						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 - 0.05 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_1
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194
		55	0.01	0.00	0.03	0	46.88	59	0.01	0.00	0.02	0	46.88

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 - 55)						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 - 0.03 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_1
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
				832	0.01	0.00	0.03	0	28.37

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 - 0.02 %

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_1
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions
0	0.01	0.00	0.01	92.5	98.75	6	0.01	0.00	0.01	0	18.47

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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-49 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 64-66 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 72-75 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 83-83 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/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
				1923	0.01	0.00	0.02	15.24	29.29

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: 2879 - 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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2898					Loop Source Regions
		63	0.01	0.00	0.02	0	32.95

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 - 0.01 %

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-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6457					Loop Source Regions		Loop Source Regions
1570	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: 4325 - 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_1
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions
		1127	0.04	0.00	0.01	0	26.56

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

▶traits.cpp: 13 - 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_1
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-409-1188/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 13-17					Loop Source Regions
		369	0.01	0.00	0.01	0	50

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: 979 - 183.32 %

▶quants.c: 910 - 3.99 %

▶<unknown>: 0 - 0.21 %

▶vec.cpp: 385 - 0.14 %

▶quants.c: 49 - 0.12 %

▶vec.cpp: 231 - 0.11 %

▶ops.cpp: 6210 - 0.11 %

▶ggml-cpu.c: 1183 - 0.11 %

▶ggml-cpu.c: 1125 - 0.09 %

▶vec.h: 411 - 0.08 %

▶ops.cpp: 6220 - 0.06 %

▶ggml-cpu.c: 1193 - 0.05 %

▶ops.cpp: 6238 - 0.03 %

▶ggml-cpu.c: 3228 - 0.02 %

▶ggml-impl.h: 354 - 0.02 %

▶ggml-cpu.c: 2879 - 0.02 %

▶ops.cpp: 6446 - 0.01 %

▶ops.cpp: 4325 - 0.01 %

▶traits.cpp: 13 - 0.01 %