OV - Compare Loops

Loops

▶quants.c: 910 - 4.19 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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	0.04	0.03	0.11	10.53	49.34	1938	0.09	0.06	1.54	16.22	51.35	1940	0.08	4.20	2.54	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 - 1940)
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues						Loop Computation Issues
Presence of a large number of scalar integer instructions						Presence of a large number of scalar integer instructions					1	Presence of a large number of scalar integer instructions					1
Data Access Issues						Data Access Issues						Data Access Issues
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1
Vectorization Roadblocks						Vectorization Roadblocks						Vectorization Roadblocks
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1

▶ops.cpp: 6210 - 0.81 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6223-6231
		790	0.04	0.02	0.48	2.33	20.2	805	0.03	0.56	0.34	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 - 805)
Analysis	Count	Analysis					Count	Analysis					Count
		Loop Computation Issues						Loop Computation Issues
		Presence of expensive FP instructions					1	Presence of expensive FP instructions					1
		Presence of a large number of scalar integer instructions					1	Presence of a large number of scalar integer instructions					1
		Control Flow Issues						Control Flow Issues
		Presence of calls					1	Presence of calls					1
		Presence of more than 4 paths					1	Presence of more than 4 paths					0
		Vectorization Roadblocks						Vectorization Roadblocks
		Presence of calls					1	Presence of calls					1
		Presence of more than 4 paths					1	Presence of more than 4 paths					1

▶quants.c: 979 - 0.74 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 986-1000
2447	0.05	0.04	0.14	56.25	68.36	1940	0.08	0.01	0.18	58.06	69.56	1942	0.05	0.70	0.42	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 - 1942)
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

▶vec.cpp: 385 - 0.68 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1008-1034					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034
1015	0.06	0.02	0.08	68.18	82.24	767	0.04	0.01	0.32	80	97.68	790	0.02	0.47	0.28	90	98.67

Sum on 1 analyzed binary loop (libggml-cpu.so - 1015)						Sum on 1 analyzed binary loop (libggml-cpu.so - 767)						Sum on 1 analyzed binary loop (libggml-cpu.so - 790)
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						Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access
Vectorization Roadblocks						Vectorization Roadblocks						Vectorization Roadblocks
Presence of constant non-unit stride data access						Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access

▶ops.cpp: 6238 - 0.53 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
				829	0.03	0.88	0.53	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.		Sum on 1 analyzed binary loop (libggml-cpu.so - 829)
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

▶ops.cpp: 4325 - 0.44 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326
1398	0.02	0.00	0.02	96.97	98.48	1127	0.03	0.01	0.14	0	26.56	1159	0.03	0.46	0.28	17.39	56.52

Sum on 1 analyzed binary loop (libggml-cpu.so - 1398)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1127)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1159)
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						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						Presence of constant non-unit stride data access						Presence of constant non-unit stride data access					1

▶ggml-cpu.c: 3228 - 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_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404
		6	0.02	0.00	0.13	0	18.47	1	0.01	0.19	0.11	72.6	83.56

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

▶binary-ops.cpp: 18 - 0.20 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
		495	0.01	0.00	0.08	25	100	501	0.01	0.21	0.12	25	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 - 495)						Sum on 1 analyzed binary loop (libggml-cpu.so - 501)
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

▶binary-ops.cpp: 10 - 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	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
434	0.03	0.00	0.01	0	25	411	0.02	0.00	0.08	25	100	413	0.01	0.14	0.09	25	100

Sum on 1 analyzed binary loop (libggml-cpu.so - 434)						Sum on 1 analyzed binary loop (libggml-cpu.so - 411)						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.h: 411 - 0.18 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458
		1454	0.02	0.00	0.07	100	100	1501	0.01	0.18	0.11	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

▶vec.cpp: 231 - 0.16 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262
		764	0.01	0.00	0.05	100	100	788	0.02	0.18	0.11	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.						Sum on 1 analyzed binary loop (libggml-cpu.so - 788)
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

▶<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_2
Loop Source Regions						Loop Source Regions						Loop Source Regions
2483	0.01	0.00	0.00	0	0	3764	0.01	0.00	0.00	0	0	4195	0.01	0.00	0.00	0	0
1151	0.01	0.00	0.00	0	0	1648	0.00	0.00	0.00	0	0	3220	0.01	0.00	0.00	0	0
2457	0.00	0.00	0.00	0	0	4472	0.00	0.00	0.00	0	0	3799	0.01	0.00	0.00	0	0
2634	0.00	0.00	0.00	0	0	4127	0.00	0.00	0.00	0	0	4538	0.01	0.01	0.01	0	0
2480	0.00	0.00	0.00	0	0	3732	0.01	0.00	0.00	0	0	1674	0.01	0.01	0.01	0	0
2650	0.00	0.00	0.00	0	0	4141	0.00	0.00	0.00	0	0	1653	0.01	0.00	0.00	0	0
2514	0.00	0.00	0.00	0	0	4180	0.01	0.00	0.00	0	0	4245	0.01	0.01	0.01	0	0
2767	0.01	0.00	0.00	0	0	620	0.01	0.00	0.01	0	0	4198	0.01	0.00	0.00	0	0
2649	0.01	0.00	0.00	0	0	1915	0.01	0.00	0.00	0	0	64	0.00	0.00	0.00	0	0
314	0.03	0.00	0.00	0	0	59	0.01	0.00	0.00	0	0	1916	0.00	0.00	0.00	0	0
1024	0.00	0.00	0.00	0	0	51	0.01	0.00	0.01	0	0	63	0.00	0.00	0.00	0	0
0	0.01	0.00	0.01	0	0	63	0.01	0.00	0.00	0	0	67	0.00	0.00	0.00	0	0
1901	0.01	0.00	0.00	0	0	369	0.00	0.00	0.00	0	0	1498	0.00	0.00	0.00	0	0
1401	0.01	0.00	0.00	0	0	1455	0.00	0.00	0.00	0	0	1072	0.01	0.00	0.00	0	0
1906	0.01	0.00	0.00	0	0							1193	0.01	0.00	0.00	0	0
2041	0.00	0.00	0.00	0	0
1007	0.01	0.00	0.01	0	0
77	0.00	0.00	0.00	0	0
1483	0.00	0.00	0.00	0	0
400	0.00	0.00	0.00	0	0
1904	0.01	0.00	0.00	0	0
2427	0.00	0.00	0.00	0	0
551	0.02	0.00	0.01	0	0
78	0.01	0.00	0.00	0	0
1570	0.01	0.00	0.00	0	0
1900	0.01	0.00	0.01	0	0
96	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

▶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_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653
		1126	0.00	0.00	0.01	100	100	1161	0.01	0.07	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: 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_2
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions		Loop Source Regions
1565	0.04	0.01	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

▶ops.cpp: 6446 - 0.04 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/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/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456
		800	0.01	0.00	0.02	37.5	81.25	839	0.00	0.03	0.02	37.5	81.25

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

▶ops.cpp: 8825 - 0.02 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run gcc_2
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8826					Loop Source Regions
		1447	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

▶basic_string.h: 6237 - 0.01 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/usr/include/c++/11/bits/char_traits.h: 374-374 /usr/include/c++/11/bits/char_traits.h: 389-389 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable_policy.h: 1251-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/stl_pair.h: 466-466
				4209	0.02	0.02	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

▶ggml-impl.h: 354 - 0.01 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run gcc_default		Run gcc_2
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-quants.c: 408-412 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 354-361 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-35-140.ec2.internal/176-410-1312/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 369-377
				592	0.02	0.02	0.01	39.13	58.42

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 - 4.19 %

▶ops.cpp: 6210 - 0.81 %

▶quants.c: 979 - 0.74 %

▶vec.cpp: 385 - 0.68 %

▶ops.cpp: 6238 - 0.53 %

▶ops.cpp: 4325 - 0.44 %

▶ggml-cpu.c: 3228 - 0.25 %

▶binary-ops.cpp: 18 - 0.20 %

▶binary-ops.cpp: 10 - 0.18 %

▶vec.h: 411 - 0.18 %

▶vec.cpp: 231 - 0.16 %

▶<unknown>: 0 - 0.14 %

▶vec.h: 646 - 0.06 %

▶ops.cpp: 6220 - 0.06 %

▶ops.cpp: 6446 - 0.04 %

▶ops.cpp: 8825 - 0.02 %

▶basic_string.h: 6237 - 0.01 %

▶ggml-impl.h: 354 - 0.01 %