OV - Compare Loops

Loops

▶quants.c: 979 - 200.36 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/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-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 979-979 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 986-1000					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 979-979 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 986-1000
2220	8.49	8.24	67.23	0	0	2041	8.36	8.27	67.28	0	0			1945	8.09	7.96	65.85	0	0

Sum on 1 analyzed binary loop (libggml-cpu.so - 2220)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2041)						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 - 1945)
Analysis					Count	Analysis					Count	Analysis	Count	Analysis					Count

▶quants.c: 1089 - 70.99 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 1089-1089 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 1095-1112					Loop Source Regions
				2416	7.77	7.49	70.99	53.85	63.46

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 1 analyzed binary loop (libggml-cpu.so - 2416)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count
				Loop Computation Issues
				Presence of a large number of scalar integer instructions					1

▶ggml-cpu.c: 533 - 1.08 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2093-2096 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2871-2879 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2895-2897					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-539 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2093-2096 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2871-2879 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2895-2897					Loop Source Regions
72	0.14	0.06	0.47	0	50			72	0.15	0.06	0.61	0	50

Sum on 1 analyzed binary loop (libggml-cpu.so - 72)						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 - 72)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis	Count	Analysis					Count	Analysis	Count
Control Flow Issues								Control Flow Issues
Presence of calls					1			Presence of calls					1
Vectorization Roadblocks								Vectorization Roadblocks
Presence of calls					1			Presence of calls					1
Presence of more than 4 paths					1			Presence of more than 4 paths					1

▶vec.cpp: 231 - 0.58 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262
879	0.11	0.02	0.15	100	100	754	0.13	0.03	0.23	100	100			712	0.10	0.02	0.20	100	100

Sum on 1 analyzed binary loop (libggml-cpu.so - 879)						Sum on 1 analyzed binary loop (libggml-cpu.so - 754)						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 - 712)
Analysis					Count	Analysis					Count	Analysis	Count	Analysis					Count
Data Access Issues						Data Access Issues								Data Access Issues
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1			Presence of constant non-unit stride data access					1
Vectorization Roadblocks						Vectorization Roadblocks								Vectorization Roadblocks
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1			Presence of constant non-unit stride data access					1

▶vec.h: 411 - 0.46 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458
1719	0.09	0.02	0.14	100	100	1525	0.11	0.02	0.18	96.97	100			1495	0.10	0.02	0.14	96.97	100

Sum on 1 analyzed binary loop (libggml-cpu.so - 1719)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1525)						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 - 1495)
Analysis					Count	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

▶ggml-cpu.c: 2879 - 0.41 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2879 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2886-2898					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2879 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2886-2898
		70	0.05	0.02	0.17	0	62.5			59	0.08	0.03	0.24	0	55.26

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 - 70)						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 - 59)
Analysis	Count	Analysis					Count	Analysis	Count	Analysis					Count
		Control Flow Issues								Control Flow Issues
		Presence of calls					1			Presence of calls					1
		Vectorization Roadblocks								Vectorization Roadblocks
		Presence of calls					1			Presence of calls					1
		Presence of more than 4 paths					1			Presence of more than 4 paths					1

▶vec.cpp: 311 - 0.28 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316					Loop Source Regions
				908	0.13	0.03	0.28	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 - 908)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count

▶ggml-cpu.c: 1183 - 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	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1183-1187 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194					Loop Source Regions
53	0.04	0.02	0.13	0	52.17			53	0.02	0.01	0.08	0	52.17

Sum on 1 analyzed binary loop (libggml-cpu.so - 53)						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 - 53)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis	Count	Analysis					Count	Analysis	Count
Control Flow Issues								Control Flow Issues
Presence of calls					1			Presence of calls					1
Vectorization Roadblocks								Vectorization Roadblocks
Presence of calls					1			Presence of calls					1

▶quants.c: 910 - 0.20 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/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-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10238-10238 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12569-12569 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 16570-16570 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25379-25379 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25654-25654 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 28759-28759 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 910-910 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 929-929					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 910-929 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 936-948					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10238-10238 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12569-12569 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 16570-16570 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25379-25379 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 25654-25654 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 28759-28759 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 910-910 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 929-929
2223	0.02	0.01	0.06	72.22	77.08	2042	0.02	0.01	0.05	70	73.75	2417	0.02	0.00	0.04	81.25	84.38	1946	0.01	0.01	0.05	72.5	74.38

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

▶ggml-impl.h: 355 - 0.17 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	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 armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 392-392 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-72					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 2792-2792 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 6853-6853 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10568-10568 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 15594-15594 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 16191-16191 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 17374-17374 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-54 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 63-66 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 72-75
				2401	0.02	0.01	0.06	70.21	72.86	1925	0.04	0.01	0.10	32.41	43.85

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 1 analyzed binary loop (libggml-cpu.so - 2401)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1925)
Analysis	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					0
				Control Flow Issues						Control Flow Issues
				Presence of 2 to 4 paths					1	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					1	Presence of 2 to 4 paths					1
				Presence of constant non-unit stride data access					0	Presence of constant non-unit stride data access					1

▶ops.cpp: 6220 - 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	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions
1408	0.03	0.01	0.08	15.38	32.69			1596	0.04	0.01	0.06	27.27	36.36

Sum on 1 analyzed binary loop (libggml-cpu.so - 1408)						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 - 1596)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					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					1
Control Flow Issues								Control Flow Issues
Presence of calls					1			Presence of calls					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 calls					1			Presence of calls					1
Presence of constant non-unit stride data access					1			Presence of constant non-unit stride data access					1

▶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	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 armclang_3		Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1008-1034 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1009-1023 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1009-1023 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387
886	0.96	0.01	0.09	70.45	84.66	756	0.27	0.00	0.02	80	97.66			714	0.30	0.00	0.03	91.43	97.32

Sum on 1 analyzed binary loop (libggml-cpu.so - 886)						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	Analysis					Count
Loop Computation Issues
Presence of expensive FP instructions					1

▶quants.c: 49 - 0.13 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 355-355 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-392 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-72					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 2792-2792 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 6853-6853 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 10568-10568 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 12531-12531 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 15594-15594 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 16191-16191 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/include/arm_neon.h: 17374-17374 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 49-49 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 63-66 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 72-75					Loop Source Regions		Loop Source Regions
2199	0.02	0.01	0.05	62.35	67.5	2022	0.04	0.01	0.09	34.17	44.67

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 - 2022)						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	Analysis	Count
						Loop Computation Issues
						Presence of expensive FP instructions					1
						Control Flow Issues
						Presence of 2 to 4 paths					1
						Data Access Issues
						Presence of constant non-unit stride data access					1
						Vectorization Roadblocks
						Presence of 2 to 4 paths					1
						Presence of constant non-unit stride data access					1

▶ops.cpp: 6210 - 0.13 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6211-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6223-6231
		775	0.03	0.01	0.09	1.83	26.33			725	0.03	0.00	0.04	7.41	34.26

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 - 775)						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	Analysis					Count
		Loop Computation Issues
		Presence of expensive FP instructions					1
		Presence of a large number of scalar integer instructions					1
		Control Flow Issues
		Presence of calls					1
		Presence of 2 to 4 paths					1
		Data Access Issues
		Presence of indirect access					1
		Vectorization Roadblocks
		Presence of calls					1
		Presence of 2 to 4 paths					1
		Presence of indirect access					1

▶vec.h: 491 - 0.12 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497					Loop Source Regions
				1910	0.06	0.01	0.12	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 - 1910)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count

▶ggml-cpu.c: 1125 - 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	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1198-1198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1395					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1198-1198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1386-1395					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1125-1130 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1142-1142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1371-1395
54	0.02	0.00	0.03	0	55	62	0.01	0.00	0.02	0	60.94	54	0.02	0.00	0.04	0	55	51	0.01	0.00	0.03	0	58.82

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

▶ggml-cpu.c: 1193 - 0.09 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1397-1397					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1193-1194
		58	0.01	0.00	0.00	0	0			53	0.03	0.01	0.05	0	47.92
		56	0.02	0.00	0.04	0	45

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

▶ops.cpp: 6238 - 0.05 %

ASM Loop ID	Vector Length Use (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
						726	0.03	0.01	0.05	0	34.25

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.		Sum on 1 analyzed binary loop (libggml-cpu.so - 726)
Analysis	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
						Presence of 2 to 4 paths					1
						Data Access Issues
						Presence of constant non-unit stride data access					1
						Presence of indirect access					1
						Vectorization Roadblocks
						Presence of calls					1
						Presence of 2 to 4 paths					1
						Presence of constant non-unit stride data access					1
						Presence of indirect access					1

▶ops.cpp: 6446 - 0.03 %

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 (%)	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6457					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6457
1403	0.02	0.00	0.01	47.06	44.12	785	0.01	0.00	0.01	42.86	57.14	1591	0.02	0.00	0.01	66.67	47.22	742	0.01	0.00	0.01	2.56	25.64

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

▶binary-ops.cpp: 18 - 0.03 %

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 (%)	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
520	0.10	0.00	0.01	0	28.95	493	0.05	0.00	0.00	100	100	541	0.07	0.00	0.01	0	28.95	440	0.07	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count

▶ggml-cpu.c: 3228 - 0.03 %

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 (%)	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404
0	0.02	0.00	0.01	97.5	98.75	5	0.01	0.00	0.01	88.37	93.9	0	0.01	0.00	0.00	97.22	98.61	4	0.03	0.00	0.01	82.05	93.27

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

▶vec.h: 1045 - 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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1045-1058 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1072-1072 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 390-391					Loop Source Regions
				916	0.24	0.00	0.02	83.33	91.67

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

▶binary-ops.cpp: 10 - 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	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
413	0.09	0.00	0.01	0	30	419	0.04	0.00	0.00	100	100	437	0.05	0.00	0.01	0	30	362	0.09	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count

▶ggml-cpu.c: 1132 - 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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1132-1137 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1146-1147 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1165					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1132-1137 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1146-1147 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1156-1156 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1162-1165 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1198-1198
		63	0.01	0.00	0.00	0	49.29			49	0.01	0.00	0.02	0	46.64

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

▶ggml-cpu.c: 1289 - 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	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1297					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1289-1297					Loop Source Regions
58	0.01	0.00	0.01	0	50			58	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis	Count	Analysis					Count	Analysis	Count

▶ops.cpp: 4325 - 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	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326
1249	0.08	0.00	0.01	94.12	97.06	1148	0.08	0.00	0.01	0	31.25	1353	0.03	0.00	0.00	91.67	87.5	1124	0.04	0.00	0.00	100	82.5

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

▶ops.cpp: 8816 - 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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8816-8818					Loop Source Regions		Loop Source Regions
		1516	0.02	0.00	0.02	0	29.17

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

▶sampling.cpp: 125 - 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	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126					Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 1128-1128 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/common/sampling.cpp: 125-126
3062	0.04	0.00	0.00	75	87.5	4164	0.05	0.00	0.00	25	37.5	3379	0.02	0.00	0.00	75	87.5	4227	0.05	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count

▶vec.h: 646 - 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	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	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 armclang_3		Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653
1723	0.01	0.00	0.00	100	100	1147	0.01	0.00	0.00	100	100			1128	0.02	0.00	0.00	100	100
1252	0.02	0.00	0.00	100	100	1520	0.02	0.00	0.01	100	100			1499	0.00	0.00	0.00	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.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis	Count	Analysis					Count

▶ggml-cpu.c: 1291 - 0.01 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1291-1297					Loop Source Regions		Loop Source Regions
		67	0.01	0.00	0.01	0	51.25

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

▶traits.cpp: 13 - 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	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 armclang_3						Run gcc_5
Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1102-1102 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 13-17					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 13-17					Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1102-1102 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 13-17					Loop Source Regions
365	0.00	0.00	0.00	0	50	382	0.01	0.00	0.01	0	47.92	407	0.00	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis	Count

▶ops.cpp: 8824 - 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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8824-8825					Loop Source Regions		Loop Source Regions
		1523	0.01	0.00	0.01	0	0

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

▶new_allocator.h: 172 - 0.00 %

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	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 armclang_3						Run gcc_5
Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/new_allocator.h: 172-172 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 387-387 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 2058-2058 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 223-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 246-246 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 269-269 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 288-288 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 294-294 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 1182-1182 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 1575-1576 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1102-1102 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2763-2766 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 350-350					Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/new_allocator.h: 172-172 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 387-387 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 2058-2058 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 246-246 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 269-269 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 288-288 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 294-294 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 368-369 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 388-388 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_construct.h: 162-162					Loop Source Regions
2867	0.01	0.00	0.00	0	46.35			3227	0.01	0.00	0.00	0	50
2609	0.00	0.00	0.00	0	40.44			3224	0.00	0.00	0.00	0	45.83
								490	0.00	0.00	0.00	0	47.5
								1014	0.00	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis	Count	Analysis					Count	Analysis	Count

▶ggml-cpu.cpp: 39 - 0.00 %

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	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 armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp: 39-39 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp: 63-63					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp: 39-39 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp: 63-63					Loop Source Regions
95	0.01	0.00	0.00	0	62.5			95	0.01	0.00	0.00	0	62.5

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

▶hashtable.h: 2077 - 0.00 %

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	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 armclang_3						Run gcc_5
Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable.h: 2077-2077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 534-534 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 1375-1375 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 1759-1759 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 3760-3760					Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable.h: 2077-2077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 534-534 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 1375-1375 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 1759-1759 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 3760-3760					Loop Source Regions
2984	0.01	0.00	0.00	0	50			3374	0.02	0.00	0.00	0	50
2733	0.00	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis	Count	Analysis					Count	Analysis	Count

▶hashtable.h: 2627 - 0.00 %

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 (%)	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 armclang_3						Run gcc_5
Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable.h: 2627-2644 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 387-387 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 534-534 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 1375-1375					Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable.h: 2627-2632 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable.h: 2643-2644 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 387-387 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 534-534					Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable.h: 2627-2637 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable.h: 2644-2644 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 387-387 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 534-534 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 1375-1375					Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable.h: 2627-2632 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable.h: 2643-2644 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 387-387 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 534-534
2750	0.01	0.00	0.00	0	50	4166	0.01	0.00	0.00	0	50	3085	0.01	0.00	0.00	0	50	3749	0.00	0.00	0.00	0	50
						4137	0.00	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count

▶basic_string.h: 1077 - 0.00 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 3760-3760 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable.h: 2072-2079 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 368-368 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 534-534 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 1375-1375 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 1759-1759					Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 3760-3760 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable.h: 2072-2079 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 368-368 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 534-534 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 1375-1375 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 1759-1759
		3770	0.00	0.00	0.00	0	50			3391	0.00	0.00	0.00	0	50
		4537	0.01	0.00	0.00	0	50			3907	0.01	0.00	0.00	0	50
										3392	0.00	0.00	0.00	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.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis					Count	Analysis	Count	Analysis					Count

▶ggml-cpu.cpp: 61 - 0.00 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp: 61-64					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.cpp: 61-64
		96	0.00	0.00	0.00	0	100			86	0.01	0.00	0.00	0	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.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis					Count	Analysis	Count	Analysis					Count

▶regex_executor.tcc: 180 - 0.00 %

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	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 armclang_3						Run gcc_5
Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/shared_ptr_base.h: 1667-1667 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1219-1219 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1235-1235 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.h: 169-175 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.h: 196-199 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.h: 232-232 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 1131-1131 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 1150-1150 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 180-194 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 211-215 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 290-290 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 300-300 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 312-312 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 485-485 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 513-513 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_constants.h: 194-194 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_pair.h: 925-925 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_automaton.h: 166-166 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_automaton.h: 202-202					Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/shared_ptr_base.h: 1667-1667 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1219-1219 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1235-1235 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.h: 169-175 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.h: 196-199 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.h: 232-232 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 1131-1131 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 1150-1150 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 180-194 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 211-215 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 290-290 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 300-300 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 312-312 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 485-485 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_executor.tcc: 513-513 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_constants.h: 194-194 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_pair.h: 925-925 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_automaton.h: 166-166 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex_automaton.h: 202-202					Loop Source Regions
1418	0.02	0.00	0.00	0	35.31			1487	0.01	0.00	0.00	0	35.31

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

▶stl_algo.h: 1594 - 0.00 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_algo.h: 1594-1595 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_heap.h: 262-267					Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_algo.h: 1594-1595 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_heap.h: 262-267
		3491	0.01	0.00	0.00	0	30.36			3130	0.01	0.00	0.00	0	30.83

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

▶ggml-cpu.c: 1197 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1197-1198					Loop Source Regions		Loop Source Regions
		57	0.01	0.00	0.00	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.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis					Count	Analysis	Count	Analysis	Count

▶vec.h: 677 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 677-682					Loop Source Regions
				1916	0.01	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count

▶ops.cpp: 8884 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run gcc_default						Run armclang_3						Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8884-8885					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8884-8885					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8884-8885					Loop Source Regions
1725	0.00	0.00	0.00	87.5	81.25	1522	0.00	0.00	0.00	100	87.5	1894	0.01	0.00	0.00	87.5	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis	Count

▶ops.cpp: 6389 - 0.00 %

ASM Loop ID	Vector Length Use (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6389-6395 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6402-6407
						733	0.01	0.00	0.00	0	44.94

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

▶ggml.c: 1367 - 0.00 %

ASM Loop ID	Vector Length Use (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1367-1380
						15	0.01	0.00	0.00	0	51.92

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

▶hashtable_policy.h: 387 - 0.00 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/new_allocator.h: 172-172 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 246-246 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 269-269 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 294-294 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 387-387 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 2058-2058					Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/new_allocator.h: 172-172 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 246-246 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 269-269 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 294-294 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 387-387 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 2058-2058
		3836	0.01	0.00	0.00	0	50			3495	0.00	0.00	0.00	0	50
										3675	0.00	0.00	0.00	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.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis					Count	Analysis	Count	Analysis					Count

▶repack.cpp: 1968 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/repack.cpp: 1968-1968 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/repack.cpp: 1981-1981					Loop Source Regions
				299	0.01	0.00	0.00	0	62.5

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

▶llama-vocab.cpp: 2160 - 0.00 %

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 (%)	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 armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 3776-3776 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 1131-1131 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2160-2178 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2184-2192 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2198-2212 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2218-2232 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2238-2252 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2258-2269 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2275-2287 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2293-2301 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 387-387					Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 1131-1131 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 447-447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2160-2178 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2184-2192 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2198-2198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2208-2212 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2218-2218 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2228-2232 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2238-2252 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2258-2269 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2275-2287 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2293-2301 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 3776-3776					Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 3776-3776 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 1131-1131 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2160-2178 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2184-2192 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2198-2212 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2218-2232 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2238-2252 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2258-2269 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2275-2287 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2293-2301 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 387-387
		3991	0.00	0.00	0.00	6.67	37.19	2874	0.00	0.00	0.00	0	44.79	3601	0.00	0.00	0.00	13.77	39.67

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

▶char_traits.h: 381 - 0.00 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2355-2357 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 3776-3776					Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 3776-3776 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 1131-1131 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2355-2357 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 387-387					Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 3776-3776 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 1131-1131 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2355-2357 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/hashtable_policy.h: 387-387
2567	0.00	0.00	0.00	0	48.08	3985	0.00	0.00	0.00	16.67	39.58			3569	0.00	0.00	0.00	10.53	38.49

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

▶stl_heap.h: 229 - 0.00 %

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	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 armclang_3						Run gcc_5
Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_heap.h: 229-235					Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_heap.h: 229-235					Loop Source Regions
2229	0.00	0.00	0.00	0	33.85			2505	0.00	0.00	0.00	0	35.71

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

▶vec.h: 710 - 0.00 %

ASM Loop ID	Vector Length Use (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 710-717
						1496	0.00	0.00	0.00	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.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count

▶ggml.c: 1444 - 0.00 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1444-1448					Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1444-1448
		40	0.00	0.00	0.00	0	37.5			22	0.00	0.00	0.00	0	43.75

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

▶basic_string.h: 218 - 0.00 %

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 (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 218-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 246-246 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 432-432 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 879-881 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 918-918 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 350-351 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 427-427					Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/new_allocator.h: 172-172 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 218-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 255-255 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 263-263 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 269-269 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 294-294 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 432-432 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 881-881 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 897-897 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 905-906 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/basic_string.h: 1084-1084 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2432-2435 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 350-351 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/char_traits.h: 427-427
		3243	0.00	0.00	0.00	0	43.18			3580	0.00	0.00	0.00	0	45.34

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

▶ggml-impl.h: 346 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-quants.c: 408-412 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 346-346 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 355-361 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 369-377					Loop Source Regions		Loop Source Regions
		607	0.01	0.00	0.00	84.35	73.2

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

▶stl_tree.h: 1963 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_function.h: 405-405 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_tree.h: 1963-1964					Loop Source Regions
				427	0.00	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count

▶stl_heap.h: 140 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_heap.h: 140-142					Loop Source Regions
				2504	0.00	0.00	0.00	0	37.5

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

▶hashtable.h: 2074 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable.h: 2074-2077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 534-534 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 1375-1375 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 1759-1759 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 381-381 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 228-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 1077-1077 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 3760-3760 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_pair.h: 1034-1034					Loop Source Regions
				3083	0.00	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count

▶basic_string.h: 198 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_uninitialized.h: 119-119 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.tcc: 225-230 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.tcc: 251-251 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1102-1102 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 350-350 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 198-198 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 218-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 235-235 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 255-255 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 432-433					Loop Source Regions
				1136	0.00	0.00	0.00	0	42.05

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

▶stl_algobase.h: 401 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/regex.h: 920-920 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_algobase.h: 401-405 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_pair.h: 925-926					Loop Source Regions
				1484	0.00	0.00	0.00	0	35.42

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

▶llama-sampling.cpp: 364 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_iterator.h: 1102-1102 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-sampling.cpp: 364-365 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-sampling.cpp: 451-451					Loop Source Regions
				2478	0.00	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count

▶llama-batch.cpp: 95 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default		Run armclang_3						Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-batch.cpp: 95-100					Loop Source Regions
				483	0.00	0.00	0.00	0	33.33

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

▶llama-kv-cells.h: 125 - 0.00 %

ASM Loop ID	Vector Length Use (%)	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 armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_vector.h: 1150-1150 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-kv-cells.h: 125-129
						1880	0.00	0.00	0.00	0	35

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

▶ostream: 578 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run gcc_default		Run armclang_3		Run gcc_5
Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.tcc: 225-230 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.tcc: 251-251 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/ostream: 578-580 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/ostream: 673-673 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/new_allocator.h: 172-172 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/ios_base.h: 776-776 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 350-350 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 391-391 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/char_traits.h: 427-427 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-impl.cpp: 145-150 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-impl.cpp: 157-157 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 194-194 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 218-228 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 255-255 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 269-269 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 288-288 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 294-294 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 432-433 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 650-650 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/basic_string.h: 4082-4082					Loop Source Regions		Loop Source Regions		Loop Source Regions
1259	0.00	0.00	0.00	0	42.38

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

▶llama-vocab.cpp: 1216 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run gcc_default		Run armclang_3		Run gcc_5
Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable.h: 392-395 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/stl_vector.h: 99-99 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/hashtable_policy.h: 551-551 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 1216-1217 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2586-2586 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2597-2608 /opt/arm/gcc-14.2.0_AmazonLinux-2023/lib/gcc/aarch64-linux-gnu/14.2.0/../../../../include/c++/14.2.0/bits/unique_ptr.h: 1076-1076					Loop Source Regions		Loop Source Regions		Loop Source Regions
2578	0.00	0.00	0.00	16	58

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

▶ggml-alloc.c: 804 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run gcc_default		Run armclang_3		Run gcc_5
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-alloc.c: 804-811 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-alloc.c: 829-833 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-alloc.c: 841-842					Loop Source Regions		Loop Source Regions		Loop Source Regions
120	0.00	0.00	0.00	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.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis	Count	Analysis	Count	Analysis	Count

▶repack.cpp: 1979 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/repack.cpp: 1979-1982					Loop Source Regions		Loop Source Regions
		231	0.00	0.00	0.00	0	75

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

▶ggml.c: 1363 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1363-1372 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1379-1379 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1388-1388					Loop Source Regions		Loop Source Regions
		35	0.00	0.00	0.00	0	48.08

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

▶vec.h: 89 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 89-89					Loop Source Regions		Loop Source Regions
		1212	0.00	0.00	0.00	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.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis					Count	Analysis	Count	Analysis	Count

▶stl_tree.h: 777 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/new_allocator.h: 172-172 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_tree.h: 777-778 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_tree.h: 1930-1932					Loop Source Regions		Loop Source Regions
		427	0.00	0.00	0.00	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.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis					Count	Analysis	Count	Analysis	Count

▶ggml-impl.h: 192 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 192-192 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 288-297					Loop Source Regions		Loop Source Regions
		240	0.00	0.00	0.00	0	31.25

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

▶llama-kv-cells.h: 14 - 0.00 %

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 (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run gcc_default						Run armclang_3		Run gcc_5
Loop Source Regions		Loop Source Regions	/opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_tree.h: 178-182 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_tree.h: 191-196 /opt/arm/gcc-14.2.0_AmazonLinux-2023/include/c++/14.2.0/bits/stl_tree.h: 204-206 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-47-249.ec2.internal/175-802-9624/llama.cpp/build/llama.cpp/src/llama-kv-cells.h: 14-14					Loop Source Regions		Loop Source Regions
		2071	0.00	0.00	0.00	0	66.88

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

Report Configuration

Loops

▶quants.c: 979 - 200.36 %

▶quants.c: 1089 - 70.99 %

▶ggml-cpu.c: 533 - 1.08 %

▶vec.cpp: 231 - 0.58 %

▶vec.h: 411 - 0.46 %

▶ggml-cpu.c: 2879 - 0.41 %

▶vec.cpp: 311 - 0.28 %

▶ggml-cpu.c: 1183 - 0.21 %

▶quants.c: 910 - 0.20 %

▶ggml-impl.h: 355 - 0.17 %

▶ops.cpp: 6220 - 0.15 %

▶vec.cpp: 385 - 0.14 %

▶quants.c: 49 - 0.13 %

▶ops.cpp: 6210 - 0.13 %

▶vec.h: 491 - 0.12 %

▶ggml-cpu.c: 1125 - 0.12 %

▶ggml-cpu.c: 1193 - 0.09 %

▶ops.cpp: 6238 - 0.05 %

▶ops.cpp: 6446 - 0.03 %

▶binary-ops.cpp: 18 - 0.03 %

▶ggml-cpu.c: 3228 - 0.03 %

▶vec.h: 1045 - 0.02 %

▶binary-ops.cpp: 10 - 0.02 %

▶ggml-cpu.c: 1132 - 0.02 %

▶ggml-cpu.c: 1289 - 0.02 %

▶ops.cpp: 4325 - 0.02 %

▶ops.cpp: 8816 - 0.02 %

▶sampling.cpp: 125 - 0.01 %

▶vec.h: 646 - 0.01 %

▶ggml-cpu.c: 1291 - 0.01 %

▶traits.cpp: 13 - 0.01 %

▶ops.cpp: 8824 - 0.01 %

▶new_allocator.h: 172 - 0.00 %

▶ggml-cpu.cpp: 39 - 0.00 %

▶hashtable.h: 2077 - 0.00 %

▶hashtable.h: 2627 - 0.00 %

▶basic_string.h: 1077 - 0.00 %

▶ggml-cpu.cpp: 61 - 0.00 %

▶regex_executor.tcc: 180 - 0.00 %

▶stl_algo.h: 1594 - 0.00 %

▶ggml-cpu.c: 1197 - 0.00 %

▶vec.h: 677 - 0.00 %

▶ops.cpp: 8884 - 0.00 %

▶ops.cpp: 6389 - 0.00 %

▶ggml.c: 1367 - 0.00 %

▶hashtable_policy.h: 387 - 0.00 %

▶repack.cpp: 1968 - 0.00 %

▶llama-vocab.cpp: 2160 - 0.00 %

▶char_traits.h: 381 - 0.00 %

▶stl_heap.h: 229 - 0.00 %

▶vec.h: 710 - 0.00 %

▶ggml.c: 1444 - 0.00 %

▶basic_string.h: 218 - 0.00 %

▶ggml-impl.h: 346 - 0.00 %

▶stl_tree.h: 1963 - 0.00 %

▶stl_heap.h: 140 - 0.00 %

▶hashtable.h: 2074 - 0.00 %

▶basic_string.h: 198 - 0.00 %

▶stl_algobase.h: 401 - 0.00 %

▶llama-sampling.cpp: 364 - 0.00 %

▶llama-batch.cpp: 95 - 0.00 %

▶llama-kv-cells.h: 125 - 0.00 %

▶ostream: 578 - 0.00 %

▶llama-vocab.cpp: 1216 - 0.00 %

▶ggml-alloc.c: 804 - 0.00 %

▶repack.cpp: 1979 - 0.00 %

▶ggml.c: 1363 - 0.00 %

▶vec.h: 89 - 0.00 %

▶stl_tree.h: 777 - 0.00 %

▶ggml-impl.h: 192 - 0.00 %

▶llama-kv-cells.h: 14 - 0.00 %