OV - Compare Loops

MAQAO

options

Loops

▶kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 131 - 194.68 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 131-131					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 131-131					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc_4/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 131-131
2426	0.22	0.52	45.91	28.14	27.69	2092	0.22	1.12	75.18	28.14	27.69	2104	0.22	1.24	73.60	28.14	27.69

Sum on 1 analyzed binary loop (libggml-cpu.so - 2426)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2092)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2104)
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

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 115 - 1.93 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 115-118					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 115-118					Loop Source Regions
2410	0.19	0.01	0.70	0	15.63	2075	0.21	0.02	1.23	0	15.63

Sum on 1 analyzed binary loop (libggml-cpu.so - 2410)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2075)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count
Data Access Issues						Data Access Issues
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					0
Presence of indirect access					1	Presence of indirect access					1
Vectorization Roadblocks						Vectorization Roadblocks
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					0
Presence of indirect access					1	Presence of indirect access					1

▶ops.cpp: 6210 - 1.69 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6413-6413					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6211-6211 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6223-6231
						789	0.01	0.02	1.20	2.33	10.1	814	0.01	0.01	0.49	0	12.76

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.						Sum on 1 analyzed binary loop (libggml-cpu.so - 789)						Sum on 1 analyzed binary loop (libggml-cpu.so - 814)
Analysis					Count	Analysis					Count	Analysis					Count
						Loop Computation Issues						Loop Computation Issues
						Presence of expensive FP instructions					1	Presence of expensive FP instructions					1
						Presence of a large number of scalar integer instructions					1	Presence of a large number of scalar integer instructions					1
						Control Flow Issues						Control Flow Issues
						Presence of calls					1	Presence of calls					1
						Presence of more than 4 paths					1	Presence of more than 4 paths					0
						Vectorization Roadblocks						Vectorization Roadblocks
						Presence of calls					1	Presence of calls					1
						Presence of more than 4 paths					1	Presence of more than 4 paths					1

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 127 - 1.63 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 127-128 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 137-139					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 127-134					Loop Source Regions
2409	0.30	0.01	1.10	0	25	2074	0.02	0.00	0.09	0	0
						2073	0.08	0.01	0.44	0	21.88

Sum on 1 analyzed binary loop (libggml-cpu.so - 2409)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2073)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count
Data Access Issues						Data Access Issues
Presence of indirect access					1	Presence of indirect access					1
Vectorization Roadblocks						Vectorization Roadblocks
Presence of indirect access					1	Presence of indirect access					1

▶quants.c: 2683 - 1.44 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2683-2684 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2693-2699 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2769-2812					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2683-2683 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2693-2702 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2709-2758 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2769-2814					Loop Source Regions
2306	0.00	0.01	1.06	85.27	88.52	1970	0.01	0.01	0.38	59.53	74.79

Sum on 1 analyzed binary loop (libggml-cpu.so - 2306)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1970)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count
Control Flow Issues						Control Flow Issues
Presence of 2 to 4 paths						Presence of 2 to 4 paths					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 2 to 4 paths					0	Presence of 2 to 4 paths					1
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1

▶vec.cpp: 385 - 0.94 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1008-1034					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 385-387 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1009-1023 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1031-1034					Loop Source Regions
908	0.01	0.00	0.44	68.18	79.76	766	0.01	0.01	0.50	80	97.59

Sum on 1 analyzed binary loop (libggml-cpu.so - 908)						Sum on 1 analyzed binary loop (libggml-cpu.so - 766)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues
Presence of expensive FP instructions					1	Presence of expensive FP instructions					1
Data Access Issues						Data Access Issues
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1
Vectorization Roadblocks						Vectorization Roadblocks
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1

▶binary-ops.cpp: 10 - 0.88 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 10-10 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
433	0.00	0.00	0.27	0	12.5	410	0.01	0.01	0.35	25	50	416	0.01	0.00	0.26	25	50

Sum on 1 analyzed binary loop (libggml-cpu.so - 433)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
Data Access Issues
Presence of constant non-unit stride data access					1
Vectorization Roadblocks
Presence of constant non-unit stride data access					1

▶ops.cpp: 6238 - 0.83 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245
												838	0.01	0.01	0.83	0	14.18

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.						Sum on 1 analyzed binary loop (libggml-cpu.so - 838)
Analysis					Count	Analysis					Count	Analysis					Count
												Loop Computation Issues
												Presence of expensive FP instructions					1
												Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
												Control Flow Issues
												Presence of calls					1
												Data Access Issues
												Presence of constant non-unit stride data access					1
												Presence of indirect access					1
												Vectorization Roadblocks
												Presence of calls					1
												Presence of constant non-unit stride data access					1
												Presence of indirect access					1

▶quants.c: 2835 - 0.75 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2835-2835 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2879-2882 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/arm/quants.c: 2906-2913 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 772-772 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1614-1614 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1726-1726 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 7991-7991 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 8403-8403 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 10376-10376 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16103-16103 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16309-16309 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16345-16345 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16517-16517 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16589-16589 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 25465-25465 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 25803-25803 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 32322-32322
												1988	0.00	0.01	0.75	59.22	39.16

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.						Sum on 1 analyzed binary loop (libggml-cpu.so - 1988)
Analysis					Count	Analysis					Count	Analysis					Count
												Loop Computation Issues
												Presence of a large number of scalar integer instructions					1
												Data Access Issues
												Presence of constant non-unit stride data access					1
												Vectorization Roadblocks
												Presence of constant non-unit stride data access					1

▶vec.cpp: 390 - 0.72 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 390-390 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 1057-1057 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 786-786 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 814-814 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1388-1388 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1487-1487 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1628-1628 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 2188-2188 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 2216-2216 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 10248-10248 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 10997-10997 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 12284-12284 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 15253-15253 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 15426-15426 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16065-16065 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 21933-21933 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 25479-25479 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 26472-26472
												790	0.01	0.01	0.72	85.29	48.53

No Optimizer analysis found for any assembly loop. More loops can be 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 - 790)
Analysis					Count	Analysis					Count	Analysis					Count
												Loop Computation Issues
												Presence of expensive FP instructions					1
												Data Access Issues
												Presence of constant non-unit stride data access					1
												Vectorization Roadblocks
												Presence of constant non-unit stride data access					1

▶ops.cpp: 6220 - 0.64 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions						Loop Source Regions
1432	0.01	0.01	0.64	0	13.17

Sum on 1 analyzed binary loop (libggml-cpu.so - 1432)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues
Presence of expensive FP instructions					1
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
Control Flow Issues
Presence of calls					1
Data Access Issues
Presence of constant non-unit stride data access					1
Vectorization Roadblocks
Presence of calls					1
Presence of constant non-unit stride data access					1

▶kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 96 - 0.64 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 96-96 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 111-142 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/build/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 151-258					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 96-96 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 262-262 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1388-1388 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 6218-6218 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 10248-10248 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 10549-10549 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 11192-11192 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13324-13324 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13947-13947 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 14184-14184 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16065-16065 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 19789-19789 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 20386-20386 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 21569-21569 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 26440-26440 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 26510-26510 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30199-30199 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30211-30211					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc_4/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 96-96 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc_4/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 262-262 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1388-1388 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 6218-6218 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 10248-10248 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 10549-10549 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 11192-11192 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13324-13324 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13947-13947 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 14184-14184 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16065-16065 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 19789-19789 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 20386-20386 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 21569-21569 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 26440-26440 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 26510-26510 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30199-30199 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30211-30211
2389	0.01	0.00	0.15	77.23	48.22	2060	0.01	0.00	0.26	69.7	48.55	2073	0.01	0.00	0.23	69.7	48.55

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

▶binary-ops.cpp: 18 - 0.56 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 18-18 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/binary-ops.cpp: 31-32
538	0.00	0.00	0.18	0	11.84	494	0.00	0.00	0.20	25	50	502	0.00	0.00	0.17	25	50

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

▶ops.cpp: 4325 - 0.43 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 4325-4326
1278	0.00	0.00	0.16	94.12	95.59	1132	0.00	0.00	0.20	0	13.28	1170	0.00	0.00	0.06	17.39	28.26

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

▶ggml-cpu.c: 3228 - 0.32 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3229 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404
0	0.00	0.00	0.15	86.36	95.61	4	0.00	0.00	0.06	93.18	94.03	1	0.00	0.00	0.11	72.6	41.78

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

▶basic_string.h: 6237 - 0.26 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions	/usr/include/c++/11/bits/stl_function.h: 369-369 /usr/include/c++/11/bits/char_traits.h: 374-374 /usr/include/c++/11/bits/char_traits.h: 389-389 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable_policy.h: 1251-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/stl_pair.h: 466-466					Loop Source Regions	/usr/include/c++/11/bits/stl_function.h: 369-369 /usr/include/c++/11/bits/char_traits.h: 374-374 /usr/include/c++/11/bits/char_traits.h: 389-389 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable_policy.h: 1251-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/stl_pair.h: 466-466
						4472	0.02	0.00	0.09	0	25	4200	0.00	0.00	0.03	0	25
						4141	0.01	0.00	0.06	0	25	4211	0.00	0.00	0.03	0	25
												4540	0.01	0.00	0.06	0	25

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

▶vec.h: 411 - 0.25 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 411-458					Loop Source Regions
1753	0.01	0.00	0.13	100	100	1470	0.00	0.00	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.						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count

▶hashtable.h: 2386 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions	/usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable.h: 2386-2391 /usr/include/c++/11/bits/hashtable.h: 2402-2403					Loop Source Regions	/usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable.h: 2386-2391 /usr/include/c++/11/bits/hashtable.h: 2402-2403
						4180	0.01	0.00	0.03	0	25	4247	0.02	0.00	0.11	0	25
						4127	0.01	0.00	0.06	0	25

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

▶llama-vocab.cpp: 3216 - 0.17 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 3216-3216 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1916 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 195-195 /usr/include/c++/11/bits/basic_string.h: 211-211 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 3216-3216 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1916 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 195-195 /usr/include/c++/11/bits/basic_string.h: 211-211 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245
						3732	0.02	0.00	0.12	0	25	3801	0.01	0.00	0.06	0	25

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

▶vec.h: 486 - 0.14 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 486-491 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 502-502 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8853-8853 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 14177-14177
												1526	0.00	0.00	0.14	10	19.69

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

▶vec.h: 646 - 0.14 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 646-653					Loop Source Regions
1282	0.00	0.00	0.09	100	100	1466	0.00	0.00	0.03	100	100
1756	0.00	0.00	0.02	100	100

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

▶new_allocator.h: 172 - 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	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/new_allocator.h: 172-172 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 223-228 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 246-246 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 269-269 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 288-288 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 294-294 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 1182-1182 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 1575-1576 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 387-387 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 2060-2060 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2751-2754 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/char_traits.h: 350-350 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_iterator.h: 1102-1102 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_construct.h: 162-162					Loop Source Regions						Loop Source Regions
2767	0.01	0.00	0.05	0	22.72
2514	0.00	0.00	0.02	0	19.72
2764	0.01	0.00	0.04	0	17.19
745	0.00	0.00	0.02	0	25

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

▶ops.cpp: 6446 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6457					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6446-6447 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6453-6456
1437	0.00	0.00	0.04	0	12.5	799	0.00	0.00	0.06	37.5	40.63	848	0.00	0.00	0.03	37.5	40.63

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

▶vec.cpp: 231 - 0.11 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 231-262					Loop Source Regions
901	0.00	0.00	0.05	96	97	763	0.00	0.00	0.06	100	100

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

▶vec.cpp: 311 - 0.09 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-311 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16058-16058 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31977-31977
												782	0.00	0.00	0.09	52.63	50

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

▶vec.h: 491 - 0.09 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-491 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16058-16058 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 26465-26465 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31977-31977
												1518	0.00	0.00	0.09	27.59	50

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

▶basic_string.h: 194 - 0.08 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.tcc: 225-230 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.tcc: 251-251 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/new_allocator.h: 172-172 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 1004-1004 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 1725-1726 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 1732-1736 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 194-198 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 218-228 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 255-255 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 269-271 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 288-288 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 294-294 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 393-393 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 414-415 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 432-433 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 591-591 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 650-650 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 881-881 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 897-897 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 906-906 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 1077-1077 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 1084-1084 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/char_traits.h: 350-350 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/char_traits.h: 391-391 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/char_traits.h: 427-427 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_pair.h: 1137-1137					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 3216-3216 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1916 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 195-195 /usr/include/c++/11/bits/basic_string.h: 211-211 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245					Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 3216-3216 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1916 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 195-195 /usr/include/c++/11/bits/basic_string.h: 211-211 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245
2483	0.00	0.00	0.02	0	23.43	3728	0.01	0.00	0.03	0	25	3797	0.00	0.00	0.03	0	25

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

▶ops.cpp: 8825 - 0.06 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8826					Loop Source Regions
						1463	0.00	0.00	0.06	0	0

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

▶basic_string.h: 165 - 0.06 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions	/usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 399-399 /usr/include/c++/11/bits/char_traits.h: 431-431 /usr/include/c++/11/bits/char_traits.h: 437-437 /usr/include/c++/11/ostream: 525-525 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 165-165 /usr/include/c++/11/bits/basic_string.h: 187-195 /usr/include/c++/11/bits/basic_string.h: 219-219 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245 /usr/include/c++/11/bits/basic_string.h: 356-356 /usr/include/c++/11/bits/basic_string.h: 6536-6536 /usr/include/c++/11/bits/basic_string.tcc: 215-219 /usr/include/c++/11/bits/basic_string.tcc: 232-232 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-impl.cpp: 149-157					Loop Source Regions	/usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 399-399 /usr/include/c++/11/bits/char_traits.h: 431-431 /usr/include/c++/11/bits/char_traits.h: 437-437 /usr/include/c++/11/ostream: 525-525 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 165-165 /usr/include/c++/11/bits/basic_string.h: 187-195 /usr/include/c++/11/bits/basic_string.h: 219-219 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245 /usr/include/c++/11/bits/basic_string.h: 356-356 /usr/include/c++/11/bits/basic_string.h: 6536-6536 /usr/include/c++/11/bits/basic_string.tcc: 215-219 /usr/include/c++/11/bits/basic_string.tcc: 232-232 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-impl.cpp: 149-157
						1648	0.01	0.00	0.03	0	19.04	1677	0.00	0.00	0.03	0	19.77

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

▶hashtable.h: 2081 - 0.05 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2081-2081 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 228-228 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 1077-1077 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 3760-3760 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/char_traits.h: 381-381 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 534-534 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 1377-1377 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 1761-1761					Loop Source Regions						Loop Source Regions
2886	0.01	0.00	0.04	0	25
2633	0.00	0.00	0.02	0	25

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

▶hashtable.h: 2631 - 0.04 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2631-2648 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 387-387 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 534-534 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 1377-1377					Loop Source Regions						Loop Source Regions
2650	0.01	0.00	0.04	0	25

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

▶ops.cpp: 8885 - 0.04 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8885-8886					Loop Source Regions						Loop Source Regions
1744	0.00	0.00	0.04	85.71	89.29

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

▶ggml-cpu.c: 2879 - 0.03 %

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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2898					Loop Source Regions
						60	0.00	0.00	0.03	0	16.48

No Optimizer analysis found for any assembly loop. More loops can be 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

▶llama-vocab.cpp: 2343 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2343-2345 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/stl_vector.h: 1046-1046 /usr/include/c++/11/bits/basic_string.h: 6250-6250					Loop Source Regions
						3896	0.01	0.00	0.03	0	14.58

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.
Analysis					Count	Analysis					Count	Analysis					Count

▶llama-vocab.cpp: 1575 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 437-437 /usr/include/c++/11/bits/unordered_map.h: 389-389 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 1575-1575 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 1725-1726 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 1732-1736 /usr/include/c++/11/bits/hashtable_policy.h: 219-219 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable_policy.h: 1268-1268 /usr/include/c++/11/bits/hashtable.h: 308-308 /usr/include/c++/11/bits/hashtable.h: 795-795 /usr/include/c++/11/bits/hashtable.h: 810-811 /usr/include/c++/11/bits/hashtable.h: 1890-1895 /usr/include/c++/11/bits/hashtable.h: 1902-1910 /usr/include/c++/11/bits/hashtable.h: 1970-1970 /usr/include/c++/11/bits/hashtable.h: 2014-2021 /usr/include/c++/11/bits/hashtable.h: 2029-2029 /usr/include/c++/11/bits/functional_hash.h: 198-198 /usr/include/c++/11/ext/new_allocator.h: 127-127 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 168-168 /usr/include/c++/11/bits/basic_string.h: 187-195 /usr/include/c++/11/bits/basic_string.h: 201-201 /usr/include/c++/11/bits/basic_string.h: 219-219 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245 /usr/include/c++/11/bits/basic_string.h: 255-255 /usr/include/c++/11/bits/basic_string.h: 320-320 /usr/include/c++/11/bits/basic_string.h: 459-459 /usr/include/c++/11/bits/basic_string.h: 490-490 /usr/include/c++/11/bits/basic_string.h: 568-568 /usr/include/c++/11/bits/basic_string.h: 921-921 /usr/include/c++/11/bits/basic_string.h: 927-927 /usr/include/c++/11/bits/stl_pair.h: 353-353
												3973	0.00	0.00	0.03	0	23.54

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

▶ggml-impl.h: 354 - 0.03 %

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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 3228-3231 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 354-354 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-404
												0	0.00	0.00	0.03	0	10.59

No Optimizer analysis found for any assembly loop. More loops can be 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

▶kai_matmul_clamp_f32_qsi8d32p1x8_qsi4c32p4x8_1x4x32_neon_dotprod.c: 128 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc_4/_deps/kleidiai_download-src/kai/ukernels/matmul/matmul_clamp_f32_qsi8d32p_qsi4c32p/kai_matmul_clamp_f32_qsi8d32p1x8_qsi4c32p4x8_1x4x32_neon_dotprod.c: 128-128
												2089	0.00	0.00	0.03	57.14	39.64

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.
Analysis					Count	Analysis					Count	Analysis					Count

▶ops.cpp: 8787 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 751-751 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 51-51 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8787-8787 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8817-8819 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8825-8826 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 8841-8841
												1533	0.00	0.00	0.03	0	26.88

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.
Analysis					Count	Analysis					Count	Analysis					Count

▶vec.h: 677 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 677-677 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1487-1487 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16065-16065 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 26472-26472
												1169	0.00	0.00	0.03	50	50

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

▶kleidiai.cpp: 535 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 535-535 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 546-547
												2048	0.00	0.00	0.03	0	25

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

▶kleidiai.cpp: 92 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/gcc_4/_deps/kleidiai_download-src/kai/kai_common.h: 143-143 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 92-92 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 341-342 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/kleidiai/kleidiai.cpp: 348-382 /usr/include/c++/11/variant: 1594-1594 /usr/include/c++/11/variant: 1726-1727
												2044	0.00	0.00	0.03	0	22.98

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

▶llama-vocab.cpp: 2751 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/usr/include/c++/11/bits/char_traits.h: 357-357 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2751-2754 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 191-195 /usr/include/c++/11/bits/basic_string.h: 239-239 /usr/include/c++/11/bits/basic_string.h: 245-245 /usr/include/c++/11/bits/basic_string.h: 921-921 /usr/include/c++/11/bits/basic_string.h: 978-978 /usr/include/c++/11/bits/basic_string.h: 1344-1345
												3834	0.00	0.00	0.03	0	21.92

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.
Analysis					Count	Analysis					Count	Analysis					Count

▶gguf.cpp: 142 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/gguf.cpp: 142-144
												1214	0.00	0.00	0.03	0	9.38

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

▶llama-vocab.cpp: 2312 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions						Loop Source Regions						Loop Source Regions	/usr/include/c++/11/bits/stl_set.h: 512-512 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2312-2331 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/stl_vector.h: 1046-1046 /usr/include/c++/11/bits/basic_string.h: 6250-6250
												3948	0.00	0.00	0.03	0	21.58

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.
Analysis					Count	Analysis					Count	Analysis					Count

▶vector.tcc: 614 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/new_allocator.h: 151-151 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/new_allocator.h: 172-172 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/new_allocator.h: 191-191 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-vocab.cpp: 2399-2400 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_uninitialized.h: 1117-1117 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_uninitialized.h: 1129-1129 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/vector.tcc: 614-614 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/vector.tcc: 635-635 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/vector.tcc: 649-649 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/vector.tcc: 692-694 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 993-993 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 1131-1131 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 1285-1290 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 1908-1912					Loop Source Regions						Loop Source Regions
2465	0.00	0.00	0.02	0	23.05

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.
Analysis					Count	Analysis					Count	Analysis					Count

▶traits.cpp: 13 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/traits.cpp: 13-17 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_iterator.h: 1102-1102					Loop Source Regions						Loop Source Regions
396	0.00	0.00	0.02	0	25

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

▶vec.h: 710 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 710-717					Loop Source Regions						Loop Source Regions
1754	0.00	0.00	0.02	96	97

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

▶ops.cpp: 5552 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 5552-5563					Loop Source Regions						Loop Source Regions
1357	0.00	0.00	0.02	0	25

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

▶ggml-quants.c: 314 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 346-346 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 360-360 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-impl.h: 369-377 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml-quants.c: 314-322					Loop Source Regions						Loop Source Regions
310	0.00	0.00	0.02	45.68	24.85

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

▶stl_tree.h: 1963 - 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 (%)
Run orig_default						Run gcc_default						Run gcc_4
Loop Source Regions	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 1963-1964 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_function.h: 405-405					Loop Source Regions						Loop Source Regions
282	0.00	0.00	0.02	0	25

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

×