OV - Compare Functions

Functions

▶kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 119 - 195.76 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default							Run gcc_4
	/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: 119-131 /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: 682-682							/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: 119-131 /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: 682-682							/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: 119-131 /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: 682-682
565	46.21	0.52	0.22	64	4.62	0.01	607	75.67	1.13	0.22	64	9.12	0.01	609	73.88	1.25	0.22	64	9.30	0.01

▶<unknown>: 0 - 74.20 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default							Run gcc_4

-1	0.13	0.00	0.01	6	0.49	0.00	-1	0.06	0.00	0.01	1	0.00	0.00	-1	0.09	0.00	0.01	1	0.00	0.00
62	0.07	0.00	0.01	2	0.02	0.01	166	10.89	0.16	0.05	64	3.81	0.01	-1	0.09	0.00	0.00	3	0.06	0.00
98	0.02	0.00	0.00	1	0.00	0.00	62	0.03	0.00	0.01	1	0.00	0.00	166	10.67	0.18	0.05	64	4.04	0.01
1293	0.13	0.00	0.02	4	0.28	0.01	61	0.03	0.00	0.01	1	0.00	0.00	62	0.09	0.00	0.01	1	0.00	0.00
927	0.27	0.00	0.01	14	0.32	0.00	1295	0.26	0.00	0.05	1	0.00	0.00	1295	0.32	0.01	0.05	1	0.00	0.00
822	0.07	0.00	0.00	4	0.05	0.00	927	0.56	0.01	0.01	18	0.49	0.00	927	0.75	0.01	0.01	21	0.99	0.00
934	0.04	0.00	0.00	2	0.01	0.00	822	0.03	0.00	0.00	1	0.00	0.00	822	0.03	0.00	0.00	1	0.00	0.00
784	0.02	0.00	0.00	1	0.00	0.00	1204	0.09	0.00	0.02	1	0.00	0.00	1204	0.03	0.00	0.00	1	0.00	0.00
1114	0.02	0.00	0.00	1	0.00	0.00	824	0.03	0.00	0.00	1	0.00	0.00	467	0.03	0.00	0.00	1	0.00	0.00
1295	0.11	0.00	0.03	1	0.00	0.00	1114	0.03	0.00	0.01	1	0.00	0.00	1114	0.03	0.00	0.00	1	0.00	0.00
1115	0.04	0.00	0.01	1	0.00	0.00	1293	0.15	0.00	0.02	3	0.63	0.01	1115	0.11	0.00	0.02	1	0.00	0.00
510	0.05	0.00	0.01	1	0.00	0.00	1115	0.09	0.00	0.02	1	0.00	0.00	510	0.14	0.00	0.03	1	0.00	0.00
1122	0.02	0.00	0.00	1	0.00	0.00	1300	0.06	0.00	0.01	1	0.00	0.00	1122	0.06	0.00	0.01	1	0.00	0.00
1124	0.04	0.00	0.01	1	0.00	0.00	510	0.12	0.00	0.02	1	0.00	0.00	1131	0.06	0.00	0.01	1	0.00	0.00
1131	0.07	0.00	0.02	1	0.00	0.00	1124	0.03	0.00	0.01	1	0.00	0.00	1303	0.03	0.00	0.00	1	0.00	0.00
1689	1.23	0.01	0.02	43	0.94	0.00	1303	0.06	0.00	0.01	1	0.00	0.00	1293	0.20	0.00	0.03	3	0.32	0.01
1956	0.04	0.00	0.00	2	0.02	0.00	1131	0.09	0.00	0.02	1	0.00	0.00	2811	0.03	0.00	0.00	1	0.00	0.00
786	0.02	0.00	0.00	1	0.00	0.00	2811	0.06	0.00	0.01	1	0.00	0.00	2936	0.03	0.00	0.00	1	0.00	0.00
857	38.09	0.43	0.22	64	6.22	0.03	2543	0.06	0.00	0.01	1	0.00	0.00	2543	0.06	0.00	0.01	1	0.00	0.00
837	0.04	0.00	0.00	2	0.07	0.00	2957	0.03	0.00	0.01	1	0.00	0.00	3009	0.03	0.00	0.00	1	0.00	0.00
529	0.02	0.00	0.00	1	0.00	0.00	2950	0.03	0.00	0.01	1	0.00	0.00	3033	0.17	0.00	0.03	1	0.00	0.00
531	4.75	0.05	0.05	63	2.76	0.01	3033	0.15	0.00	0.03	1	0.00	0.00	1	0.03	0.00	0.00	1	0.00	0.00
1247	0.07	0.00	0.00	4	0.04	0.00	378	0.32	0.00	0.00	11	0.08	0.00	197	0.03	0.00	0.00	1	0.00	0.00
841	0.05	0.00	0.00	3	0.01	0.00	338	0.35	0.01	0.01	12	0.48	0.00	-1	0.03	0.00	0.00	1	0.00	0.00
-1	0.05	0.00	0.00	3	0.08	0.00								378	0.49	0.01	0.01	16	0.53	0.00
-1	0.02	0.00	0.00	1	0.00	0.00								338	0.40	0.01	0.01	12	1.24	0.00
350	0.02	0.00	0.00	1	0.00	0.00
378	0.27	0.00	0.00	15	0.05	0.00
338	0.38	0.00	0.01	18	0.62	0.00
1	0.02	0.00	0.00	1	0.00	0.00
197	0.04	0.00	0.01	1	0.00	0.00
2811	0.02	0.00	0.00	1	0.00	0.00
2543	0.02	0.00	0.00	1	0.00	0.00
2528	0.02	0.00	0.00	1	0.00	0.00
-1	0.27	0.00	0.00	15	0.04	0.00
-1	0.09	0.00	0.03	1	0.00	0.00

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 36 - 11.00 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/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/kai_common.h: 143-143 /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: 36-36 /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: 80-95 /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: 102-158							/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/gcc_4/_deps/kleidiai_download-src/kai/ukernels/matmul/pack/kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 36-36 /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_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 80-95 /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_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 102-158
	562	5.01	0.07	0.86	1	0.00	0.00	564	5.99	0.10	1.04	1	0.00	0.00

▶ops.cpp: 6210 - 2.63 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default							Run gcc_4
	/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: 6261-6279 /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: 6285-6303 /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: 6310-6312 /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: 6333-6361 /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: 6367-6379 /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: 6385-6393 /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: 6407-6484 /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: 6490-6490							/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: 6310-6314 /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: 6320-6323 /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: 6331-6379 /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: 6385-6395 /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: 6402-6484 /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: 6490-6490							/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: 6218-6231
318	0.71	0.01	0.01	34	0.42	0.00	299	1.35	0.02	0.01	36	1.10	0.00	298	0.57	0.01	0.01	18	0.68	0.00

▶quants.c: 2466 - 2.19 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default							Run gcc_4
	/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: 2466-2466 /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: 2481-2495 /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: 2506-2558 /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: 2565-2590 /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: 2600-2616 /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: 2650-2660 /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: 2666-2668 /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: 2675-2675 /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: 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: 2769-2812 /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: 2821-2821 /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: 2923-2923							/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: 2466-2466 /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: 2481-2506 /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: 2572-2575 /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: 2600-2615 /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: 2653-2654 /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: 2668-2676 /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: 2765-2814 /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: 2821-2821 /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: 2923-2923 /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: 2174-2174 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 6414-6414 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 7465-7465 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13617-13617 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 15065-15065 /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: 16589-16589 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 20765-20765 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 21604-21604 /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: 26367-26367 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30698-30698 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30781-30781 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31056-31056 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 34664-34664							/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: 2466-2466 /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: 2481-2484 /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: 2490-2506 /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: 2572-2575 /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: 2632-2632 /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: 2653-2654 /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: 2668-2668 /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: 2824-2824 /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: 2906-2916 /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: 2923-2923 /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: 2174-2174 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 6358-6358 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 6414-6414 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 6456-6456 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 7465-7465 /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: 13617-13617 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 15065-15065 /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: 20765-20765 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 21604-21604 /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: 26367-26367 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30698-30698 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 30781-30781 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31056-31056 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 32322-32322 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 34664-34664
431	1.06	0.01	0.00	58	0.05	0.00	456	0.38	0.01	0.01	13	0.46	0.00	458	0.75	0.01	0.00	26	0.06	0.00

▶ops.cpp: 8690 - 2.15 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/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: 282-357 /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: 403-474 /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: 638-661 /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: 703-725 /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 /usr/include/c++/11/cmath: 1582-1583 /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: 8690-8706 /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: 8712-8720 /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: 8727-8749 /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: 8755-8819 /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: 8825-8853 /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: 8859-8862 /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: 8868-8873 /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: 8881-8908 /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: 8920-8920 /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: 8926-8927 /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: 8936-8939							/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: 375-375 /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: 386-387 /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: 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: 502-503 /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: 671-671 /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 /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: 687-688 /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: 734-740 /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: 750-751 /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-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 /usr/include/c++/11/cmath: 1582-1583 /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: 8690-8706 /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: 8712-8720 /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: 8727-8749 /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: 8755-8819 /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: 8825-8847 /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 /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: 8859-8873 /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: 8881-8908 /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: 8920-8920 /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: 8926-8927 /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: 8936-8939 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1487-1487 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 14177-14177 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 14184-14184 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 15253-15253 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16058-16058 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16065-16065 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 26465-26465 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 26472-26472 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31835-31835 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31977-31977
	359	1.14	0.02	0.01	35	0.74	0.00	361	1.00	0.02	0.01	29	0.81	0.00

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 80 - 2.03 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 80-95 /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: 102-158
521	2.03	0.02	0.56	1	0.00	0.00

▶vec.cpp: 369 - 1.65 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default							Run gcc_4
	/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: 369-369 /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.cpp: 402-405 /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: 957-957 /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							/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: 369-370 /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.cpp: 405-405 /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							/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: 369-370 /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.cpp: 402-405 /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: 957-957 /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: 10549-10549 /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
270	0.44	0.00	0.01	22	0.39	0.00	292	0.50	0.01	0.01	16	0.66	0.00	293	0.72	0.01	0.01	21	0.77	0.00

▶ops.cpp: 8692 - 1.10 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/cmath: 2544-2544 /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: 282-357 /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: 403-405 /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: 411-474 /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: 638-662 /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: 704-725 /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: 8692-8692 /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: 8700-8702 /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: 8712-8720 /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: 8727-8730 /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: 8742-8749 /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: 8755-8819 /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: 8825-8834 /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: 8841-8847 /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 /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: 8859-8862 /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: 8868-8873 /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: 8881-8908 /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: 8920-8920 /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: 8926-8927 /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: 8936-8939
338	1.10	0.01	0.02	42	0.79	0.00

▶ops.cpp: 6238 - 0.97 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/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: 6310-6314 /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: 6320-6323 /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: 6331-6379 /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: 6385-6395 /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: 6402-6484 /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: 6490-6490
		302	0.97	0.02	0.01	27	0.88	0.00

▶binary-ops.cpp: 10 - 0.91 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default							Run gcc_4
	/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/common.h: 61-68 /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 /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: 42-45 /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: 54-65 /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: 84-95 /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: 101-101 /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: 110-110 /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: 121-146 /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-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: 355-355 /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 /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: 518-518 /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: 537-541							/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/common.h: 58-68 /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 /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: 42-45 /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: 54-65 /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: 84-101 /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: 122-146 /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-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 /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: 518-519 /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: 536-541							/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/common.h: 58-68 /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 /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: 42-45 /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: 54-65 /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: 84-101 /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: 122-146 /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-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 /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: 518-519 /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: 536-541
246	0.27	0.00	0.00	15	0.04	0.00	268	0.38	0.01	0.01	13	0.47	0.00	269	0.26	0.00	0.01	8	0.71	0.00

▶kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 21 - 0.64 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default							Run gcc_4
	/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/kai_common.h: 136-136 /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: 21-27 /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: 67-75 /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: 92-96 /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 /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: 264-271 /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: 282-292 /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: 299-340							/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: 21-27 /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: 67-75 /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: 90-96 /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: 114-120 /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: 262-271 /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: 289-292 /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: 335-340 /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: 6449-6449 /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: 26404-26404 /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							/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: 21-27 /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: 67-75 /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: 90-96 /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: 114-120 /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: 262-271 /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: 289-292 /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: 335-340 /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: 6449-6449 /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: 26404-26404 /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
506	0.15	0.00	0.01	7	0.44	0.00	547	0.26	0.00	0.01	9	0.57	0.00	549	0.23	0.00	0.01	6	1.62	0.00

▶ops.cpp: 4304 - 0.58 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default							Run gcc_4
	/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: 638-661 /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: 4304-4306 /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: 4314-4338 /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: 4351-4355 /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: 4362-4365							/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: 638-661 /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: 4304-4343 /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: 4351-4355 /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: 4362-4365							/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: 671-671 /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 /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: 687-688 /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: 4304-4343 /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: 4351-4355 /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: 4362-4365 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 1487-1487 /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: 26472-26472
293	0.26	0.00	0.00	14	0.05	0.00	317	0.20	0.00	0.00	7	0.07	0.00	319	0.11	0.00	0.00	4	0.10	0.00

▶binary-ops.cpp: 18 - 0.56 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default							Run gcc_4
	/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/common.h: 61-68 /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 /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: 42-45 /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: 54-65 /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: 84-95 /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: 101-101 /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: 110-110 /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: 121-139 /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: 152-154 /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-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: 355-355 /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 /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: 518-518 /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: 537-541							/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/common.h: 58-68 /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 /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: 42-45 /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: 54-65 /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: 84-101 /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: 122-139 /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: 152-154 /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-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 /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: 518-519 /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: 536-541							/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/common.h: 58-68 /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 /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: 42-45 /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: 54-65 /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: 84-101 /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: 122-139 /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: 152-154 /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-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 /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: 518-519 /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: 536-541
248	0.18	0.00	0.00	10	0.24	0.00	270	0.20	0.00	0.00	7	0.06	0.00	271	0.17	0.00	0.00	6	0.07	0.00

▶hashtable.h: 1827 - 0.35 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/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: 1600-1600 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 1827-1827 /usr/include/c++/11/bits/hashtable.h: 1833-1837 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/hashtable.h: 1849-1849 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/stl_pair.h: 466-466							/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: 1600-1600 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 1827-1827 /usr/include/c++/11/bits/hashtable.h: 1833-1837 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/hashtable.h: 1849-1849 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/stl_pair.h: 466-466
	1811	0.18	0.00	0.03	1	0.00	0.00	1812	0.17	0.00	0.03	1	0.00	0.00

▶hashtable.h: 795 - 0.29 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/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: 1255-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1600-1600 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 795-795 /usr/include/c++/11/bits/hashtable.h: 813-813 /usr/include/c++/11/bits/hashtable.h: 1588-1588 /usr/include/c++/11/bits/hashtable.h: 1596-1596 /usr/include/c++/11/bits/hashtable.h: 1833-1837 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/functional_hash.h: 198-198 /usr/include/c++/11/bits/basic_string.h: 6237-6237							/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: 1255-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1600-1600 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 795-795 /usr/include/c++/11/bits/hashtable.h: 813-813 /usr/include/c++/11/bits/hashtable.h: 1588-1588 /usr/include/c++/11/bits/hashtable.h: 1596-1596 /usr/include/c++/11/bits/hashtable.h: 1833-1837 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/functional_hash.h: 198-198 /usr/include/c++/11/bits/basic_string.h: 6237-6237
	1896	0.18	0.00	0.03	1	0.00	0.00	1897	0.11	0.00	0.02	1	0.00	0.00

▶llama-vocab.cpp: 3216 - 0.23 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/usr/include/c++/11/bits/stl_tree.h: 735-735 /usr/include/c++/11/bits/stl_tree.h: 780-780 /usr/include/c++/11/bits/stl_tree.h: 1887-1889 /usr/include/c++/11/bits/stl_construct.h: 162-162 /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: 3216-3217 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1916 /usr/include/c++/11/bits/hashtable.h: 422-422 /usr/include/c++/11/bits/hashtable.h: 446-446 /usr/include/c++/11/bits/hashtable.h: 454-454 /usr/include/c++/11/bits/hashtable.h: 463-463 /usr/include/c++/11/bits/hashtable.h: 2321-2323 /usr/include/c++/11/bits/stl_vector.h: 335-336 /usr/include/c++/11/bits/stl_vector.h: 353-353 /usr/include/c++/11/bits/stl_vector.h: 678-680 /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 /usr/include/c++/11/bits/unique_ptr.h: 85-85 /usr/include/c++/11/bits/unique_ptr.h: 360-360							/usr/include/c++/11/bits/stl_tree.h: 735-735 /usr/include/c++/11/bits/stl_tree.h: 780-780 /usr/include/c++/11/bits/stl_tree.h: 1887-1889 /usr/include/c++/11/bits/stl_construct.h: 162-162 /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: 3216-3217 /usr/include/c++/11/bits/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1916 /usr/include/c++/11/bits/hashtable.h: 422-422 /usr/include/c++/11/bits/hashtable.h: 446-446 /usr/include/c++/11/bits/hashtable.h: 454-454 /usr/include/c++/11/bits/hashtable.h: 463-463 /usr/include/c++/11/bits/hashtable.h: 2321-2323 /usr/include/c++/11/bits/stl_vector.h: 335-336 /usr/include/c++/11/bits/stl_vector.h: 353-353 /usr/include/c++/11/bits/stl_vector.h: 678-680 /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 /usr/include/c++/11/bits/unique_ptr.h: 85-85 /usr/include/c++/11/bits/unique_ptr.h: 360-360
	1639	0.15	0.00	0.03	1	0.00	0.00	1640	0.09	0.00	0.01	1	0.00	0.00

▶ggml-cpu.c: 1424 - 0.23 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/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: 1424-1429 /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: 1436-1445 /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: 1454-1465 /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: 1474-1475 /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: 1483-1539 /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: 1552-1560 /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: 1567-1579 /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: 1585-1601 /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: 1623-1628 /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: 1634-1642 /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: 1650-1650 /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: 1664-1785 /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: 1792-2040 /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: 2047-2047 /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: 2055-2055 /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: 2061-2076 /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: 2085-2096 /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: 2862-2873 /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 /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: 137-137							/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: 1424-1429 /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: 1436-1445 /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: 1454-1465 /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: 1474-1475 /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: 1483-1539 /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: 1552-1560 /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: 1567-1579 /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: 1585-1601 /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: 1623-1628 /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: 1634-1642 /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: 1650-1650 /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: 1664-1785 /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: 1792-2040 /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: 2047-2047 /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: 2055-2055 /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: 2061-2076 /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: 2085-2096 /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: 2862-2873 /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 /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: 137-137
	50	0.12	0.00	0.00	4	0.09	0.00	51	0.11	0.00	0.00	4	0.08	0.00

▶hashtable.h: 434 - 0.23 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/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_policy.h: 486-486 /usr/include/c++/11/bits/hashtable_policy.h: 1933-1933 /usr/include/c++/11/bits/hashtable.h: 434-437 /usr/include/c++/11/bits/hashtable.h: 446-446 /usr/include/c++/11/bits/hashtable.h: 454-454 /usr/include/c++/11/bits/hashtable.h: 463-463 /usr/include/c++/11/bits/hashtable.h: 2355-2355 /usr/include/c++/11/bits/hashtable.h: 2363-2370 /usr/include/c++/11/bits/hashtable.h: 2384-2403 /usr/include/c++/11/bits/hashtable.h: 2410-2410 /usr/include/c++/11/ext/new_allocator.h: 111-117 /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/hashtable_policy.h: 287-287 /usr/include/c++/11/bits/hashtable_policy.h: 434-434 /usr/include/c++/11/bits/hashtable_policy.h: 486-486 /usr/include/c++/11/bits/hashtable_policy.h: 1933-1933 /usr/include/c++/11/bits/hashtable.h: 434-437 /usr/include/c++/11/bits/hashtable.h: 446-446 /usr/include/c++/11/bits/hashtable.h: 454-454 /usr/include/c++/11/bits/hashtable.h: 463-463 /usr/include/c++/11/bits/hashtable.h: 2355-2355 /usr/include/c++/11/bits/hashtable.h: 2363-2370 /usr/include/c++/11/bits/hashtable.h: 2384-2403 /usr/include/c++/11/bits/hashtable.h: 2410-2410 /usr/include/c++/11/ext/new_allocator.h: 111-117 /usr/include/c++/11/ext/new_allocator.h: 127-127 /usr/include/c++/11/ext/new_allocator.h: 145-145
	1805	0.06	0.00	0.01	1	0.00	0.00	1817	0.14	0.00	0.03	1	0.00	0.00
	1816	0.03	0.00	0.01	1	0.00	0.00

▶ggml-cpu.c: 3228 - 0.21 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default							Run gcc_default							Run gcc_4
	/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: 389-404							/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: 389-404
12	0.15	0.00	0.00	8	0.27	0.00	30	0.06	0.00	0.00	2	0.12	0.00

▶vec.cpp: 207 - 0.20 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default	Run gcc_default							Run gcc_4
		/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: 207-207 /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: 220-279 /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: 336-337
	290	0.20	0.00	0.00	7	0.07	0.00

▶vec.cpp: 221 - 0.15 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 221-221 /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: 231-279 /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: 336-337
268	0.15	0.00	0.00	8	0.04	0.00

▶ggml-cpu.c: 3201 - 0.14 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/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: 3201-3201 /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
		27	0.14	0.00	0.00	5	0.08	0.00

▶llama-vocab.cpp: 1575 - 0.12 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/usr/include/c++/11/bits/stl_tree.h: 208-211 /usr/include/c++/11/bits/stl_tree.h: 368-368 /usr/include/c++/11/bits/stl_tree.h: 376-376 /usr/include/c++/11/bits/stl_tree.h: 735-735 /usr/include/c++/11/bits/stl_tree.h: 745-745 /usr/include/c++/11/bits/stl_tree.h: 780-780 /usr/include/c++/11/bits/stl_tree.h: 788-792 /usr/include/c++/11/bits/stl_tree.h: 1000-1000 /usr/include/c++/11/bits/stl_tree.h: 1254-1254 /usr/include/c++/11/bits/stl_tree.h: 1904-1905 /usr/include/c++/11/bits/stl_tree.h: 1920-1924 /usr/include/c++/11/bits/stl_tree.h: 1936-1937 /usr/include/c++/11/bits/stl_tree.h: 1971-1975 /usr/include/c++/11/bits/stl_tree.h: 2485-2488 /usr/include/c++/11/bits/stl_tree.h: 2497-2500 /usr/include/c++/11/bits/stl_tree.h: 2539-2539 /usr/include/c++/11/bits/stl_uninitialized.h: 578-578 /usr/include/c++/11/bits/stl_set.h: 512-512 /usr/include/c++/11/bits/stl_set.h: 734-734 /usr/include/c++/11/bits/stl_set.h: 749-749 /usr/include/c++/11/bits/stl_function.h: 400-400 /usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 389-389 /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/bits/charconv.h: 52-52 /usr/include/c++/11/bits/charconv.h: 58-63 /usr/include/c++/11/bits/charconv.h: 83-99 /usr/include/c++/11/string_view: 132-133 /usr/include/c++/11/bits/stl_construct.h: 162-162 /usr/include/c++/11/bits/unordered_map.h: 389-389 /usr/include/c++/11/bits/unordered_map.h: 980-980 /usr/include/c++/11/bits/stl_algobase.h: 430-432 /usr/include/c++/11/bits/stl_algobase.h: 1515-1515 /usr/include/c++/11/bits/stl_iterator.h: 1028-1028 /usr/include/c++/11/bits/stl_iterator.h: 1054-1054 /usr/include/c++/11/bits/stl_iterator.h: 1091-1091 /usr/include/c++/11/bits/stl_iterator.h: 1271-1271 /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: 1661-1726 /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 /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: 1743-1766 /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: 1780-2085 /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: 2092-2105 /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: 2113-2125 /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: 2131-2140 /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: 2148-2166 /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: 2172-2180 /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: 2186-2200 /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: 2206-2220 /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: 2226-2240 /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: 2246-2257 /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: 2263-2275 /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: 2281-2289 /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: 2300-2336 /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: 2343-2362 /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: 2369-2392 /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 /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: 2411-2429 /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: 2437-2438 /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: 2446-2452 /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: 2459-2466 /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: 2475-2492 /usr/include/c++/11/bits/hashtable_policy.h: 219-219 /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_policy.h: 760-763 /usr/include/c++/11/bits/hashtable_policy.h: 1255-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1268-1268 /usr/include/c++/11/bits/hashtable_policy.h: 1600-1600 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 308-308 /usr/include/c++/11/bits/hashtable.h: 463-463 /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: 1833-1837 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /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/predefined_ops.h: 240-240 /usr/include/c++/11/bits/functional_hash.h: 198-198 /usr/include/c++/11/utility: 213-213 /usr/include/c++/11/bits/stl_vector.h: 98-98 /usr/include/c++/11/bits/stl_vector.h: 111-113 /usr/include/c++/11/bits/stl_vector.h: 336-336 /usr/include/c++/11/bits/stl_vector.h: 346-346 /usr/include/c++/11/bits/stl_vector.h: 353-353 /usr/include/c++/11/bits/stl_vector.h: 361-363 /usr/include/c++/11/bits/stl_vector.h: 680-683 /usr/include/c++/11/bits/stl_vector.h: 918-919 /usr/include/c++/11/bits/stl_vector.h: 939-942 /usr/include/c++/11/bits/stl_vector.h: 1000-1000 /usr/include/c++/11/bits/stl_vector.h: 1046-1046 /usr/include/c++/11/bits/stl_vector.h: 1072-1073 /usr/include/c++/11/bits/stl_vector.h: 1189-1198 /usr/include/c++/11/bits/stl_vector.h: 1605-1605 /usr/include/c++/11/bits/stl_vector.h: 1769-1770 /usr/include/c++/11/bits/stl_vector.h: 1794-1798 /usr/include/c++/11/ext/new_allocator.h: 89-89 /usr/include/c++/11/ext/new_allocator.h: 127-127 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/ext/new_allocator.h: 162-162 /usr/include/c++/11/bits/basic_string.h: 165-168 /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: 211-211 /usr/include/c++/11/bits/basic_string.h: 219-219 /usr/include/c++/11/bits/basic_string.h: 226-226 /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: 320-321 /usr/include/c++/11/bits/basic_string.h: 330-331 /usr/include/c++/11/bits/basic_string.h: 356-356 /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: 536-536 /usr/include/c++/11/bits/basic_string.h: 555-555 /usr/include/c++/11/bits/basic_string.h: 568-568 /usr/include/c++/11/bits/basic_string.h: 576-576 /usr/include/c++/11/bits/basic_string.h: 732-739 /usr/include/c++/11/bits/basic_string.h: 751-751 /usr/include/c++/11/bits/basic_string.h: 757-757 /usr/include/c++/11/bits/basic_string.h: 765-766 /usr/include/c++/11/bits/basic_string.h: 833-833 /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/basic_string.h: 1260-1260 /usr/include/c++/11/bits/basic_string.h: 1960-1960 /usr/include/c++/11/bits/basic_string.h: 2398-2398 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/basic_string.h: 6250-6250 /usr/include/c++/11/bits/basic_string.h: 6673-6674 /usr/include/c++/11/bits/stl_algo.h: 1803-1812 /usr/include/c++/11/bits/stl_algo.h: 1846-1846 /usr/include/c++/11/bits/stl_algo.h: 1864-1871 /usr/include/c++/11/bits/stl_algo.h: 1949-1954 /usr/include/c++/11/bits/stl_algo.h: 4295-4296 /usr/include/c++/11/bits/basic_string.tcc: 212-219 /usr/include/c++/11/bits/basic_string.tcc: 232-232 /usr/include/c++/11/bits/stl_pair.h: 323-323 /usr/include/c++/11/bits/stl_pair.h: 353-353 /usr/include/c++/11/bits/vector.tcc: 306-306 /usr/include/c++/11/bits/vector.tcc: 315-320 /usr/include/c++/11/bits/vector.tcc: 329-329 /usr/include/c++/11/bits/unique_ptr.h: 173-173							/usr/include/c++/11/bits/stl_tree.h: 208-211 /usr/include/c++/11/bits/stl_tree.h: 368-368 /usr/include/c++/11/bits/stl_tree.h: 376-376 /usr/include/c++/11/bits/stl_tree.h: 735-735 /usr/include/c++/11/bits/stl_tree.h: 745-745 /usr/include/c++/11/bits/stl_tree.h: 780-780 /usr/include/c++/11/bits/stl_tree.h: 788-792 /usr/include/c++/11/bits/stl_tree.h: 1000-1000 /usr/include/c++/11/bits/stl_tree.h: 1254-1254 /usr/include/c++/11/bits/stl_tree.h: 1904-1905 /usr/include/c++/11/bits/stl_tree.h: 1920-1924 /usr/include/c++/11/bits/stl_tree.h: 1936-1937 /usr/include/c++/11/bits/stl_tree.h: 1971-1975 /usr/include/c++/11/bits/stl_tree.h: 2485-2488 /usr/include/c++/11/bits/stl_tree.h: 2497-2500 /usr/include/c++/11/bits/stl_tree.h: 2539-2539 /usr/include/c++/11/bits/stl_uninitialized.h: 578-578 /usr/include/c++/11/bits/stl_set.h: 512-512 /usr/include/c++/11/bits/stl_set.h: 734-734 /usr/include/c++/11/bits/stl_set.h: 749-749 /usr/include/c++/11/bits/stl_function.h: 400-400 /usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 389-389 /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/bits/charconv.h: 52-52 /usr/include/c++/11/bits/charconv.h: 58-63 /usr/include/c++/11/bits/charconv.h: 83-99 /usr/include/c++/11/string_view: 132-133 /usr/include/c++/11/bits/stl_construct.h: 162-162 /usr/include/c++/11/bits/unordered_map.h: 389-389 /usr/include/c++/11/bits/unordered_map.h: 980-980 /usr/include/c++/11/bits/stl_algobase.h: 430-432 /usr/include/c++/11/bits/stl_algobase.h: 1515-1515 /usr/include/c++/11/bits/stl_iterator.h: 1028-1028 /usr/include/c++/11/bits/stl_iterator.h: 1054-1054 /usr/include/c++/11/bits/stl_iterator.h: 1091-1091 /usr/include/c++/11/bits/stl_iterator.h: 1271-1271 /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: 1661-1726 /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 /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: 1743-1766 /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: 1780-2085 /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: 2092-2105 /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: 2113-2125 /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: 2131-2140 /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: 2148-2166 /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: 2172-2180 /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: 2186-2200 /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: 2206-2220 /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: 2226-2240 /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: 2246-2257 /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: 2263-2275 /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: 2281-2289 /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: 2300-2336 /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: 2343-2362 /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: 2369-2392 /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 /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: 2411-2429 /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: 2437-2438 /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: 2446-2452 /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: 2459-2466 /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: 2475-2492 /usr/include/c++/11/bits/hashtable_policy.h: 219-219 /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_policy.h: 760-763 /usr/include/c++/11/bits/hashtable_policy.h: 1255-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1268-1268 /usr/include/c++/11/bits/hashtable_policy.h: 1600-1600 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable.h: 308-308 /usr/include/c++/11/bits/hashtable.h: 463-463 /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: 1833-1837 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /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/predefined_ops.h: 240-240 /usr/include/c++/11/bits/functional_hash.h: 198-198 /usr/include/c++/11/utility: 213-213 /usr/include/c++/11/bits/stl_vector.h: 98-98 /usr/include/c++/11/bits/stl_vector.h: 111-113 /usr/include/c++/11/bits/stl_vector.h: 336-336 /usr/include/c++/11/bits/stl_vector.h: 346-346 /usr/include/c++/11/bits/stl_vector.h: 353-353 /usr/include/c++/11/bits/stl_vector.h: 361-363 /usr/include/c++/11/bits/stl_vector.h: 680-680 /usr/include/c++/11/bits/stl_vector.h: 919-919 /usr/include/c++/11/bits/stl_vector.h: 939-942 /usr/include/c++/11/bits/stl_vector.h: 1000-1000 /usr/include/c++/11/bits/stl_vector.h: 1046-1046 /usr/include/c++/11/bits/stl_vector.h: 1072-1073 /usr/include/c++/11/bits/stl_vector.h: 1189-1198 /usr/include/c++/11/bits/stl_vector.h: 1605-1605 /usr/include/c++/11/bits/stl_vector.h: 1769-1770 /usr/include/c++/11/bits/stl_vector.h: 1794-1798 /usr/include/c++/11/ext/new_allocator.h: 89-89 /usr/include/c++/11/ext/new_allocator.h: 127-127 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/ext/new_allocator.h: 162-162 /usr/include/c++/11/bits/basic_string.h: 165-168 /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: 211-211 /usr/include/c++/11/bits/basic_string.h: 219-219 /usr/include/c++/11/bits/basic_string.h: 226-226 /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: 320-321 /usr/include/c++/11/bits/basic_string.h: 330-331 /usr/include/c++/11/bits/basic_string.h: 356-356 /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: 536-536 /usr/include/c++/11/bits/basic_string.h: 555-555 /usr/include/c++/11/bits/basic_string.h: 568-568 /usr/include/c++/11/bits/basic_string.h: 576-576 /usr/include/c++/11/bits/basic_string.h: 732-739 /usr/include/c++/11/bits/basic_string.h: 751-751 /usr/include/c++/11/bits/basic_string.h: 757-757 /usr/include/c++/11/bits/basic_string.h: 765-766 /usr/include/c++/11/bits/basic_string.h: 833-833 /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/basic_string.h: 1260-1260 /usr/include/c++/11/bits/basic_string.h: 1960-1960 /usr/include/c++/11/bits/basic_string.h: 2398-2398 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/basic_string.h: 6250-6250 /usr/include/c++/11/bits/basic_string.h: 6673-6674 /usr/include/c++/11/bits/stl_algo.h: 1803-1812 /usr/include/c++/11/bits/stl_algo.h: 1846-1846 /usr/include/c++/11/bits/stl_algo.h: 1864-1871 /usr/include/c++/11/bits/stl_algo.h: 1949-1954 /usr/include/c++/11/bits/stl_algo.h: 4295-4296 /usr/include/c++/11/bits/basic_string.tcc: 212-219 /usr/include/c++/11/bits/basic_string.tcc: 232-232 /usr/include/c++/11/bits/stl_pair.h: 323-323 /usr/include/c++/11/bits/stl_pair.h: 353-353 /usr/include/c++/11/bits/vector.tcc: 306-306 /usr/include/c++/11/bits/vector.tcc: 315-320 /usr/include/c++/11/bits/vector.tcc: 329-329 /usr/include/c++/11/bits/unique_ptr.h: 173-173
	1755	0.06	0.00	0.01	1	0.00	0.00	1756	0.06	0.00	0.01	1	0.00	0.00

▶vec.cpp: 304 - 0.11 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/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: 304-311 /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: 321-325 /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: 336-337 /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 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 786-786 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 10425-10425 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 13354-13354 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 16058-16058 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31555-31555 /usr/lib/gcc/aarch64-amazon-linux/11/include/arm_neon.h: 31977-31977
		291	0.11	0.00	0.01	3	1.02	0.00

▶basic_string.tcc: 206 - 0.09 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 431-431 /usr/include/c++/11/bits/char_traits.h: 437-437 /usr/include/c++/11/bits/stl_iterator_base_funcs.h: 104-104 /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: 356-356 /usr/include/c++/11/bits/basic_string.tcc: 206-219 /usr/include/c++/11/bits/basic_string.tcc: 232-233							/usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 431-431 /usr/include/c++/11/bits/char_traits.h: 437-437 /usr/include/c++/11/bits/stl_iterator_base_funcs.h: 104-104 /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: 356-356 /usr/include/c++/11/bits/basic_string.tcc: 206-219 /usr/include/c++/11/bits/basic_string.tcc: 232-233
	334	0.03	0.00	0.01	1	0.00	0.00	650	0.03	0.00	0.00	1	0.00	0.00
	649	0.03	0.00	0.01	1	0.00	0.00

▶hashtable_policy.h: 219 - 0.09 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/usr/include/c++/11/bits/stl_function.h: 369-369 /usr/include/c++/11/bits/char_traits.h: 357-357 /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/char_traits.h: 431-431 /usr/include/c++/11/bits/char_traits.h: 437-437 /usr/include/c++/11/tuple: 1834-1834 /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: 700-700 /usr/include/c++/11/bits/hashtable_policy.h: 709-709 /usr/include/c++/11/bits/hashtable_policy.h: 720-721 /usr/include/c++/11/bits/hashtable_policy.h: 1255-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1268-1268 /usr/include/c++/11/bits/hashtable_policy.h: 1600-1600 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable_policy.h: 1887-1890 /usr/include/c++/11/bits/hashtable.h: 795-795 /usr/include/c++/11/bits/hashtable.h: 1833-1837 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /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: 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: 356-356 /usr/include/c++/11/bits/basic_string.h: 927-927 /usr/include/c++/11/bits/basic_string.h: 6237-6237 /usr/include/c++/11/bits/basic_string.tcc: 211-219 /usr/include/c++/11/bits/basic_string.tcc: 232-232
		1807	0.09	0.00	0.01	1	0.00	0.00

▶hashtable_policy.h: 534 - 0.07 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/tuple: 202-202 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 312-312 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 800-804 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 843-849 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 855-863 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2071-2075 /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/hashtable.h: 2234-2241 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2250-2250 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/functional_hash.h: 206-206 /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/basic_string.h: 4617-4617 /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: 578-578 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 586-586 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 836-836 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 853-853 /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: 1390-1390 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 1720-1720 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 1761-1761
1930	0.07	0.00	0.02	1	0.00	0.00

▶llama-impl.cpp: 132 - 0.06 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default							Run gcc_4
		/usr/include/c++/11/sstream: 72-72 /usr/include/c++/11/sstream: 127-127 /usr/include/c++/11/sstream: 432-435 /usr/include/c++/11/sstream: 1013-1014 /usr/include/c++/11/sstream: 1055-1055 /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/bits/basic_ios.h: 282-282 /usr/include/c++/11/bits/basic_ios.h: 461-462 /usr/include/c++/11/ostream: 93-93 /usr/include/c++/11/ostream: 398-398 /usr/include/c++/11/ostream: 525-525 /usr/include/c++/11/ostream: 616-616 /usr/include/c++/11/istream: 103-104 /usr/include/c++/11/istream: 607-608 /usr/include/c++/11/istream: 922-926 /usr/include/c++/11/streambuf: 203-203 /usr/include/c++/11/streambuf: 469-471 /usr/include/c++/11/streambuf: 534-537 /usr/include/c++/11/ext/new_allocator.h: 89-89 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 165-168 /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: 356-356 /usr/include/c++/11/bits/basic_string.h: 536-536 /usr/include/c++/11/bits/basic_string.h: 681-681 /usr/include/c++/11/bits/basic_string.h: 1387-1387 /usr/include/c++/11/bits/basic_string.h: 1960-1960 /usr/include/c++/11/bits/basic_string.h: 6536-6536 /usr/include/c++/11/bits/basic_string.tcc: 212-219 /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: 132-157 /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: 163-167							/usr/include/c++/11/sstream: 72-72 /usr/include/c++/11/sstream: 127-127 /usr/include/c++/11/sstream: 432-435 /usr/include/c++/11/sstream: 1013-1014 /usr/include/c++/11/sstream: 1055-1055 /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/bits/basic_ios.h: 282-282 /usr/include/c++/11/bits/basic_ios.h: 461-462 /usr/include/c++/11/ostream: 93-93 /usr/include/c++/11/ostream: 398-398 /usr/include/c++/11/ostream: 525-525 /usr/include/c++/11/ostream: 616-616 /usr/include/c++/11/istream: 104-104 /usr/include/c++/11/istream: 607-608 /usr/include/c++/11/istream: 922-926 /usr/include/c++/11/streambuf: 203-203 /usr/include/c++/11/streambuf: 469-471 /usr/include/c++/11/streambuf: 534-537 /usr/include/c++/11/ext/new_allocator.h: 89-89 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/bits/basic_string.h: 165-168 /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: 356-356 /usr/include/c++/11/bits/basic_string.h: 536-536 /usr/include/c++/11/bits/basic_string.h: 681-681 /usr/include/c++/11/bits/basic_string.h: 1387-1387 /usr/include/c++/11/bits/basic_string.h: 1960-1960 /usr/include/c++/11/bits/basic_string.h: 6536-6536 /usr/include/c++/11/bits/basic_string.tcc: 212-219 /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: 132-157 /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: 163-167
	668	0.03	0.00	0.01	1	0.00	0.00	669	0.03	0.00	0.00	1	0.00	0.00

▶hashtable.h: 657 - 0.05 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 657-657 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 804-804 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 1731-1734 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 1743-1743 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2071-2075 /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/functional_hash.h: 206-206 /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/basic_string.h: 4617-4617 /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: 1720-1720 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 1761-1761
2031	0.05	0.00	0.01	1	0.00	0.00

▶llama-vocab.cpp: 1661 - 0.05 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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/basic_string.tcc: 590-590 /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 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 657-657 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 1004-1004 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 1828-1828 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_set.h: 687-687 /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: 1661-1677 /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: 1684-1687 /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: 1693-1726 /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: 1732-1767 /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: 1780-2052 /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: 2059-2085 /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: 2092-2105 /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: 2113-2125 /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: 2131-2140 /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: 2148-2166 /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: 2172-2180 /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: 2186-2186 /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: 2196-2200 /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: 2206-2206 /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: 2216-2220 /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: 2226-2240 /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: 2246-2257 /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: 2263-2275 /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: 2281-2289 /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: 2298-2336 /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: 2343-2362 /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: 2373-2392 /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 /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: 2411-2411 /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: 2420-2429 /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: 2446-2452 /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: 2459-2466 /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: 2475-2481 /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: 2492-2492 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algo.h: 1754-1763 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algo.h: 1775-1777 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algo.h: 1797-1797 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algo.h: 1815-1815 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algo.h: 1903-1906 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algo.h: 4219-4220 /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: 235-235 /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: 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: 393-394 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 404-405 /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: 650-651 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 689-694 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 879-881 /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: 905-906 /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/basic_string.h: 1485-1485 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 2253-2253 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 2723-2724 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 3735-3735 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 3776-3776 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 4266-4266 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_uninitialized.h: 642-642 /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/char_traits.h: 350-350 /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/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 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_pair.h: 1235-1235 /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/bit: 206-206 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_construct.h: 119-119 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_construct.h: 162-162 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/unordered_map.h: 988-988 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 204-206 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 298-298 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 364-364 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 733-733 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 743-743 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 994-998 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 1251-1252 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 1823-1823 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 1829-1831 /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_tree.h: 2111-2125 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 2543-2543 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 447-447 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 812-814 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_function.h: 405-405 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 114-116 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 368-369 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 380-380 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 388-388 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 398-400 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 829-829 /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: 1015-1018 /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: 1159-1160 /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: 1719-1719 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 1908-1912 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 1945-1949 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/charconv.h: 67-71 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/charconv.h: 94-109 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/predefined_ops.h: 158-158 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/predefined_ops.h: 240-240 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algobase.h: 262-262 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algobase.h: 438-438 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algobase.h: 764-767 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/unique_ptr.h: 193-193 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_iterator.h: 1068-1068 /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_iterator.h: 1139-1139 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_iterator.h: 1235-1235 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_iterator.h: 1328-1328
1753	0.05	0.00	0.01	1	0.00	0.00

▶ggml-cpu.c: 533 - 0.05 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 533-539 /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: 682-682 /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: 1436-1444 /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: 1454-1465 /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: 1474-1475 /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: 1483-1539 /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: 1552-1560 /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: 1567-1579 /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: 1585-1601 /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: 1623-1628 /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: 1635-1642 /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: 1664-1784 /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: 1792-2038 /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: 2047-2047 /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: 2055-2055 /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: 2061-2077 /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: 2083-2096 /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: 2862-2897
41	0.05	0.00	0.00	3	0.05	0.00

▶hashtable.h: 422 - 0.05 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 422-422 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 453-453 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 461-461 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 474-474 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 1661-1661 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 1673-1673 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2589-2592 /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: 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/hashtable_policy.h: 387-387 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 2060-2060
1986	0.05	0.00	0.01	1	0.00	0.00

▶traits.cpp: 12 - 0.05 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default	Run gcc_4
	/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: 12-17 /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: 23-23 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_iterator.h: 1068-1068 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_iterator.h: 1102-1102								/usr/include/c++/11/bits/stl_iterator.h: 1028-1028 /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: 12-23
244	0.02	0.00	0.00	1	0.00	0.00		267	0.03	0.00	0.00	1	0.00	0.00

▶ggml.c: 1432 - 0.05 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default							Run gcc_default	Run gcc_4
	/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1432-1432 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1438-1438								/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1432-1438
74	0.02	0.00	0.00	1	0.00	0.00		87	0.03	0.00	0.00	1	0.00	0.00

▶hashtable.h: 441 - 0.04 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/new_allocator.h: 134-140 /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/hashtable.h: 441-443 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 453-453 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 461-461 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 474-474 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2626-2648 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2655-2657 /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 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 2077-2077
1939	0.04	0.00	0.01	1	0.00	0.00

▶ggml-cpu.c: 3497 - 0.04 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 3497-3497
69	0.04	0.00	0.00	2	0.03	0.00

▶llama-vocab.cpp: 1590 - 0.04 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 422-422 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 453-453 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 461-461 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 474-474 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2589-2592 /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: 1590-1590 /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: 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/stl_construct.h: 162-162 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/unordered_map.h: 109-109 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 733-733 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 982-982 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 2060-2060 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 368-369 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 388-388 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 735-735 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/unique_ptr.h: 93-93 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/unique_ptr.h: 398-400
1985	0.04	0.00	0.01	1	0.00	0.00

▶hashtable.h: 2070 - 0.04 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2070-2081 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2087-2087 /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/stl_pair.h: 1034-1034 /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: 1720-1720 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 1761-1761
1938	0.04	0.00	0.01	1	0.00	0.00

▶llama-impl.cpp: 82 - 0.03 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default	Run gcc_default							Run gcc_4
		/usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/char_traits.h: 431-431 /usr/include/c++/11/bits/char_traits.h: 437-437 /usr/include/c++/11/bits/stl_algobase.h: 944-944 /usr/include/c++/11/bits/stl_algobase.h: 1115-1115 /usr/include/c++/11/ext/new_allocator.h: 89-89 /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: 165-165 /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: 356-356 /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: 82-95
	664	0.03	0.00	0.01	1	0.00	0.00

▶ggml.c: 1229 - 0.03 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default	Run gcc_default							Run gcc_4
		/home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/ggml/src/ggml.c: 1229-1230
	53	0.03	0.00	0.01	1	0.00	0.00

▶invoke.h: 61 - 0.03 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default	Run gcc_default							Run gcc_4
		/usr/include/c++/11/bits/std_function.h: 288-288 /usr/include/c++/11/bits/invoke.h: 61-61
	519	0.03	0.00	0.00	1	0.00	0.00

▶stl_vector.h: 919 - 0.03 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default	Run gcc_default							Run gcc_4
		/usr/include/c++/11/bits/stl_vector.h: 919-919 /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: 772-772
	659	0.03	0.00	0.01	1	0.00	0.00

▶unicode.cpp: 180 - 0.03 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default	Run gcc_default							Run gcc_4
		/usr/include/c++/11/bits/char_traits.h: 389-389 /usr/include/c++/11/bits/unordered_map.h: 984-984 /usr/include/c++/11/bits/hashtable_policy.h: 219-219 /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_policy.h: 451-451 /usr/include/c++/11/bits/hashtable_policy.h: 760-763 /usr/include/c++/11/bits/hashtable_policy.h: 1255-1255 /usr/include/c++/11/bits/hashtable_policy.h: 1600-1600 /usr/include/c++/11/bits/hashtable_policy.h: 1621-1621 /usr/include/c++/11/bits/hashtable_policy.h: 1916-1919 /usr/include/c++/11/bits/hashtable.h: 446-446 /usr/include/c++/11/bits/hashtable.h: 454-454 /usr/include/c++/11/bits/hashtable.h: 463-463 /usr/include/c++/11/bits/hashtable.h: 528-528 /usr/include/c++/11/bits/hashtable.h: 795-795 /usr/include/c++/11/bits/hashtable.h: 1833-1837 /usr/include/c++/11/bits/hashtable.h: 1843-1843 /usr/include/c++/11/bits/hashtable.h: 2321-2323 /usr/include/c++/11/bits/functional_hash.h: 198-198 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/unicode.cpp: 180-196 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/unicode.cpp: 833-836 /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 /usr/include/c++/11/bits/basic_string.h: 6237-6237
	1845	0.03	0.00	0.01	1	0.00	0.00

▶kernels.cpp: 442 - 0.03 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default	Run gcc_default							Run gcc_4
		/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/kernels.cpp: 442-451 /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/kernels.cpp: 458-458
	512	0.03	0.00	0.00	1	0.00	0.00

▶variant: 1000 - 0.03 %

ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID
Run orig_default	Run gcc_default							Run gcc_4
		/usr/include/c++/11/bits/std_function.h: 247-247 /usr/include/c++/11/bits/std_function.h: 588-590 /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: 94-94 /usr/include/c++/11/variant: 1000-1000 /usr/include/c++/11/variant: 1023-1023
	480	0.03	0.00	0.00	1	0.00	0.00

▶kai_matmul_clamp_f32_qsi8d32p1x8_qsi4c32p4x8_1x4x32_neon_dotprod.c: 116 - 0.03 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/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: 116-128 /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: 213-213
		575	0.03	0.00	0.00	1	0.00	0.00

▶kleidiai.cpp: 445 - 0.03 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/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: 445-445 /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: 532-547
		510	0.03	0.00	0.00	1	0.00	0.00

▶kleidiai.cpp: 56 - 0.03 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/usr/include/stdlib.h: 363-363 /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: 56-75 /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: 82-82 /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: 551-552 /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: 562-569 /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/kernels.h: 19-20
		501	0.03	0.00	0.00	1	0.00	0.00

▶gguf.cpp: 139 - 0.03 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/usr/include/c++/11/bits/stl_algobase.h: 924-924 /usr/include/c++/11/bits/stl_algobase.h: 1115-1115 /usr/include/c++/11/bits/stl_iterator.h: 1027-1027 /usr/include/c++/11/bits/alloc_traits.h: 496-496 /usr/include/c++/11/bits/stl_vector.h: 98-98 /usr/include/c++/11/bits/stl_vector.h: 336-336 /usr/include/c++/11/bits/stl_vector.h: 353-353 /usr/include/c++/11/bits/stl_vector.h: 680-680 /usr/include/c++/11/bits/stl_vector.h: 919-919 /usr/include/c++/11/bits/stl_vector.h: 939-939 /usr/include/c++/11/bits/stl_vector.h: 1758-1759 /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: 139-146 /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: 226-226 /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: 232-232 /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: 240-240 /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: 294-295 /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: 301-305 /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: 311-317 /usr/include/c++/11/ext/new_allocator.h: 89-89 /usr/include/c++/11/ext/new_allocator.h: 127-127 /usr/include/c++/11/ext/new_allocator.h: 145-145 /usr/include/c++/11/ext/new_allocator.h: 162-162 /usr/include/c++/11/bits/basic_string.h: 168-168 /usr/include/c++/11/bits/basic_string.h: 195-195 /usr/include/c++/11/bits/basic_string.h: 201-201 /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: 459-459 /usr/include/c++/11/bits/vector.tcc: 112-121 /usr/include/c++/11/bits/vector.tcc: 679-680
		776	0.03	0.00	0.00	1	0.00	0.00

▶gguf.cpp: 812 - 0.03 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/usr/include/c++/11/bits/stl_vector.h: 1064-1064 /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: 812-816 /usr/include/c++/11/bits/basic_string.h: 195-195
		666	0.03	0.00	0.00	1	0.00	0.00

▶kleidiai.cpp: 92 - 0.03 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/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: 302-342 /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
		508	0.03	0.00	0.00	1	0.00	0.00

▶llama-vocab.cpp: 2744 - 0.03 %

ASM Fct ID	ASM Fct ID	ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)
Run orig_default	Run gcc_default	Run gcc_4
			/usr/include/c++/11/ext/string_conversions.h: 63-64 /usr/include/c++/11/ext/string_conversions.h: 76-86 /usr/include/c++/11/bits/char_traits.h: 357-357 /usr/include/c++/11/bits/stl_iterator.h: 1028-1028 /usr/include/c++/11/bits/stl_iterator.h: 1052-1055 /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: 2744-2744 /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: 2750-2761 /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: 2959-2964 /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: 2970-2983 /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: 2989-2989 /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: 2995-2997 /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: 3003-3013 /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: 3020-3050 /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: 3059-3064 /usr/include/c++/11/bits/alloc_traits.h: 496-496 /usr/include/c++/11/bits/stl_vector.h: 336-336 /usr/include/c++/11/bits/stl_vector.h: 353-353 /usr/include/c++/11/bits/stl_vector.h: 680-680 /usr/include/c++/11/bits/stl_vector.h: 918-919 /usr/include/c++/11/bits/stl_vector.h: 1064-1064 /usr/include/c++/11/bits/stl_vector.h: 1072-1073 /usr/include/c++/11/ext/new_allocator.h: 89-89 /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: 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: 255-255 /usr/include/c++/11/bits/basic_string.h: 459-459 /usr/include/c++/11/bits/basic_string.h: 672-672 /usr/include/c++/11/bits/basic_string.h: 841-841 /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: 1170-1170 /usr/include/c++/11/bits/basic_string.h: 1214-1214 /usr/include/c++/11/bits/basic_string.h: 1344-1345 /usr/include/c++/11/bits/basic_string.h: 6250-6250
		1742	0.03	0.00	0.00	1	0.00	0.00

▶ops.cpp: 3430 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 1312-1320 /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: 1327-1335 /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: 1349-1351 /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: 1358-1376 /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: 1383-1386 /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: 1399-1401 /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-impl.h: 137-137 /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: 355-355 /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 /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: 3430-3462 /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: 3489-3521 /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: 3548-3550 /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: 3561-3561 /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: 3573-3605 /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: 3632-3664 /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: 3691-3693 /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: 3704-3704 /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: 3716-3748 /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: 3757-3757 /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: 3775-3807 /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: 3834-3836 /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: 3847-3847 /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: 3859-3880 /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: 3887-3893 /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: 3903-3907 /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: 3925-3927 /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: 3934-3934 /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: 3946-3978 /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: 4005-4037 /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: 4064-4066 /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: 4077-4077 /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: 4089-4121 /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: 4148-4180 /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: 4207-4209 /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: 4220-4220 /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: 9781-9785 /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: 9812-9815 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algobase.h: 238-238 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_algobase.h: 262-262
345	0.02	0.00	0.00	1	0.00	0.00

▶unicode.cpp: 36 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 1250-1250 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/unicode.cpp: 36-71
1994	0.02	0.00	0.00	1	0.00	0.00

▶ops.cpp: 5524 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 5524-5526 /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: 5542-5563 /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: 5571-5585
307	0.02	0.00	0.00	1	0.00	0.00

▶kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 79 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 79-79
560	0.02	0.00	0.00	1	0.00	0.00

▶kleidiai.cpp: 96 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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/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: 96-96 /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: 302-321 /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: 327-340 /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: 348-381 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/variant: 1629-1629 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/variant: 1817-1820 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/std_function.h: 247-247 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/std_function.h: 589-591
475	0.02	0.00	0.00	1	0.00	0.00

▶stl_construct.h: 162 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 228-228 /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/stl_construct.h: 162-164 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 368-369 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 388-388 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 735-735
725	0.02	0.00	0.00	1	0.00	0.00

▶ggml-quants.c: 312 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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: 312-325
557	0.02	0.00	0.00	1	0.00	0.00

▶llama-arch.cpp: 2339 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/new_allocator.h: 172-172 /home/eoseret/Tools/QaaS/qaas_runs/ip-172-31-46-37.ec2.internal/176-399-4104/llama.cpp/build/llama.cpp/src/llama-arch.cpp: 2339-2348 /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: 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: 404-405 /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: 1485-1485 /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/stl_map.h: 561-561 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_tree.h: 743-743 /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
88	0.02	0.00	0.00	1	0.00	0.00

▶llama-vocab.cpp: 2747 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/new_allocator.h: 172-172 /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: 2747-2765 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 198-198 /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: 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: 1077-1077 /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/char_traits.h: 350-350 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 368-369 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_vector.h: 388-388 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_iterator.h: 1068-1068 /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_iterator.h: 1235-1235
1775	0.02	0.00	0.00	1	0.00	0.00

▶hashtable.h: 311 - 0.02 %

ASM Fct ID	Coverage (%)	Inc Time w.r.t. Wall Time (s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (cov)	Deviation (tps)	ASM Fct ID	ASM Fct ID
Run orig_default							Run gcc_default	Run gcc_4
	/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/hashtable.h: 311-312 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 657-657 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 800-804 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 822-824 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 843-849 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 855-863 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2145-2153 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2160-2161 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2169-2169 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2234-2241 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable.h: 2250-2250 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/functional_hash.h: 206-206 /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: 1574-1574 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/basic_string.h: 198-198 /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: 235-235 /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: 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: 689-694 /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/basic_string.h: 4617-4617 /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: 368-368 /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/char_traits.h: 427-427 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_pair.h: 882-882 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/stl_pair.h: 1034-1034 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 319-319 /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: 578-578 /usr/lib/gcc/aarch64-amazon-linux/14/../../../../include/c++/14/bits/hashtable_policy.h: 586-586 /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: 1390-1390
1936	0.02	0.00	0.00	1	0.00	0.00

▶Old Layout

Functions

Name	Module	Coverage (%)	Inclusive Time w.r.t. Wall Time(s)	Max Inc. Time over Threads(s)	Nb Threads	Deviation (coverage)	Deviation (time)
Name	Module	orig_default	gcc_default	gcc_4	orig_default	gcc_default	gcc_4	orig_default	gcc_default	gcc_4	orig_default	gcc_default	gcc_4	orig_default	gcc_default	gcc_4	orig_default	gcc_default	gcc_4
kai_run_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm	libggml-cpu.so	46.21	75.67	73.88	0.52	1.13	1.25	0.22	0.22	0.22	64	64	64	4.62	9.12	9.30	0.01	0.01	0.01
kmp_flag_64<false, true>::wait(kmp_info, int, void)	libomp.so	38.09	NA	NA	0.43	NA	NA	0.22	NA	NA	64	NA	NA	6.22	NA	NA	0.03	NA	NA
omp_get_num_procs	libgomp.so.1.0.0	NA	10.89	10.67	NA	0.16	0.18	NA	0.05	0.05	NA	64	64	NA	3.81	4.04	NA	0.01	0.01
kai_run_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0	libggml-cpu.so	2.03	5.01	5.99	0.02	0.07	0.10	0.56	0.86	1.04	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
kmp_flag_native<unsigned long long, (flag_type)1, true>::notdone_check()	libomp.so	4.75	NA	NA	0.05	NA	NA	0.05	NA	NA	63	NA	NA	2.76	NA	NA	0.01	NA	NA
ggml_compute_forward_flash_attn_ext	libggml-cpu.so	1.10	1.14	1.00	0.01	0.02	0.02	0.02	0.01	0.01	42	35	29	0.79	0.74	0.81	0.00	0.00	0.00
ggml_compute_forward_rope_f32(ggml_compute_params const, ggml_tensor, bool)	libggml-cpu.so	0.71	1.35	0.97	0.01	0.02	0.02	0.01	0.01	0.01	34	36	27	0.42	1.10	0.88	0.00	0.00	0.00
ggml_vec_dot_q6_K_q8_K	libggml-cpu.so	1.06	0.38	0.75	0.01	0.01	0.01	0.00	0.01	0.00	58	13	26	0.05	0.46	0.06	0.00	0.00	0.00
ggml_vec_swiglu_f32	libggml-cpu.so	0.44	0.50	0.72	0.00	0.01	0.01	0.01	0.01	0.01	22	16	21	0.39	0.66	0.77	0.00	0.00	0.00
__GI___pthread_mutex_lock	libc.so.6	0.27	0.56	0.75	0.00	0.01	0.01	0.01	0.01	0.01	14	18	21	0.32	0.49	0.99	0.00	0.00	0.00
__GI___sched_yield	libc.so.6	1.23	NA	NA	0.01	NA	NA	0.02	NA	NA	43	NA	NA	0.94	NA	NA	0.00	NA	NA
__expf_finite	libm.so.6	0.38	0.35	0.40	0.00	0.01	0.01	0.01	0.01	0.01	18	12	12	0.62	0.48	1.24	0.00	0.00	0.00
sincosf	libm.so.6	0.27	0.32	0.49	0.00	0.00	0.01	0.00	0.00	0.01	15	11	16	0.05	0.08	0.53	0.00	0.00	0.00
ggml_compute_forward_add_non_quantized	libggml-cpu.so	0.27	0.38	0.26	0.00	0.01	0.00	0.00	0.01	0.01	15	13	8	0.04	0.47	0.71	0.00	0.00	0.00
__GI___memset_generic	libc.so.6	0.11	0.26	0.32	0.00	0.00	0.01	0.03	0.05	0.05	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
kai_run_lhs_quant_pack_qsi8d32p4x8sb_f32_neon	libggml-cpu.so	0.15	0.26	0.23	0.00	0.00	0.00	0.01	0.01	0.01	7	9	6	0.44	0.57	1.62	0.00	0.00	0.00
ggml_compute_forward_rms_norm	libggml-cpu.so	0.26	0.20	0.11	0.00	0.00	0.00	0.00	0.00	0.00	14	7	4	0.05	0.07	0.10	0.00	0.00	0.00
rope_yarn(float, float, float, long, float, float, float, float*)	libggml-cpu.so	NA	NA	0.57	NA	NA	0.01	NA	NA	0.01	NA	NA	18	NA	NA	0.68	NA	NA	0.00
ggml_compute_forward_mul	libggml-cpu.so	0.18	0.20	0.17	0.00	0.00	0.00	0.00	0.00	0.00	10	7	6	0.24	0.06	0.07	0.00	0.00	0.00
__GI___memcpy_sve	libc.so.6	0.13	0.15	0.20	0.00	0.00	0.00	0.02	0.02	0.03	4	3	3	0.28	0.63	0.32	0.01	0.01	0.01
ggml_vec_dot_f16	libggml-cpu.so	0.15	0.20	0.11	0.00	0.00	0.00	0.00	0.00	0.01	8	7	3	0.04	0.07	1.02	0.00	0.00	0.00
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	0.04	0.18	0.17	0.00	0.00	0.00	0.01	0.03	0.03	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
ggml_cpu_fp32_to_fp16	libggml-cpu.so	0.15	0.06	0.14	0.00	0.00	0.00	0.00	0.00	0.00	8	2	5	0.27	0.12	0.08	0.00	0.00	0.00
std::_Hashtable<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, unsigned char>, s...	libllama.so	0.05	0.18	0.11	0.00	0.00	0.00	0.01	0.03	0.02	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::compare(char const*) const	libstdc++.so.6.0.33	NA	0.15	0.17	NA	0.00	0.00	NA	0.03	0.03	NA	1	1	NA	0.00	0.00	NA	0.00	0.00
_IO_fread	libc.so.6	0.05	0.12	0.14	0.00	0.00	0.00	0.01	0.02	0.03	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
unknown_function	[vdso]	0.27	NA	NA	0.00	NA	NA	0.00	NA	NA	15	NA	NA	0.04	NA	NA	0.00	NA	NA
malloc_consolidate	libc.so.6	0.04	0.09	0.11	0.00	0.00	0.00	0.01	0.02	0.02	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
unknown_function	libllama.so	0.09	0.06	0.09	0.00	0.00	0.00	0.03	0.01	0.01	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
llama_vocab::~llama_vocab()	libllama.so	NA	0.15	0.09	NA	0.00	0.00	NA	0.03	0.01	NA	1	1	NA	0.00	0.00	NA	0.00	0.00
ggml_graph_compute_thread	libggml-cpu.so	NA	0.12	0.11	NA	0.00	0.00	NA	0.00	0.00	NA	4	4	NA	0.09	0.08	NA	0.00	0.00
__GI___libc_malloc	libc.so.6	0.07	0.09	0.06	0.00	0.00	0.00	0.02	0.02	0.01	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
unknown_function	libggml-cpu.so	0.13	NA	0.09	0.00	NA	0.00	0.01	NA	0.00	6	NA	3	0.49	NA	0.06	0.00	NA	0.00
_dl_lookup_symbol_x	ld-linux-aarch64.so.1	0.07	0.03	0.09	0.00	0.00	0.00	0.01	0.01	0.01	2	1	1	0.02	0.00	0.00	0.01	0.00	0.00
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	NA	0.03	0.14	NA	0.00	0.00	NA	0.01	0.03	NA	1	1	NA	0.00	0.00	NA	0.00	0.00
llama_vocab::impl::load(llama_model_loader&, LLM_KV const&)	libllama.so	0.05	0.06	0.06	0.00	0.00	0.00	0.01	0.01	0.01	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
std::__detail::_Map_base<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, int>, st...	libllama.so	0.07	NA	0.09	0.00	NA	0.00	0.02	NA	0.01	1	NA	1	0.00	NA	0.00	0.00	NA	0.00
std::basic_ostream<char, std::char_traits<char> >& std::__ostream_insert<char, std::char_traits<char> >(std::basic_ostream<char, std::char_traits<char> >&, char const*, long)	libstdc++.so.6.0.33	0.02	0.06	0.06	0.00	0.00	0.00	0.00	0.01	0.01	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
__GI___lll_lock_wait	libc.so.6	0.07	0.03	0.03	0.00	0.00	0.00	0.00	0.00	0.00	4	1	1	0.05	0.00	0.00	0.00	0.00	0.00
__GI_memcmp	libc.so.6	NA	0.09	0.03	NA	0.00	0.00	NA	0.02	0.00	NA	1	1	NA	0.00	0.00	NA	0.00	0.00
std::basic_streambuf<char, std::char_traits<char> >::xsputn(char const*, long)	libstdc++.so.6.0.33	0.02	0.06	0.03	0.00	0.00	0.00	0.00	0.01	0.00	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
__GI___strlen_asimd	libc.so.6	NA	0.06	0.03	NA	0.00	0.00	NA	0.01	0.00	NA	1	1	NA	0.00	0.00	NA	0.00	0.00
unlink_chunk.constprop.0	libc.so.6	0.02	0.03	0.03	0.00	0.00	0.00	0.00	0.01	0.00	1	1	1	0.00	0.00	0.00	0.00	0.00	0.00
_int_free	libc.so.6	0.02	NA	0.06	0.00	NA	0.00	0.00	NA	0.01	1	NA	1	0.00	NA	0.00	0.00	NA	0.00
__kmp_yield	libomp.so	0.07	NA	NA	0.00	NA	NA	0.00	NA	NA	4	NA	NA	0.04	NA	NA	0.00	NA	NA
_int_malloc	libc.so.6	0.04	0.03	NA	0.00	0.00	NA	0.01	0.01	NA	1	1	NA	0.00	0.00	NA	0.00	0.00	NA
std::_Hash_bytes(void const*, unsigned long, unsigned long)	libstdc++.so.6.0.33	0.04	NA	0.03	0.00	NA	0.00	0.01	NA	0.00	1	NA	1	0.00	NA	0.00	0.00	NA	0.00
__GI_memchr	libc.so.6	NA	0.06	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
std::_Hashtable<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, int>, std::alloca...	libllama.so	NA	0.06	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
gguf_kv_to_str[abi:cxx11](gguf_context const*, int)	libllama.so	NA	0.03	0.03	NA	0.00	0.00	NA	0.01	0.00	NA	1	1	NA	0.00	0.00	NA	0.00	0.00
void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_construct<char>(char, char*, std::forward_iterator_tag) [clone .constprop.0]	libggml-base.so	NA	0.03	0.03	NA	0.00	0.00	NA	0.01	0.00	NA	1	1	NA	0.00	0.00	NA	0.00	0.00
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	0.05	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
ggml_graph_compute_thread	libggml-cpu.so	0.05	NA	NA	0.00	NA	NA	0.00	NA	NA	3	NA	NA	0.05	NA	NA	0.00	NA	NA
__kmp_hyper_barrier_release(barrier_type, kmp_info, int, int, int, void)	libomp.so	0.05	NA	NA	0.00	NA	NA	0.00	NA	NA	3	NA	NA	0.01	NA	NA	0.00	NA	NA
unknown_function	libomp.so	0.05	NA	NA	0.00	NA	NA	0.00	NA	NA	3	NA	NA	0.08	NA	NA	0.00	NA	NA
ggml_cpu_extra_compute_forward	libggml-cpu.so	0.02	NA	0.03	0.00	NA	0.00	0.00	NA	0.00	1	NA	1	0.00	NA	0.00	0.00	NA	0.00
ggml_is_empty	libggml-base.so	0.02	NA	0.03	0.00	NA	0.00	0.00	NA	0.00	1	NA	1	0.00	NA	0.00	0.00	NA	0.00
unknown_function	libggml-base.so	0.02	NA	0.03	0.00	NA	0.00	0.00	NA	0.00	1	NA	1	0.00	NA	0.00	0.00	NA	0.00
@plt_start@	libstdc++.so.6.0.33	0.02	NA	0.03	0.00	NA	0.00	0.00	NA	0.00	1	NA	1	0.00	NA	0.00	0.00	NA	0.00
ggml::cpu::kleidiai::tensor_traits::compute_forward_q4_0(ggml_compute_params, ggml_tensor)	libggml-cpu.so	0.02	NA	0.03	0.00	NA	0.00	0.00	NA	0.00	1	NA	1	0.00	NA	0.00	0.00	NA	0.00
__kmp_barrier	libomp.so	0.04	NA	NA	0.00	NA	NA	0.00	NA	NA	2	NA	NA	0.07	NA	NA	0.00	NA	NA
std::_Hashtable<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::pair<std::pai...	libllama.so	0.04	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
__GI___pthread_mutex_unlock_usercnt	libc.so.6	0.04	NA	NA	0.00	NA	NA	0.00	NA	NA	2	NA	NA	0.01	NA	NA	0.00	NA	NA
ggml_cpu_get_sve_cnt	libggml-cpu.so	0.04	NA	NA	0.00	NA	NA	0.00	NA	NA	2	NA	NA	0.03	NA	NA	0.00	NA	NA
__aarch64_ldadd8_acq_rel	libomp.so	0.04	NA	NA	0.00	NA	NA	0.00	NA	NA	2	NA	NA	0.02	NA	NA	0.00	NA	NA
llama_vocab::impl::~impl()	libllama.so	0.04	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
format[abi:cxx11](char const*, ...)	libllama.so	NA	0.03	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
std::__detail::__variant::__gen_vtable_impl<std::__detail::__variant::_Multi_array<std::__detail::__variant::__deduce_visit_result<unsigned long> (*)(variant_call<unsigned long, std::variant<std::function<unsigned long (unsigned long, ...	libggml-cpu.so	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::push_back(char)	libstdc++.so.6.0.33	NA	0.03	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
unicode_utf8_to_byte(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	NA	0.03	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_replace_aux(unsigned long, unsigned long, unsigned long, char)	libstdc++.so.6.0.33	NA	0.03	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
__GI___lll_lock_wake	libc.so.6	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
void std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::_M_construct<char>(char, char*, std::forward_iterator_tag) [clone .constprop.0]	libllama.so	NA	0.03	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
gguf_get_n_kv	libggml-base.so	NA	0.03	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
ggml_blck_size	libggml-base.so	NA	0.03	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
std::_Function_handler<void (unsigned long, unsigned long, unsigned long, unsigned long, void const, void const, float, unsigned long, unsigned long, float, float), void ()(unsigned long, unsigned long, unsigned long, unsigned long, void const*, voi...	libggml-cpu.so	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
do_lookup_x	ld-linux-aarch64.so.1	NA	0.03	NA	NA	0.00	NA	NA	0.01	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
ggml_kleidiai_select_kernels(cpu_feature, ggml_tensor const*)	libggml-cpu.so	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA
kai_run_matmul_clamp_f32_qsi8d32p1x8_qsi4c32p4x8_1x4x32_neon_dotprod	libggml-cpu.so	NA	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00
gguf_get_arr_str	libggml-base.so	NA	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::reserve(unsigned long)	libstdc++.so.6.0.33	NA	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00
std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >::find(char, unsigned long) const	libstdc++.so.6.0.33	NA	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00
bool gguf_read_emplace_helper<int>(gguf_reader const&, std::vector<gguf_kv, std::allocator<gguf_kv> >&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, bool, unsigned l...	libggml-base.so	NA	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00
llama_vocab::impl::token_to_piece(int, char*, int, int, bool) const	libllama.so	NA	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00
ggml::cpu::kleidiai::extra_buffer_type::get_tensor_traits(ggml_tensor const*)	libggml-cpu.so	NA	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00
__vfscanf_internal	libc.so.6	NA	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00
ggml_backend_cpu_kleidiai_buffer_type	libggml-cpu.so	NA	NA	0.03	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00
_dl_fixup	ld-linux-aarch64.so.1	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
__kmp_task_team_sync	libomp.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
_IO_str_init_static_internal	libc.so.6	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
std::pair<std::__detail::_Node_iterator<std::pair<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<c...	libllama.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
std::ostream::put(char)	libstdc++.so.6.0.33	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
unicode_cpt_from_utf8(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, unsigned long&)	libllama.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
LLM_KV::operator()[abi:cxx11](llm_kv) const	libllama.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
void std::_Destroy_aux<false>::__destroy<gguf_kv>(gguf_kv, gguf_kv*)	libggml-base.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
dequantize_row_q4_0	libggml-base.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
ggml_compute_forward_set_rows	libggml-cpu.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
kai_get_sr_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm	libggml-cpu.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
ggml_compute_forward_glu	libggml-cpu.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
kmp_flag_native<unsigned long long, (flag_type)1, true>::done_check()	libomp.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
__powf_finite	libm.so.6	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA
llama_decode_text(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&)	libllama.so	0.02	NA	NA	0.00	NA	NA	0.00	NA	NA	1	NA	NA	0.00	NA	NA	0.00	NA	NA

Report Configuration

Functions

▶kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 119 - 195.76 %

▶<unknown>: 0 - 74.20 %

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 36 - 11.00 %

▶ops.cpp: 6210 - 2.63 %

▶quants.c: 2466 - 2.19 %

▶ops.cpp: 8690 - 2.15 %

▶kai_rhs_pack_nxk_qsi4c32pscalef16_qsu4c32s16s0.c: 80 - 2.03 %

▶vec.cpp: 369 - 1.65 %

▶ops.cpp: 8692 - 1.10 %

▶ops.cpp: 6238 - 0.97 %

▶binary-ops.cpp: 10 - 0.91 %

▶kai_lhs_quant_pack_qsi8d32p4x8sb_f32_neon.c: 21 - 0.64 %

▶ops.cpp: 4304 - 0.58 %

▶binary-ops.cpp: 18 - 0.56 %

▶hashtable.h: 1827 - 0.35 %

▶hashtable.h: 795 - 0.29 %

▶llama-vocab.cpp: 3216 - 0.23 %

▶ggml-cpu.c: 1424 - 0.23 %

▶hashtable.h: 434 - 0.23 %

▶ggml-cpu.c: 3228 - 0.21 %

▶vec.cpp: 207 - 0.20 %

▶vec.cpp: 221 - 0.15 %

▶ggml-cpu.c: 3201 - 0.14 %

▶llama-vocab.cpp: 1575 - 0.12 %

▶vec.cpp: 304 - 0.11 %

▶basic_string.tcc: 206 - 0.09 %

▶hashtable_policy.h: 219 - 0.09 %

▶hashtable_policy.h: 534 - 0.07 %

▶llama-impl.cpp: 132 - 0.06 %

▶hashtable.h: 657 - 0.05 %

▶llama-vocab.cpp: 1661 - 0.05 %

▶ggml-cpu.c: 533 - 0.05 %

▶hashtable.h: 422 - 0.05 %

▶traits.cpp: 12 - 0.05 %

▶ggml.c: 1432 - 0.05 %

▶hashtable.h: 441 - 0.04 %

▶ggml-cpu.c: 3497 - 0.04 %

▶llama-vocab.cpp: 1590 - 0.04 %

▶hashtable.h: 2070 - 0.04 %

▶llama-impl.cpp: 82 - 0.03 %

▶ggml.c: 1229 - 0.03 %

▶invoke.h: 61 - 0.03 %

▶stl_vector.h: 919 - 0.03 %

▶unicode.cpp: 180 - 0.03 %

▶kernels.cpp: 442 - 0.03 %

▶variant: 1000 - 0.03 %

▶kai_matmul_clamp_f32_qsi8d32p1x8_qsi4c32p4x8_1x4x32_neon_dotprod.c: 116 - 0.03 %

▶kleidiai.cpp: 445 - 0.03 %

▶kleidiai.cpp: 56 - 0.03 %

▶gguf.cpp: 139 - 0.03 %

▶gguf.cpp: 812 - 0.03 %

▶kleidiai.cpp: 92 - 0.03 %

▶llama-vocab.cpp: 2744 - 0.03 %

▶ops.cpp: 3430 - 0.02 %

▶unicode.cpp: 36 - 0.02 %

▶ops.cpp: 5524 - 0.02 %

▶kai_matmul_clamp_f32_qsi8d32p4x8_qsi4c32p4x8_16x4_neon_i8mm.c: 79 - 0.02 %

▶kleidiai.cpp: 96 - 0.02 %

▶stl_construct.h: 162 - 0.02 %

▶ggml-quants.c: 312 - 0.02 %

▶llama-arch.cpp: 2339 - 0.02 %

▶llama-vocab.cpp: 2747 - 0.02 %

▶hashtable.h: 311 - 0.02 %

▶Old Layout

▶Filters

Functions