OV - - Loops

MAQAO

options

Loops Index

44 loops have been discarded from the report because their ratio ((Max Inclusive Time Over Threads * 100) / Max Thread Active Time) is lower than the threshold set by object_coverage_threshold (0.1%). It represents about 0.12% of the application. To include them, change the value of object_coverage_threshold in the experiment directory configuration file, then rerun the command with the additionnal parameter --force-static-analysis

▶Filters

Loop id	Source Location	Source Function	Level	Max Thread Time / Walltime orig_0 (%)	Exclusive Coverage orig_0 (%)	Inclusive Coverage orig_0 (%)	Max Exclusive Time Over Threads orig_0 (s)	Max Inclusive Time Over Threads orig_0 (s)	Exclusive Time w.r.t. Wall Time orig_0 (s)	Inclusive Time w.r.t. Wall Time orig_0 (s)	Nb Threads orig_0	GFLOPS orig_0	Vectorization Ratio (%)	Vector Length Use (%)	Speedup If No Scalar Integer	Speedup If FP Vectorized	Speedup If Fully Vectorized	Speedup If Perfect Load Balancing orig_0	Stride 0	Stride 1	Stride n	Stride Unknown	Stride Indirect	Array Access Efficiency
2866	libggml-cpu.so - quants.c:108-1042 [...]	ggml_vec_dot_q8_0_q8_0	Single	82.41	61.72	61.72	56.92	56.92	37.42	37.42	192	54.14	NA	NA	NA	NA	NA	1.53	NA	NA	NA	NA	NA	0.00
2625	libggml-cpu.so - sgemm.cpp:138-1044 [...]	void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<4>(long, long, long, long)	Innermost	0.19	0.12	0.12	0.13	0.13	0.07	0.07	189	208.39	NA	NA	NA	NA	NA	1.82	NA	NA	NA	NA	NA	0.00
2639	libggml-cpu.so - sgemm.cpp:138-1044 [...]	void (anonymous namespace)::tinyBLAS_Q0_AVX<block_q8_0, block_q8_0, float>::gemm4xN<2>(long, long, long, long)	Innermost	0.20	0.12	0.12	0.14	0.14	0.07	0.07	189	98.81	NA	NA	NA	NA	NA	1.97	NA	NA	NA	NA	NA	0.00
105	libggml-cpu.so - ggml-cpu.c:1164-1198 [...]	ggml_compute_forward_mul_mat	InBetween	0.30	0.11	0.12	0.21	0.24	0.07	0.07	192	50.82	0	11.14	1	1	9.6	3.25	NA	NA	NA	NA	NA	0.00
864	libggml-cpu.so - vec.cpp:311-316	ggml_vec_dot_f16	Single	0.26	0.04	0.04	0.18	0.18	0.02	0.02	32	752.21	100	66.67	1	1	1.57	1.38	0	2	0	0	0	100.00
2062	libggml-cpu.so - vec.h:491-497	ggml_compute_forward_flash_attn_ext	Innermost	0.39	0.04	0.04	0.27	0.27	0.02	0.02	36	1564.38	100	75	1	1	1.45	2.34	0	2	0	0	0	100.00
2855	libggml-cpu.so - quants.c:298-355 [...]	quantize_row_q8_0	Single	0.12	0.03	0.03	0.08	0.08	0.02	0.02	142	0.43	60.7	29.66	1	1.11	2.67	3.44	0	2	0	0	0	100.00
2053	libggml-cpu.so - ops.cpp:8759-8927 [...]	ggml_compute_forward_flash_attn_ext	InBetween	0.10	0.01	0.05	0.07	0.27	0.01	0.03	36	1722.43	53.38	48.02	1.41	1.01	1.36	2.19	NA	NA	NA	NA	NA	0.00
871	libggml-cpu.so - vec.h:1084-1116 [...]	ggml_vec_swiglu_f32	Single	0.32	0.00	0.00	0.22	0.22	0.00	0.00	7	4099.26	100	100	1	1	1	6.7	0	3	0	0	0	100.00
442	libggml-cpu.so - binary-ops.cpp:10-32 [...]	ggml_compute_forward_add_non_quantized	Innermost	0.16	0.00	0.00	0.11	0.11	0.00	0.00	1	289.66	0	6.25	1	1.33	16	1	0	3	0	0	0	100.00

×