OV - Compare Loops

Loops

▶repack.cpp: 153 - 159.24 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_9						Run icx_9
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 153-153 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 170-172 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 559-575 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 582-586 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 616-616					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 153-153 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 170-172 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 559-575 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 582-586 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 616-616					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 153-153 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 170-172 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 559-575 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 582-586 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 616-616					Loop Source Regions
2569	2.39	2.13	54.24	0	0	2960	2.11	2.01	53.05	0	0	2000	1.92	1.84	51.95	0	0

Sum on 1 analyzed binary loop (libggml-cpu.so - 2569)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2960)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2000)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis	Count

▶quants.c: 682 - 64.30 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_9		Run icx_9
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 682-682 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 690-695
						3839	4.53	3.91	64.30	93.02	21.37

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 1 analyzed binary loop (libggml-cpu.so - 3839)
Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count
						Loop Computation Issues
						Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
						Data Access Issues
						Presence of indirect access					1
						Presence of special instructions executing on a single port					1
						Vectorization Roadblocks
						Presence of indirect access					1
						Inefficient Vectorization
						Presence of special instructions executing on a single port					1

▶quants.c: 2150 - 35.79 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_9						Run icx_9
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 2150-2152 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 2158-2158 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 2166-2216					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 2150-2152 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 2158-2158 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 2166-2216					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 2150-2152 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 2158-2158 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/quants.c: 2166-2216					Loop Source Regions
2544	0.46	0.43	10.86	97.09	43.87	2936	0.44	0.46	12.16	96.81	44.08	1970	0.45	0.45	12.77	97.09	43.87

Sum on 1 analyzed binary loop (libggml-cpu.so - 2544)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2936)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1970)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis	Count
Data Access Issues						Data Access Issues						Data Access Issues
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1
Presence of indirect access					1	Presence of indirect access					1	Presence of indirect access					1
Presence of special instructions executing on a single port					1	Presence of special instructions executing on a single port					1	Presence of special instructions executing on a single port					1
Vectorization Roadblocks						Vectorization Roadblocks						Vectorization Roadblocks
Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1
Presence of indirect access					1	Presence of indirect access					1	Presence of indirect access					1
Inefficient Vectorization						Inefficient Vectorization						Inefficient Vectorization
Presence of special instructions executing on a single port					1	Presence of special instructions executing on a single port					1	Presence of special instructions executing on a single port					1

▶quants.c: 716 - 7.54 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_9		Run icx_9
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/quants.c: 716-716 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/quants.c: 725-725 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/quants.c: 733-736 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/quants.c: 745-754 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
						499	0.50	0.46	7.54	46.92	13.2

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 1 analyzed binary loop (libggml-cpu.so - 499)
Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count
						Loop Computation Issues
						Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
						Presence of a large number of scalar integer instructions					1
						Data Access Issues
						Presence of constant non-unit stride data access					1
						Presence of indirect access					1
						Presence of special instructions executing on a single port					1
						More than 20% of the loads are accessing the stack					1
						Vectorization Roadblocks
						Presence of constant non-unit stride data access					1
						Presence of indirect access					1
						Inefficient Vectorization
						Presence of special instructions executing on a single port					1

▶<unknown>: 0 - 1.98 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_9						Run icx_9
Loop Source Regions						Loop Source Regions						Loop Source Regions						Loop Source Regions
2485	0.00	0.00	0.00	0	0	1023	0.00	0.00	0.00	0	0	2125	0.01	0.00	0.00	0	0	4301	0.00	0.00	0.00	0	0
2640	0.00	0.00	0.00	0	0	2395	0.01	0.00	0.00	0	0	2262	0.01	0.00	0.00	0	0	3825	0.00	0.00	0.00	0	0
1126	0.00	0.00	0.00	0	0	2155	0.00	0.00	0.00	0	0	2256	0.00	0.00	0.00	0	0	1922	0.00	0.00	0.00	0	0
2842	0.00	0.00	0.00	0	0	2504	0.00	0.00	0.00	0	0	2448	0.02	0.00	0.01	0	0	4341	0.00	0.00	0.00	0	0
2638	0.00	0.00	0.00	0	0	2294	0.00	0.00	0.00	0	0	2346	0.00	0.00	0.00	0	0	4117	0.00	0.00	0.00	0	0
2741	0.00	0.00	0.00	0	0	444	0.09	0.00	0.04	0	0	2349	0.01	0.00	0.00	0	0	4118	0.01	0.00	0.00	0	0
765	0.03	0.00	0.02	0	0	278	0.01	0.00	0.06	0	0	1139	0.01	0.00	0.02	0	0	4130	0.00	0.00	0.00	0	0
2586	0.02	0.00	0.06	0	0	114	0.00	0.00	0.00	0	0	2017	0.02	0.00	0.06	0	0	1714	0.01	0.00	0.00	0	0
2527	0.04	0.00	0.02	0	0	124	0.02	0.00	0.09	0	0	423	0.02	0.00	0.01	0	0	1561	0.00	0.00	0.00	0	0
358	0.01	0.00	0.01	0	0	2954	0.00	0.00	0.00	0	0	353	0.05	0.00	0.04	0	0	648	0.02	0.00	0.07	0	0
1704	0.01	0.00	0.00	0	0	108	0.00	0.00	0.00	0	0	56	0.01	0.00	0.01	0	0	877	0.00	0.00	0.00	0	0
1709	0.02	0.00	0.08	0	0	873	0.04	0.00	0.03	0	0	1297	0.00	0.00	0.00	0	0	3505	0.00	0.00	0.00	0	0
1456	0.02	0.00	0.03	0	0	2099	0.02	0.00	0.06	0	0	1301	0.02	0.00	0.06	0	0	1747	0.05	0.00	0.02	0	0
87	0.00	0.00	0.00	0	0	2980	0.01	0.00	0.06	0	0	1951	0.05	0.00	0.03	0	0	114	0.00	0.00	0.00	0	0
2562	0.01	0.00	0.00	0	0	1412	0.00	0.00	0.00	0	0	195	0.26	0.00	0.09	0	0	2574	0.04	0.00	0.01	0	0
82	0.01	0.00	0.01	0	0	1418	0.02	0.00	0.01	0	0	227	0.01	0.00	0.02	0	0	530	0.01	0.00	0.01	0	0
1195	0.01	0.00	0.00	0	0	1707	0.01	0.00	0.04	0	0	0	0.01	0.00	0.00	0	0	108	0.02	0.00	0.07	0	0
484	0.03	0.00	0.01	0	0	2111	0.00	0.00	0.00	0	0	1076	0.00	0.00	0.00	0	0	117	0.01	0.00	0.01	0	0
99	0.01	0.00	0.05	0	0	558	0.01	0.00	0.00	0	0	1992	0.01	0.00	0.00	0	0	2572	0.01	0.00	0.00	0	0
398	0.05	0.00	0.03	0	0	401	0.01	0.00	0.01	0	0	4	0.01	0.00	0.01	0	0	2986	0.03	0.00	0.08	0	0
233	0.21	0.00	0.06	0	0	2918	0.03	0.00	0.02	0	0	993	0.00	0.00	0.00	0	0	2975	0.01	0.00	0.03	0	0
274	0.01	0.00	0.02	0	0	102	0.01	0.00	0.00	0	0	71	0.02	0.00	0.06	0	0	119	0.01	0.00	0.06	0	0
5	0.01	0.00	0.02	0	0	2094	0.01	0.00	0.01	0	0	994	0.00	0.00	0.00	0	0	3433	0.01	0.00	0.01	0	0
						6	0.00	0.00	0.01	0	0	55	0.01	0.00	0.00	0	0	649	0.03	0.00	0.01	0	0
						257	0.29	0.00	0.09	0	0	319	0.01	0.00	0.01	0	0	3	0.03	0.00	0.04	0	0
						490	0.00	0.00	0.00	0	0	695	0.02	0.00	0.01	0	0	3446	0.02	0.00	0.03	0	0
						27	0.00	0.00	0.00	0	0	57	0.00	0.00	0.00	0	0	112	0.01	0.00	0.01	0	0
						368	0.00	0.00	0.00	0	0	431	0.00	0.00	0.00	0	0	3429	0.01	0.00	0.01	0	0
						1947	0.00	0.00	0.00	0	0	707	0.00	0.00	0.00	0	0	945	0.02	0.00	0.01	0	0
						1948	0.00	0.00	0.00	0	0

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

▶repack.cpp: 125 - 1.78 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_9						Run icx_9
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 125-125 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 137-140 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 755-779 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 822-842					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 125-125 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 137-140 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 755-760 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 766-766 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 772-779 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 822-842					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 125-125 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 137-140 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 755-779 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/arch/x86/repack.cpp: 822-842					Loop Source Regions
2593	0.04	0.02	0.57	99.51	83.19	2990	0.04	0.02	0.57	99.48	85.43	2024	0.04	0.02	0.64	99.51	83.19

Sum on 1 analyzed binary loop (libggml-cpu.so - 2593)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2990)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2024)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis	Count
Data Access Issues						Data Access Issues						Data Access Issues
Presence of special instructions executing on a single port					1	Presence of special instructions executing on a single port					1	Presence of special instructions executing on a single port					1
More than 20% of the loads are accessing the stack					1	More than 20% of the loads are accessing the stack					1	More than 20% of the loads are accessing the stack					1
Inefficient Vectorization						Inefficient Vectorization						Inefficient Vectorization
Presence of special instructions executing on a single port					1	Presence of special instructions executing on a single port					1	Presence of special instructions executing on a single port					1
Use of masked instructions					1	Use of masked instructions					1	Use of masked instructions					1

▶vec.cpp: 331 - 1.02 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_9		Run icx_9
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 331-332
						1733	0.15	0.06	1.02	5.88	8.82

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 1 analyzed binary loop (libggml-cpu.so - 1733)
Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count
						Loop Computation Issues
						Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
						Data Access Issues
						Presence of indirect access					1
						Vectorization Roadblocks
						Presence of indirect access					1

▶vec.h: 491 - 0.95 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_9						Run icx_9
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 491-497					Loop Source Regions
1723	0.04	0.01	0.31	100	75	2109	0.04	0.01	0.29	100	75	1312	0.05	0.01	0.36	100	75

Sum on 1 analyzed binary loop (libggml-cpu.so - 1723)						Sum on 1 analyzed binary loop (libggml-cpu.so - 2109)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1312)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis	Count

▶vec.h: 508 - 0.92 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_9		Run icx_9
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 346-346 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 389-389 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/./ggml-impl.h: 399-404 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.h: 508-509 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/simd-mappings.h: 130-130
						3443	0.15	0.06	0.92	85.05	20.79

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 1 analyzed binary loop (libggml-cpu.so - 3443)
Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count
						Loop Computation Issues
						Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
						Data Access Issues
						Presence of indirect access					1
						Presence of special instructions executing on a single port					1
						Vectorization Roadblocks
						Presence of indirect access					1
						Inefficient Vectorization
						Presence of special instructions executing on a single port					1

▶vec.cpp: 311 - 0.69 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_9						Run icx_9
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/vec.cpp: 311-316					Loop Source Regions
761	0.04	0.01	0.21	100	66.67	866	0.03	0.01	0.24	100	66.67	689	0.04	0.01	0.24	100	66.67

Sum on 1 analyzed binary loop (libggml-cpu.so - 761)						Sum on 1 analyzed binary loop (libggml-cpu.so - 866)						Sum on 1 analyzed binary loop (libggml-cpu.so - 689)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis	Count
Loop Computation Issues						Loop Computation Issues						Loop Computation Issues
Low iteration count						Low iteration count					1	Low iteration count
Control Flow Issues						Control Flow Issues						Control Flow Issues
Low iteration count						Low iteration count					1	Low iteration count

▶ops.cpp: 6220 - 0.31 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default						Run icx_default						Run aocc_9		Run icx_9
Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6220 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6229-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions		Loop Source Regions
1462	0.03	0.01	0.17	6.67	7.5	1734	0.02	0.01	0.14	15.56	9.17

Sum on 1 analyzed binary loop (libggml-cpu.so - 1462)						Sum on 1 analyzed binary loop (libggml-cpu.so - 1734)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis					Count	Analysis					Count	Analysis	Count	Analysis	Count
Loop Computation Issues						Loop Computation Issues
Presence of expensive FP instructions					1	Presence of expensive FP instructions					1
Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
Presence of a large number of scalar integer instructions					1	Presence of a large number of scalar integer instructions					0
Control Flow Issues						Control Flow Issues
Presence of calls					1	Presence of calls					1
Data Access Issues						Data Access Issues
More than 20% of the loads are accessing the stack					1	More than 20% of the loads are accessing the stack					1
Vectorization Roadblocks						Vectorization Roadblocks
Presence of calls					1	Presence of calls					1

▶ops.cpp: 6210 - 0.22 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_9						Run icx_9
Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6210-6211 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6220-6230 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ops.cpp: 6238-6245					Loop Source Regions
				1142	0.03	0.01	0.22	5.56	7.29

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 1 analyzed binary loop (libggml-cpu.so - 1142)						No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count
				Loop Computation Issues
				Presence of expensive FP instructions					1
				Presence of a large number of scalar integer instructions					1
				Control Flow Issues
				Presence of calls					1
				Presence of more than 4 paths					1
				Data Access Issues
				Presence of special instructions executing on a single port					1
				More than 20% of the loads are accessing the stack					1
				Vectorization Roadblocks
				Presence of calls					1
				Presence of more than 4 paths					1
				Inefficient Vectorization
				Presence of special instructions executing on a single port					1
				Use of masked instructions					1

▶ggml-cpu.c: 533 - 0.11 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run orig_default		Run icx_default		Run aocc_9		Run icx_9
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 533-534 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 1664-1673 /beegfs/hackathon/users/eoseret/qaas_runs_test/gmz12.benchmarkcenter.megware.com/177-002-5325/llama.cpp/build/llama.cpp/ggml/src/ggml-cpu/ggml-cpu.c: 2879-2891
						135	0.03	0.01	0.11	0	9.82

No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count.		Sum on 1 analyzed binary loop (libggml-cpu.so - 135)
Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count
						Control Flow Issues
						Presence of calls					1
						Data Access Issues
						More than 20% of the loads are accessing the stack					1
						Vectorization Roadblocks
						Presence of calls					1
						Presence of more than 4 paths					1

Report Configuration

Loops

▶repack.cpp: 153 - 159.24 %

▶quants.c: 682 - 64.30 %

▶quants.c: 2150 - 35.79 %

▶quants.c: 716 - 7.54 %

▶<unknown>: 0 - 1.98 %

▶repack.cpp: 125 - 1.78 %

▶vec.cpp: 331 - 1.02 %

▶vec.h: 491 - 0.95 %

▶vec.h: 508 - 0.92 %

▶vec.cpp: 311 - 0.69 %

▶ops.cpp: 6220 - 0.31 %

▶ops.cpp: 6210 - 0.22 %

▶ggml-cpu.c: 533 - 0.11 %