OV - Compare Loops

Loops

▶attention_v2.cpp: 30 - 469.26 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	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 gcc-256						Run gcc-512						Run clang-256						Run clang-512						Run aocc-256						Run aocc-512
Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 30-31					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 30-31					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 30-31					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 30-31					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 30-31					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 30-31
2	0.41	0.42	6.23	0	8.75	2	0.34	0.34	5.01	0	8.75	53	3.03	3.03	34.43	0	7.5	44	0.50	0.50	5.67	0	7.5	30	0.52	0.52	5.27	0	8.33	32	0.54	0.53	5.42	0	8.33
5	0.44	0.43	6.53	0	8.75	5	0.37	0.37	5.46	0	8.75	64	1.86	1.86	21.08	0	7.5	43	0.49	0.49	5.61	0	7.5	29	0.65	0.65	6.53	0	8.33	31	0.65	0.65	6.58	0	8.33
8	0.48	0.48	7.28	0	8.75	8	0.41	0.42	6.20	0	8.75	41	0.57	0.58	6.53	0	7.5	54	3.19	3.19	36.54	0	7.5	28	0.62	0.62	6.28	0	8.33	41	3.69	3.69	37.37	0	8.33
13	1.68	1.68	25.23	0	8.75	13	1.79	1.79	26.76	0	8.75	43	0.49	0.49	5.57	0	7.5	66	1.91	1.91	21.88	0	7.5	33	2.37	2.37	23.96	0	8.33	33	0.66	0.66	6.68	0	8.33
16	2.24	2.24	33.71	0	8.75	16	2.35	2.35	35.20	0	8.75	42	0.63	0.62	7.10	0	7.5	42	0.50	0.50	5.73	0	7.5	38	3.80	3.79	38.45	0	8.33	36	2.46	2.46	24.96	0	8.33

Sum on 5 analyzed binary loops (attention-gcc-znver5-256 - 2, attention-gcc-znver5-256 - 5, attention-gcc-znver5-256 - 8, attention-gcc-znver5-256 - 13, attention-gcc-znver5-256 - 16)						Sum on 5 analyzed binary loops (attention-gcc-znver5-512 - 2, attention-gcc-znver5-512 - 5, attention-gcc-znver5-512 - 8, attention-gcc-znver5-512 - 13, attention-gcc-znver5-512 - 16)						Sum on 5 analyzed binary loops (attention-clang-znver5-256 - 53, attention-clang-znver5-256 - 64, attention-clang-znver5-256 - 41, attention-clang-znver5-256 - 43, attention-clang-znver5-256 - 42)						Sum on 5 analyzed binary loops (attention-clang-znver5-512 - 44, attention-clang-znver5-512 - 43, attention-clang-znver5-512 - 54, attention-clang-znver5-512 - 66, attention-clang-znver5-512 - 42)						Sum on 5 analyzed binary loops (attention-aocc-znver5-256 - 30, attention-aocc-znver5-256 - 29, attention-aocc-znver5-256 - 28, attention-aocc-znver5-256 - 33, attention-aocc-znver5-256 - 38)						Sum on 5 analyzed binary loops (attention-aocc-znver5-512 - 32, attention-aocc-znver5-512 - 31, attention-aocc-znver5-512 - 41, attention-aocc-znver5-512 - 33, attention-aocc-znver5-512 - 36)
Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues						Loop Computation Issues						Loop Computation Issues						Loop Computation Issues						Loop Computation Issues
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	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA						Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					0	Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					0
Low iteration count					0	Low iteration count					0	Low iteration count						Low iteration count						Low iteration count					1	Low iteration count					1
Control Flow Issues						Control Flow Issues						Control Flow Issues						Control Flow Issues						Control Flow Issues						Control Flow Issues
Low iteration count						Low iteration count						Low iteration count						Low iteration count						Low iteration count					1	Low iteration count					1
Data Access Issues						Data Access Issues						Data Access Issues						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 constant non-unit stride data access					1	Presence of constant non-unit stride data access					1	Presence of constant non-unit stride data access					1
Vectorization Roadblocks						Vectorization Roadblocks						Vectorization Roadblocks						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 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

▶attention_v2.cpp: 55 - 12.08 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	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 gcc-256						Run gcc-512						Run clang-256						Run clang-512						Run aocc-256						Run aocc-512
Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 55-56					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 55-56					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 55-56					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 55-56					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 55-56					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 55-56
28	0.22	0.22	3.23	0	6.25	28	0.25	0.25	3.74	0	6.25	49	0.10	0.10	1.14	83.33	25.35	60	0.02	0.02	0.23	83.33	21.18	37	0.15	0.15	1.47	81.08	25	49	0.00	0.00	0.05	42.86	14.29
												58	0.02	0.02	0.23	42.86	14.29	59	0.03	0.03	0.29	37.5	14.06	44	0.01	0.01	0.10	78.95	20.72	48	0.01	0.01	0.10	81.08	25
																		50	0.08	0.08	0.86	83.33	30.21	45	0.01	0.01	0.10	42.86	14.29	40	0.05	0.05	0.56	82.19	29.97

Sum on 1 analyzed binary loop (attention-gcc-znver5-256 - 28)						Sum on 1 analyzed binary loop (attention-gcc-znver5-512 - 28)						Sum on 1 analyzed binary loop (attention-clang-znver5-256 - 49)						Sum on 1 analyzed binary loop (attention-clang-znver5-512 - 50)						Sum on 1 analyzed binary loop (attention-aocc-znver5-256 - 37)						Sum on 1 analyzed binary loop (attention-aocc-znver5-512 - 40)
Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues						Loop Computation Issues						Loop Computation Issues						Loop Computation Issues						Loop Computation Issues
Presence of expensive FP instructions					1	Presence of expensive FP instructions					1	Presence of expensive FP instructions					1	Presence of expensive FP instructions					1	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	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	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					0	Presence of a large number of scalar integer instructions					0	Presence of a large number of scalar integer instructions					0	Presence of a large number of scalar integer instructions					0	Presence of a large number of scalar integer instructions					1	Presence of a large number of scalar integer instructions					0
Control Flow Issues						Control Flow Issues						Control Flow Issues						Control Flow Issues						Control Flow Issues						Control Flow Issues
Presence of calls					1	Presence of calls					1	Presence of calls					1	Presence of calls					1	Presence of calls					1	Presence of calls					1
Data Access Issues						Data Access Issues						Data Access Issues						Data Access Issues						Data Access Issues						Data Access Issues
Presence of indirect access					0	Presence of indirect access					0	Presence of indirect access					0	Presence of indirect access					0	Presence of indirect access					1	Presence of indirect access					1
More than 10% of the vector loads instructions are unaligned					0	More than 10% of the vector loads instructions are unaligned					0	More than 10% of the vector loads instructions are unaligned					1	More than 10% of the vector loads instructions are unaligned					1	More than 10% of the vector loads instructions are unaligned					1	More than 10% of the vector loads instructions are unaligned					1
Presence of special instructions executing on a single port					0	Presence of special instructions executing on a single port					0	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	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	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
Vectorization Roadblocks						Vectorization Roadblocks						Vectorization Roadblocks						Vectorization Roadblocks						Vectorization Roadblocks						Vectorization Roadblocks
Presence of calls					1	Presence of calls					1	Presence of calls					1	Presence of calls					1	Presence of calls					1	Presence of calls					1
Presence of indirect access					0	Presence of indirect access					0	Presence of indirect access					0	Presence of indirect access					0	Presence of indirect access					1	Presence of indirect access					1
Inefficient Vectorization						Inefficient Vectorization						Inefficient Vectorization						Inefficient Vectorization						Inefficient Vectorization						Inefficient Vectorization
Presence of special instructions executing on a single port						Presence of special instructions executing on a single port						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	Presence of special instructions executing on a single port					1

▶attention_v2.cpp: 52 - 5.53 %

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 (%)	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 gcc-256						Run gcc-512						Run clang-256						Run clang-512						Run aocc-256						Run aocc-512
Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 52-53					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 52-53					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 52-53					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 52-53					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 52-53					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 52-53
27	0.13	0.13	2.03	0	6.25	27	0.07	0.07	1.05	0	6.25	47	0.02	0.03	0.28	84.21	26.64	48	0.04	0.04	0.40	83.78	32.09	36	0.01	0.01	0.10	50	16.41	39	0.01	0.01	0.10	57.14	16.96
												59	0.02	0.02	0.23	80	20.94	61	0.02	0.02	0.23	81.58	25.66	46	0.01	0.01	0.10	84.21	21.38	50	0.02	0.02	0.25	83.78	26.01
																								35	0.05	0.05	0.51	84.21	26.64	38	0.02	0.02	0.25	83.5	32.03

Sum on 1 analyzed binary loop (attention-gcc-znver5-256 - 27)						Sum on 1 analyzed binary loop (attention-gcc-znver5-512 - 27)						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						Sum on 1 analyzed binary loop (attention-aocc-znver5-256 - 35)						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count
Loop Computation Issues						Loop Computation Issues																		Loop Computation Issues
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													Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA					1
Control Flow Issues						Control Flow Issues																		Control Flow Issues
Presence of calls					1	Presence of calls					1													Presence of calls					1
Data Access Issues						Data Access Issues																		Data Access Issues
More than 10% of the vector loads instructions are unaligned					0	More than 10% of the vector loads instructions are unaligned					0													More than 10% of the vector loads instructions are unaligned					1
Presence of special instructions executing on a single port					0	Presence of special instructions executing on a single port					0													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
Vectorization Roadblocks						Vectorization Roadblocks																		Vectorization Roadblocks
Presence of calls					1	Presence of calls					1													Presence of calls					1
Inefficient Vectorization						Inefficient Vectorization																		Inefficient Vectorization
Presence of special instructions executing on a single port						Presence of special instructions executing on a single port																		Presence of special instructions executing on a single port					1

▶random.tcc: 458 - 0.97 %

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 (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run gcc-256						Run gcc-512						Run clang-256		Run clang-512		Run aocc-256		Run aocc-512
Loop Source Regions	/cluster/comp/gcc/15.1.0/include/c++/15.1.0/bits/random.tcc: 458-466 /cluster/comp/gcc/15.1.0/include/c++/15.1.0/bits/random.tcc: 3367-3374 /home/eoseret/llm-attention/attention_v2.cpp: 164-167 /home/eoseret/llm-attention/attention_v2.cpp: 163-163					Loop Source Regions	/cluster/comp/gcc/15.1.0/include/c++/15.1.0/bits/random.tcc: 458-466 /cluster/comp/gcc/15.1.0/include/c++/15.1.0/bits/random.tcc: 3367-3374 /home/eoseret/llm-attention/attention_v2.cpp: 164-167 /home/eoseret/llm-attention/attention_v2.cpp: 163-163					Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions
21	0.01	0.01	0.23	10	11.25	21	0.01	0.01	0.15	10	11.25
22	0.03	0.03	0.45	9.13	11.53	22	0.01	0.01	0.15	9.13	11.53

No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.
Analysis					Count	Analysis					Count	Analysis	Count	Analysis	Count	Analysis	Count	Analysis	Count

▶attention_v2.cpp: 237 - 0.74 %

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 (%)	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 gcc-256						Run gcc-512						Run clang-256						Run clang-512						Run aocc-256		Run aocc-512
Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 237-238					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 237-238					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 237-238					Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 237-238					Loop Source Regions		Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 237-238
11	0.01	0.01	0.23	0	6.25	11	0.00	0.01	0.07	0	6.25	45	0.01	0.01	0.11	100	37.5	45	0.00	0.00	0.06	100	75			34	0.01	0.01	0.15	0	6.25
																		46	0.01	0.01	0.11	100	75

No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.
Analysis					Count	Analysis					Count	Analysis					Count	Analysis					Count	Analysis	Count	Analysis					Count

▶random.tcc: 333 - 0.45 %

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 (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run gcc-256						Run gcc-512						Run clang-256		Run clang-512		Run aocc-256		Run aocc-512
Loop Source Regions	/cluster/comp/gcc/15.1.0/include/c++/15.1.0/bits/random.h: 248-248 /cluster/comp/gcc/15.1.0/include/c++/15.1.0/bits/random.tcc: 333-339					Loop Source Regions	/cluster/comp/gcc/15.1.0/include/c++/15.1.0/bits/random.h: 248-248 /cluster/comp/gcc/15.1.0/include/c++/15.1.0/bits/random.tcc: 333-339					Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions
1	0.01	0.01	0.15	0	12.5	1	0.02	0.02	0.30	0	12.5

No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.
Analysis					Count	Analysis					Count	Analysis	Count	Analysis	Count	Analysis	Count	Analysis	Count

▶attention_v2.cpp: 47 - 0.44 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	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 (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)
Run gcc-256						Run gcc-512		Run clang-256		Run clang-512						Run aocc-256		Run aocc-512
Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 47-48					Loop Source Regions		Loop Source Regions		Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 47-48					Loop Source Regions		Loop Source Regions	/home/eoseret/llm-attention/attention_v2.cpp: 47-48
29	0.01	0.01	0.23	100	50					63	0.00	0.00	0.06	100	50			52	0.01	0.01	0.10	100	50
										47	0.00	0.00	0.06	100	100

No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.
Analysis					Count	Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count	Analysis					Count

▶random.tcc: 412 - 0.38 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	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 gcc-256		Run gcc-512		Run clang-256						Run clang-512						Run aocc-256		Run aocc-512
Loop Source Regions		Loop Source Regions		Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.tcc: 412-414					Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.tcc: 412-414					Loop Source Regions		Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.tcc: 412-414
				101	0.01	0.01	0.11	88.89	23.61	106	0.00	0.00	0.06	88.89	23.61			72	0.01	0.01	0.10	90	23.75
										96	0.00	0.00	0.06	88.89	23.61			82	0.00	0.00	0.05	90	23.75

No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis					Count	Analysis	Count	Analysis					Count

▶random.tcc: 330 - 0.27 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	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 gcc-256		Run gcc-512		Run clang-256						Run clang-512						Run aocc-256		Run aocc-512
Loop Source Regions		Loop Source Regions		Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.h: 140-140 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.tcc: 330-336					Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.h: 140-140 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.tcc: 330-336					Loop Source Regions		Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.h: 140-140 /usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.tcc: 330-336
				40	0.00	0.00	0.06	0	9.01	41	0.01	0.01	0.11	0	9.01			30	0.01	0.01	0.10	0	9.38

No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis					Count	Analysis	Count	Analysis					Count

▶random.tcc: 404 - 0.11 %

ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)	ASM Loop ID	Vector Length Use (%)
Run gcc-256		Run gcc-512		Run clang-256						Run clang-512						Run aocc-256		Run aocc-512
Loop Source Regions		Loop Source Regions		Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.tcc: 404-406					Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.tcc: 404-406					Loop Source Regions		Loop Source Regions
				100	0.00	0.00	0.06	100	50	95	0.00	0.00	0.06	100	100

No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.
Analysis	Count	Analysis	Count	Analysis					Count	Analysis					Count	Analysis	Count	Analysis	Count

▶random.tcc: 401 - 0.05 %

ASM Loop ID	Vector Length Use (%)	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 (%)	ASM Loop ID	Vector Length Use (%)
Run gcc-256		Run gcc-512		Run clang-256		Run clang-512		Run aocc-256						Run aocc-512
Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions		Loop Source Regions	/usr/lib/gcc/x86_64-redhat-linux/11/../../../../include/c++/11/bits/random.tcc: 401-406					Loop Source Regions
								73	0.00	0.01	0.05	100	50

No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.		No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.						No Loops Overview analysis found for any assembly loop. More loops can be analyzed using option --summary-loop-count.
Analysis	Count	Analysis	Count	Analysis	Count	Analysis	Count	Analysis					Count	Analysis	Count

Report Configuration

Loops

▶attention_v2.cpp: 30 - 469.26 %

▶attention_v2.cpp: 55 - 12.08 %

▶attention_v2.cpp: 52 - 5.53 %

▶random.tcc: 458 - 0.97 %

▶attention_v2.cpp: 237 - 0.74 %

▶random.tcc: 333 - 0.45 %

▶attention_v2.cpp: 47 - 0.44 %

▶random.tcc: 412 - 0.38 %

▶random.tcc: 330 - 0.27 %

▶random.tcc: 404 - 0.11 %

▶random.tcc: 401 - 0.05 %