OV - Compare Loops

MAQAO

options

Loops

▶kernel.c: 105 - 294.99 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run gcc_G3_ftz							Run gcc_G3_noftz							Run clang_G3_ftz							Run clang_G3_noftz							Run armclang_G3_ftz							Run armclang_G3_noftz
Loop Source Regions	/home/eoseret/subnormals/kernel.c: 105-115 /home/eoseret/subnormals/kernel.c: 129-130						Loop Source Regions	/home/eoseret/subnormals/kernel.c: 105-115 /home/eoseret/subnormals/kernel.c: 129-130						Loop Source Regions	/home/eoseret/subnormals/kernel.c: 106-115 /home/eoseret/subnormals/kernel.c: 129-130						Loop Source Regions	/home/eoseret/subnormals/kernel.c: 106-115 /home/eoseret/subnormals/kernel.c: 129-130						Loop Source Regions	/home/eoseret/subnormals/kernel.c: 106-115 /home/eoseret/subnormals/kernel.c: 129-130						Loop Source Regions	/home/eoseret/subnormals/kernel.c: 106-115 /home/eoseret/subnormals/kernel.c: 129-130
8	13.27	13.27	48.55	10.81	13.85	7.51	8	13.26	13.26	48.54	10.81	13.85	7.52	15	3.31	3.31	49.85	100	100	29.23	15	3.24	3.24	48.80	100	100	29.64	15	3.32	3.32	49.78	100	100	29.11	15	3.29	3.29	49.47	100	100	29.4

Sum on 1 analyzed binary loop (kernel_gcc14_ftz_nooutput - 8)							Sum on 1 analyzed binary loop (kernel_gcc14_nooutput - 8)							Sum on 1 analyzed binary loop (kernel_clang22_ftz_nooutput - 15)							Sum on 1 analyzed binary loop (kernel_clang22_nooutput - 15)							Sum on 1 analyzed binary loop (kernel_armclang_ftz_nooutput - 15)							Sum on 1 analyzed binary loop (kernel_armclang_nooutput - 15)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
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

▶kernel.c: 159 - 169.94 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run gcc_G3_ftz							Run gcc_G3_noftz							Run clang_G3_ftz							Run clang_G3_noftz							Run armclang_G3_ftz							Run armclang_G3_noftz
Loop Source Regions							Loop Source Regions							Loop Source Regions	/home/eoseret/subnormals/kernel.c: 159-169						Loop Source Regions	/home/eoseret/subnormals/kernel.c: 159-169						Loop Source Regions	/home/eoseret/subnormals/kernel.c: 159-169						Loop Source Regions	/home/eoseret/subnormals/kernel.c: 159-169
														18	2.82	2.82	42.39	100	100	31.09	18	2.91	2.91	43.83	100	100	30.23	18	2.80	2.80	41.98	100	100	31.29	18	2.78	2.77	41.73	100	100	31.47

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 (kernel_clang22_ftz_nooutput - 18)							Sum on 1 analyzed binary loop (kernel_clang22_nooutput - 18)							Sum on 1 analyzed binary loop (kernel_armclang_ftz_nooutput - 18)							Sum on 1 analyzed binary loop (kernel_armclang_nooutput - 18)
Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count	Analysis						Count
														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
														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
														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

▶kernel.c: 157 - 101.67 %

ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s	ASM Loop ID	Max Time Over Threads (s)	Time w.r.t. Wall Time (s)	Cov (%)	Vect. Ratio (%)	Vector Length Use (%)	GFLOP/s
Run gcc_G3_ftz							Run gcc_G3_noftz							Run clang_G3_ftz							Run clang_G3_noftz							Run armclang_G3_ftz							Run armclang_G3_noftz
Loop Source Regions	/home/eoseret/subnormals/kernel.c: 157-169						Loop Source Regions	/home/eoseret/subnormals/kernel.c: 157-169						Loop Source Regions							Loop Source Regions							Loop Source Regions							Loop Source Regions
6	13.92	13.92	50.93	13.51	14.19	6.92	6	13.87	13.87	50.73	13.51	14.19	6.94

Sum on 1 analyzed binary loop (kernel_gcc14_ftz_nooutput - 6)							Sum on 1 analyzed binary loop (kernel_gcc14_nooutput - 6)							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
Loop Computation Issues							Loop Computation Issues
Presence of expensive FP instructions						1	Presence of expensive FP instructions						1
Data Access Issues							Data Access Issues
Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1
Vectorization Roadblocks							Vectorization Roadblocks
Presence of constant non-unit stride data access						1	Presence of constant non-unit stride data access						1

×