Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
[ 4 / 4 ] Application profile is long enough (123.47 s)
To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.
[ 2.75 / 3 ] Optimization level option is correctly used
[ 2.74 / 3 ] Most of time spent in analyzed modules comes from functions compiled with -g and -fno-omit-frame-pointer
-g option gives access to debugging informations, such are source locations. -fno-omit-frame-pointer improve the accuracy of callchains found during the application profiling.
[ 2.74 / 3 ] Architecture specific option -xCORE is used
[ 2 / 2 ] Application is correctly profiled ("Others" category represents 0.1 % of the execution time)
To have a representative profiling, it is advised that the category "Others" represents less than 20% of the execution time in order to analyze as much as possible of the user code
[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (46.40%)
If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.
[ 4 / 4 ] Loop profile is not flat
At least one loop coverage is greater than 4% (4.05%), representing an hotspot for the application
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (38.53%)
If the time spent in analyzed innermost loops is less than 15%, standard innermost loop optimizations such as vectorisation will have a limited impact on application performances.
[ 0 / 3 ] More than 10% (18.22%) is spend in BLAS1 operations
It could be more efficient to inline by hand BLAS1 operations
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (7.87%) lower than cumulative innermost loop coverage (38.53%)
Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex
[ 2 / 2 ] Less than 10% (0%) is spend in Libm/SVML (special functions)
[ 0 / 2 ] More than 10% (19.16%) is spend in BLAS2 operations
BLAS2 calls usually make a poor cache usage. Try blocking. Such calls should probably benefit from inlining. Such inlining will have to be hand made.
| Loop ID | Module | Analysis | Penalty Score | Coverage (%) | Vectorization Ratio (%) | Vector Length Use (%) |
|---|---|---|---|---|---|---|
| ►2338 | exec | Partial or unexisting vectorization - Use pragma to force vectorization and check potential dependencies between array access. | 28 | 4.05 | 0 | 12.5 |
| ○ | [SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 7 issues ( = indirect data accesses) costing 4 point each. | 28 | ||||
| ►3176 | exec | Partial or unexisting vectorization - Use pragma to force vectorization and check potential dependencies between array access. | 29 | 3.25 | 18.18 | 13.64 |
| ○ | [SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 14 issues ( = data accesses) costing 2 point each. | 28 | ||||
| ○ | [SA] Presence of calls - Inline either by compiler or by hand and use SVML for libm calls. There are 1 issues (= calls) costing 1 point each. | 1 | ||||
| ►2997 | exec | Inefficient vectorization. | 2 | 3.25 | 100 | 50 |
| ○ | [SA] Inefficient vectorization: use of shorter than available vector length - Force compiler to use proper vector length. CAUTION: use of 512 bits vectors could be more expensive than 256 bits on some processors. Use intrinsics (costly and not portable). The issue costs 2 points. | 2 | ||||
| ○ | Warning! There is no dynamic data for this loop. Some checks can not been performed. | 0 | ||||
| ○4649 | exec | Partial or unexisting vectorization - No issue detected | 0 | 2.54 | 0 | 6.25 |
| ►2944 | exec | Inefficient vectorization. | 2 | 2.19 | 100 | 50 |
| ○ | [SA] Inefficient vectorization: use of shorter than available vector length - Force compiler to use proper vector length. CAUTION: use of 512 bits vectors could be more expensive than 256 bits on some processors. Use intrinsics (costly and not portable). The issue costs 2 points. | 2 | ||||
| ○ | Warning! There is no dynamic data for this loop. Some checks can not been performed. | 0 | ||||
| ►2063 | exec | Inefficient vectorization. | 2 | 1.8 | 100 | 50 |
| ○ | [SA] Inefficient vectorization: use of shorter than available vector length - Force compiler to use proper vector length. CAUTION: use of 512 bits vectors could be more expensive than 256 bits on some processors. Use intrinsics (costly and not portable). The issue costs 2 points. | 2 | ||||
| ○ | Warning! There is no dynamic data for this loop. Some checks can not been performed. | 0 | ||||
| ►2336 | exec | Partial or unexisting vectorization - Use pragma to force vectorization and check potential dependencies between array access. | 12 | 1.68 | 0 | 12.5 |
| ○ | [SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 6 issues ( = data accesses) costing 2 point each. | 12 | ||||
| ○4599 | exec | Partial or unexisting vectorization - No issue detected | 0 | 1.43 | 0 | 6.25 |
| ►2235 | exec | Partial or unexisting vectorization - Use pragma to force vectorization and check potential dependencies between array access. | 8 | 1.33 | 0 | 12.5 |
| ○ | [SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 2 issues ( = indirect data accesses) costing 4 point each. | 8 | ||||
| ►2248 | exec | Partial or unexisting vectorization - Use pragma to force vectorization and check potential dependencies between array access. | 8 | 1.23 | 11.11 | 13.89 |
| ○ | [SA] Presence of constant non unit stride data access - Use array restructuring, perform loop interchange or use gather instructions to lower a bit the cost. There are 4 issues ( = data accesses) costing 2 point each. | 8 |