Help is available by moving the cursor above any symbol or by checking MAQAO website.
[ 4 / 4 ] Application profile is long enough (80.55 s)
To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.
[ 2.91 / 3 ] Optimization level option is correctly used
[ 2.91 / 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.
[ 2.91 / 3 ] Architecture specific option -march=native is used
[ 2 / 2 ] Application is correctly profiled ("Others" category represents 0.77 % 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 (65.07%)
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% (28.41%), representing an hotspot for the application
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (64.85%)
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.
[ 3 / 3 ] Less than 10% (0%) is spend in BLAS1 operations
It could be more efficient to inline by hand BLAS1 operations
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.22%) lower than cumulative innermost loop coverage (64.85%)
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)
[ 2 / 2 ] Less than 10% (2.73%) is spend in BLAS2 operations
BLAS2 calls usually could make a poor cache usage and could benefit from inlining.
Loop ID | Analysis | Penalty Score |
---|---|---|
○Loop 873 - exec | Execution Time: 28 % - Vectorization Ratio: 100.00 % - Vector Length Use: 25.00 % | |
►Loop 880 - exec | Execution Time: 11 % - Vectorization Ratio: 100.00 % - Vector Length Use: 50.00 % | |
►Data Access Issues | 24 | |
○ | [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 1 issues ( = data accesses) costing 2 point each. | 2 |
○ | [SA] Inefficient vectorization: more than 10% of the vector loads instructions are unaligned - When allocating arrays, don’t forget to align them. There are 11 issues ( = arrays) costing 2 points each | 22 |
►Vectorization Roadblocks | 2 | |
○ | [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 1 issues ( = data accesses) costing 2 point each. | 2 |
►Loop 2090 - exec | Execution Time: 9 % - Vectorization Ratio: 12.77 % - Vector Length Use: 14.10 % | |
►Loop Computation Issues | 4 | |
○ | [SA] Presence of expensive FP instructions - Perform hoisting, change algorithm, use SVML or proper numerical library or perform value profiling (count the number of distinct input values). There are 1 issues (= instructions) costing 4 points each. | 4 |
►Loop 1864 - exec | Execution Time: 5 % - Vectorization Ratio: 54.55 % - Vector Length Use: 15.91 % | |
►Loop Computation Issues | 2 | |
○ | [SA] Presence of a large number of scalar integer instructions - Simplify loop structure, perform loop splitting or perform unroll and jam. This issue costs 2 points. | 2 |
►Data Access Issues | 16 | |
○ | [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 |
○ | [SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 1 issues ( = indirect data accesses) costing 4 point each. | 4 |
►Vectorization Roadblocks | 16 | |
○ | [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 |
○ | [SA] Presence of indirect accesses - Use array restructuring or gather instructions to lower the cost. There are 1 issues ( = indirect data accesses) costing 4 point each. | 4 |
►Loop 1370 - exec | Execution Time: 2 % - Vectorization Ratio: 97.00 % - Vector Length Use: 48.88 % | |
►Loop Computation Issues | 64 | |
○ | [SA] Presence of expensive FP instructions - Perform hoisting, change algorithm, use SVML or proper numerical library or perform value profiling (count the number of distinct input values). There are 16 issues (= instructions) costing 4 points each. | 64 |
►Data Access Issues | 26 | |
○ | [SA] Inefficient vectorization: more than 10% of the vector loads instructions are unaligned - When allocating arrays, don’t forget to align them. There are 9 issues ( = arrays) costing 2 points each | 18 |
○ | [SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 6 issues (= instructions) costing 1 point each. | 6 |
○ | [SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points. | 2 |
►Inefficient Vectorization | 6 | |
○ | [SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 6 issues (= instructions) costing 1 point each. | 6 |
►Loop 393 - exec | Execution Time: 1 % - Vectorization Ratio: 89.47 % - Vector Length Use: 44.08 % | |
►Loop Computation Issues | 2 | |
○ | [SA] Presence of a large number of scalar integer instructions - Simplify loop structure, perform loop splitting or perform unroll and jam. This issue costs 2 points. | 2 |
►Data Access Issues | 23 | |
○ | [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 3 issues ( = data accesses) costing 2 point each. | 6 |
○ | [SA] Inefficient vectorization: more than 10% of the vector loads instructions are unaligned - When allocating arrays, don’t forget to align them. There are 5 issues ( = arrays) costing 2 points each | 10 |
○ | [SA] Presence of special instructions executing on a single port (COMPRESS/EXPAND, BROADCAST) - Simplify data access and try to get stride 1 access. There are 5 issues (= instructions) costing 1 point each. | 5 |
○ | [SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points. | 2 |
►Vectorization Roadblocks | 6 | |
○ | [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 3 issues ( = data accesses) costing 2 point each. | 6 |
►Inefficient Vectorization | 7 | |
○ | [SA] Presence of special instructions executing on a single port (COMPRESS/EXPAND, BROADCAST) - Simplify data access and try to get stride 1 access. There are 5 issues (= instructions) costing 1 point each. | 5 |
○ | [SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points. | 2 |
►Loop 875 - exec | Execution Time: 0 % - Vectorization Ratio: 30.00 % - Vector Length Use: 15.31 % | |
►Loop Computation Issues | 2 | |
○ | [SA] Presence of a large number of scalar integer instructions - Simplify loop structure, perform loop splitting or perform unroll and jam. This issue costs 2 points. | 2 |
►Data Access Issues | 22 | |
○ | [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 9 issues ( = data accesses) costing 2 point each. | 18 |
○ | [SA] Presence of special instructions executing on a single port (INSERT/EXTRACT, BROADCAST) - Simplify data access and try to get stride 1 access. There are 4 issues (= instructions) costing 1 point each. | 4 |
►Vectorization Roadblocks | 18 | |
○ | [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 9 issues ( = data accesses) costing 2 point each. | 18 |
►Inefficient Vectorization | 4 | |
○ | [SA] Presence of special instructions executing on a single port (INSERT/EXTRACT, BROADCAST) - Simplify data access and try to get stride 1 access. There are 4 issues (= instructions) costing 1 point each. | 4 |
○Loop 2345 - exec | Execution Time: 0 % - Vectorization Ratio: 100.00 % - Vector Length Use: 50.00 % | |
►Loop 332 - exec | Execution Time: 0 % - Vectorization Ratio: 86.96 % - Vector Length Use: 44.57 % | |
►Loop Computation Issues | 2 | |
○ | [SA] Presence of a large number of scalar integer instructions - Simplify loop structure, perform loop splitting or perform unroll and jam. This issue costs 2 points. | 2 |
►Data Access Issues | 38 | |
○ | [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 |
○ | [SA] Inefficient vectorization: more than 10% of the vector loads instructions are unaligned - When allocating arrays, don’t forget to align them. There are 8 issues ( = arrays) costing 2 points each | 16 |
○ | [SA] Presence of special instructions executing on a single port (COMPRESS/EXPAND, BROADCAST) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
○ | [SA] More than 20% of the loads are accessing the stack - Perform loop splitting to decrease pressure on registers. This issue costs 2 points. | 2 |
►Vectorization Roadblocks | 12 | |
○ | [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 |
►Inefficient Vectorization | 10 | |
○ | [SA] Presence of special instructions executing on a single port (COMPRESS/EXPAND, BROADCAST) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
○ | [SA] Inefficient vectorization: use of masked instructions - Simplify control structure. The issue costs 2 points. | 2 |
►Loop 994 - exec | Execution Time: 0 % - Vectorization Ratio: 33.33 % - Vector Length Use: 16.67 % | |
►Data Access Issues | 6 | |
○ | [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 1 issues ( = data accesses) costing 2 point each. | 2 |
○ | [SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 4 issues (= instructions) costing 1 point each. | 4 |
►Vectorization Roadblocks | 2 | |
○ | [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 1 issues ( = data accesses) costing 2 point each. | 2 |
►Inefficient Vectorization | 4 | |
○ | [SA] Presence of special instructions executing on a single port (BROADCAST) - Simplify data access and try to get stride 1 access. There are 4 issues (= instructions) costing 1 point each. | 4 |