Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
[ 4 / 4 ] Application profile is long enough (335.99 s)
To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.
[ 0 / 3 ] Some functions are compiled with a low optimization level (O0 or O1)
To have better performances, it is advised to help the compiler by using a proper optimization level (-O2 of higher). Warning, depending on compilers, faster optimization levels can decrease numeric accuracy.
[ 0 / 3 ] Most of time spent in analyzed modules comes from functions without compilation information
Functions without compilation information (typically not compiled with -g and -grecord-gcc-switches) cumulate 100.00% of the time spent in analyzed modules. Check that -g and -grecord-gcc-switches are present. Remark: if -g and -grecord-gcc-switches are indeed used, this can also be due to some compiler built-in functions (typically math) or statically linked libraries. This warning can be ignored in that case.
[ 0 / 3 ] Compilation of some functions is not optimized for the target processor
Architecture specific options are needed to produce efficient code for a specific processor ( -x(target) or -ax(target) ).
[ 2 / 2 ] Application is correctly profiled ("Others" category represents 0.00 % 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
[ 0 / 0 ] Fastmath not used
Consider to add ffast-math to compilation flags (or replace -O3 with -Ofast) to unlock potential extra speedup by relaxing floating-point computation consistency. Warning: floating-point accuracy may be reduced and the compliance to IEEE/ISO rules/specifications for math functions will be relaxed, typically 'errno' will no longer be set after calling some math functions.
[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (98.97%)
If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.
[ 4 / 4 ] CPU activity is good
CPU cores are active 99.86% of time
[ 4 / 4 ] Threads activity is good
On average, more than 99.86% of observed threads are actually active
[ 4 / 4 ] Affinity is good (100.00%)
Threads are not migrating to CPU cores: probably successfully pinned
[ 4 / 4 ] Loop profile is not flat
At least one loop coverage is greater than 4% (38.61%), representing an hotspot for the application
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (98.97%)
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 ] Cumulative Outermost/In between loops coverage (0.00%) lower than cumulative innermost loop coverage (98.97%)
Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex
[ 3 / 3 ] Less than 10% (0.00%) is spend in BLAS1 operations
It could be more efficient to inline by hand BLAS1 operations
[ 2 / 2 ] Less than 10% (0.00%) is spend in BLAS2 operations
BLAS2 calls usually could make a poor cache usage and could benefit from inlining.
[ 2 / 2 ] Less than 10% (0.00%) is spend in Libm/SVML (special functions)
| Loop ID | Analysis | Penalty Score |
|---|---|---|
| ►Loop 1435 - bench | Execution Time: 38 % - Vectorization Ratio: 98.53 % - Vector Length Use: 49.45 % | |
| ►Loop Computation Issues | 12 | |
| ○ | [SA] Large loop body: over microp cache size - Perform loop splitting or reduce unrolling. There are 4 issues (= chunks of 50 instructions) costing 2 point each. | 8 |
| ○ | [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 |
| ○ | [SA] Bottleneck in the front end - If loop size is very small (rare occurrences), perform unroll and jam. If loop size is large, perform loop splitting. This issue costs 2 points. | 2 |
| ►Data Access Issues | 113 | |
| ○ | [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 2 issues ( = data accesses) costing 2 point each. | 4 |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 109 issues (= instructions) costing 1 point each. | 109 |
| ►Vectorization Roadblocks | 4 | |
| ○ | [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 2 issues ( = data accesses) costing 2 point each. | 4 |
| ►Inefficient Vectorization | 109 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 109 issues (= instructions) costing 1 point each. | 109 |
| ►Loop 980 - bench | Execution Time: 34 % - Vectorization Ratio: 98.34 % - Vector Length Use: 44.94 % | |
| ►Data Access Issues | 59 | |
| ○ | [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] Presence of special instructions executing on a single port (INSERT/EXTRACT, SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 53 issues (= instructions) costing 1 point each. | 53 |
| ►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 | 53 | |
| ○ | [SA] Presence of special instructions executing on a single port (INSERT/EXTRACT, SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 53 issues (= instructions) costing 1 point each. | 53 |
| ►Loop 1310 - bench | Execution Time: 25 % - Vectorization Ratio: 100.00 % - Vector Length Use: 48.10 % | |
| ►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 | 28 | |
| ○ | [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 2 issues ( = data accesses) costing 2 point each. | 4 |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 24 issues (= instructions) costing 1 point each. | 24 |
| ►Vectorization Roadblocks | 4 | |
| ○ | [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 2 issues ( = data accesses) costing 2 point each. | 4 |
| ►Inefficient Vectorization | 24 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM, BROADCAST) - Simplify data access and try to get stride 1 access. There are 24 issues (= instructions) costing 1 point each. | 24 |
| ►Loop 282 - bench | Execution Time: 0 % - Vectorization Ratio: 0.00 % - Vector Length Use: 12.50 % | |
| ►Control Flow Issues | 1 | |
| ○ | [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 |
| ►Data Access Issues | 4 | |
| ○ | [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] 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 | 3 | |
| ○ | [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 |
| ○ | [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 256 - bench | Execution Time: 0 % - Vectorization Ratio: 0.00 % - Vector Length Use: 12.50 % | |
| ►Control Flow Issues | 1 | |
| ○ | [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 |
| ►Data Access Issues | 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 |
| ►Vectorization Roadblocks | 3 | |
| ○ | [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 |
| ○ | [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 |