| clang o3 spread | clang o3 close |
|---|---|
[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics. | [ 3 / 3 ] Host configuration allows retrieval of all necessary metrics. |
[ 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. | [ 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. |
[ 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) ). | [ 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) ). |
[ 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 ] 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. |
[ 4 / 4 ] Application profile is long enough (55.87 s) To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds. | [ 4 / 4 ] Application profile is long enough (46.48 s) To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds. |
[ 2 / 2 ] Application is correctly profiled ("Others" category represents 1.57 % 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 | [ 2 / 2 ] Application is correctly profiled ("Others" category represents 1.90 % 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 / 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 ] 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. |
[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated. | [ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated. |
| clang o3 spread | clang o3 close |
|---|---|
[ 4 / 4 ] CPU activity is good CPU cores are active 94.87% of time | [ 4 / 4 ] CPU activity is good CPU cores are active 94.10% of time |
[ 4 / 4 ] Affinity is good (98.64%) Threads are not migrating to CPU cores: probably successfully pinned | [ 4 / 4 ] Affinity is good (98.48%) Threads are not migrating to CPU cores: probably successfully pinned |
[ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (21.02%) If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances. | [ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (18.06%) If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances. |
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.19%) lower than cumulative innermost loop coverage (20.84%) Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex | [ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.15%) lower than cumulative innermost loop coverage (17.91%) Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex |
[ 4 / 4 ] Threads activity is good On average, more than 2253.98% of observed threads are actually active | [ 4 / 4 ] Threads activity is good On average, more than 2267.39% of observed threads are actually active |
[ 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 BLAS2 operations BLAS2 calls usually could make a poor cache usage and could benefit from inlining. |
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (20.84%) 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. | [ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (17.91%) 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% (0.00%) is spend in BLAS1 operations It could be more efficient to inline by hand BLAS1 operations | [ 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% (0.04%) is spend in Libm/SVML (special functions) | [ 2 / 2 ] Less than 10% (0.05%) is spend in Libm/SVML (special functions) |
[ 4 / 4 ] Loop profile is not flat At least one loop coverage is greater than 4% (20.42%), representing an hotspot for the application | [ 4 / 4 ] Loop profile is not flat At least one loop coverage is greater than 4% (17.46%), representing an hotspot for the application |
| Analysis | r_1 | r_2 | |
|---|---|---|---|
| Loop Computation Issues | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 | 1 |
| Presence of a large number of scalar integer instructions | 3 | 3 | |
| Control Flow Issues | Presence of calls | 4 | 4 |
| Presence of 2 to 4 paths | 3 | 3 | |
| Presence of more than 4 paths | 5 | 5 | |
| Non-innermost loop | 1 | 1 | |
| Data Access Issues | Presence of constant non-unit stride data access | 4 | 4 |
| More than 20% of the loads are accessing the stack | 2 | 2 | |
| Vectorization Roadblocks | Presence of calls | 4 | 4 |
| Presence of 2 to 4 paths | 3 | 3 | |
| Presence of more than 4 paths | 5 | 5 | |
| Non-innermost loop | 1 | 1 | |
| Presence of constant non-unit stride data access | 4 | 4 | |