Help is available by moving the cursor above any 
symbol or by checking MAQAO website.
[ 4 / 4 ] Application profile is long enough (303.40 s)
To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.
[ 3.00 / 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.
[ 3 / 3 ] Optimization level option is correctly used
[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.
[ 3.00 / 3 ] Architecture specific option -x Host is used
[ 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
[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.
[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (100.00%)
If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.
[ 4 / 4 ] Threads activity is good
On average, more than 98.69% of observed threads are actually active
[ 4 / 4 ] CPU activity is good
CPU cores are active 98.69% of time
[ 4 / 4 ] Loop profile is not flat
At least one loop coverage is greater than 4% (99.14%), representing an hotspot for the application
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (99.14%)
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.
[ 2 / 4 ] Affinity stability is lower than 90% (69.81%)
Threads are often migrating to other CPU cores/threads. For OpenMP, typically set (OMP_PLACES=cores OMP_PROC_BIND=close) or (OMP_PLACES=threads OMP_PROC_BIND=spread). With OpenMPI + OpenMP, use --bind-to core --map-by node:PE=$OMP_NUM_THREADS --report-bindings. With IntelMPI + OpenMP, set I_MPI_PIN_DOMAIN=omp:compact or I_MPI_PIN_DOMAIN=omp:scatter and use -print-rank-map.
[ 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 ] Functions mostly use all threads
Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (0.00%)
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.86%) lower than cumulative innermost loop coverage (99.14%)
Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex
[ 2 / 2 ] Less than 10% (0.00%) 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 26 - kmeans-icpx-Ofast | Execution Time: 99 % - Vectorization Ratio: 57.89 % - Vector Length Use: 18.86 % | |
| ►Loop Computation Issues | 4 | |
| ○ | [SA] Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA - Reorganize arithmetic expressions to exhibit potential for FMA. This issue costs 4 points. | 4 |
| ►Control Flow Issues | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Data Access Issues | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Vectorization Roadblocks | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Inefficient Vectorization | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Loop 25 - kmeans-icpx-Ofast | Execution Time: 0 % - Vectorization Ratio: 94.12 % - Vector Length Use: 23.90 % | |
| ►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 |
| ►Control Flow Issues | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
| ►Vectorization Roadblocks | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
[ 4 / 4 ] Application profile is long enough (153.56 s)
To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.
[ 3.00 / 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.
[ 3 / 3 ] Optimization level option is correctly used
[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.
[ 3.00 / 3 ] Architecture specific option -x Host is used
[ 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
[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.
[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (97.87%)
If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.
[ 4 / 4 ] Threads activity is good
On average, more than 130.11% of observed threads are actually active
[ 3 / 4 ] CPU activity is below 90% (84.32%)
CPU cores are idle more than 10% of time. Threads supposed to run on these cores are probably IO/sync waiting. Some hints: use faster filesystems to read/write data, improve parallel load balancing and/or scheduling.
[ 4 / 4 ] Loop profile is not flat
At least one loop coverage is greater than 4% (96.99%), representing an hotspot for the application
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (97.02%)
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 / 4 ] Affinity stability is lower than 90% (70.33%)
Threads are often migrating to other CPU cores/threads. For OpenMP, typically set (OMP_PLACES=cores OMP_PROC_BIND=close) or (OMP_PLACES=threads OMP_PROC_BIND=spread). With OpenMPI + OpenMP, use --bind-to core --map-by node:PE=$OMP_NUM_THREADS --report-bindings. With IntelMPI + OpenMP, set I_MPI_PIN_DOMAIN=omp:compact or I_MPI_PIN_DOMAIN=omp:scatter and use -print-rank-map.
[ 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 ] Functions mostly use all threads
Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (0.07%)
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.85%) lower than cumulative innermost loop coverage (97.02%)
Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex
[ 2 / 2 ] Less than 10% (0.00%) 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 26 - kmeans-icpx-Ofast | Execution Time: 96 % - Vectorization Ratio: 57.89 % - Vector Length Use: 18.86 % | |
| ►Loop Computation Issues | 4 | |
| ○ | [SA] Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA - Reorganize arithmetic expressions to exhibit potential for FMA. This issue costs 4 points. | 4 |
| ►Control Flow Issues | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Data Access Issues | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Vectorization Roadblocks | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Inefficient Vectorization | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Loop 25 - kmeans-icpx-Ofast | Execution Time: 0 % - Vectorization Ratio: 94.12 % - Vector Length Use: 23.90 % | |
| ►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 |
| ►Control Flow Issues | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
| ►Vectorization Roadblocks | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
[ 4 / 4 ] Application profile is long enough (78.21 s)
To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.
[ 3.00 / 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.
[ 3 / 3 ] Optimization level option is correctly used
[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.
[ 3.00 / 3 ] Architecture specific option -x Host is used
[ 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
[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.
[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (95.56%)
If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.
[ 4 / 4 ] Threads activity is good
On average, more than 165.92% of observed threads are actually active
[ 3 / 4 ] CPU activity is below 90% (77.73%)
CPU cores are idle more than 10% of time. Threads supposed to run on these cores are probably IO/sync waiting. Some hints: use faster filesystems to read/write data, improve parallel load balancing and/or scheduling.
[ 4 / 4 ] Loop profile is not flat
At least one loop coverage is greater than 4% (94.69%), representing an hotspot for the application
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (94.75%)
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 / 4 ] Affinity stability is lower than 90% (70.82%)
Threads are often migrating to other CPU cores/threads. For OpenMP, typically set (OMP_PLACES=cores OMP_PROC_BIND=close) or (OMP_PLACES=threads OMP_PROC_BIND=spread). With OpenMPI + OpenMP, use --bind-to core --map-by node:PE=$OMP_NUM_THREADS --report-bindings. With IntelMPI + OpenMP, set I_MPI_PIN_DOMAIN=omp:compact or I_MPI_PIN_DOMAIN=omp:scatter and use -print-rank-map.
[ 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 ] Functions mostly use all threads
Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (0.06%)
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.80%) lower than cumulative innermost loop coverage (94.75%)
Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex
[ 2 / 2 ] Less than 10% (0.00%) 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 26 - kmeans-icpx-Ofast | Execution Time: 94 % - Vectorization Ratio: 57.89 % - Vector Length Use: 18.86 % | |
| ►Loop Computation Issues | 4 | |
| ○ | [SA] Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA - Reorganize arithmetic expressions to exhibit potential for FMA. This issue costs 4 points. | 4 |
| ►Control Flow Issues | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Data Access Issues | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Vectorization Roadblocks | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Inefficient Vectorization | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Loop 25 - kmeans-icpx-Ofast | Execution Time: 0 % - Vectorization Ratio: 94.12 % - Vector Length Use: 23.90 % | |
| ►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 |
| ►Control Flow Issues | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
| ►Vectorization Roadblocks | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
[ 4 / 4 ] Application profile is long enough (40.02 s)
To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.
[ 2.99 / 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.
[ 3 / 3 ] Optimization level option is correctly used
[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.
[ 2.99 / 3 ] Architecture specific option -x Host is used
[ 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
[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.
[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (92.62%)
If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.
[ 4 / 4 ] Threads activity is good
On average, more than 200.60% of observed threads are actually active
[ 3 / 4 ] CPU activity is below 90% (74.92%)
CPU cores are idle more than 10% of time. Threads supposed to run on these cores are probably IO/sync waiting. Some hints: use faster filesystems to read/write data, improve parallel load balancing and/or scheduling.
[ 4 / 4 ] Loop profile is not flat
At least one loop coverage is greater than 4% (91.67%), representing an hotspot for the application
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (91.85%)
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 / 4 ] Affinity stability is lower than 90% (71.55%)
Threads are often migrating to other CPU cores/threads. For OpenMP, typically set (OMP_PLACES=cores OMP_PROC_BIND=close) or (OMP_PLACES=threads OMP_PROC_BIND=spread). With OpenMPI + OpenMP, use --bind-to core --map-by node:PE=$OMP_NUM_THREADS --report-bindings. With IntelMPI + OpenMP, set I_MPI_PIN_DOMAIN=omp:compact or I_MPI_PIN_DOMAIN=omp:scatter and use -print-rank-map.
[ 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 ] Functions mostly use all threads
Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (0.05%)
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.78%) lower than cumulative innermost loop coverage (91.85%)
Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex
[ 2 / 2 ] Less than 10% (0.00%) 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 26 - kmeans-icpx-Ofast | Execution Time: 91 % - Vectorization Ratio: 57.89 % - Vector Length Use: 18.86 % | |
| ►Loop Computation Issues | 4 | |
| ○ | [SA] Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA - Reorganize arithmetic expressions to exhibit potential for FMA. This issue costs 4 points. | 4 |
| ►Control Flow Issues | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Data Access Issues | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Vectorization Roadblocks | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Inefficient Vectorization | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Loop 25 - kmeans-icpx-Ofast | Execution Time: 0 % - Vectorization Ratio: 94.12 % - Vector Length Use: 23.90 % | |
| ►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 |
| ►Control Flow Issues | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
| ►Vectorization Roadblocks | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
[ 4 / 4 ] Application profile is long enough (20.73 s)
To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.
[ 2.98 / 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.
[ 3 / 3 ] Optimization level option is correctly used
[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.
[ 2.98 / 3 ] Architecture specific option -x Host is used
[ 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
[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.
[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (88.44%)
If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.
[ 4 / 4 ] Threads activity is good
On average, more than 233.19% of observed threads are actually active
[ 3 / 4 ] CPU activity is below 90% (74.27%)
CPU cores are idle more than 10% of time. Threads supposed to run on these cores are probably IO/sync waiting. Some hints: use faster filesystems to read/write data, improve parallel load balancing and/or scheduling.
[ 4 / 4 ] Loop profile is not flat
At least one loop coverage is greater than 4% (87.00%), representing an hotspot for the application
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (87.73%)
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 / 4 ] Affinity stability is lower than 90% (72.60%)
Threads are often migrating to other CPU cores/threads. For OpenMP, typically set (OMP_PLACES=cores OMP_PROC_BIND=close) or (OMP_PLACES=threads OMP_PROC_BIND=spread). With OpenMPI + OpenMP, use --bind-to core --map-by node:PE=$OMP_NUM_THREADS --report-bindings. With IntelMPI + OpenMP, set I_MPI_PIN_DOMAIN=omp:compact or I_MPI_PIN_DOMAIN=omp:scatter and use -print-rank-map.
[ 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 ] Functions mostly use all threads
Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (0.00%)
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.71%) lower than cumulative innermost loop coverage (87.73%)
Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex
[ 2 / 2 ] Less than 10% (0.00%) 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 26 - kmeans-icpx-Ofast | Execution Time: 87 % - Vectorization Ratio: 57.89 % - Vector Length Use: 18.86 % | |
| ►Loop Computation Issues | 4 | |
| ○ | [SA] Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA - Reorganize arithmetic expressions to exhibit potential for FMA. This issue costs 4 points. | 4 |
| ►Control Flow Issues | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Data Access Issues | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Vectorization Roadblocks | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Inefficient Vectorization | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Loop 25 - kmeans-icpx-Ofast | Execution Time: 0 % - Vectorization Ratio: 94.12 % - Vector Length Use: 23.90 % | |
| ►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 |
| ►Control Flow Issues | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
| ►Vectorization Roadblocks | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
[ 4 / 4 ] Application profile is long enough (13.65 s)
To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.
[ 2.92 / 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.
[ 3 / 3 ] Optimization level option is correctly used
[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics.
[ 2.92 / 3 ] Architecture specific option -x Host is used
[ 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
[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated.
[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (81.55%)
If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances.
[ 4 / 4 ] Threads activity is good
On average, more than 267.43% of observed threads are actually active
[ 3 / 4 ] CPU activity is below 90% (75.51%)
CPU cores are idle more than 10% of time. Threads supposed to run on these cores are probably IO/sync waiting. Some hints: use faster filesystems to read/write data, improve parallel load balancing and/or scheduling.
[ 4 / 4 ] Loop profile is not flat
At least one loop coverage is greater than 4% (78.66%), representing an hotspot for the application
[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (80.92%)
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 / 4 ] Affinity stability is lower than 90% (74.43%)
Threads are often migrating to other CPU cores/threads. For OpenMP, typically set (OMP_PLACES=cores OMP_PROC_BIND=close) or (OMP_PLACES=threads OMP_PROC_BIND=spread). With OpenMPI + OpenMP, use --bind-to core --map-by node:PE=$OMP_NUM_THREADS --report-bindings. With IntelMPI + OpenMP, set I_MPI_PIN_DOMAIN=omp:compact or I_MPI_PIN_DOMAIN=omp:scatter and use -print-rank-map.
[ 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 ] Functions mostly use all threads
Functions running on a reduced number of threads (typically sequential code) cover less than 10% of application walltime (0.14%)
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.63%) lower than cumulative innermost loop coverage (80.92%)
Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex
[ 2 / 2 ] Less than 10% (0.00%) 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 26 - kmeans-icpx-Ofast | Execution Time: 78 % - Vectorization Ratio: 57.89 % - Vector Length Use: 18.86 % | |
| ►Loop Computation Issues | 4 | |
| ○ | [SA] Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA - Reorganize arithmetic expressions to exhibit potential for FMA. This issue costs 4 points. | 4 |
| ►Control Flow Issues | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Data Access Issues | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Vectorization Roadblocks | 260 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ►Inefficient Vectorization | 8 | |
| ○ | [SA] Presence of special instructions executing on a single port (SHUFFLE/PERM) - Simplify data access and try to get stride 1 access. There are 8 issues (= instructions) costing 1 point each. | 8 |
| ►Loop 25 - kmeans-icpx-Ofast | Execution Time: 0 % - Vectorization Ratio: 94.12 % - Vector Length Use: 23.90 % | |
| ►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 |
| ►Control Flow Issues | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |
| ►Vectorization Roadblocks | 262 | |
| ○ | [SA] Too many paths (256 paths) - Simplify control structure. There are 256 issues ( = paths) costing 1 point each with a malus of 4 points. | 260 |
| ○ | [SA] Non innermost loop (Outermost) - Collapse loop with innermost ones. This issue costs 2 points. | 2 |