[ 4 / 4 ] Application profile is long enough (164.16 s)

To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3 / 3 ] Most of time spent in analyzed modules (100.00%) comes from functions compiled with architecture specialization option -mcpu

[ 2.40 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations but -fno-omit-frame-pointer is missing

-fno-omit-frame-pointer improves 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 / 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.

[ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (18.17%)

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 99.95% of observed threads are actually active

[ 4 / 4 ] CPU activity is good

CPU cores are active 99.95% of time

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (16.76%), representing an hotspot for the application

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (18.17%)

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 ] Affinity is good (99.99%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 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 (0.00%) lower than cumulative innermost loop coverage (18.17%)

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.

[ 0 / 2 ] More than 10% (79.59%) is spend in Libm/SVML (special functions)

The application is heavily using special math functions (powers, exp, sin etc…) proper library version have to be used. Exact accuracy needs have to be evaluated. Perform input value profiling, first count how many different input values. If the Arm Performance Libraries (ArmPL) are installed, load it and link to it with -lamath -lm.

[ 4 / 4 ] Application profile is long enough (82.12 s)

To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3 / 3 ] Most of time spent in analyzed modules (100.00%) comes from functions compiled with architecture specialization option -mcpu

[ 2.40 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations but -fno-omit-frame-pointer is missing

-fno-omit-frame-pointer improves 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 / 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.

[ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (17.69%)

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 199.81% of observed threads are actually active

[ 4 / 4 ] CPU activity is good

CPU cores are active 99.84% of time

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (16.26%), representing an hotspot for the application

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (17.69%)

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 ] Affinity is good (99.89%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 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 (0.00%) lower than cumulative innermost loop coverage (17.69%)

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.

[ 0 / 2 ] More than 10% (80.02%) is spend in Libm/SVML (special functions)

The application is heavily using special math functions (powers, exp, sin etc…) proper library version have to be used. Exact accuracy needs have to be evaluated. Perform input value profiling, first count how many different input values. If the Arm Performance Libraries (ArmPL) are installed, load it and link to it with -lamath -lm.

[ 4 / 4 ] Application profile is long enough (41.07 s)

To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3.00 / 3 ] Most of time spent in analyzed modules (99.98%) comes from functions compiled with architecture specialization option -mcpu

[ 2.40 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations but -fno-omit-frame-pointer is missing

-fno-omit-frame-pointer improves 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 / 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.

[ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (17.92%)

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 399.36% of observed threads are actually active

[ 4 / 4 ] CPU activity is good

CPU cores are active 99.77% of time

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (16.45%), representing an hotspot for the application

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (17.92%)

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.

[ 4 / 4 ] Affinity is good (99.81%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 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 (0.00%) lower than cumulative innermost loop coverage (17.92%)

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.

[ 0 / 2 ] More than 10% (79.81%) is spend in Libm/SVML (special functions)

The application is heavily using special math functions (powers, exp, sin etc…) proper library version have to be used. Exact accuracy needs have to be evaluated. Perform input value profiling, first count how many different input values. If the Arm Performance Libraries (ArmPL) are installed, load it and link to it with -lamath -lm.

[ 4 / 4 ] Application profile is long enough (20.55 s)

To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3.00 / 3 ] Most of time spent in analyzed modules (99.98%) comes from functions compiled with architecture specialization option -mcpu

[ 2.40 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations but -fno-omit-frame-pointer is missing

-fno-omit-frame-pointer improves 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 / 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.

[ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (17.83%)

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 797.52% of observed threads are actually active

[ 4 / 4 ] CPU activity is good

CPU cores are active 99.66% of time

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (16.32%), representing an hotspot for the application

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (17.83%)

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 ] Affinity is good (99.68%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 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 (0.00%) lower than cumulative innermost loop coverage (17.83%)

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.

[ 0 / 2 ] More than 10% (79.63%) is spend in Libm/SVML (special functions)

The application is heavily using special math functions (powers, exp, sin etc…) proper library version have to be used. Exact accuracy needs have to be evaluated. Perform input value profiling, first count how many different input values. If the Arm Performance Libraries (ArmPL) are installed, load it and link to it with -lamath -lm.

[ 4 / 4 ] Application profile is long enough (10.28 s)

To have good quality measurements, it is advised that the application profiling time is greater than 10 seconds.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3 / 3 ] Most of time spent in analyzed modules (100.00%) comes from functions compiled with architecture specialization option -mcpu

[ 2.40 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations but -fno-omit-frame-pointer is missing

-fno-omit-frame-pointer improves 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 / 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.

[ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (18.02%)

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 1589.77% of observed threads are actually active

[ 4 / 4 ] CPU activity is good

CPU cores are active 99.42% of time

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (16.47%), representing an hotspot for the application

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (18.02%)

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.

[ 4 / 4 ] Affinity is good (99.41%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 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 (0.00%) lower than cumulative innermost loop coverage (18.02%)

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.

[ 0 / 2 ] More than 10% (79.55%) is spend in Libm/SVML (special functions)

The application is heavily using special math functions (powers, exp, sin etc…) proper library version have to be used. Exact accuracy needs have to be evaluated. Perform input value profiling, first count how many different input values. If the Arm Performance Libraries (ArmPL) are installed, load it and link to it with -lamath -lm.

[ 0 / 4 ] Application profile is too short (5.17 s)

If the overall application profiling time is less than 10 seconds, many of the measurements at function or loop level will very likely be under the measurement quality threshold (0,1 seconds).
Rerun to increase runtime duration: for example use a larger dataset or include a repetition loop.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3.00 / 3 ] Most of time spent in analyzed modules (99.95%) comes from functions compiled with architecture specialization option -mcpu

[ 2.40 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations but -fno-omit-frame-pointer is missing

-fno-omit-frame-pointer improves 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 / 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.

[ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (17.84%)

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 3159.10% of observed threads are actually active

[ 4 / 4 ] CPU activity is good

CPU cores are active 96.98% of time

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (16.44%), representing an hotspot for the application

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (17.84%)

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 ] Affinity is good (96.90%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 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 (0.00%) lower than cumulative innermost loop coverage (17.84%)

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.

[ 0 / 2 ] More than 10% (79.04%) is spend in Libm/SVML (special functions)

The application is heavily using special math functions (powers, exp, sin etc…) proper library version have to be used. Exact accuracy needs have to be evaluated. Perform input value profiling, first count how many different input values. If the Arm Performance Libraries (ArmPL) are installed, load it and link to it with -lamath -lm.

[ 0 / 4 ] Application profile is too short (2.59 s)

If the overall application profiling time is less than 10 seconds, many of the measurements at function or loop level will very likely be under the measurement quality threshold (0,1 seconds).
Rerun to increase runtime duration: for example use a larger dataset or include a repetition loop.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3 / 3 ] Most of time spent in analyzed modules (100.00%) comes from functions compiled with architecture specialization option -mcpu

[ 2.40 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations but -fno-omit-frame-pointer is missing

-fno-omit-frame-pointer improves 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 / 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.

[ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (17.95%)

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 6161.59% of observed threads are actually active

[ 4 / 4 ] CPU activity is good

CPU cores are active 93.79% of time

[ 4 / 4 ] Loop profile is not flat

At least one loop coverage is greater than 4% (16.47%), representing an hotspot for the application

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (17.94%)

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 ] Affinity is good (93.77%)

Threads are not migrating to CPU cores: probably successfully pinned

[ 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 (0.01%) lower than cumulative innermost loop coverage (17.94%)

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.

[ 0 / 2 ] More than 10% (79.07%) is spend in Libm/SVML (special functions)

The application is heavily using special math functions (powers, exp, sin etc…) proper library version have to be used. Exact accuracy needs have to be evaluated. Perform input value profiling, first count how many different input values. If the Arm Performance Libraries (ArmPL) are installed, load it and link to it with -lamath -lm.

[ 0 / 4 ] Application profile is too short (1.73 s)

If the overall application profiling time is less than 10 seconds, many of the measurements at function or loop level will very likely be under the measurement quality threshold (0,1 seconds).
Rerun to increase runtime duration: for example use a larger dataset or include a repetition loop.

[ 3 / 3 ] Most of time spent in analyzed modules comes from functions with source/debug info

-g option gives access to debugging informations, such are source locations.

[ 3 / 3 ] Most of time spent in analyzed modules (100.00%) comes from functions compiled with architecture specialization option -mcpu

[ 2.40 / 3 ] Most of time spent in analyzed modules comes from functions with compilation options informations but -fno-omit-frame-pointer is missing

-fno-omit-frame-pointer improves 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 / 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.

[ 0 / 4 ] Too little time of the experiment time spent in analyzed loops (17.62%)

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 8789.32% of observed threads are actually active

[ 3 / 4 ] CPU activity is below 90% (84.03%)

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% (16.19%), representing an hotspot for the application

[ 4 / 4 ] Enough time of the experiment time spent in analyzed innermost loops (17.62%)

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% (85.22%)

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 (0.00%) lower than cumulative innermost loop coverage (17.62%)

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.

[ 0 / 2 ] More than 10% (79.15%) is spend in Libm/SVML (special functions)

The application is heavily using special math functions (powers, exp, sin etc…) proper library version have to be used. Exact accuracy needs have to be evaluated. Perform input value profiling, first count how many different input values. If the Arm Performance Libraries (ArmPL) are installed, load it and link to it with -lamath -lm.