| orig_default | icx_default | aocc_9 | icx_1 |
|---|---|---|---|
[ 3 / 3 ] Host configuration allows retrieval of all necessary metrics. | [ 3 / 3 ] Host configuration allows retrieval of all necessary metrics. | [ 3 / 3 ] Host configuration allows retrieval of all necessary metrics. | [ 3 / 3 ] Host configuration allows retrieval of all necessary metrics. |
[ 4 / 4 ] Application profile is long enough (10.75 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 (10.84 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 (10.76 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 (20.81 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 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 | [ 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 | [ 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 | [ 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 / 9 ] Compilation options are not available Compilation options are an important optimization leverage but ONE-View is not able to analyze them. | [ 0 / 9 ] Compilation options are not available Compilation options are an important optimization leverage but ONE-View is not able to analyze them. | [ 0 / 9 ] Compilation options are not available Compilation options are an important optimization leverage but ONE-View is not able to analyze them. | [ 0 / 9 ] Compilation options are not available Compilation options are an important optimization leverage but ONE-View is not able to analyze them. |
[ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated. | [ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated. | [ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated. | [ 1 / 1 ] Lstopo present. The Topology lstopo report will be generated. |
| orig_default | icx_default | aocc_9 | icx_1 |
|---|---|---|---|
[ 4 / 4 ] CPU activity is good CPU cores are active 98.17% of time | [ 4 / 4 ] CPU activity is good CPU cores are active 98.33% of time | [ 4 / 4 ] CPU activity is good CPU cores are active 98.32% of time | [ 4 / 4 ] CPU activity is good CPU cores are active 99.24% of time |
[ 4 / 4 ] Affinity is good (98.89%) Threads are not migrating to CPU cores: probably successfully pinned | [ 4 / 4 ] Affinity is good (98.99%) Threads are not migrating to CPU cores: probably successfully pinned | [ 4 / 4 ] Affinity is good (98.95%) Threads are not migrating to CPU cores: probably successfully pinned | [ 4 / 4 ] Affinity is good (99.49%) Threads are not migrating to CPU cores: probably successfully pinned |
[ 0 / 3 ] Too many functions do not use all threads Functions running on a reduced number of threads (typically sequential code) cover at least 10% of application walltime (19.74%). Check both "Max Inclusive Time Over Threads" and "Nb Threads" in Functions or Loops tabs and consider parallelizing sequential regions or improving parallelization of regions running on a reduced number of threads | [ 0 / 3 ] Too many functions do not use all threads Functions running on a reduced number of threads (typically sequential code) cover at least 10% of application walltime (11.02%). Check both "Max Inclusive Time Over Threads" and "Nb Threads" in Functions or Loops tabs and consider parallelizing sequential regions or improving parallelization of regions running on a reduced number of threads | [ 0 / 3 ] Too many functions do not use all threads Functions running on a reduced number of threads (typically sequential code) cover at least 10% of application walltime (18.99%). Check both "Max Inclusive Time Over Threads" and "Nb Threads" in Functions or Loops tabs and consider parallelizing sequential regions or improving parallelization of regions running on a reduced number of threads | [ 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 (9.28%) |
[ 3 / 3 ] Cumulative Outermost/In between loops coverage (0.44%) lower than cumulative innermost loop coverage (67.34%) 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 (0.49%) lower than cumulative innermost loop coverage (67.04%) 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 (23.91%) lower than cumulative innermost loop coverage (45.20%) 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 (0.55%) lower than cumulative innermost loop coverage (86.86%) Having cumulative Outermost/In between loops coverage greater than cumulative innermost loop coverage will make loop optimization more complex |
[ 2 / 4 ] A significant amount of threads are idle (48.61%) On average, more than 10% of observed threads are idle. Such threads are probably IO/sync waiting. Some hints: use faster filesystems to read/write data, improve parallel load balancing and/or scheduling. | [ 2 / 4 ] A significant amount of threads are idle (45.41%) On average, more than 10% of observed threads are idle. Such threads are probably IO/sync waiting. Some hints: use faster filesystems to read/write data, improve parallel load balancing and/or scheduling. | [ 2 / 4 ] A significant amount of threads are idle (44.94%) On average, more than 10% of observed threads are idle. Such threads are probably IO/sync waiting. Some hints: use faster filesystems to read/write data, improve parallel load balancing and/or scheduling. | [ 3 / 4 ] A significant amount of threads are idle (29.59%) On average, more than 10% of observed threads are idle. Such threads are probably IO/sync waiting. Some hints: use faster filesystems to read/write data, improve parallel load balancing and/or scheduling. |
[ 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. | [ 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 (67.34%) 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 (67.04%) 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 (45.20%) 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 (86.86%) 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 | [ 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% (0.47%) is spend in Libm/SVML (special functions) | [ 2 / 2 ] Less than 10% (0.00%) is spend in Libm/SVML (special functions) | [ 2 / 2 ] Less than 10% (0.27%) is spend in Libm/SVML (special functions) | [ 2 / 2 ] Less than 10% (0.00%) is spend in Libm/SVML (special functions) |
[ 4 / 4 ] Loop profile is not flat At least one loop coverage is greater than 4% (64.39%), representing an hotspot for the application | [ 4 / 4 ] Loop profile is not flat At least one loop coverage is greater than 4% (64.20%), representing an hotspot for the application | [ 4 / 4 ] Loop profile is not flat At least one loop coverage is greater than 4% (41.90%), representing an hotspot for the application | [ 4 / 4 ] Loop profile is not flat At least one loop coverage is greater than 4% (83.87%), representing an hotspot for the application |
[ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (67.79%) If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances. | [ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (67.53%) If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances. | [ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (69.12%) If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances. | [ 4 / 4 ] Enough time of the experiment time spent in analyzed loops (87.41%) If the time spent in analyzed loops is less than 30%, standard loop optimizations will have a limited impact on application performances. |
| Analysis | r0 | r1 | r2 | r3 | |
|---|---|---|---|---|---|
| Loop Computation Issues | Presence of expensive FP instructions | 3 | 3 | 3 | 3 |
| Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 3 | 2 | 2 | 7 | |
| Presence of a large number of scalar integer instructions | 2 | 1 | 3 | 2 | |
| Low iteration count | 0 | 1 | 0 | 0 | |
| Control Flow Issues | Presence of calls | 2 | 2 | 2 | 3 |
| Presence of 2 to 4 paths | 3 | 3 | 2 | 2 | |
| Presence of more than 4 paths | 1 | 1 | 2 | 0 | |
| Non-innermost loop | 2 | 2 | 2 | 1 | |
| Low iteration count | 0 | 1 | 0 | 0 | |
| Data Access Issues | Presence of constant non-unit stride data access | 2 | 1 | 3 | 2 |
| Presence of indirect access | 2 | 1 | 1 | 3 | |
| More than 10% of the vector loads instructions are unaligned | 1 | 2 | 1 | 3 | |
| Presence of expensive instructions: scatter/gather | 0 | 1 | 0 | 0 | |
| Presence of special instructions executing on a single port | 4 | 3 | 6 | 5 | |
| More than 20% of the loads are accessing the stack | 4 | 3 | 3 | 4 | |
| Vectorization Roadblocks | Presence of calls | 2 | 2 | 2 | 3 |
| Presence of 2 to 4 paths | 3 | 3 | 2 | 2 | |
| Presence of more than 4 paths | 1 | 1 | 2 | 0 | |
| Non-innermost loop | 2 | 2 | 2 | 1 | |
| Presence of constant non-unit stride data access | 2 | 1 | 3 | 2 | |
| Presence of indirect access | 2 | 1 | 1 | 3 | |
| Inefficient Vectorization | Presence of expensive instructions: scatter/gather | 0 | 1 | 0 | 0 |
| Presence of special instructions executing on a single port | 4 | 3 | 6 | 5 | |
| Use of masked instructions | 1 | 2 | 2 | 0 | |