- r_1 - O2 - 10 analyzed loop(s)
- Loop 11911 - engine_linuxa64_gf_ompi
- Loop 5976 - engine_linuxa64_gf_ompi
- Loop 10481 - engine_linuxa64_gf_ompi
- Loop 29846 - engine_linuxa64_gf_ompi
- Loop 29826 - engine_linuxa64_gf_ompi
- Loop 6181 - engine_linuxa64_gf_ompi
- Loop 30139 - engine_linuxa64_gf_ompi
- Loop 6251 - engine_linuxa64_gf_ompi
- Loop 22622 - engine_linuxa64_gf_ompi
- Loop 11625 - engine_linuxa64_gf_ompi
- r_2 - O3 - 10 analyzed loop(s)
- Loop 12756 - engine_linuxa64_gf_ompi
- Loop 6583 - engine_linuxa64_gf_ompi
- Loop 11257 - engine_linuxa64_gf_ompi
- Loop 30855 - engine_linuxa64_gf_ompi
- Loop 30830 - engine_linuxa64_gf_ompi
- Loop 6802 - engine_linuxa64_gf_ompi
- Loop 31178 - engine_linuxa64_gf_ompi
- Loop 6883 - engine_linuxa64_gf_ompi
- Loop 23947 - engine_linuxa64_gf_ompi
- Loop 12489 - engine_linuxa64_gf_ompi
- r_3 - O3+nosve - 10 analyzed loop(s)
- Loop 12439 - engine_linuxa64_gf_ompi
- Loop 6413 - engine_linuxa64_gf_ompi
- Loop 10963 - engine_linuxa64_gf_ompi
- Loop 29988 - engine_linuxa64_gf_ompi
- Loop 6632 - engine_linuxa64_gf_ompi
- Loop 30301 - engine_linuxa64_gf_ompi
- Loop 29963 - engine_linuxa64_gf_ompi
- Loop 6701 - engine_linuxa64_gf_ompi
- Loop 12178 - engine_linuxa64_gf_ompi
- Loop 23328 - engine_linuxa64_gf_ompi
- r_4 - O3+nosve2 - 10 analyzed loop(s)
- Loop 12756 - engine_linuxa64_gf_ompi
- Loop 6583 - engine_linuxa64_gf_ompi
- Loop 11257 - engine_linuxa64_gf_ompi
- Loop 30855 - engine_linuxa64_gf_ompi
- Loop 30830 - engine_linuxa64_gf_ompi
- Loop 6802 - engine_linuxa64_gf_ompi
- Loop 31178 - engine_linuxa64_gf_ompi
- Loop 6883 - engine_linuxa64_gf_ompi
- Loop 23947 - engine_linuxa64_gf_ompi
- Loop 12489 - engine_linuxa64_gf_ompi
| Analysis | Count | Percentage | Weighted Count |
|---|
| ▼Loop Computation Issues– | 68 | | |
| ○Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 36 | 90.00 | 0.92 |
| ○Presence of a large number of scalar integer instructions | 28 | 70.00 | 0.69 |
| ○Presence of expensive FP instructions | 4 | 10.00 | 0.06 |
| ▼Control Flow Issues– | 17 | | |
| ○Presence of 2 to 4 paths | 12 | 30.00 | 0.22 |
| ○Presence of more than 4 paths | 4 | 10.00 | 0.17 |
| ○Non-innermost loop | 1 | 2.50 | 0.04 |
| ▼Data Access Issues– | 41 | | |
| ○Presence of constant non-unit stride data access | 25 | 62.50 | 0.51 |
| ○Presence of indirect access | 16 | 40.00 | 0.35 |
| ▼Vectorization Roadblocks– | 62 | | |
| ○Presence of constant non-unit stride data access | 25 | 62.50 | 0.51 |
| ○Presence of indirect access | 16 | 40.00 | 0.35 |
| ○Presence of 2 to 4 paths | 12 | 30.00 | 0.22 |
| ○Presence of more than 4 paths | 8 | 20.00 | 0.27 |
| ○Non-innermost loop | 1 | 2.50 | 0.04 |
| Analysis | r_1 | r_2 | r_3 | r_4 |
|---|
| Loop Computation Issues | Presence of expensive FP instructions | 1 | 1 | 1 | 1 |
|---|
| Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 9 | 9 | 9 | 9 |
| Presence of a large number of scalar integer instructions | 7 | 7 | 7 | 7 |
| Control Flow Issues | Presence of 2 to 4 paths | 3 | 3 | 3 | 3 |
|---|
| Presence of more than 4 paths | 1 | 1 | 1 | 1 |
| Non-innermost loop | 1 | 0 | 0 | 0 |
| Data Access Issues | Presence of constant non-unit stride data access | 7 | 6 | 6 | 6 |
|---|
| Presence of indirect access | 4 | 4 | 4 | 4 |
| Vectorization Roadblocks | Presence of 2 to 4 paths | 3 | 3 | 3 | 3 |
|---|
| Presence of more than 4 paths | 2 | 2 | 2 | 2 |
| Non-innermost loop | 1 | 0 | 0 | 0 |
| Presence of constant non-unit stride data access | 7 | 6 | 6 | 6 |
| Presence of indirect access | 4 | 4 | 4 | 4 |
