- r_1 - O2 - 10 analyzed loop(s)
- Loop 36711 - engine_linuxa64_ompi
- Loop 5796 - engine_linuxa64_ompi
- Loop 13063 - engine_linuxa64_ompi
- Loop 41148 - engine_linuxa64_ompi
- Loop 10784 - engine_linuxa64_ompi
- Loop 36691 - engine_linuxa64_ompi
- Loop 6086 - engine_linuxa64_ompi
- Loop 48493 - engine_linuxa64_ompi
- Loop 37051 - engine_linuxa64_ompi
- Loop 6174 - engine_linuxa64_ompi
- r_2 - O3 - 10 analyzed loop(s)
- Loop 40764 - engine_linuxa64_ompi
- Loop 6105 - engine_linuxa64_ompi
- Loop 14281 - engine_linuxa64_ompi
- Loop 45327 - engine_linuxa64_ompi
- Loop 11492 - engine_linuxa64_ompi
- Loop 40744 - engine_linuxa64_ompi
- Loop 6415 - engine_linuxa64_ompi
- Loop 52901 - engine_linuxa64_ompi
- Loop 41106 - engine_linuxa64_ompi
- Loop 6507 - engine_linuxa64_ompi
- r_3 - O3+nosve - 10 analyzed loop(s)
- Loop 40706 - engine_linuxa64_ompi
- Loop 6042 - engine_linuxa64_ompi
- Loop 14390 - engine_linuxa64_ompi
- Loop 45323 - engine_linuxa64_ompi
- Loop 11606 - engine_linuxa64_ompi
- Loop 40687 - engine_linuxa64_ompi
- Loop 41049 - engine_linuxa64_ompi
- Loop 6407 - engine_linuxa64_ompi
- Loop 6547 - engine_linuxa64_ompi
- Loop 31916 - engine_linuxa64_ompi
- r_4 - O3+nosve2 - 10 analyzed loop(s)
- Loop 40770 - engine_linuxa64_ompi
- Loop 6105 - engine_linuxa64_ompi
- Loop 14284 - engine_linuxa64_ompi
- Loop 45334 - engine_linuxa64_ompi
- Loop 11495 - engine_linuxa64_ompi
- Loop 40750 - engine_linuxa64_ompi
- Loop 6414 - engine_linuxa64_ompi
- Loop 52911 - engine_linuxa64_ompi
- Loop 41112 - engine_linuxa64_ompi
- Loop 6506 - engine_linuxa64_ompi
| Analysis | Count | Percentage | Weighted Count |
|---|
| ▼Loop Computation Issues– | 64 | | |
| ○Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 39 | 97.50 | 1.00 |
| ○Presence of a large number of scalar integer instructions | 25 | 62.50 | 0.64 |
| ▼Control Flow Issues– | 5 | | |
| ○Non-innermost loop | 4 | 10.00 | 0.08 |
| ○Presence of 2 to 4 paths | 1 | 2.50 | 0.01 |
| ▼Data Access Issues– | 24 | | |
| ○Presence of constant non-unit stride data access | 16 | 40.00 | 0.28 |
| ○Presence of indirect access | 8 | 20.00 | 0.16 |
| ▼Vectorization Roadblocks– | 42 | | |
| ○Presence of constant non-unit stride data access | 16 | 40.00 | 0.28 |
| ○Presence of more than 4 paths | 13 | 32.50 | 0.43 |
| ○Presence of indirect access | 8 | 20.00 | 0.16 |
| ○Non-innermost loop | 4 | 10.00 | 0.08 |
| ○Presence of 2 to 4 paths | 1 | 2.50 | 0.01 |
| Analysis | r_1 | r_2 | r_3 | r_4 |
|---|
| Loop Computation Issues | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 10 | 10 | 9 | 10 |
|---|
| Presence of a large number of scalar integer instructions | 6 | 6 | 7 | 6 |
| Control Flow Issues | Presence of 2 to 4 paths | 0 | 0 | 1 | 0 |
|---|
| Non-innermost loop | 1 | 1 | 1 | 1 |
| Data Access Issues | Presence of constant non-unit stride data access | 4 | 4 | 4 | 4 |
|---|
| Presence of indirect access | 2 | 2 | 2 | 2 |
| Vectorization Roadblocks | Presence of 2 to 4 paths | 0 | 0 | 1 | 0 |
|---|
| Presence of more than 4 paths | 3 | 3 | 4 | 3 |
| Non-innermost loop | 1 | 1 | 1 | 1 |
| Presence of constant non-unit stride data access | 4 | 4 | 4 | 4 |
| Presence of indirect access | 2 | 2 | 2 | 2 |
