- r_1 - engine_NEON1M11-0001_o2_m48_gcc - 30 analyzed loop(s)
- Loop 6195 - engine_linuxa64_gf_ompi
- Loop 10581 - engine_linuxa64_gf_ompi
- Loop 10282 - engine_linuxa64_gf_ompi
- Loop 6410 - engine_linuxa64_gf_ompi
- Loop 29120 - engine_linuxa64_gf_ompi
- Loop 10533 - engine_linuxa64_gf_ompi
- Loop 37963 - engine_linuxa64_gf_ompi
- Loop 10312 - engine_linuxa64_gf_ompi
- Loop 10472 - engine_linuxa64_gf_ompi
- Loop 10349 - engine_linuxa64_gf_ompi
- Loop 6475 - engine_linuxa64_gf_ompi
- Loop 10457 - engine_linuxa64_gf_ompi
- Loop 10304 - engine_linuxa64_gf_ompi
- Loop 29119 - engine_linuxa64_gf_ompi
- Loop 29118 - engine_linuxa64_gf_ompi
- Loop 10347 - engine_linuxa64_gf_ompi
- Loop 38138 - engine_linuxa64_gf_ompi
- Loop 31053 - engine_linuxa64_gf_ompi
- Loop 38106 - engine_linuxa64_gf_ompi
- Loop 6477 - engine_linuxa64_gf_ompi
- Loop 30872 - engine_linuxa64_gf_ompi
- Loop 30875 - engine_linuxa64_gf_ompi
- Loop 7665 - engine_linuxa64_gf_ompi
- Loop 10283 - engine_linuxa64_gf_ompi
- Loop 30878 - engine_linuxa64_gf_ompi
- Loop 5672 - engine_linuxa64_gf_ompi
- Loop 5677 - engine_linuxa64_gf_ompi
- Loop 31047 - engine_linuxa64_gf_ompi
- Loop 30849 - engine_linuxa64_gf_ompi
- Loop 10302 - engine_linuxa64_gf_ompi
- r_2 - engine_NEON1M11-0001_o2_m48_acfl - 30 analyzed loop(s)
- Loop 5290 - engine_linuxa64_ompi
- Loop 10194 - engine_linuxa64_ompi
- Loop 9850 - engine_linuxa64_ompi
- Loop 38994 - engine_linuxa64_ompi
- Loop 5587 - engine_linuxa64_ompi
- Loop 36824 - engine_linuxa64_ompi
- Loop 9938 - engine_linuxa64_ompi
- Loop 38981 - engine_linuxa64_ompi
- Loop 9877 - engine_linuxa64_ompi
- Loop 47760 - engine_linuxa64_ompi
- Loop 9933 - engine_linuxa64_ompi
- Loop 10130 - engine_linuxa64_ompi
- Loop 47929 - engine_linuxa64_ompi
- Loop 10078 - engine_linuxa64_ompi
- Loop 47848 - engine_linuxa64_ompi
- Loop 9888 - engine_linuxa64_ompi
- Loop 5670 - engine_linuxa64_ompi
- Loop 39163 - engine_linuxa64_ompi
- Loop 36823 - engine_linuxa64_ompi
- Loop 47726 - engine_linuxa64_ompi
- Loop 10055 - engine_linuxa64_ompi
- Loop 36822 - engine_linuxa64_ompi
- Loop 9851 - engine_linuxa64_ompi
- Loop 39158 - engine_linuxa64_ompi
- Loop 38957 - engine_linuxa64_ompi
- Loop 5674 - engine_linuxa64_ompi
- Loop 39157 - engine_linuxa64_ompi
- Loop 9890 - engine_linuxa64_ompi
- Loop 38992 - engine_linuxa64_ompi
- Loop 7060 - engine_linuxa64_ompi
| Analysis | Count | Percentage | Weighted Count |
|---|
| ▼Loop Computation Issues– | 95 | | |
| ○Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 50 | 83.33 | 0.69 |
| ○Presence of a large number of scalar integer instructions | 29 | 48.33 | 0.45 |
| ○Presence of expensive FP instructions | 12 | 20.00 | 0.11 |
| ○Large loop body over microp cache size | 2 | 3.33 | 0.03 |
| ○Bottleneck in the front-end | 2 | 3.33 | 0.03 |
| ▼Control Flow Issues– | 25 | | |
| ○Presence of 2 to 4 paths | 15 | 25.00 | 0.16 |
| ○Presence of calls | 4 | 6.67 | 0.04 |
| ○Non-innermost loop | 4 | 6.67 | 0.04 |
| ○Presence of more than 4 paths | 2 | 3.33 | 0.02 |
| ▼Data Access Issues– | 46 | | |
| ○Presence of constant non-unit stride data access | 37 | 61.67 | 0.64 |
| ○Presence of indirect access | 9 | 15.00 | 0.18 |
| ▼Vectorization Roadblocks– | 76 | | |
| ○Presence of constant non-unit stride data access | 37 | 61.67 | 0.64 |
| ○Presence of 2 to 4 paths | 15 | 25.00 | 0.16 |
| ○Presence of indirect access | 9 | 15.00 | 0.18 |
| ○Presence of more than 4 paths | 7 | 11.67 | 0.06 |
| ○Non-innermost loop | 4 | 6.67 | 0.04 |
| ○Presence of calls | 4 | 6.67 | 0.04 |
| Analysis | r_1 | r_2 |
|---|
| Loop Computation Issues | Presence of expensive FP instructions | 8 | 4 |
|---|
| Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 26 | 24 |
| Large loop body over microp cache size | 1 | 1 |
| Presence of a large number of scalar integer instructions | 12 | 17 |
| Bottleneck in the front-end | 1 | 1 |
| Control Flow Issues | Presence of calls | 3 | 1 |
|---|
| Presence of 2 to 4 paths | 7 | 8 |
| Presence of more than 4 paths | 1 | 1 |
| Non-innermost loop | 3 | 1 |
| Data Access Issues | Presence of constant non-unit stride data access | 25 | 12 |
|---|
| Presence of indirect access | 2 | 7 |
| Vectorization Roadblocks | Presence of calls | 3 | 1 |
|---|
| Presence of 2 to 4 paths | 7 | 8 |
| Presence of more than 4 paths | 5 | 2 |
| Non-innermost loop | 3 | 1 |
| Presence of constant non-unit stride data access | 25 | 12 |
| Presence of indirect access | 2 | 7 |
