- r_1 - armclang_o3_ov1_o96/ - 4 analyzed loop(s)
- Loop 24 - spmxv.exe
- Loop 25 - spmxv.exe
- Loop 23 - spmxv.exe
- Loop 22 - spmxv.exe
- r_2 - gcc_o3_ov1_o96/ - 3 analyzed loop(s)
- Loop 24 - spmxv.exe
- Loop 22 - spmxv.exe
- Loop 23 - spmxv.exe
| Analysis | Count | Percentage | Weighted Count |
|---|
| ▼Loop Computation Issues– | 3 | | |
| ○Presence of a large number of scalar integer instructions | 2 | 28.57 | 0.10 |
| ○Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 | 14.29 | 0.82 |
| ▼Control Flow Issues– | 8 | | |
| ○Non-innermost loop | 4 | 57.14 | 0.10 |
| ○Presence of more than 4 paths | 2 | 28.57 | 0.06 |
| ○Presence of 2 to 4 paths | 2 | 28.57 | 0.04 |
| ▼Data Access Issues– | 7 | | |
| ○Presence of indirect access | 5 | 71.43 | 1.63 |
| ○Presence of constant non-unit stride data access | 2 | 28.57 | 1.01 |
| ▼Vectorization Roadblocks– | 15 | | |
| ○Presence of indirect access | 5 | 71.43 | 1.63 |
| ○Non-innermost loop | 4 | 57.14 | 0.10 |
| ○Presence of constant non-unit stride data access | 2 | 28.57 | 1.01 |
| ○Presence of 2 to 4 paths | 2 | 28.57 | 0.04 |
| ○Presence of more than 4 paths | 2 | 28.57 | 0.06 |
| Analysis | r_1 | r_2 |
|---|
| Loop Computation Issues | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 0 | 1 |
|---|
| Presence of a large number of scalar integer instructions | 1 | 1 |
| Control Flow Issues | Presence of 2 to 4 paths | 0 | 2 |
|---|
| Presence of more than 4 paths | 2 | 0 |
| Non-innermost loop | 2 | 2 |
| Data Access Issues | Presence of constant non-unit stride data access | 1 | 1 |
|---|
| Presence of indirect access | 2 | 3 |
| Vectorization Roadblocks | Presence of 2 to 4 paths | 0 | 2 |
|---|
| Presence of more than 4 paths | 2 | 0 |
| Non-innermost loop | 2 | 2 |
| Presence of constant non-unit stride data access | 1 | 1 |
| Presence of indirect access | 2 | 3 |
