| ID | Module | Source Location | Source Function | Level | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Coverage (% app. time) | Speedup if no scalar integer | Speedup if FP arith vectorized | Speedup if fully vectorized | Speedup if FP only | Number of paths | Vectorization Ratio (%) | Vector Length Use (%) | Flops (GFLOP/s) | CQA cycles | CQA cycles if no scalar integer | CQA cycles if FP arith vectorized | CQA cycles if fully vectorized | CQA cycles if FP only |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ○Loop 31 | attention-avx512 | attention.cpp:30-31 | main | Innermost | 1.06 | 1.06 | 20.54 | 1.00 | 1.00 | 2.15 | 1.75 | 1 | 87.50 | 41.41 | 2.66 | 7.00 | 7.00 | 7.00 | 3.25 | 4.00 |
| ○Loop 30 | attention-avx512 | attention.cpp:27-27,attention.cpp:30-33,attention.cpp:98-98 | main | InBetween | 1.03 | 1.03 | 19.96 | 1.07 | 1.10 | 1.90 | 3.58 | 3 | 63.23 | 36.38 | 9.35 | 8.94 | 8.33 | 8.13 | 4.72 | 2.50 |
| ○Loop 21 | attention-avx512 | attention.cpp:30-31 | main | Innermost | 1.03 | 1.03 | 19.96 | 1.00 | 1.00 | 1.91 | 1.25 | 1 | 90.91 | 46.02 | 8.19 | 5.00 | 5.00 | 5.00 | 2.62 | 4.00 |
| ○Loop 20 | attention-avx512 | attention.cpp:27-27,attention.cpp:30-33,attention.cpp:98-98 | main | InBetween | 0.34 | 0.34 | 6.59 | 1.06 | 1.06 | 1.84 | 4.31 | 3 | 68.14 | 38.37 | 7.38 | 8.61 | 8.11 | 8.11 | 4.68 | 2.00 |
| ○Loop 42 | attention-avx512 | attention.cpp:27-27,attention.cpp:30-33,attention.cpp:98-98 | main | InBetween | 0.32 | 0.32 | 6.30 | 1.07 | 1.07 | 1.84 | 4.33 | 3 | 66.02 | 37.67 | 6.73 | 8.67 | 8.11 | 8.13 | 4.72 | 2.00 |
| ○Loop 46 | attention-avx512 | attention.cpp:27-27,attention.cpp:30-33,attention.cpp:98-98 | main | InBetween | 0.28 | 0.28 | 5.52 | 1.07 | 1.07 | 1.84 | 4.33 | 3 | 66.02 | 37.67 | 7.72 | 8.67 | 8.11 | 8.13 | 4.72 | 2.00 |
| ○Loop 39 | attention-avx512 | attention.cpp:30-31 | main | Innermost | 0.28 | 0.28 | 5.52 | 1.00 | 1.00 | 2.15 | 1.75 | 1 | 87.50 | 41.41 | 2.90 | 7.00 | 7.00 | 7.00 | 3.25 | 4.00 |
| ○Loop 47 | attention-avx512 | attention.cpp:30-31 | main | Innermost | 0.23 | 0.23 | 4.55 | 1.00 | 1.00 | 2.15 | 1.75 | 1 | 87.50 | 41.41 | 3.66 | 7.00 | 7.00 | 7.00 | 3.25 | 4.00 |
| ○Loop 38 | attention-avx512 | attention.cpp:27-27,attention.cpp:30-33,attention.cpp:98-98 | main | InBetween | 0.23 | 0.23 | 4.55 | 1.07 | 1.07 | 1.84 | 4.33 | 3 | 66.02 | 37.67 | 9.54 | 8.67 | 8.11 | 8.13 | 4.72 | 2.00 |
| ○Loop 43 | attention-avx512 | attention.cpp:30-31 | main | Innermost | 0.19 | 0.19 | 3.68 | 1.00 | 1.00 | 2.15 | 1.75 | 1 | 87.50 | 41.41 | 4.64 | 7.00 | 7.00 | 7.00 | 3.25 | 4.00 |
| ○Loop 27 | attention-avx512 | attention.cpp:47-48 | main | Innermost | 0.06 | 0.06 | 1.26 | 1.00 | 1.00 | 16.00 | 1.00 | 1 | 0.00 | 6.25 | 7.15 | 32.00 | 32.00 | 32.00 | 2.00 | 32.00 |
| ○Loop 23 | attention-avx512 | attention.cpp:43-44,attention.cpp:47-47,attention.cpp:52-61,attention.cpp:98-98,attention.cpp:284-284 | main | InBetween | 0.03 | 0.03 | 0.58 | 1.39 | 1.02 | 1.36 | 4.39 | 72 | 44.29 | 35.89 | 45.00 | 26.33 | 19.00 | 25.75 | 19.39 | 6.00 |
| ○Loop 35 | attention-avx512 | attention.cpp:240-241 | main | Innermost | 0.01 | 0.01 | 0.19 | 1.00 | 1.00 | 1.38 | 10.17 | 1 | 92.31 | 66.35 | 0.00 | 10.17 | 10.17 | 10.17 | 7.39 | 1.00 |
| ○Loop 41 | attention-avx512 | attention.cpp:26-26,attention.cpp:31-31 | main | InBetween | 0.00 | 0.00 | 0.10 | 1.83 | 1.00 | 13.54 | 3.67 | 3 | 0.00 | 8.33 | 0.80 | 1.83 | 1.00 | 1.83 | 0.14 | 0.50 |
| ○Loop 29 | attention-avx512 | attention.cpp:26-26,attention.cpp:31-33 | main | InBetween | 0.00 | 0.00 | 0.10 | 2.60 | 1.00 | 14.86 | 5.20 | 3 | 0.00 | 7.81 | 1.90 | 2.60 | 1.00 | 2.60 | 0.17 | 0.50 |
| ○Loop 26 | attention-avx512 | attention.cpp:47-48 | main | Innermost | 0.00 | 0.00 | 0.10 | 1.00 | 1.00 | 16.00 | 1.00 | 1 | 0.00 | 6.25 | 2.60 | 4.00 | 4.00 | 4.00 | 0.25 | 4.00 |
| ○Loop 24 | attention-avx512 | attention.cpp:55-56 | main | Innermost | 0.00 | 0.00 | 0.10 | 1.50 | 1.00 | 1.00 | 1.50 | 1 | 100.00 | 100.00 | 38.80 | 1.50 | 1.00 | 1.50 | 1.50 | 1.00 |