| 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 50 | attention-avx512 | attention.cpp:30-31 | main | Innermost | 7.35 | 7.35 | 38.20 | 1.00 | 1.71 | 13.22 | 1.00 | 1 | 0.00 | 8.33 | 1.18 | 8.00 | 8.00 | 4.68 | 0.61 | 8.00 |
| ○Loop 69 | attention-avx512 | attention.cpp:30-31 | main | Innermost | 2.03 | 2.03 | 10.52 | 1.00 | 2.00 | 14.67 | 1.00 | 1 | 0.00 | 7.50 | 1.20 | 8.00 | 8.00 | 4.00 | 0.55 | 8.00 |
| ○Loop 61 | attention-avx512 | attention.cpp:30-31 | main | Innermost | 2.00 | 2.00 | 10.40 | 1.00 | 2.00 | 14.67 | 1.00 | 1 | 0.00 | 7.50 | 1.23 | 8.00 | 8.00 | 4.00 | 0.55 | 8.00 |
| ○Loop 65 | attention-avx512 | attention.cpp:30-31 | main | Innermost | 1.98 | 1.98 | 10.27 | 1.00 | 2.00 | 14.67 | 1.00 | 1 | 0.00 | 7.50 | 1.24 | 8.00 | 8.00 | 4.00 | 0.55 | 8.00 |
| ○Loop 49 | attention-avx512 | attention.cpp:27-27,attention.cpp:30-33 | main | InBetween | 1.83 | 1.82 | 9.49 | 2.36 | 1.06 | 1.37 | 4.18 | 23 | 42.11 | 24.67 | 1.07 | 23.00 | 9.75 | 21.69 | 16.80 | 5.50 |
| ○Loop 33 | attention-avx512 | attention.cpp:30-30 | main | Innermost | 1.28 | 1.28 | 6.63 | 1.00 | NA | NA | 1.00 | 1 | NA | NA | 0.00 | 1.00 | 1.00 | NA | NA | 1.00 |
| ○Loop 39 | attention-avx512 | attention.cpp:55-56 | main | Innermost | 0.53 | 0.53 | 2.73 | 1.44 | 1.00 | 1.58 | 3.60 | 1 | 83.33 | 30.21 | 0.25 | 36.00 | 25.00 | 36.00 | 22.75 | 10.00 |
| ○Loop 64 | attention-avx512 | attention.cpp:26-27,attention.cpp:30-33 | main | InBetween | 0.16 | 0.16 | 0.83 | 1.89 | 1.61 | 13.84 | 3.50 | 3 | 15.96 | 11.55 | 1.06 | 5.83 | 3.08 | 3.62 | 0.42 | 1.67 |
| ○Loop 32 | attention-avx512 | attention.cpp:27-27,attention.cpp:30-30 | main | InBetween | 0.15 | 0.15 | 0.78 | 2.61 | 1.00 | 23.14 | 2.61 | 23 | 14.29 | 11.89 | 0.00 | 11.75 | 4.50 | 11.75 | 0.51 | 4.50 |
| ○Loop 43 | attention-avx512 | attention.cpp:55-56 | main | Innermost | 0.13 | 0.13 | 0.68 | 1.44 | 1.42 | 3.00 | 3.00 | 1 | 78.95 | 20.72 | 0.08 | 9.00 | 6.25 | 6.35 | 3.00 | 3.00 |
| ○Loop 60 | attention-avx512 | attention.cpp:26-27,attention.cpp:30-33 | main | InBetween | 0.13 | 0.13 | 0.65 | 1.86 | 1.59 | 13.81 | 3.45 | 3 | 15.96 | 11.55 | 1.28 | 5.75 | 3.08 | 3.62 | 0.42 | 1.67 |
| ○Loop 68 | attention-avx512 | attention.cpp:26-27,attention.cpp:30-33 | main | InBetween | 0.12 | 0.12 | 0.62 | 1.89 | 1.61 | 13.84 | 3.50 | 3 | 15.96 | 11.55 | 1.50 | 5.83 | 3.08 | 3.62 | 0.42 | 1.67 |
| ○Loop 41 | attention-avx512 | attention.cpp:43-44,attention.cpp:47-47,attention.cpp:52-52,attention.cpp:55-55,attention.cpp:58-61,attention.cpp:284-284 | main | InBetween | 0.08 | 0.08 | 0.39 | 2.16 | 1.02 | 1.56 | 6.06 | 490 | 46.88 | 27.83 | 4.27 | 54.50 | 25.25 | 53.26 | 34.86 | 9.00 |
| ○Loop 53 | attention-avx512 | attention.cpp:240-241 | main | Innermost | 0.04 | 0.04 | 0.18 | 1.03 | 1.00 | 1.18 | 17.00 | 1 | 100.00 | 75.00 | 0.00 | 17.00 | 16.50 | 17.00 | 14.38 | 1.00 |
| ○Loop 42 | attention-avx512 | attention.cpp:55-56 | main | Innermost | 0.04 | 0.04 | 0.18 | 1.42 | 2.52 | 5.67 | 1.42 | 1 | 37.50 | 14.06 | 0.57 | 4.25 | 3.00 | 1.69 | 0.75 | 3.00 |
| ○Loop 44 | attention-avx512 | attention.cpp:52-53 | main | Innermost | 0.03 | 0.03 | 0.16 | 1.41 | 1.23 | 5.07 | 14.40 | 1 | 81.58 | 25.66 | 1.67 | 18.00 | 12.75 | 14.63 | 3.55 | 1.25 |
| ○Loop 37 | attention-avx512 | attention.cpp:52-53 | main | Innermost | 0.03 | 0.03 | 0.16 | 1.48 | 1.00 | 1.59 | 36.25 | 1 | 83.50 | 32.03 | 3.00 | 145.00 | 98.00 | 145.00 | 91.13 | 4.00 |
| ○Loop 45 | attention-avx512 | attention.cpp:47-48 | main | Innermost | 0.02 | 0.02 | 0.10 | 1.00 | 1.00 | 16.00 | 2.00 | 1 | 0.00 | 6.25 | 0.00 | 1.00 | 1.00 | 1.00 | 0.06 | 0.50 |
| ○Loop 38 | attention-avx512 | attention.cpp:52-53 | main | Innermost | 0.02 | 0.02 | 0.08 | 1.25 | 2.21 | 8.00 | 3.75 | 1 | 57.14 | 16.96 | 0.00 | 3.75 | 3.00 | 1.70 | 0.47 | 1.00 |
| ○Loop 31 | attention-avx512 | attention.cpp:26-26 | main | InBetween | 0.02 | 0.02 | 0.08 | 1.00 | 1.00 | 14.67 | 2.20 | 23 | 0.00 | 7.81 | 0.00 | 2.75 | 2.75 | 2.75 | 0.19 | 1.25 |
| ○Loop 46 | attention-avx512 | attention.cpp:47-48 | main | Innermost | 0.01 | 0.01 | 0.05 | 1.00 | 1.00 | 2.00 | 1.00 | 1 | 100.00 | 50.00 | 0.00 | 4.00 | 4.00 | 4.00 | 2.00 | 4.00 |