| Run Neoverse V1 ACFL Ofast (base) | Run Neoverse V1 ACFL Ofast SoA | Run Neoverse V1 ACFL Ofast Manual Unroll |
| Loop Source Regions | - /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 117-123
| Loop Source Regions | | Loop Source Regions | - /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 118-131
|
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s |
|---|
| 7 | 1.74 | 1.47 | 70.23 | 41.67 | 37.5 | 17.02 | | 8 | 1.16 | 1.02 | 60.13 | 35.71 | 38.39 | 10.73 |
| | |
| Sum on 1 analyzed binary loop (kmeans-acfl-Ofast - 7) | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | Sum on 1 analyzed binary loop (kmeans-acfl-Ofast - 8) |
| Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| Loop Computation Issues | | | | Loop Computation Issues | |
| Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 | | | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 |
| Control Flow Issues | | | | Control Flow Issues | |
| Presence of 2 to 4 paths | 1 | | | Presence of 2 to 4 paths | |
| Vectorization Roadblocks | | | | Vectorization Roadblocks | |
| Presence of 2 to 4 paths | 1 | | | Presence of 2 to 4 paths | |
| Run Neoverse V1 ACFL Ofast (base) | Run Neoverse V1 ACFL Ofast SoA | Run Neoverse V1 ACFL Ofast Manual Unroll |
| Loop Source Regions | | Loop Source Regions | - /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 71-76
| Loop Source Regions | |
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s |
|---|
| 8 | 1.51 | 1.28 | 66.10 | 12.5 | 26.56 | 8.73 | |
| | |
| No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | Sum on 1 analyzed binary loop (kmeans-acfl-Ofast - 8) | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. |
| Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| Run Neoverse V1 ACFL Ofast (base) | Run Neoverse V1 ACFL Ofast SoA | Run Neoverse V1 ACFL Ofast Manual Unroll |
| Loop Source Regions | | Loop Source Regions | | Loop Source Regions | - /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 156-160
|
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s |
|---|
| | 39 | 0.20 | 0.15 | 8.57 | 0 | 20.83 | 1.51 |
| | |
| No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | Sum on 1 analyzed binary loop (kmeans-acfl-Ofast - 39) |
| Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| | | | Loop Computation Issues | |
| | | | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 |
| | | | Presence of a large number of scalar integer instructions | 1 |
| | | | Data Access Issues | |
| | | | Presence of indirect access | 1 |
| | | | Vectorization Roadblocks | |
| | | | Presence of indirect access | 1 |
| Run Neoverse V1 ACFL Ofast (base) | Run Neoverse V1 ACFL Ofast SoA | Run Neoverse V1 ACFL Ofast Manual Unroll |
| Loop Source Regions | - /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 140-144
| Loop Source Regions | | Loop Source Regions | |
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s |
|---|
| 25 | 0.19 | 0.17 | 7.87 | 0 | 20.83 | 1.2 | | |
| | |
| Sum on 1 analyzed binary loop (kmeans-acfl-Ofast - 25) | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. |
| Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| Loop Computation Issues | | | | | |
| Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 | | | | |
| Presence of a large number of scalar integer instructions | 1 | | | | |
| Data Access Issues | | | | | |
| Presence of indirect access | 1 | | | | |
| Vectorization Roadblocks | | | | | |
| Presence of indirect access | 1 | | | | |
| Run Neoverse V1 ACFL Ofast (base) | Run Neoverse V1 ACFL Ofast SoA | Run Neoverse V1 ACFL Ofast Manual Unroll |
| Loop Source Regions | | Loop Source Regions | - /home/fmusial/KMEANS_Benchmarks/kmeans/main.cpp: 93-97
| Loop Source Regions | |
| ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s | ASM Loop ID | Max Time Over Threads (s) | Time w.r.t. Wall Time (s) | Cov (%) | Vect. Ratio (%) | Vector Length Use (%) | GFLOP/s |
|---|
| 39 | 0.19 | 0.12 | 6.34 | 0 | 20.83 | 1.47 | |
| | |
| No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. | Sum on 1 analyzed binary loop (kmeans-acfl-Ofast - 39) | No Optimizer analysis found for any assembly loop. More loops can be analyzed using option --optimizer-loop-count. |
| Analysis | Count | Analysis | Count | Analysis | Count |
|---|
| | Loop Computation Issues | | | |
| | Less than 10% of the FP ADD/SUB/MUL arithmetic operations are performed using FMA | 1 | | |
| | Presence of a large number of scalar integer instructions | 1 | | |
| | Data Access Issues | | | |
| | Presence of indirect access | 1 | | |
| | Vectorization Roadblocks | | | |
| | Presence of indirect access | 1 | | |
