face-recognition-rk3588-opencl/modules/knn-opencl/reference/VALIDATION.md

Validazione kNN OpenCL Mali-G610

Parametri

• Database: 350000 embedding
• Query: 256
• Dimensione: 128
• TOPK: 32
• Chunk: 50000
• GPU: Mali-G610 r0p0

Correttezza

• Posizioni TOPK confrontate: 8192
• Posizioni identiche CPU/OpenCL: 8192
• Exact ratio: 100.000%

Prestazioni

• CPU: 9663.226 ms
• OpenCL: 1373.797 ms
• Speedup: 7.034x
• Throughput: 65220680 vettori/s

Variante float4 min-replace

• Kernel: 1244.576 ms
• Throughput: 71.992 M vettori/s
• Invalid indices: 0