A hardware-independent time estimation method for inference process of convolutional layers on GPU.

Chengzhen Meng Hongjun Dai

Published in: Perform. Evaluation (2023)

Keyphrases

inference process
high accuracy
estimation algorithm
preprocessing
support vector machine
clustering method
similarity measure
significant improvement
dynamic programming
computational cost
low cost
estimation accuracy
real time
prior knowledge
detection method
parallel implementation