FRAME: Fast Roofline Analytical Modeling and Estimation

Abstract

Frame is a roofline cost model for DNN accelerators. We support CNNs, MLPs, and Transformers workload. What it does:

• Given DNN accelerator system information (using the System class in src/system.py), where you can specify PE array shape (mxu_shape), on-chip BWs, off-chip BWs, etcs.
• Given DNN workload (e.g., model='vgg16') FRAME generate a table of layer-wise latency and memory usage information as well as a roofline figure.

Code available

FRAME Github Repo