TinyML systems are enabling machine learning (ML) inference at the edge. However, there
exists little quantitative analysis of such systems. This paper presents a systematic …

We present Phronesis, a learning framework for efficiently modeling the performance of data
analytic workloads as a function of their high-dimensional software configuration …

Generative large language models'(LLMs) inference suffers from inefficiency because of the
token dependency brought by autoregressive decoding. Recently, speculative inference has …

A large portion of current cloud and edge workloads feature Machine Learning (ML) tasks,
thereby requiring a deep understanding of their energy efficiency. While the holy grail for …

The runtime performance of a software system often depends on a large number of static
parameters, which usually interact in complex ways to carry out system functionality and …

• Cost model based on input and output size and computation time for a device.• Can be
heuristic or based on measured time for previous placement decisions.• Device for a node is …

With the recent advances in both machine learning and embedded systems research, the
demand to deploy computational models for real-time execution on edge devices has …

Numerous software systems are highly configurable and provide a myriad of configuration
options that users can tune to fit their functional and performance requirements (eg …

New computing systems have emerged in response to the increasing size and complexity of
modern datasets. For best performance, machine learning methods must be designed to …

Random Forests (RFs) are widely used Machine Learning models in low-power embedded
devices, due to their hardware friendly operation and high accuracy on practically relevant …