200 citations · 258 across the 10 of their papers we have counts for
10 papers
MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI
Arya Tschand, Arun Tejusve Raghunath Rajan, Sachin Idgunji +23
Rapid adoption of machine learning (ML) technologies has led to a surge in power consumption across diverse systems, from tiny IoT devices to massive datacenter clusters. Benchmark…
Dynamic Network selection for the Object Detection task: why it matters and what we (didn't) achieve
Emanuele Vitali, Anton Lokhmotov, Gianluca Palermo
In this paper, we want to show the potential benefit of a dynamic auto-tuning approach for the inference process in the Deep Neural Network (DNN) context, tackling the object detec…
Benchmarking TinyML Systems: Challenges and Direction
Colby R. Banbury, Vijay Janapa Reddi, Max Lam +14
Recent advancements in ultra-low-power machine learning (TinyML) hardware promises to unlock an entirely new class of smart applications. However, continued progress is limited by…
A model-driven approach for a new generation of adaptive libraries
Marco Cianfriglia, Flavio Vella, Cedric Nugteren +2
Efficient high-performance libraries often expose multiple tunable parameters to provide highly optimized routines. These can range from simple loop unroll factors or vector sizes…
A Collective Knowledge workflow for collaborative research into multi-objective autotuning and machine learning techniques
Grigori Fursin, Anton Lokhmotov, Dmitry Savenko +1
Developing efficient software and hardware has never been harder whether it is for a tiny IoT device or an Exascale supercomputer. Apart from the ever growing design and optimizati…
Introducing ReQuEST: an Open Platform for Reproducible and Quality-Efficient Systems-ML Tournaments
Thierry Moreau, Anton Lokhmotov, Grigori Fursin
Co-designing efficient machine learning based systems across the whole hardware/software stack to trade off speed, accuracy, energy and costs is becoming extremely complex and time…
GEMMbench: a framework for reproducible and collaborative benchmarking of matrix multiplication
Anton Lokhmotov
The generic matrix-matrix multiplication (GEMM) is arguably the most popular computational kernel of the 20th century. Yet, surprisingly, no common methodology for evaluating GEMM…
Collective Mind, Part II: Towards Performance- and Cost-Aware Software Engineering as a Natural Science
Grigori Fursin, Abdul Memon, Christophe Guillon +1
Nowadays, engineers have to develop software often without even knowing which hardware it will eventually run on in numerous mobile phones, tablets, desktops, laptops, data centers…
Proceedings of the DATE Friday Workshop on Heterogeneous Architectures and Design Methods for Embedded Image Systems (HIS 2015)
Frank Hannig, Dietmar Fey, Anton Lokhmotov
This volume contains the papers accepted at the DATE Friday Workshop on Heterogeneous Architectures and Design Methods for Embedded Image Systems (HIS 2015), held in Grenoble, Fran…
PENCIL: Towards a Platform-Neutral Compute Intermediate Language for DSLs
Riyadh Baghdadi, Albert Cohen, Serge Guelton +9
We motivate the design and implementation of a platform-neutral compute intermediate language (PENCIL) for productive and performance-portable accelerator programming.