M
Martin Foltin
Researcher at Hewlett-Packard
Publications - 54
Citations - 1006
Martin Foltin is an academic researcher from Hewlett-Packard. The author has contributed to research in topics: Memristor & Computer science. The author has an hindex of 13, co-authored 48 publications receiving 466 citations.
Papers
More filters
Proceedings ArticleDOI
PUMA: A Programmable Ultra-efficient Memristor-based Accelerator for Machine Learning Inference
Aayush Ankit,Izzat El Hajj,Sai Rahul Chalamalasetti,Geoffrey Ndu,Martin Foltin,R. Stanley Williams,Paolo Faraboschi,Wen-mei W. Hwu,John Paul Strachan,Kaushik Roy,Dejan Milojicic +10 more
TL;DR: The Programmable Ultra-efficient Memristor-based Accelerator (PUMA) as mentioned in this paper enhances memristor crossbars with general purpose execution units to enable the acceleration of a wide variety of Machine Learning (ML) inference workloads.
Journal ArticleDOI
Power-efficient combinatorial optimization using intrinsic noise in memristor Hopfield neural networks
Fuxi Cai,Fuxi Cai,Suhas Kumar,Thomas Van Vaerenbergh,Xia Sheng,Rui Liu,Rui Liu,Can Li,Zhan Liu,Martin Foltin,Shimeng Yu,Qiangfei Xia,Jianhua Yang,Raymond G. Beausoleil,Wei Lu,John Paul Strachan +15 more
TL;DR: A memristor-based annealing system that uses an analogue neuromorphic architecture based on a Hopfield neural network can solve non-deterministic polynomial-time (NP)-hard max-cut problems in an approach that is potentially more efficient than current quantum, optical and digital approaches.
Posted Content
PUMA: A Programmable Ultra-efficient Memristor-based Accelerator for Machine Learning Inference
Aayush Ankit,Izzat El Hajj,Sai Rahul Chalamalasetti,Geoffrey Ndu,Martin Foltin,R. Stanley Williams,Paolo Faraboschi,Wen-mei W. Hwu,John Paul Strachan,Kaushik Roy,Dejan Milojicic +10 more
TL;DR: The Programmable Ultra-efficient Memristor-based Accelerator (PUMA) is presented which enhances memristor crossbars with general purpose execution units to enable the acceleration of a wide variety of Machine Learning (ML) inference workloads.
Journal ArticleDOI
Analog content-addressable memories with memristors.
Can Li,Catherine Graves,Xia Sheng,Darrin Miller,Martin Foltin,Giacomo Pedretti,Giacomo Pedretti,John Paul Strachan +7 more
TL;DR: In this paper, the analog content-addressable memory (CA-MAM) concept and circuit is proposed to reduce the area and power consumption by utilizing the analog conductance tunability of memristors.
Journal ArticleDOI
PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy-Efficient ReRAM
Aayush Ankit,Izzat El Hajj,Sai Rahul Chalamalasetti,Sapan Agarwal,Matthew J. Marinella,Martin Foltin,John Paul Strachan,Dejan Milojicic,Wen-mei W. Hwu,Wen-mei W. Hwu,Kaushik Roy +10 more
TL;DR: PANTHER, an ISA-programmable training accelerator with compiler support, is developed and can be integrated into other accelerators in the literature to enhance their efficiency.