Specialization improves energy-efficiency in computing but only makes economic sense if there is significant demand. A balance can often be found by designing...Trevor Mudge From Communications of the ACM | April 2015
We present the Convolution Engine (CE) — a programmable processor specialized for the convolution-like data-flow prevalent in computational photography, computer...Wajahat Qadeer, Rehan Hameed, Ofer Shacham, Preethi Venkatesan, Christos Kozyrakis, Mark Horowitz From Communications of the ACM | April 2015
As GPUs have become mainstream parallel processing engines, many applications targeting GPUs now have data locality more amenable to traditional caching. The...Stephen W. Keckler From Communications of the ACM | December 2014
This paper studies the effect of accelerating highly parallel workloads with significant locality on a massively multithreaded GPU.Timothy G. Rogers, Mike O'Connor, Tor M. Aamodt From Communications of the ACM | December 2014
The following paper is a breakthrough in which the authors offer a formula to calculate the probability of reading data that was not written by one of the K most...Philip A. Bernstein From Communications of the ACM | August 2014
Eventual consistency is often "good enough" for practitioners given its latency and availability benefits. In this work, we explain this phenomenon and demonstrate...Peter Bailis, Shivaram Venkataraman, Michael J. Franklin, Joseph M. Hellerstein, Ion Stoica From Communications of the ACM | August 2014
An ideal scheme for password storage would enable a password with more than 20 bits of randomness to be input and output from the brain of a human being who is...Ari Juels, Bonnie Wong From Communications of the ACM | May 2014
We present a defense against coercion attacks using the concept of implicit learning from cognitive psychology. We use a carefully crafted computer game to allow...Hristo Bojinov, Daniel Sanchez, Paul Reber, Dan Boneh, Patrick Lincoln From Communications of the ACM | May 2014
Moore's Law has been the mainstay of semiconductor electronics since the invention of the transistor and its application to the integrated circuit. Implicit in...Subramanian S. Iyer From Communications of the ACM | January 2014
Three-dimensional integrated circuit (3D IC) with through-silicon-via (TSV) is believed to offer new levels of efficiency, power, performance, and form-factor advantages...Moongon Jung, Joydeep Mitra, David Z. Pan, Sung Kyu Lim From Communications of the ACM | January 2014
In quite a tour de force, the authors of the following paper have built a provably correct real-time garbage collector for reconfigurable hardware (field programmable...Eliot Moss From Communications of the ACM | December 2013
We present a garbage collector synthesized directly to hardware, capable of collecting a heap of uniform objects completely concurrently. These heaps are composed...David F. Bacon, Perry Cheng, Sunil Shukla From Communications of the ACM | December 2013
Exponentially increasing transistor integration also demands more interconnections, which have started hitting fundamental limits. The Centip3De design demonstrates...Shekhar Borkar From Communications of the ACM | November 2013
This paper evaluates the use of three-dimensional integration to reduce global interconnect by adding multiple layers of silicon with vertical connections between...Ronald G. Dreslinski, David Fick, Bharan Giridhar, Gyouho Kim, Sangwon Seo, Matthew Fojtik, Sudhir Satpathy, Yoonmyung Lee, Daeyeon Kim, Nurrachman Liu, Michael Wieckowski, Gregory Chen, Dennis Sylvester, David Blaauw, Trevor Mudge From Communications of the ACM | November 2013
Our visual system helps us carry out our daily business. Our eyes and brain help us by measuring shapes, trajectories, and distances in world around us, and by...Pietro Perona From Communications of the ACM | September 2013
We describe a state-of-the-art system for finding objects in cluttered images. Our system is based on deformable models that represent objects using local part...Pedro Felzenszwalb, Ross Girshick, David McAllester, Deva Ramanan From Communications of the ACM | September 2013
For a semiconductor circuit with billions of transistors, finding desired locations of circuit components is a challenging task that substantially impacts circuit...Yao-Wen Chang From Communications of the ACM | June 2013
VLSI placement optimizes locations of circuit components so as to reduce interconnect. We propose an algorithm for large-scale placement that outperforms prior...Myung-Chul Kim, Dong-Jin Lee, Igor L. Markov From Communications of the ACM | June 2013
As Internet-based videos become mainstream, user expectation for high quality is constantly increasing. In this context, it is crucial for content providers to...Florin Dobrian, Asad Awan, Dilip Joseph, Aditya Ganjam, Jibin Zhan, Vyas Sekar, Ion Stoica, Hui Zhang From Communications of the ACM | March 2013
The microprocessor chip R&D community has been well aware of the so-called "power wall" challenge for over a decade. The following work by Esmaeilzadeh et al. is...Pradip Bose From Communications of the ACM | February 2013