scispace - formally typeset
Search or ask a question
JournalISSN: 1550-4832

ACM Journal on Emerging Technologies in Computing Systems 

Association for Computing Machinery
About: ACM Journal on Emerging Technologies in Computing Systems is an academic journal published by Association for Computing Machinery. The journal publishes majorly in the area(s): Computer science & Artificial neural network. It has an ISSN identifier of 1550-4832. Over the lifetime, 588 publications have been published receiving 11697 citations. The journal is also known as: JETC & Journal on emerging technologies in computing systems.


Papers
More filters
Journal ArticleDOI
TL;DR: The proposed work shows that when pruning granularities are applied in combination, the CIFAR-10 network can be pruned by more than 70% with less than a 1% loss in accuracy.
Abstract: Real-time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular network connections that not only demand extra representation efforts but also do not fit well on parallel computation. We introduce structured sparsity at various scales for convolutional neural networks: feature map-wise, kernel-wise, and intra-kernel strided sparsity. This structured sparsity is very advantageous for direct computational resource savings on embedded computers, in parallel computing environments, and in hardware-based systems. To decide the importance of network connections and paths, the proposed method uses a particle filtering approach. The importance weight of each particle is assigned by assessing the misclassification rate with a corresponding connectivity pattern. The pruned network is retrained to compensate for the losses due to pruning. While implementing convolutions as matrix products, we particularly show that intra-kernel strided sparsity with a simple constraint can significantly reduce the size of the kernel and feature map tensors. The proposed work shows that when pruning granularities are applied in combination, we can prune the CIFAR-10 network by more than 70% with less than a 1% loss in accuracy.

476 citations

Journal ArticleDOI
TL;DR: It is shown that in-plane STT-MRAM technology, particularly the DMTJ design, is a mature technology that meets all conventional requirements for an STT -MRAM cell to be a nonvolatile solution matching DRAM and/or SRAM drive circuitry.
Abstract: Spin-transfer torque magnetic random access memory (STT-MRAM) is a novel, magnetic memory technology that leverages the base platform established by an existing 100pnm node memory product called MRAM to enable a scalable nonvolatile memory solution for advanced process nodes. STT-MRAM features fast read and write times, small cell sizes of 6F2 and potentially even smaller, and compatibility with existing DRAM and SRAM architecture with relatively small associated cost added. STT-MRAM is essentially a magnetic multilayer resistive element cell that is fabricated as an additional metal layer on top of conventional CMOS access transistors. In this review we give an overview of the existing STT-MRAM technologies currently in research and development across the world, as well as some specific discussion of results obtained at Grandis and with our foundry partners. We will show that in-plane STT-MRAM technology, particularly the DMTJ design, is a mature technology that meets all conventional requirements for an STT-MRAM cell to be a nonvolatile solution matching DRAM and/or SRAM drive circuitry. Exciting recent developments in perpendicular STT-MRAM also indicate that this type of STT-MRAM technology may reach maturity faster than expected, allowing even smaller cell size and product introduction at smaller nodes.

390 citations

Journal ArticleDOI
TL;DR: A new generation of predictive technology model (PTM) is developed, covering emerging physical effects and alternative structures, based on physical models and early stage silicon data, and correctly captures process sensitivities in the nanometer regime.
Abstract: A predictive MOSFET model is critical for early circuit design research. In this work, a new generation of Predictive Technology Model (PTM) is developed, covering emerging physical effects and alternative structures, such as the double-gate device (i.e., FinFET). Based on physical models and early stage silicon data, PTM of bulk and double-gate devices are successfully generated from 130nm to 32nm technology nodes, with effective channel length down to 13nm. By tuning only ten primary parameters, PTM can be easily customized to cover a wide range of process uncertainties. The accuracy of PTM predictions is comprehensively verified with published silicon data: the error of the current is below 10p for both NMOS and PMOS. Furthermore, the new PTM correctly captures process sensitivities in the nanometer regime. PTM is available online at http://www.eas.asu.edu/~ptm.

385 citations

Journal ArticleDOI
TL;DR: A brief introduction to 3D integration technology is given, the EDA design tools that can enable the adoption of 3D ICs are discussed, and the implementation of various microprocessor components using 3D technology is presented.
Abstract: As technology scales, interconnects have become a major performance bottleneck and a major source of power consumption for microprocessors. Increasing interconnect costs make it necessary to consider alternate ways of building modern microprocessors. One promising option is 3D architectures where a stack of multiple device layers with direct vertical tunneling through them are put together on the same chip. As fabrication of 3D integrated circuits has become viable, developing CAD tools and architectural techniques is imperative to explore the design space to 3D microarchitectures. In this article, we give a brief introduction to 3D integration technology, discuss the EDA design tools that can enable the adoption of 3D ICs, and present the implementation of various microprocessor components using 3D technology. An industrial case study is presented as an initial attempt to design 3D microarchitectures.

338 citations

Journal ArticleDOI
TL;DR: This work develops nanowire-based architectures which can bridge between lithographic and atomic-scale feature sizes and tolerate defective and stochastic assembly of regular arrays to deliver high density universal computing devices.
Abstract: Chemists can now construct wires which are just a few atoms in diameter; these wires can be selectively field-effect gated, and wire crossings can act as diodes with programmable resistance. These new capabilities present both opportunities and challenges for constructing nanoscale computing systems. The tiny feature sizes offer a path to economically scale down to atomic dimensions. However, the associated bottom-up synthesis techniques only produce highly regular structures and come with high defect rates and minimal control during assembly. To exploit these technologies, we develop nanowire-based architectures which can bridge between lithographic and atomic-scale feature sizes and tolerate defective and stochastic assembly of regular arrays to deliver high density universal computing devices. Using 10nm pitch nanowires, these nanowire-based programmable architectures offer one to two orders of magnitude greater mapped-logic density than defect-free lithographic FPGAs at 22nm.

257 citations

Performance
Metrics
No. of papers from the Journal in previous years
YearPapers
202315
202281
202150
202038
201947
201836