Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2023
Runtime Variation in Big Data Analytics
Proceedings of the ACM on Management of Data (PACMMOD), Volume 1, Issue 1Article No.: 67, Pages 1–20https://doi.org/10.1145/3588921The dynamic nature of resource allocation and runtime conditions on Cloud can result in high variability in a job's runtime across multiple iterations, leading to a poor experience. Identifying the sources of such variation and being able to predict and ...
- research-articleMay 2023
A Mapping Method Tolerating SAF and Variation for Memristor Crossbar Array Based Neural Network Inference on Edge Devices
ACM Journal on Emerging Technologies in Computing Systems (JETC), Volume 19, Issue 2Article No.: 15, Pages 1–21https://doi.org/10.1145/3585518There is an increasing demand for running neural network inference on edge devices. Memristor crossbar array (MCA) based accelerators can be used to accelerate neural networks on edge devices. However, reliability issues in memristors, such as stuck-at ...
- invited-talkJanuary 2023
Improving the Robustness and Efficiency of PIM-Based Architecture by SW/HW Co-Design
ASPDAC '23: Proceedings of the 28th Asia and South Pacific Design Automation ConferencePages 618–623https://doi.org/10.1145/3566097.3568358Processing-in-memory (PIM) based architecture shows great potential to process several emerging artificial intelligence workloads, including vision and language models. Cross-layer optimizations could bridge the gap between computing density and the ...
- research-articleJanuary 2023
Factors influencing activity-based costing adoption: do they vary among types of organisation?
International Journal of Information Systems and Change Management (IJISCM), Volume 13, Issue 3Pages 284–305https://doi.org/10.1504/ijiscm.2023.133363Activity-based costing (ABC) serves organisations by making component costs explainable, but its adoption was not considered easy in organisations. The crucial thing is that the factors relevant to adoption process could vary in degrees of importance from ...
- research-articleJanuary 2023
Analyzing Performance and Power-Efficiency Variations among NVIDIA GPUs
ICPP '22: Proceedings of the 51st International Conference on Parallel ProcessingArticle No.: 65, Pages 1–12https://doi.org/10.1145/3545008.3545084Understanding the variations in performance and power-efficiency of compute nodes is important for enhancing these factors in modern supercomputing systems. Previous studies have focused on variations in CPUs and DRAMs, but there has been little ...
-
- research-articleAugust 2022
Write or not: programming scheme optimization for RRAM-based neuromorphic computing
DAC '22: Proceedings of the 59th ACM/IEEE Design Automation ConferencePages 985–990https://doi.org/10.1145/3489517.3530558One main fault-tolerant method for a neural network accelerator based on resistive random access memory crossbars is the programming-based method, which is also known as write-and-verify (W-V). In the basic W-V scheme, all devices in crossbars are ...
- research-articleMarch 2022
Revisiting Human-Robot Teaching and Learning Through the Lens of Human Concept Learning
HRI '22: Proceedings of the 2022 ACM/IEEE International Conference on Human-Robot InteractionPages 147–156When interacting with a robot, humans form conceptual models (of varying quality) which capture how the robot behaves. These conceptual models form just from watching or interacting with the robot, with or without conscious thought. Some methods select ...
- research-articleNovember 2021
A variational database management system
GPCE 2021: Proceedings of the 20th ACM SIGPLAN International Conference on Generative Programming: Concepts and ExperiencesPages 29–42https://doi.org/10.1145/3486609.3487197Many problems require working with data that varies in its structure and content. Current approaches, such as schema evolution or data integration tools, are highly tailored to specific kinds of variation in databases. While these approaches work well ...
- research-articleJune 2021
Monte Carlo Variation Analysis of NCFET-based 6-T SRAM: Design Opportunities and Trade-offs
GLSVLSI '21: Proceedings of the 2021 Great Lakes Symposium on VLSIPages 467–472https://doi.org/10.1145/3453688.3461742Negative Capacitance FET (NCFET) is one of the most promising variants of the emerging steep-slope transistors, able to overcome the ?Boltzmann limit'. The ferroelectric layer in the gate stack brings in new dynamics to the transistor operation by ...
- research-articleJune 2021
Tolerating Stuck-at Fault and Variation in Resistive Edge Inference Engine via Weight Mapping
GLSVLSI '21: Proceedings of the 2021 Great Lakes Symposium on VLSIPages 313–318https://doi.org/10.1145/3453688.3461487There is an increasing demand for running neural network inference on edge devices. Memristor crossbar array (MCA) based accelerators can be used to accelerate neural networks on edge devices. However, reliability issues in memristors, such as stuck-at ...
- research-articleFebruary 2021
Research on image enhancement algorithm based on Retinex theory
EITCE '20: Proceedings of the 2020 4th International Conference on Electronic Information Technology and Computer EngineeringPages 361–365https://doi.org/10.1145/3443467.3443782Retinex is a method to simulate the imaging principle of human brain visual cortex, which has been widely used in solving uneven illumination. This paper introduces the origin and development of the Retinex theory firstly. Then according to the current ...
- research-articleDecember 2020
Hessian-driven unequal protection of DNN parameters for robust inference
ICCAD '20: Proceedings of the 39th International Conference on Computer-Aided DesignArticle No.: 76, Pages 1–9https://doi.org/10.1145/3400302.3415679This paper presents an algorithmic approach to design reliable deep neural networks (DNN) in the presence of stochastic variations in the network parameters induced by process variations in the bit-cells in a processing-in-memory (PIM) architecture. We ...
Variational satisfiability solving
SPLC '20: Proceedings of the 24th ACM Conference on Systems and Software Product Line: Volume A - Volume AArticle No.: 18, Pages 1–12https://doi.org/10.1145/3382025.3414965Incremental satisfiability (SAT) solving is an extension of classic SAT solving that allows users to efficiently solve a set of related SAT problems by identifying and exploiting shared terms. However, using incremental solvers effectively is hard since ...
- research-articleJune 2020
Go unary: a novel synapse coding and mapping scheme for reliable reram-based neuromorphic computing
DATE '20: Proceedings of the 23rd Conference on Design, Automation and Test in EuropePages 1432–1437Neural network (NN) computing contains a large number of multiply-and-accumulate (MAC) operations, which is the speed bottleneck in traditional von Neumann architecture. Resistive random access memory (ReRAM)-based crossbar is well suited for matrix-...
- research-articleFebruary 2020
Computer comparisons in the presence of performance variation
Frontiers of Computer Science: Selected Publications from Chinese Universities (FCS), Volume 14, Issue 1Pages 21–41https://doi.org/10.1007/s11704-018-7319-2AbstractPerformance variability, stemming from non-deterministic hardware and software behaviors or deterministic behaviors such as measurement bias, is a well-known phenomenon of computer systems which increases the difficulty of comparing computer ...
- short-paperNovember 2019
Deep Colorization by Variation
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementPages 2201–2204https://doi.org/10.1145/3357384.3358085We propose an adversarial learning based model for image colorization in which we elaborately adapt image translation mechanism that are optimized according to the task. After developing approaches on improving the global and local quality of the image ...
- research-articleJuly 2019
Semantic variation operators for multidimensional genetic programming
GECCO '19: Proceedings of the Genetic and Evolutionary Computation ConferencePages 1056–1064https://doi.org/10.1145/3321707.3321776Multidimensional genetic programming represents candidate solutions as sets of programs, and thereby provides an interesting framework for exploiting building block identification. Towards this goal, we investigate the use of machine learning as a way ...
- research-articleApril 2018
Binarization of Nonuniform Illumination Barcode
ICMVA '18: Proceedings of the International Conference on Machine Vision and ApplicationsPages 18–21https://doi.org/10.1145/3220511.3220520This paper proposes a novel binarization approach, appropriate for nonuniform illumination barcode. The proposed method firstly clusters pixels of the image into two categories, which is black and white. Next, the variations of these two parts are ...
- research-articleJune 2017
Improving Performance under Process and Voltage Variations in Near-Threshold Computing Using 3D ICs
ACM Journal on Emerging Technologies in Computing Systems (JETC), Volume 13, Issue 4Article No.: 59, Pages 1–18https://doi.org/10.1145/3060579Near-threshold computing (NTC) circuits have been shown to offer significant energy efficiency and power benefits but with a huge performance penalty. This performance loss exacerbates if process and voltage variations are considered. In this article, ...
- research-articleFebruary 2017
Quality-Time Tradeoffs in Component-Specific Mapping: How to Train Your Dynamically Reconfigurable Array of Gates with Outrageous Network-delays
FPGA '17: Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate ArraysPages 85–94https://doi.org/10.1145/3020078.3026124How should we perform component-specific adaptation for FPGAs? Prior work has demonstrated that the negative effects of variation can be largely mitigated using complete knowledge of device characteristics and full per-FPGA CAD flow. However, the cost ...