arXiv subjects

Saibal Mukhopadhyay

Publications and source records attributed to Saibal Mukhopadhyay.

61 records · Page 4Linked to original sources

arXiv2018

Memory Slices: A Modular Building Block for Scalable, Intelligent Memory Systems

While reduction in feature size makes computation cheaper in terms of latency, area, and power consumption, performance of emerging data-intensive applications is determined by data movement. These trends have introduced the concept of scalability as reaching a desirable performance per unit cost by using as few number of units as possible. Many proposals have moved compute closer to the memory. However, these efforts ignored maintaining a balance between bandwidth and compute rate of an architecture, with those of applications, which is a key principle in designing scalable large systems. This paper proposes the use of memory slices, a modular building block for scalable memory systems integrated with compute, in which performance scales with memory size (and volume of data). The slice architecture utilizes a programmable memory interface feeding a systolic compute engine with high reuse rate. The modularity feature of slice-based systems is exploited with a partitioning and data mapping strategy across allocated memory slices where training performance scales with the data size. These features enable shifting the most pressure to cheap compute units rather than expensive memory accesses or transfers via interconnection network. An application of the memory slices to a scale-out memory system is accelerating the training of recurrent, convolutional, and hybrid neural networks (RNNs and RNNs+CNN) that are forming cloud workloads. The results of our cycle-level simulations show that memory slices exhibits a superlinear speedup when the number of slices increases. Furthermore, memory slices improve power efficiency to 747 GFLOPs/J for training LSTMs. While our current evaluation uses memory slices with 3D packaging, a major value is that slices can also be constructed with a variety of packaging options, for example with DDR-based memory units.

cs.AR↗

arXiv2018

Blindsight: Blinding EM Side-Channel Leakage using Built-In Fully Integrated Inductive Voltage Regulator

Modern high-performance as well as power-constrained System-on-Chips (SoC) are increasingly using hardware accelerated encryption engines to secure computation, memory access, and communication operations. The electromagnetic (EM) emission from a chip leaks information of the underlying logical operations and can be collected using low-cost non-invasive measurements. EM based side-channel attacks (EMSCA) have emerged as a major threat to security of encryption engines in a SoC. This paper presents the concept of Blindsight where a high-frequency inductive voltage regulator (IVR) integrated on the same chip with an encryption engine is used to increase resistance against EMSCA. High-frequency (~100MHz) IVRs are present in modern microprocessors to improve energy-efficiency. We show that an IVR with a randomized control loop (R-IVR) can reduce EMSCA as the integrated inductance acts as a strong EM emitter and blinds an adversary from EM emission of the encryption engine. The EM measurements are performed on a test-chip containing two architectures of a 128-bit Advanced Encryption Standard (AES) engine powered by a high-frequency R-IVR and under two attack scenarios, one, where an adversary gains complete physical access of the target device and the other, where the adversary is only in proximity of the device. In both attack modes, an adversary can observe information leakage in Test Vector Leakage Assessment (TVLA) test in a baseline IVR (B-IVR, without control loop randomization). However, we show that EM emission from the R-IVR blinds the attacker and significantly reduces SCA vulnerability of the AES engine. A range of practical side-channel analysis including TVLA, Correlation Electromagnetic Analysis (CEMA), and a template based CEMA shows that R-IVR can reduce information leakage and prevent key extraction even against a skilled adversary.

cs.CR↗

arXiv2018

Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms

This paper introduces partitioning an inference task of a deep neural network between an edge and a host platform in the IoT environment. We present a DNN as an encoding pipeline, and propose to transmit the output feature space of an intermediate layer to the host. The lossless or lossy encoding of the feature space is proposed to enhance the maximum input rate supported by the edge platform and/or reduce the energy of the edge platform. Simulation results show that partitioning a DNN at the end of convolutional (feature extraction) layers coupled with feature space encoding enables significant improvement in the energy-efficiency and throughput over the baseline configurations that perform the entire inference at the edge or at the host.

cs.CV↗

arXiv2017

NeuroTrainer: An Intelligent Memory Module for Deep Learning Training

This paper presents, NeuroTrainer, an intelligent memory module with in-memory accelerators that forms the building block of a scalable architecture for energy efficient training for deep neural networks. The proposed architecture is based on integration of a homogeneous computing substrate composed of multiple processing engines in the logic layer of a 3D memory module. NeuroTrainer utilizes a programmable data flow based execution model to optimize memory mapping and data re-use during different phases of training operation. A programming model and supporting architecture utilizes the flexible data flow to efficiently accelerate training of various types of DNNs. The cycle level simulation and synthesized design in 15nm FinFET showspower efficiency of 500 GFLOPS/W, and almost similar throughput for a wide range of DNNs including convolutional, recurrent, multi-layer-perceptron, and mixed (CNN+RNN) networks

cs.AR↗

arXiv2017

Demystifying the Characteristics of 3D-Stacked Memories: A Case Study for Hybrid Memory Cube

Three-dimensional (3D)-stacking technology, which enables the integration of DRAM and logic dies, offers high bandwidth and low energy consumption. This technology also empowers new memory designs for executing tasks not traditionally associated with memories. A practical 3D-stacked memory is Hybrid Memory Cube (HMC), which provides significant access bandwidth and low power consumption in a small area. Although several studies have taken advantage of the novel architecture of HMC, its characteristics in terms of latency and bandwidth or their correlation with temperature and power consumption have not been fully explored. This paper is the first, to the best of our knowledge, to characterize the thermal behavior of HMC in a real environment using the AC-510 accelerator and to identify temperature as a new limitation for this state-of-the-art design space. Moreover, besides bandwidth studies, we deconstruct factors that contribute to latency and reveal their sources for high- and low-load accesses. The results of this paper demonstrates essential behaviors and performance bottlenecks for future explorations of packet-switched and 3D-stacked memories.

cs.AR↗

arXiv2007

Statistical Modeling of Pipeline Delay and Design of Pipeline under Process Variation to Enhance Yield in sub-100nm Technologies

Operating frequency of a pipelined circuit is determined by the delay of the slowest pipeline stage. However, under statistical delay variation in sub-100nm technology regime, the slowest stage is not readily identifiable and the estimation of the pipeline yield with respect to a target delay is a challenging problem. We have proposed analytical models to estimate yield for a pipelined design based on delay distributions of individual pipe stages. Using the proposed models, we have shown that change in logic depth and imbalance between the stage delays can improve the yield of a pipeline. A statistical methodology has been developed to optimally design a pipeline circuit for enhancing yield. Optimization results show that, proper imbalance among the stage delays in a pipeline improves design yield by 9% for the same area and performance (and area reduction by about 8.4% under a yield constraint) over a balanced design.

cs.AR↗

arXiv2007

Modeling and Analysis of Loading Effect in Leakage of Nano-Scaled Bulk-CMOS Logic Circuits

In nanometer scaled CMOS devices significant increase in the subthreshold, the gate and the reverse biased junction band-to-band-tunneling (BTBT) leakage, results in the large increase of total leakage power in a logic circuit. Leakage components interact with each other in device level (through device geometry, doping profile) and also in the circuit level (through node voltages). Due to the circuit level interaction of the different leakage components, the leakage of a logic gate strongly depends on the circuit topology i.e. number and nature of the other logic gates connected to its input and output. In this paper, for the first time, we have analyzed loading effect on leakage and proposed a method to accurately estimate the total leakage in a logic circuit, from its logic level description considering the impact of loading and transistor stacking.

cs.AR↗