Janakiraman Viraraghavan

Bio: Janakiraman Viraraghavan is an academic researcher from Indian Institute of Technology Madras. The author has contributed to research in topics: Logic gate & Transistor. The author has an hindex of 6, co-authored 16 publications receiving 80 citations. Previous affiliations of Janakiraman Viraraghavan include Indian Institute of Science & IBM.

A 14 nm 1.1 Mb Embedded DRAM Macro With 1 ns Access

Abstract: A 1.1 Mb embedded DRAM macro (eDRAM), for next-generation IBM SOI processors, employs 14 nm FinFET logic technology with $\hbox{0.0174}~\mu\hbox{m}^{2}$ deep-trench capacitor cell. A Gated-feedback sense amplifier enables a high voltage gain of a power-gated inverter at mid-level input voltage, while supporting 66 cells per local bit-line. A dynamic-and-gate-thin-oxide word-line driver that tracks standard logic process variation improves the eDRAM array performance with reduced area. The 1.1 $~$ Mb macro composed of 8 $\times$ 2 72 Kb subarrays is organized with a center interface block architecture, allowing 1 ns access latency and 1 ns bank interleaving operation using two banks, each having 2 ns random access cycle. 5 GHz operation has been demonstrated in a system prototype, which includes 6 instances of 1.1 Mb eDRAM macros, integrated with an array-built-in-self-test engine, phase-locked loop (PLL), and word-line high and word-line low voltage generators. The advantage of the 14 nm FinFET array over the 22 nm array was confirmed using direct tester control of the 1.1 Mb eDRAM macros integrated in 16 Mb inline monitor.

80-kb Logic Embedded High-K Charge Trap Transistor-Based Multi-Time-Programmable Memory With No Added Process Complexity

Abstract: This paper describes the design and implementation of an 80-kb logic-embedded non-volatile multi-time programmable memory (MTPM) with no added process complexity. Charge trap transistors (CTTs) that exploit charge trapping and de-trapping behavior in high-K dielectric of 32-/22-nm Logic FETs are used as storage elements with logic-compatible programming voltages. A high-gain slew-sense amplifier (SA) is used to efficiently detect the threshold voltage difference ( $\Delta V_{\textrm {DIF}}$ ) between the true and complement FETs in the twin cell. Design-assist techniques including multi-step programming with over-write protection and block write algorithm are used to enhance the programming efficiency without causing a dielectric breakdown. High-temperature stress results show a projected data retention of 10 years at 125 °C with a signal loss of <30% that is margined in while programming, by employing a sense margining logic in the SA. Scalability of CTT has been established by the first demonstration of CTT-based MTPM in 14-nm bulk FinFET technology with read cycle time of 40 ns at 0.7-V VDD.

80Kb 10ns read cycle logic Embedded High-K charge trap Multi-Time-Programmable Memory scalable to 14nm FIN with no added process complexity

Abstract: An 80Kb logic Embedded Multi-Time Programmable Memory (MTPM) employs charge trapping and de-trapping behavior in 32nm/22nm High-K transistor, resulting in no added process complexity. Multi-step verification with overwrite protection employs block-write and signal margin degradation (∼30%) to satisfy 10 year retention at 105° C.

Statistical Compact Model Extraction: A Neural Network Approach

Abstract: A technique for extracting statistical compact model parameters using artificial neural networks (ANNs) is proposed. ANNs can model a much higher degree of nonlinearity compared to existing quadratic polynomial models and, hence, can even be used in sub-100-nm technologies to model leakage current that exponentially depends on process parameters. Existing techniques cannot be extended to handle such exponential functions. Additionally, ANNs can handle multiple input multiple output relations very effectively. The concept applied to CMOS devices improves the efficiency and accuracy of model extraction. Results from the ANN match the ones obtained from SPICE simulators within 1%.

Voltage and Temperature Scalable Standard Cell Leakage Models Based on Stacks for Statistical Leakage Characterization

Abstract: With extensive use of dynamic voltage scaling (DVS) there is increasing need for voltage scalable models. Similarly, leakage being very sensitive to temperature motivates the need for a temperature scalable model as well. We characterize standard cell libraries for statistical leakage analysis based on models for transistor stacks. Modeling stacks has the advantage of using a single model across many gates there by reducing the number of models that need to be characterized. Our experiments on 15 different gates show that we needed only 23 models to predict the leakage across 126 input vector combinations. We investigate the use of neural networks for the combined PVT model, for the stacks, which can capture the effect of inter die, intra gate variations, supply voltage(0.6-1.2 V) and temperature (0 - 100degC) on leakage. Results show that neural network based stack models can predict the PDF of leakage current across supply voltage and temperature accurately with the average error in mean being less than 2% and that in standard deviation being less than 5% across a range of voltage, temperature.

DRISA: a DRAM-based Reconfigurable In-Situ Accelerator

Abstract: Data movement between the processing units and the memory in traditional von Neumann architecture is creating the “memory wall” problem. To bridge the gap, two approaches, the memory-rich processor (more on-chip memory) and the compute-capable memory (processing-in-memory) have been studied. However, the first one has strong computing capability but limited memory capacity/bandwidth, whereas the second one is the exact the opposite.To address the challenge, we propose DRISA, a DRAM-based Reconfigurable In-Situ Accelerator architecture, to provide both powerful computing capability and large memory capacity/bandwidth. DRISA is primarily composed of DRAM memory arrays, in which every memory bitline can perform bitwise Boolean logic operations (such as NOR). DRISA can be reconfigured to compute various functions with the combination of the functionally complete Boolean logic operations and the proposed hierarchical internal data movement designs. We further optimize DRISA to achieve high performance by simultaneously activating multiple rows and subarrays to provide massive parallelism, unblocking the internal data movement bottlenecks, and optimizing activation latency and energy. We explore four design options and present a comprehensive case study to demonstrate significant acceleration of convolutional neural networks. The experimental results show that DRISA can achieve 8.8× speedup and 1.2× better energy efficiency compared with ASICs, and 7.7× speedup and 15× better energy efficiency over GPUs with integer operations.CCS CONCEPTS• Hardware → Dynamic memory; • Computer systems organization → reconfigurable computing; Neural networks;

Enabling scientific computing on memristive accelerators

Abstract: Linear algebra is ubiquitous across virtually every field of science and engineering, from climate modeling to macroeconomics. This ubiquity makes linear algebra a prime candidate for hardware acceleration, which can improve both the run time and the energy efficiency of a wide range of scientific applications. Recent work on memristive hardware accelerators shows significant potential to speed up matrix-vector multiplication (MVM), a critical linear algebra kernel at the heart of neural network inference tasks. Regrettably, the proposed hardware is constrained to a narrow range of workloads: although the eight- to 16-bit computations afforded by memristive MVM accelerators are acceptable for machine learning, they are insufficient for scientific computing where high-precision floating point is the norm. This paper presents the first proposal to enable scientific computing on memristive crossbars. Three techniques are explored---reducing overheads by exploiting exponent range locality, early termination of fixed-point computation, and static operation scheduling---that together enable a fixed-point memristive accelerator to perform high-precision floating point without the exorbitant cost of naive floating-point emulation on fixed-point hardware. A heterogeneous collection of crossbars with varying sizes is proposed to efficiently handle sparse matrices, and an algorithm for mapping the dense subblocks of a sparse matrix to an appropriate set of crossbars is investigated. The accelerator can be combined with existing GPU-based systems to handle datasets that cannot be efficiently handled by the memristive accelerator alone. The proposed optimizations permit the memristive MVM concept to be applied to a wide range of problem domains, respectively improving the execution time and energy dissipation of sparse linear solvers by 10.3x and 10.9x over a purely GPU-based system.

Charge Trap Transistor (CTT): An Embedded Fully Logic-Compatible Multiple-Time Programmable Non-Volatile Memory Element for High- $k$ -Metal-Gate CMOS Technologies

Abstract: The availability of on-chip non-volatile memory for advanced high- $k$ -metal-gate CMOS technology nodes has been limited due to integration and scaling challenges as well as operational voltage incompatibilities, while its need continues to grow rapidly in modern high-performance systems. By exploiting intrinsic device self-heating enhanced charge trapping in as fabricated high- $k$ -metal-gate logic devices, we introduce a unique multiple-time programmable embedded non-volatile memory element, called the ‘charge trap transistor’ (CTT), for high- $k$ -metal-gate CMOS technologies. Functionality and feasibility of using CTT memory devices have been demonstrated on 22 nm planar and 14 nm FinFET technology platforms, including fully functional product prototype memory arrays. These transistor memory devices offer high density ( $\sim 0.144\mu\mathrm{m}^{2}$ /bit for 22 nm and $\sim 0.082\mu\mathrm{m}^{2}$ /bit for 14 nm technology), logic voltage compatible and low peak power operation (~4mW), and excellent retention for a fully integrated and scalable embedded non-volatile memory without added process complexity or masks.

Prediction of Process Variation Effect for Ultrascaled GAA Vertical FET Devices Using a Machine Learning Approach

Abstract: In this brief, we present an accurate and efficient machine learning (ML) approach which predicts variations in key electrical parameters using process variations (PVs) from ultrascaled gate-all-around (GAA) vertical FET (VFET) devices. The 3-D stochastic TCAD simulation is the most powerful tool for analyzing PVs, but for ultrascaled devices, the computation cost is too high because this method requires simultaneous analysis of various factors. The proposed ML approach is a new method which predicts the effects of the variability sources of ultrascaled devices. It also shows the same degree of accuracy, as well as improved efficiency compared to a 3-D stochastic TCAD simulation. An artificial neural network (ANN)-based ML algorithm can make multi-input -multi-output (MIMO) predictions very effectively and uses an internal algorithm structure that is improved relative to existing techniques to capture the effects of PVs accurately. This algorithm incurs approximately 16% of the computation cost by predicting the effects of process variability sources with less than 1% error compared to a 3-D stochastic TCAD simulation.

Radiation Effects in Advanced and Emerging Nonvolatile Memories

Abstract: Despite hitting major roadblocks in 2-D scaling, NAND flash continues to scale in the vertical direction and dominate the commercial nonvolatile memory market. However, several emerging nonvolatile technologies are under development by major commercial foundries or are already in small volume production, motivated by storage-class memory and embedded application drivers. These include spin-transfer torque magnetic random access memory (STT-MRAM), resistive random access memory (ReRAM), phase change random access memory (PCRAM), and conductive bridge random access memory (CBRAM). Emerging memories have improved resilience to radiation effects compared to flash, which is based on storing charge, and hence may offer an expanded selection from which radiation-tolerant system designers can choose from in the future. This review discusses the material and device physics, fabrication, operational principles, and commercial status of scaled 2-D flash, 3-D flash, and emerging memory technologies. Radiation effects relevant to each of these memories are described, including the physics of and errors caused by total ionizing dose, displacement damage, and single-event effects, with an eye toward the future role of emerging technologies in radiation environments.