Mandovi Mukherjee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mandovi Mukherjee has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Saibal Mukhopadhyay
Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA
3 shared publications - Coleman DeLude
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA
2 shared publications - Daehyun Kim
Georgia Institute of Technology, Atlanta, Georgia, USA
2 shared publications - Edward Lee
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA
2 shared publications J. Driscoll
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA
2 shared publications- Justin Romberg
Georgia Institute of Technology
2 shared publications
Latest Publications
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radar Systems
- Vol. 2, 849-865
Real-Time Digital RF Emulation—Part II: A Near Memory Custom Accelerator
A near memory hardware accelerator, based on a novel direct path computational model, for real-time emulation of radio frequency systems is demonstrated. Our evaluation of hardware performance uses both application-specific integrated circuits (ASIC) and field programmable gate arrays (FPGA) methodologies: 1). The ASIC test-chip implementation, using TSMC 28nm CMOS, leverages distributed autonomous control to extract concurrency in compute as well as low latency. It achieves a 518 MHz per channel bandwidth in a prototype 4-node system. The maximum emulation range supported in this paradigm is 9.5 km with 0.24 μs of per-sample emulation latency. 2). The FPGA-based implementation, evaluated on a Xilinx ZCU104 board, demonstrates a 9-node test case (two Transmitters, one Receiver, and 6 passive reflectors) with an emulation range of 1.13 km to 27.3 km at 215 MHz bandwidth.
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radar Systems
- Vol. 2, 849-865
Real-Time Digital RF Emulation—Part II: A Near Memory Custom Accelerator
A near memory hardware accelerator, based on a novel direct path computational model, for real-time emulation of radio frequency systems is demonstrated. Our evaluation of hardware performance uses both application-specific integrated circuits (ASIC) and field programmable gate arrays (FPGA) methodologies: 1). The ASIC test-chip implementation, using TSMC 28nm CMOS, leverages distributed autonomous control to extract concurrency in compute as well as low latency. It achieves a 518 MHz per channel bandwidth in a prototype 4-node system. The maximum emulation range supported in this paradigm is 9.5 km with 0.24 μs of per-sample emulation latency. 2). The FPGA-based implementation, evaluated on a Xilinx ZCU104 board, demonstrates a 9-node test case (two Transmitters, one Receiver, and 6 passive reflectors) with an emulation range of 1.13 km to 27.3 km at 215 MHz bandwidth.
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radar Systems
- Vol. 2, 866-879
Real-Time Digital RF Emulation—Part I: The Direct Path Computational Model
In this paper we consider the problem of developing a computational model for emulating an RF channel. The motivation for this is that an accurate and scalable emulator has the potential to minimize the need for field testing, which is expensive, slow, and difficult to replicate. Traditionally, emulators are built using a tapped delay line model where long filters modeling the physical interactions of objects are implemented directly. For an emulation scenario consisting of M objects all interacting with one another, the tapped delay line model’s computational requirements scale as O ( M 3 ) per sample: there are O ( M 2 ) channels, each with O ( M ) complexity. In this paper, we develop a new “direct path" model that, while remaining physically faithful, allows us to carefully factor the emulator operations, resulting in an O ( M 2 ) per sample scaling of the computational requirements. The impact of this is drastic, a 200 object scenario sees about a 100× reduction in the number of per sample computations. Furthermore, the direct path model gives us a natural way to distribute the computations for an emulation: each object is mapped to a computational node, and these nodes are networked in a fully connected communication graph. Alongside a discussion of the model and the physical phenomena it emulates, we show how to efficiently parameterize antenna responses and scattering profiles within this direct path framework. To verify the model and demonstrate its viability in hardware, we provide several numerical experiments produced using a cycle level C++ simulator of a hardware implementation of the model.
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Radar Systems
- Vol. 2, 866-879
Real-Time Digital RF Emulation—Part I: The Direct Path Computational Model
In this paper we consider the problem of developing a computational model for emulating an RF channel. The motivation for this is that an accurate and scalable emulator has the potential to minimize the need for field testing, which is expensive, slow, and difficult to replicate. Traditionally, emulators are built using a tapped delay line model where long filters modeling the physical interactions of objects are implemented directly. For an emulation scenario consisting of M objects all interacting with one another, the tapped delay line model’s computational requirements scale as O ( M 3 ) per sample: there are O ( M 2 ) channels, each with O ( M ) complexity. In this paper, we develop a new “direct path" model that, while remaining physically faithful, allows us to carefully factor the emulator operations, resulting in an O ( M 2 ) per sample scaling of the computational requirements. The impact of this is drastic, a 200 object scenario sees about a 100× reduction in the number of per sample computations. Furthermore, the direct path model gives us a natural way to distribute the computations for an emulation: each object is mapped to a computational node, and these nodes are networked in a fully connected communication graph. Alongside a discussion of the model and the physical phenomena it emulates, we show how to efficiently parameterize antenna responses and scattering profiles within this direct path framework. To verify the model and demonstrate its viability in hardware, we provide several numerical experiments produced using a cycle level C++ simulator of a hardware implementation of the model.
- 23 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (12) , 11317-11327
Energy Efficient Pixel-Parallel Read-Out Circuits for Digital Image Sensors Using Cross-Layer Pixel Depth Control
Digital pixel sensors with pixel-parallel readout provide opportunities for high frame rate and high resolution in 3D integrated camera platforms with in-sensor machine learning. The active energy consumption of the digital pixels at the sensor front end is a key performance parameter for applications involving smart cameras. This work proposes a novel digital pixel design that utilizes cross-layer feedback to improve active energy efficiency of pixels in image sensors. An algorithm-circuit co-simulation of $336\times256$ image sensor in 65nm CMOS for an object detection task shows 58% active energy saving in digital pixel circuits, while maintaining accuracy of end task.
- 23 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 22 (12) , 11317-11327
Energy Efficient Pixel-Parallel Read-Out Circuits for Digital Image Sensors Using Cross-Layer Pixel Depth Control
Digital pixel sensors with pixel-parallel readout provide opportunities for high frame rate and high resolution in 3D integrated camera platforms with in-sensor machine learning. The active energy consumption of the digital pixels at the sensor front end is a key performance parameter for applications involving smart cameras. This work proposes a novel digital pixel design that utilizes cross-layer feedback to improve active energy efficiency of pixels in image sensors. An algorithm-circuit co-simulation of $336\times256$ image sensor in 65nm CMOS for an object detection task shows 58% active energy saving in digital pixel circuits, while maintaining accuracy of end task.
- 19 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 10 (4) , 444-457
Cross-Layer Noise Analysis in Smart Digital Pixel Sensors With Integrated Deep Neural Network
Digital pixel based image sensors with embedded deep neural network (DNN) allow many mission critical surveillance applications. However, image noise caused by variations and non-idealities in the sensor aggravates the quality of image and further degrades the performance of a DNN. We propose a digital pixel-DNN cross-layer simulation methodology for accurate training and evaluation of a DNN under image noise induced from sensors. In particular, this paper focuses on the image noise derived from device mismatches in digital pixel circuits with 3D integrated and pixel-parallel readout circuits, and studies the effect of the resulting image noise on the accuracy of a DNN. The simulation results show that the device mismatch in the digital pixel creates distinct noise structure on output image and should be accurately considered while training a DNN. We also present design space explorations using our cross-layer simulation.
- 19 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 10 (4) , 444-457
Cross-Layer Noise Analysis in Smart Digital Pixel Sensors With Integrated Deep Neural Network
Digital pixel based image sensors with embedded deep neural network (DNN) allow many mission critical surveillance applications. However, image noise caused by variations and non-idealities in the sensor aggravates the quality of image and further degrades the performance of a DNN. We propose a digital pixel-DNN cross-layer simulation methodology for accurate training and evaluation of a DNN under image noise induced from sensors. In particular, this paper focuses on the image noise derived from device mismatches in digital pixel circuits with 3D integrated and pixel-parallel readout circuits, and studies the effect of the resulting image noise on the accuracy of a DNN. The simulation results show that the device mismatch in the digital pixel creates distinct noise structure on output image and should be accurately considered while training a DNN. We also present design space explorations using our cross-layer simulation.
- 14 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Solid-State Circuits Letters
- Vol. 3, 450-453
A Flexible Precision Multi-Format In-Memory Vector Matrix Multiplication Engine in 65 nm CMOS With RF Machine Learning Support
An all-digital flexible precision in-memory accelerator for Vector Matrix Multiplier (VMM) is demonstrated in 65nm CMOS. The design supports flexible precision, floating-point, and complex numbers enabling in-memory Radio Frequency machine learning and signal processing computation. The measured compute efficiency normalized to memory size is 34GOPS/W/KB.
- 14 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Solid-State Circuits Letters
- Vol. 3, 450-453
A Flexible Precision Multi-Format In-Memory Vector Matrix Multiplication Engine in 65 nm CMOS With RF Machine Learning Support
An all-digital flexible precision in-memory accelerator for Vector Matrix Multiplier (VMM) is demonstrated in 65nm CMOS. The design supports flexible precision, floating-point, and complex numbers enabling in-memory Radio Frequency machine learning and signal processing computation. The measured compute efficiency normalized to memory size is 34GOPS/W/KB.