Karthik Swaminathan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Karthik Swaminathan has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Alper Buyuktosunoglu
IBM T. J. Watson Research Center, Yorktown Heights, NY, USA
4 shared publications - Pradip Bose
IBM T. J. Watson Research Center, Yorktown Heights, NY, USA
4 shared publications - Aporva Amarnath
IBM Research, Yorktown Heights, NY, USA
3 shared publications - David Brooks
Harvard University, Cambridge, MA, USA
2 shared publications - Davide Giri
Columbia University, New York, NY, USA
2 shared publications - Gu-Yeon Wei
Harvard University, Cambridge, MA, USA
2 shared publications
Latest Publications
- 22 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 46 (1) , 29-33
Robust Power Management: A Key Aspect of Silent Data Corruption-Free Systems
Silent data corruption (SDC) is a term that has created a specter of doubt and fear amongst the information community in recent years. In this position paper, we focus our attention on the problem of power management and the need for vigilance in ensuring SDC-free functionality in future power-constrained processor systems.
- 22 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 46 (1) , 29-33
Robust Power Management: A Key Aspect of Silent Data Corruption-Free Systems
Silent data corruption (SDC) is a term that has created a specter of doubt and fear amongst the information community in recent years. In this position paper, we focus our attention on the problem of power management and the need for vigilance in ensuring SDC-free functionality in future power-constrained processor systems.
- 26 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 61 (5) , 2276-2294
EPOCHS-1: A 12 nm Highly Heterogeneous Open-Source SoC With Distributed Coin-Based Power Management and Integrated Hybrid Voltage Regulation
We present EPOCHS-1, a 12 nm, 64 mm2 system-on-chip (SoC) with a high degree of heterogeneity. It features four Linux-SMP-capable RISC-V cores, 14 different types of accelerators, a distributed memory hierarchy, and various peripherals. EPOCHS-1’s memory hierarchy has the flexibility to support a diverse set of accelerators and can scale to support complex applications with 34% and 25% reduction in latency and energy, respectively. A subset of the SoC’s 23 power and 35 clock domains is regulated with a fully-decentralized power-allocation scheme and hybrid unified voltage and frequency scaling (HUVFS) that combines an in-package switched regulator with a per-tile low dropout (LDO). Combined, these techniques achieve up to a $1.57\times $ speedup versus a centralized power management baseline. Designed with an agile methodology, EPOCHS-1 is based on an open-source SoC architecture and features only open-source components, either third-party or newly designed, thus enabling design reuse for future research projects.
- 26 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 61 (5) , 2276-2294
EPOCHS-1: A 12 nm Highly Heterogeneous Open-Source SoC With Distributed Coin-Based Power Management and Integrated Hybrid Voltage Regulation
We present EPOCHS-1, a 12 nm, 64 mm2 system-on-chip (SoC) with a high degree of heterogeneity. It features four Linux-SMP-capable RISC-V cores, 14 different types of accelerators, a distributed memory hierarchy, and various peripherals. EPOCHS-1’s memory hierarchy has the flexibility to support a diverse set of accelerators and can scale to support complex applications with 34% and 25% reduction in latency and energy, respectively. A subset of the SoC’s 23 power and 35 clock domains is regulated with a fully-decentralized power-allocation scheme and hybrid unified voltage and frequency scaling (HUVFS) that combines an in-package switched regulator with a per-tile low dropout (LDO). Combined, these techniques achieve up to a $1.57\times $ speedup versus a centralized power management baseline. Designed with an agile methodology, EPOCHS-1 is based on an open-source SoC architecture and features only open-source components, either third-party or newly designed, thus enabling design reuse for future research projects.
- 30 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 45 (4) , 79-86
BlitzCoin: A Decentralized Hardware Solution for Power Management of Highly Heterogeneous Systems on Chip
The increase in both the number and the types of accelerators in modern SoCs necessitates a rethinking of power-management strategies. To overcome the scalability shortcomings of current methods, we propose BlitzCoin a fully decentralized hardware-based power management coupled with optimized unified voltage and frequency regulation. We evaluated BlitzCoin through RTL simulations of multiple SoCs targeted toward different application domains. The results are further validated through silicon measurements of a fabricated 12 nm many-accelerator SoC that includes BlitzCoin. Our evaluations show that BlitzCoin is markedly faster than state-of-the-art centralized power-management strategies, with 8× to 12× lower response times. This results in 25%-34% throughput improvement and allows for scaling to 7× to 13× larger SoCs, all with a small area overhead of <1%. BlitzCoin is an addition to the open-source ESP SoC platform, offering a foundation for further exploration of power-management strategies.
- 30 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 45 (4) , 79-86
BlitzCoin: A Decentralized Hardware Solution for Power Management of Highly Heterogeneous Systems on Chip
The increase in both the number and the types of accelerators in modern SoCs necessitates a rethinking of power-management strategies. To overcome the scalability shortcomings of current methods, we propose BlitzCoin a fully decentralized hardware-based power management coupled with optimized unified voltage and frequency regulation. We evaluated BlitzCoin through RTL simulations of multiple SoCs targeted toward different application domains. The results are further validated through silicon measurements of a fabricated 12 nm many-accelerator SoC that includes BlitzCoin. Our evaluations show that BlitzCoin is markedly faster than state-of-the-art centralized power-management strategies, with 8× to 12× lower response times. This results in 25%-34% throughput improvement and allows for scaling to 7× to 13× larger SoCs, all with a small area overhead of <1%. BlitzCoin is an addition to the open-source ESP SoC platform, offering a foundation for further exploration of power-management strategies.
- Open Access
- 27 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 186
No Time to Lose: Enabling Real-Time Fluorescence Lifetime Imaging on Resource-constrained FPGAs Through Efficient Scheduling
Fluorescence lifetime imaging (FLI) is a widely used technique in the biomedical field for measuring the decay times of fluorescent molecules, providing insights into metabolic states, protein interactions, and ligand-receptor bindings [1, 5]. However, its broader application in fast biological processes, such as dynamic activity monitoring, and clinical use, such as in guided surgery, is limited by long data acquisition times and computationally demanding data processing. While deep learning has reduced post-processing times, time-resolved data acquisition remains a bottleneck for real-time applications. To address this,we propose a method to achieve near realtime FLI using an FPGA-based hardware accelerator. Specifically,we implemented a GRU-based sequence-to-sequence (Seq2Seq) model [3] on an FPGA board compatible with time-resolved cameras. The GRU model balances accurate processing with the resource constraints of FPGAs, which have limited DSP units and BRAM. The limited memory and computational resources on the FPGA require efficient scheduling of operations and memory allocation to deploy deep learning models for low-latency applications.We address these challenges by using STOMP, a queue-based discrete-event simulator that automates and optimizes task scheduling and memory management on hardware [4]. By integrating a GRU-based Seq2Seq model and its compressed version, called Seq2SeqLite [2], generated through knowledge distillation (KD), we were able to process multiple pixels in parallel, reducing latency compared to sequential processing. We explore various levels of parallelism to achieve an optimal balance between performance and resource utilization. Our results indicate that the proposed techniques achieved a 17.7x and 52.0x speedup over manual scheduling for the Seq2Seq model and the Seq2SeqLite model, respectively. Furthermore, the Seq2SeqLite model achieved a 98% reduction in parameters compared to the Seq2Seq model.
- 27 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 186
Open AccessNo Time to Lose: Enabling Real-Time Fluorescence Lifetime Imaging on Resource-constrained FPGAs Through Efficient Scheduling
Fluorescence lifetime imaging (FLI) is a widely used technique in the biomedical field for measuring the decay times of fluorescent molecules, providing insights into metabolic states, protein interactions, and ligand-receptor bindings [1, 5]. However, its broader application in fast biological processes, such as dynamic activity monitoring, and clinical use, such as in guided surgery, is limited by long data acquisition times and computationally demanding data processing. While deep learning has reduced post-processing times, time-resolved data acquisition remains a bottleneck for real-time applications. To address this,we propose a method to achieve near realtime FLI using an FPGA-based hardware accelerator. Specifically,we implemented a GRU-based sequence-to-sequence (Seq2Seq) model [3] on an FPGA board compatible with time-resolved cameras. The GRU model balances accurate processing with the resource constraints of FPGAs, which have limited DSP units and BRAM. The limited memory and computational resources on the FPGA require efficient scheduling of operations and memory allocation to deploy deep learning models for low-latency applications.We address these challenges by using STOMP, a queue-based discrete-event simulator that automates and optimizes task scheduling and memory management on hardware [4]. By integrating a GRU-based Seq2Seq model and its compressed version, called Seq2SeqLite [2], generated through knowledge distillation (KD), we were able to process multiple pixels in parallel, reducing latency compared to sequential processing. We explore various levels of parallelism to achieve an optimal balance between performance and resource utilization. Our results indicate that the proposed techniques achieved a 17.7x and 52.0x speedup over manual scheduling for the Seq2Seq model and the Seq2SeqLite model, respectively. Furthermore, the Seq2SeqLite model achieved a 98% reduction in parameters compared to the Seq2Seq model.
- Open Access
- 27 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 746-762
MulBERRY: Enabling Bit-Error Robustness for Energy-Efficient Multi-Agent Autonomous Systems
- 27 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 746-762
Open AccessMulBERRY: Enabling Bit-Error Robustness for Energy-Efficient Multi-Agent Autonomous Systems
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Architecture Letters
- Vol. 23 (1) , 108-111
Dramaton: A Near-DRAM Accelerator for Large Number Theoretic Transforms
With the rising popularity of post-quantum cryptographic schemes, realizing practical implementations for realworld applications is still a major challenge. A major bottleneck in such schemes is the fetching and processing of large polynomials in the Number Theoretic Transform (NTT), which makes non Von Neumann paradigms, such as near-memory processing, a viable option. We, therefore, propose a novel near-DRAM NTT accelerator design, called DRAMATON. Additionally, we introduce a conflict-free mapping algorithm that enables DRAMATON to process large NTTs with minimal hardware overhead using a fixed-permutation network. DRAMATON achieves 5-207× speedup in latency over the state-of-the-art and 97× improvement in EDP over a recent near-memory NTT accelerator.
- 27 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Architecture Letters
- Vol. 23 (1) , 108-111
Dramaton: A Near-DRAM Accelerator for Large Number Theoretic Transforms
With the rising popularity of post-quantum cryptographic schemes, realizing practical implementations for realworld applications is still a major challenge. A major bottleneck in such schemes is the fetching and processing of large polynomials in the Number Theoretic Transform (NTT), which makes non Von Neumann paradigms, such as near-memory processing, a viable option. We, therefore, propose a novel near-DRAM NTT accelerator design, called DRAMATON. Additionally, we introduce a conflict-free mapping algorithm that enables DRAMATON to process large NTTs with minimal hardware overhead using a fixed-permutation network. DRAMATON achieves 5-207× speedup in latency over the state-of-the-art and 97× improvement in EDP over a recent near-memory NTT accelerator.
- 22 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 41 (6) , 168-171
Intel Wins in Four Decades, but AMD Catches Up
Reports on the history, development, and applications supported by Intel's microprocessor product line. Microprocessors have evolved substantially since the introduction of the Intel 4004 half a century ago. Over the years, several processors have stood out for their innovative designs, commercial successes, forays into new application domains, and significant performance and efficiency enhancements compared to their competitors. We polled the computer architecture community, and received votes from 254 processor designers and engineers, researchers from academia and industry, faculty, and graduate students, identifying their favorite processors from every decade since the 1970s, as well as their favorite processor of all time. The results of the poll are presented in this article.
- 22 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 41 (6) , 168-171
Intel Wins in Four Decades, but AMD Catches Up
Reports on the history, development, and applications supported by Intel's microprocessor product line. Microprocessors have evolved substantially since the introduction of the Intel 4004 half a century ago. Over the years, several processors have stood out for their innovative designs, commercial successes, forays into new application domains, and significant performance and efficiency enhancements compared to their competitors. We polled the computer architecture community, and received votes from 254 processor designers and engineers, researchers from academia and industry, faculty, and graduate students, identifying their favorite processors from every decade since the 1970s, as well as their favorite processor of all time. The results of the poll are presented in this article.
- 22 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 41 (6) , 112-120
Hardware Specialization: From Cell to Heterogeneous Microprocessors Everywhere
With advances in device technologies, design methodologies, and programming paradigms, microprocessors of today have undergone a complete metamorphosis compared to their predecessors from the 1970s and 1980s. In particular, heterogeneity has become an all-pervasive feature of modern-day processors in device and packaging technologies, architectures, and programming interfaces, resulting in unprecedented enhancements in their performance, power efficiency, and functionality. We explore these heterogeneous designs, from their inception in the early 2000s, to their culmination into a whole new class of processors termed as Systems-on-a-Chip, and finally track their evolution into the microprocessors of tomorrow.
- 22 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 41 (6) , 112-120
Hardware Specialization: From Cell to Heterogeneous Microprocessors Everywhere
With advances in device technologies, design methodologies, and programming paradigms, microprocessors of today have undergone a complete metamorphosis compared to their predecessors from the 1970s and 1980s. In particular, heterogeneity has become an all-pervasive feature of modern-day processors in device and packaging technologies, architectures, and programming interfaces, resulting in unprecedented enhancements in their performance, power efficiency, and functionality. We explore these heterogeneous designs, from their inception in the early 2000s, to their culmination into a whole new class of processors termed as Systems-on-a-Chip, and finally track their evolution into the microprocessors of tomorrow.
- 8 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 69 (8) , 1096-1098
Guest Editorial: IEEE TC Special Issue on Domain-Specific Architectures for Emerging Applications
- 8 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 69 (8) , 1096-1098
Guest Editorial: IEEE TC Special Issue on Domain-Specific Architectures for Emerging Applications
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Cascaded and resonant SRAM supply boosting for ultra-low voltage cognitive IoT applications
To enable ultra-low power cognitive IoT systems, we present novel supply boosting techniques allowing low voltage SRAM. These techniques include enhancements at both the device and circuit levels. A new 14nm SOI test chip employing the techniques shows functional 8T SRAM down to 0.24V. We also show how supply boosting can lead to lower voltage operation of cognitive IoT applications using an example of a neural network running the MNIST benchmark.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Cascaded and resonant SRAM supply boosting for ultra-low voltage cognitive IoT applications
To enable ultra-low power cognitive IoT systems, we present novel supply boosting techniques allowing low voltage SRAM. These techniques include enhancements at both the device and circuit levels. A new 14nm SOI test chip employing the techniques shows functional 8T SRAM down to 0.24V. We also show how supply boosting can lead to lower voltage operation of cognitive IoT applications using an example of a neural network running the MNIST benchmark.