Sayak Kundu
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
Sayak Kundu has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Andrew B. Kahng
University of California San Diego
9 shared publications - Zhiang Wang
Fudan University, Shanghai, China
5 shared publications - Bodhisatta Pramanik
University of California San Diego, La Jolla, CA, USA
3 shared publications - Dooseok Yoon
University of California, San Diego, La Jolla, CA, USA
3 shared publications - Amur Ghose
University of California San Diego, La Jola, San Diego, USA
2 shared publications - Chung-Kuan Cheng
University of California, San Diego, La Jolla, CA, USA
2 shared publications
Latest Publications
- Open Access
- 15 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 256-262
Invited: Post-Placement Buffering and Sizing Contest
- 15 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 256-262
Open AccessInvited: Post-Placement Buffering and Sizing Contest
- Open Access
- 15 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 133-141
Invited: Agentic AI for Physical Design R&D: Status and Prospects
- 15 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 133-141
Open AccessInvited: Agentic AI for Physical Design R&D: Status and Prospects
- Open Access
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP (02780070) , 1
An Updated Assessment of Reinforcement Learning for Macro Placement
We provide an improved assessment of Google Brain’s deep reinforcement learning approach to macro placement [29] and its updated Circuit Training (CT) implementation in GitHub [53]. A stronger simulated annealing (SA) baseline leverages the “go-with-the-winners” metaheuristic [3] and a multi-threading implementation. We develop and release new public benchmarks in sub-10nm technology: LEF/DEF for Google’s 7nm TSMC Ariane protobuf and scaled variants, as well as testcases implemented in the open-source ASAP7 7nm research enablement. We evaluate from-scratch training and fine-tuning results for the latest “AlphaChip” release of Circuit Training, alongside multiple alternative macro placers. We also study the recently-published pre-training guidance in [53]. A commercial place-and-route tool is used to provide “true reward” post-route power, performance and area metrics. All data, evaluation flows and related scripts are publicly available in the MacroPlacement GitHub repository [63]. Our study affords insights into reproducibility and reporting in the research literature, and points out still-missing confirmations (e.g., of CT’s scalability and pre-training methodology) that remain open questions for the research community.
- 15 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. PP (02780070) , 1
Open AccessAn Updated Assessment of Reinforcement Learning for Macro Placement
We provide an improved assessment of Google Brain’s deep reinforcement learning approach to macro placement [29] and its updated Circuit Training (CT) implementation in GitHub [53]. A stronger simulated annealing (SA) baseline leverages the “go-with-the-winners” metaheuristic [3] and a multi-threading implementation. We develop and release new public benchmarks in sub-10nm technology: LEF/DEF for Google’s 7nm TSMC Ariane protobuf and scaled variants, as well as testcases implemented in the open-source ASAP7 7nm research enablement. We evaluate from-scratch training and fine-tuning results for the latest “AlphaChip” release of Circuit Training, alongside multiple alternative macro placers. We also study the recently-published pre-training guidance in [53]. A commercial place-and-route tool is used to provide “true reward” post-route power, performance and area metrics. All data, evaluation flows and related scripts are publicly available in the MacroPlacement GitHub repository [63]. Our study affords insights into reproducibility and reporting in the research literature, and points out still-missing confirmations (e.g., of CT’s scalability and pre-training methodology) that remain open questions for the research community.
- Open Access
- 20 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 669-675
Use Cases and Deployment of ML in IC Physical Design
ML for IC physical design must be deployed in order to have business impacts. However, deployment in production must navigate many practical considerations, including choice of targets, skillsets and infrastructure, expectations and resources, data, and "MLOps". Furthermore, usage of ML is not the same as IC design practice and capability. In this invited paper, we give perspectives on basic strategies for selecting applications and pursuing deployment for ML in IC physical design. Example aspects include checklists for data and ML models, evaluation of model performance and progress on the path to deployment, the shifting landscape of MLOps, and challenges of "LLM-ability".
- 20 January 2025
- Published by Association for Computing Machinery (ACM)
- p. 669-675
Open AccessUse Cases and Deployment of ML in IC Physical Design
ML for IC physical design must be deployed in order to have business impacts. However, deployment in production must navigate many practical considerations, including choice of targets, skillsets and infrastructure, expectations and resources, data, and "MLOps". Furthermore, usage of ML is not the same as IC design practice and capability. In this invited paper, we give perspectives on basic strategies for selecting applications and pursuing deployment for ML in IC physical design. Example aspects include checklists for data and ML models, evaluation of model performance and progress on the path to deployment, the shifting landscape of MLOps, and challenges of "LLM-ability".
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Placement Tomography-Based Routing Blockage Generation for DRV Hotspot Mitigation
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessPlacement Tomography-Based Routing Blockage Generation for DRV Hotspot Mitigation
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Strengthening the Foundations for IC Physical Design and ML EDA Research
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessStrengthening the Foundations for IC Physical Design and ML EDA Research
- Open Access
- 9 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 29 (4) , 1-33
An Open-Source ML-Based Full-Stack Optimization Framework for Machine Learning Accelerators
Parameterizable machine learning (ML) accelerators are the product of recent breakthroughs in ML. To fully enable their design space exploration (DSE), we propose a physical-design-driven, learning-based prediction framework for hardware-accelerated deep neural network (DNN) and non-DNN ML algorithms. It adopts a unified approach that combines power, performance, and area (PPA) analysis with frontend performance simulation, thereby achieving a realistic estimation of both backend PPA and system metrics such as runtime and energy. In addition, our framework includes a fully automated DSE technique, which optimizes backend and system metrics through an automated search of architectural and backend parameters. Experimental studies show that our approach consistently predicts backend PPA and system metrics with an average 7% or less prediction error for the ASIC implementation of two deep learning accelerator platforms, VTA and VeriGOOD-ML, in both a commercial 12 nm process and a research-oriented 45 nm process.
- 9 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 29 (4) , 1-33
Open AccessAn Open-Source ML-Based Full-Stack Optimization Framework for Machine Learning Accelerators
Parameterizable machine learning (ML) accelerators are the product of recent breakthroughs in ML. To fully enable their design space exploration (DSE), we propose a physical-design-driven, learning-based prediction framework for hardware-accelerated deep neural network (DNN) and non-DNN ML algorithms. It adopts a unified approach that combines power, performance, and area (PPA) analysis with frontend performance simulation, thereby achieving a realistic estimation of both backend PPA and system metrics such as runtime and energy. In addition, our framework includes a fully automated DSE technique, which optimizes backend and system metrics through an automated search of architectural and backend parameters. Experimental studies show that our approach consistently predicts backend PPA and system metrics with an average 7% or less prediction error for the ASIC implementation of two deep learning accelerator platforms, VTA and VeriGOOD-ML, in both a commercial 12 nm process and a research-oriented 45 nm process.
- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
PPA-Relevant Clustering-Driven Placement for Large-Scale VLSI Designs
Today's place-and-route (P&R) flows are increasingly challenged by complexity and scale of modern designs. Often, heuristics must trade off between turnaround time and quality of PPA outcomes. This paper presents a clustered placement methodology that improves both turnaround time and final-routed solution quality. Our PPA-aware clustering considers timing, power and logical hierarchy during netlist clustering, effectively reducing problem size and accelerating global placement runtime while improving post-route PPA metrics. Additionally, our machine learning (ML)-accelerated virtualized P&R methodology predicts the best cluster shapes (i.e., aspect ratios and utilizations) to use in P&R of the clustered netlist. With the open-source OpenROAD tool, our methods achieve up to 47% (average: 36%) global placement runtime improvement with similar half-perimeter wirelength (HPWL) and 90% (29%) improvement in post-route total negative slack (TNS). With the commercial Cadence Innovus tool, our methods achieve up to 3.92% (1%) improvement in power and 99% (49%) improvement in TNS.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessPPA-Relevant Clustering-Driven Placement for Large-Scale VLSI Designs
Today's place-and-route (P&R) flows are increasingly challenged by complexity and scale of modern designs. Often, heuristics must trade off between turnaround time and quality of PPA outcomes. This paper presents a clustered placement methodology that improves both turnaround time and final-routed solution quality. Our PPA-aware clustering considers timing, power and logical hierarchy during netlist clustering, effectively reducing problem size and accelerating global placement runtime while improving post-route PPA metrics. Additionally, our machine learning (ML)-accelerated virtualized P&R methodology predicts the best cluster shapes (i.e., aspect ratios and utilizations) to use in P&R of the clustered netlist. With the open-source OpenROAD tool, our methods achieve up to 47% (average: 36%) global placement runtime improvement with similar half-perimeter wirelength (HPWL) and 90% (29%) improvement in post-route total negative slack (TNS). With the commercial Cadence Innovus tool, our methods achieve up to 3.92% (1%) improvement in power and 99% (49%) improvement in TNS.
- Open Access
- 12 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 177-184
Scalable Flip-Flop Clustering Using Divide and Conquer For Capacitated K-Means
Multi-bit flip-flop clustering is a well-studied optimization problem in physical design: carefully merging multiple single-bit flip-flops into a single multi-bit flip-flop can decrease the total power consumption in a clock distribution network due to lower clock power and routed clock wirelength. We propose a pointset decomposition heuristic that in conjunction with capacitated k-means [4] enables a scalable, divide-and-conquer flow for multi-bit flip-flop clustering. Our flow produces high-quality flip-flop clustering and placement solutions with respect to total power consumption, area, timing, and wirelength metrics evaluated after the post-routing optimization (PRO) stage of P&R. We test our flow on five designs of varying input size (0.5K to 64K clusterable single-bit flip-flops) implemented using the ASAP7 7nm research enablement [3] [9]. Empirical results show that our new flow is competitive with current state-of-the-art flows. Compared to MeanShift [2], we achieve 6.18% (resp. 1.90%) maximum (resp. average) reduction in total power consumption, along with improved total negative slack and wirelength. Compared to FlopTray [4], we achieve a 400 × speedup on larger designs such as VGA (17K single-bit flip-flops), but with an average 1.12% degradation in total power consumption.
- 12 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 177-184
Open AccessScalable Flip-Flop Clustering Using Divide and Conquer For Capacitated K-Means
Multi-bit flip-flop clustering is a well-studied optimization problem in physical design: carefully merging multiple single-bit flip-flops into a single multi-bit flip-flop can decrease the total power consumption in a clock distribution network due to lower clock power and routed clock wirelength. We propose a pointset decomposition heuristic that in conjunction with capacitated k-means [4] enables a scalable, divide-and-conquer flow for multi-bit flip-flop clustering. Our flow produces high-quality flip-flop clustering and placement solutions with respect to total power consumption, area, timing, and wirelength metrics evaluated after the post-routing optimization (PRO) stage of P&R. We test our flow on five designs of varying input size (0.5K to 64K clusterable single-bit flip-flops) implemented using the ASAP7 7nm research enablement [3] [9]. Empirical results show that our new flow is competitive with current state-of-the-art flows. Compared to MeanShift [2], we achieve 6.18% (resp. 1.90%) maximum (resp. average) reduction in total power consumption, along with improved total negative slack and wirelength. Compared to FlopTray [4], we achieve a 400 × speedup on larger designs such as VGA (17K single-bit flip-flops), but with an average 1.12% degradation in total power consumption.
- Open Access
- 26 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 158-166
Assessment of Reinforcement Learning for Macro Placement
We provide open, transparent implementation and assessment of Google Brain's deep reinforcement learning approach to macro placement (Nature) and its Circuit Training (CT) implementation in GitHub. We implement in open-source key "blackbox" elements of CT, and clarify discrepancies between CT and Nature. New testcases on open enablements are developed and released. We assess CT alongside multiple alternative macro placers, with all evaluation flows and related scripts public in GitHub. Our experiments also encompass academic mixed-size placement benchmarks, as well as ablation and stability studies. We comment on the impact of Nature and CT, as well as directions for future research.
- 26 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 158-166
Open AccessAssessment of Reinforcement Learning for Macro Placement
We provide open, transparent implementation and assessment of Google Brain's deep reinforcement learning approach to macro placement (Nature) and its Circuit Training (CT) implementation in GitHub. We implement in open-source key "blackbox" elements of CT, and clarify discrepancies between CT and Nature. New testcases on open enablements are developed and released. We assess CT alongside multiple alternative macro placers, with all evaluation flows and related scripts public in GitHub. Our experiments also encompass academic mixed-size placement benchmarks, as well as ablation and stability studies. We comment on the impact of Nature and CT, as well as directions for future research.