Santosh Pandey
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
Santosh Pandey has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Hang Liu
Rutgers, The State University of New Jersey, Piscataway, NJ, USA
6 shared publications - Amir Yazdanbakhsh
Google Deepmind, Mountain View, USA
4 shared publications - Arash Nasr-Esfahany
CSAIL, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
2 shared publications - Baptiste Lepers
Université Grenoble Alpes, Inria, Grenoble, France
2 shared publications - Brett W. Coon
Google
2 shared publications - Chengying Huan
Nanjing University, Nanjing, China
2 shared publications
Latest Publications
- Open Access
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 46 (5) , 29-36
Fast and Accurate CPU Performance Modeling With Compositional Analytical–Machine Learning Fusion
Cycle-level simulators like gem5 are widely used in microarchitecture design, but prohibitively slow for large-scale design space exploration. We present Concorde, a new methodology for learning fast and accurate performance models of microarchitectures. Unlike existing simulators and learning approaches that emulate each instruction, Concorde uses simple analytical models to compute per-component performance bounds, producing compact distributions that an ML model maps to program behavior. Concorde is more than five orders of magnitude faster than Google’s cycle-level simulator, with ∼2% average Cycles-Per-Instruction (CPI) prediction error across SPEC2017, open-source, and Google’s proprietary benchmarks. Concorde is already shaping large-scale architecture exploration at Google, contributing to internal CPU design projects. This enables analyses previously infeasible: in about an hour, we conducted a first-of-its-kind fine-grained performance attribution to microarchitectural components, requiring ∼150M CPI evaluations. The same compositional analytical-ML recipe extends beyond CPUs, suggesting a broader approach to building fast, interpretable performance models.
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 46 (5) , 29-36
Open AccessFast and Accurate CPU Performance Modeling With Compositional Analytical–Machine Learning Fusion
Cycle-level simulators like gem5 are widely used in microarchitecture design, but prohibitively slow for large-scale design space exploration. We present Concorde, a new methodology for learning fast and accurate performance models of microarchitectures. Unlike existing simulators and learning approaches that emulate each instruction, Concorde uses simple analytical models to compute per-component performance bounds, producing compact distributions that an ML model maps to program behavior. Concorde is more than five orders of magnitude faster than Google’s cycle-level simulator, with ∼2% average Cycles-Per-Instruction (CPI) prediction error across SPEC2017, open-source, and Google’s proprietary benchmarks. Concorde is already shaping large-scale architecture exploration at Google, contributing to internal CPU design projects. This enables analyses previously infeasible: in about an hour, we conducted a first-of-its-kind fine-grained performance attribution to microarchitectural components, requiring ∼150M CPI evaluations. The same compositional analytical-ML recipe extends beyond CPUs, suggesting a broader approach to building fast, interpretable performance models.
- Open Access
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (6) , 1-30
A Comprehensive Survey of Subgraph Matching: [Experiments & Analysis]
Subgraph matching is a fundamental problem in graph analysis with a wide range of real-world applications. As subgraph matching techniques evolve, the existing mainstream filter-order-enumeration framework falls short in two aspects: (i) this filter-order-enumeration perspective overlooks an emerging line of compiler-based approaches with caching and validation-based orderings. (ii) The recent rise of complex pruning techniques has shifted the focus of core optimizations beyond filtering and enumeration. This paper advocates the need for a comprehensive survey that not only thoroughly discusses the compiler-based approaches (i.e., cache-based methods and their ordering techniques), but also reframes algorithm-level optimizations such that the role of pruning is adequately addressed. This survey revisits 17 representative exploration-based subgraph matching methods-including both algorithm-level techniques and compiler-based ones-and establishes two optimization pillars, i.e., redundancy reduction and order generation, that can inherently summarize all these efforts. This newly established perspective permits us to systematically organize various optimization techniques and analyze how they interact with each other in the same implementation framework. Our contributions are: (i) Cache-, filter-, and prune-based strategies can remove both overlapping and different redundancies, sending our performance up to 1.81× faster than existing state-of-the-art (SOTA) settings, and (ii) heuristic and validation-based orderings, though grounded in fundamentally different design principles, often converge to similar behavior, leading to comparable performance in practice. Finally, (iii) we provide empirical guidance on when and how different strategies are most effective across diverse graph scenarios.
- 4 December 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (6) , 1-30
Open AccessA Comprehensive Survey of Subgraph Matching: [Experiments & Analysis]
Subgraph matching is a fundamental problem in graph analysis with a wide range of real-world applications. As subgraph matching techniques evolve, the existing mainstream filter-order-enumeration framework falls short in two aspects: (i) this filter-order-enumeration perspective overlooks an emerging line of compiler-based approaches with caching and validation-based orderings. (ii) The recent rise of complex pruning techniques has shifted the focus of core optimizations beyond filtering and enumeration. This paper advocates the need for a comprehensive survey that not only thoroughly discusses the compiler-based approaches (i.e., cache-based methods and their ordering techniques), but also reframes algorithm-level optimizations such that the role of pruning is adequately addressed. This survey revisits 17 representative exploration-based subgraph matching methods-including both algorithm-level techniques and compiler-based ones-and establishes two optimization pillars, i.e., redundancy reduction and order generation, that can inherently summarize all these efforts. This newly established perspective permits us to systematically organize various optimization techniques and analyze how they interact with each other in the same implementation framework. Our contributions are: (i) Cache-, filter-, and prune-based strategies can remove both overlapping and different redundancies, sending our performance up to 1.81× faster than existing state-of-the-art (SOTA) settings, and (ii) heuristic and validation-based orderings, though grounded in fundamentally different design principles, often converge to similar behavior, leading to comparable performance in practice. Finally, (iii) we provide empirical guidance on when and how different strategies are most effective across diverse graph scenarios.
- Open Access
- 20 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1480-1494
Concorde: Fast and Accurate CPU Performance Modeling with Compositional Analytical-ML Fusion
- 20 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1480-1494
Open AccessConcorde: Fast and Accurate CPU Performance Modeling with Compositional Analytical-ML Fusion
- Open Access
- 11 June 2024
- Published by Association for Computing Machinery (ACM) in ACM SIGMETRICS Performance Evaluation Review
- Vol. 52 (1) , 23-24
TAO: Re-Thinking DL-based Microarchitecture Simulation
Microarchitecture simulators are indispensable tools for microarchitecture designers to validate, estimate, and optimize new hardware that meets specific design requirements. While the quest for a fast, accurate and detailed microarchitecture simulation has been ongoing for decades, existing simulators excel and fall short at different aspects: (i) Although execution-driven simulation is accurate and detailed, it is extremely slow and requires expert-level experience to design. (ii) Trace-driven simulation reuses the execution traces in pursuit of fast simulation but faces accuracy concerns and fails to achieve significant speedup. (iii) Emerging deep learning (DL)-based simulations are remarkably fast and have acceptable accuracy, but introduce substantial overheads from trace regeneration and model re-training when simulating a new microarchitecture. Re-thinking the advantages and limitations of the aforementioned three mainstream simulation paradigms, this paper introduces TAO that redesigns the DL-based simulation with three primary contributions: First, we propose a new training dataset design such that the subsequent simulation (i.e., inference) only needs functional trace as inputs, which can be rapidly generated and reused across microarchitectures. Second, to increase the detail of the simulation, we redesign the input features and the DL model using self-attention to support predicting various performance metrics of interest. Third, we propose techniques to train a microarchitecture agnostic embedding layer that enables fast transfer learning between different microarchitectural configurations and effectively reduces the re-training overhead of conventional DL-based simulators. TAO can predict various performance metrics of interest, significantly reduce the simulation time, and maintain similar simulation accuracy as state-of-the-art DL-based endeavors.
- 11 June 2024
- Published by Association for Computing Machinery (ACM) in ACM SIGMETRICS Performance Evaluation Review
- Vol. 52 (1) , 23-24
Open AccessTAO: Re-Thinking DL-based Microarchitecture Simulation
Microarchitecture simulators are indispensable tools for microarchitecture designers to validate, estimate, and optimize new hardware that meets specific design requirements. While the quest for a fast, accurate and detailed microarchitecture simulation has been ongoing for decades, existing simulators excel and fall short at different aspects: (i) Although execution-driven simulation is accurate and detailed, it is extremely slow and requires expert-level experience to design. (ii) Trace-driven simulation reuses the execution traces in pursuit of fast simulation but faces accuracy concerns and fails to achieve significant speedup. (iii) Emerging deep learning (DL)-based simulations are remarkably fast and have acceptable accuracy, but introduce substantial overheads from trace regeneration and model re-training when simulating a new microarchitecture. Re-thinking the advantages and limitations of the aforementioned three mainstream simulation paradigms, this paper introduces TAO that redesigns the DL-based simulation with three primary contributions: First, we propose a new training dataset design such that the subsequent simulation (i.e., inference) only needs functional trace as inputs, which can be rapidly generated and reused across microarchitectures. Second, to increase the detail of the simulation, we redesign the input features and the DL model using self-attention to support predicting various performance metrics of interest. Third, we propose techniques to train a microarchitecture agnostic embedding layer that enables fast transfer learning between different microarchitectural configurations and effectively reduces the re-training overhead of conventional DL-based simulators. TAO can predict various performance metrics of interest, significantly reduce the simulation time, and maintain similar simulation accuracy as state-of-the-art DL-based endeavors.
- Open Access
- 10 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 23-24
TAO: Re-Thinking DL-based Microarchitecture Simulation
Microarchitecture simulators are indispensable tools for microarchitecture designers to validate, estimate, and optimize new hardware that meets specific design requirements. While the quest for a fast, accurate and detailed microarchitecture simulation has been ongoing for decades, existing simulators excel and fall short at different aspects: (i) Although execution-driven simulation is accurate and detailed, it is extremely slow and requires expert-level experience to design. (ii) Trace-driven simulation reuses the execution traces in pursuit of fast simulation but faces accuracy concerns and fails to achieve significant speedup. (iii) Emerging deep learning (DL)-based simulations are remarkably fast and have acceptable accuracy, but introduce substantial overheads from trace regeneration and model re-training when simulating a new microarchitecture. Re-thinking the advantages and limitations of the aforementioned three mainstream simulation paradigms, this paper introduces TAO that redesigns the DL-based simulation with three primary contributions: First, we propose a new training dataset design such that the subsequent simulation (i.e., inference) only needs functional trace as inputs, which can be rapidly generated and reused across microarchitectures. Second, to increase the detail of the simulation, we redesign the input features and the DL model using self-attention to support predicting various performance metrics of interest. Third, we propose techniques to train a microarchitecture agnostic embedding layer that enables fast transfer learning between different microarchitectural configurations and effectively reduces the re-training overhead of conventional DL-based simulators. TAO can predict various performance metrics of interest, significantly reduce the simulation time, and maintain similar simulation accuracy as state-of-the-art DL-based endeavors.
- 10 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 23-24
Open AccessTAO: Re-Thinking DL-based Microarchitecture Simulation
Microarchitecture simulators are indispensable tools for microarchitecture designers to validate, estimate, and optimize new hardware that meets specific design requirements. While the quest for a fast, accurate and detailed microarchitecture simulation has been ongoing for decades, existing simulators excel and fall short at different aspects: (i) Although execution-driven simulation is accurate and detailed, it is extremely slow and requires expert-level experience to design. (ii) Trace-driven simulation reuses the execution traces in pursuit of fast simulation but faces accuracy concerns and fails to achieve significant speedup. (iii) Emerging deep learning (DL)-based simulations are remarkably fast and have acceptable accuracy, but introduce substantial overheads from trace regeneration and model re-training when simulating a new microarchitecture. Re-thinking the advantages and limitations of the aforementioned three mainstream simulation paradigms, this paper introduces TAO that redesigns the DL-based simulation with three primary contributions: First, we propose a new training dataset design such that the subsequent simulation (i.e., inference) only needs functional trace as inputs, which can be rapidly generated and reused across microarchitectures. Second, to increase the detail of the simulation, we redesign the input features and the DL model using self-attention to support predicting various performance metrics of interest. Third, we propose techniques to train a microarchitecture agnostic embedding layer that enables fast transfer learning between different microarchitectural configurations and effectively reduces the re-training overhead of conventional DL-based simulators. TAO can predict various performance metrics of interest, significantly reduce the simulation time, and maintain similar simulation accuracy as state-of-the-art DL-based endeavors.
- Open Access
- 21 May 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Measurement and Analysis of Computing Systems
- Vol. 8 (2) , 1-25
TAO: Re-Thinking DL-based Microarchitecture Simulation
Microarchitecture simulators are indispensable tools for microarchitecture designers to validate, estimate, optimize, and manufacture new hardware that meets specific design requirements. While the quest for a fast, accurate and detailed microarchitecture simulation has been ongoing for decades, existing simulators excel and fall short at different aspects: (i) Although execution-driven simulation is accurate and detailed, it is extremely slow and requires expert-level experience to design. (ii) Trace-driven simulation reuses the execution traces in pursuit of fast simulation but faces accuracy concerns and fails to achieve significant speedup. (iii) Emerging deep learning (DL)-based simulations are remarkably fast and have acceptable accuracy, but fail to provide adequate low-level microarchitectural performance metrics such as branch mispredictions or cache misses, which is crucial for microarchitectural bottleneck analysis. Additionally, they introduce substantial overheads from trace regeneration and model re-training when simulating a new microarchitecture. Re-thinking the advantages and limitations of the aforementioned three mainstream simulation paradigms, this paper introduces TAO that redesigns the DL-based simulation with three primary contributions: First, we propose a new training dataset design such that the subsequent simulation (i.e., inference) only needs functional trace as inputs, which can be rapidly generated and reused across microarchitectures. Second, to increase the detail of the simulation, we redesign the input features and the DL model using self-attention to support predicting various performance metrics of interest. Third, we propose techniques to train a microarchitecture agnostic embedding layer that enables fast transfer learning between different microarchitectural configurations and effectively reduces the re-training overhead of conventional DL-based simulators. TAO can predict various performance metrics of interest, significantly reduce the simulation time, and maintain similar simulation accuracy as state-of-the-art DL-based endeavors. Our extensive evaluation shows TAO can reduce the overall training and simulation time by 18.06x over the state-of-the-art DL-based endeavors.
- 21 May 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Measurement and Analysis of Computing Systems
- Vol. 8 (2) , 1-25
Open AccessTAO: Re-Thinking DL-based Microarchitecture Simulation
Microarchitecture simulators are indispensable tools for microarchitecture designers to validate, estimate, optimize, and manufacture new hardware that meets specific design requirements. While the quest for a fast, accurate and detailed microarchitecture simulation has been ongoing for decades, existing simulators excel and fall short at different aspects: (i) Although execution-driven simulation is accurate and detailed, it is extremely slow and requires expert-level experience to design. (ii) Trace-driven simulation reuses the execution traces in pursuit of fast simulation but faces accuracy concerns and fails to achieve significant speedup. (iii) Emerging deep learning (DL)-based simulations are remarkably fast and have acceptable accuracy, but fail to provide adequate low-level microarchitectural performance metrics such as branch mispredictions or cache misses, which is crucial for microarchitectural bottleneck analysis. Additionally, they introduce substantial overheads from trace regeneration and model re-training when simulating a new microarchitecture. Re-thinking the advantages and limitations of the aforementioned three mainstream simulation paradigms, this paper introduces TAO that redesigns the DL-based simulation with three primary contributions: First, we propose a new training dataset design such that the subsequent simulation (i.e., inference) only needs functional trace as inputs, which can be rapidly generated and reused across microarchitectures. Second, to increase the detail of the simulation, we redesign the input features and the DL model using self-attention to support predicting various performance metrics of interest. Third, we propose techniques to train a microarchitecture agnostic embedding layer that enables fast transfer learning between different microarchitectural configurations and effectively reduces the re-training overhead of conventional DL-based simulators. TAO can predict various performance metrics of interest, significantly reduce the simulation time, and maintain similar simulation accuracy as state-of-the-art DL-based endeavors. Our extensive evaluation shows TAO can reduce the overall training and simulation time by 18.06x over the state-of-the-art DL-based endeavors.
- Open Access
- 21 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 21 (2) , 1-26
TEA+ : A Novel Temporal Graph Random Walk Engine with Hybrid Storage Architecture
Many real-world networks are characterized by being temporal and dynamic, wherein the temporal information signifies the changes in connections, such as the addition or removal of links between nodes. Employing random walks on these temporal networks is a crucial technique for understanding the structural evolution of such graphs over time. However, existing state-of-the-art sampling methods are designed for traditional static graphs, and as such, they struggle to efficiently handle the dynamic aspects of temporal networks. This deficiency can be attributed to several challenges, including increased sampling complexity, extensive index space, limited programmability, and a lack of scalability. In this article, we introduce TEA+ , a robust, fast, and scalable engine for conducting random walks on temporal graphs. Central to TEA+ is an innovative hybrid sampling method that amalgamates two Monte Carlo sampling techniques. This fusion significantly diminishes space complexity while maintaining a fast sampling speed. Additionally, TEA+ integrates a range of optimizations that significantly enhance sampling efficiency. This is further supported by an effective graph updating strategy, skilled in managing dynamic graph modifications and adeptly handling the insertion and deletion of both edges and vertices. For ease of implementation, we propose a temporal-centric programming model, designed to simplify the development of various random walk algorithms on temporal graphs. To ensure optimal performance across storage constraints, TEA+ features a degree-aware hybrid storage architecture, capable of adeptly scaling in different memory environments. Experimental results showcase the prowess of TEA+ , as it attains up to three orders of magnitude speedups compared to current random walk engines on extensive temporal graphs.
- 21 May 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 21 (2) , 1-26
Open AccessTEA+ : A Novel Temporal Graph Random Walk Engine with Hybrid Storage Architecture
Many real-world networks are characterized by being temporal and dynamic, wherein the temporal information signifies the changes in connections, such as the addition or removal of links between nodes. Employing random walks on these temporal networks is a crucial technique for understanding the structural evolution of such graphs over time. However, existing state-of-the-art sampling methods are designed for traditional static graphs, and as such, they struggle to efficiently handle the dynamic aspects of temporal networks. This deficiency can be attributed to several challenges, including increased sampling complexity, extensive index space, limited programmability, and a lack of scalability. In this article, we introduce TEA+ , a robust, fast, and scalable engine for conducting random walks on temporal graphs. Central to TEA+ is an innovative hybrid sampling method that amalgamates two Monte Carlo sampling techniques. This fusion significantly diminishes space complexity while maintaining a fast sampling speed. Additionally, TEA+ integrates a range of optimizations that significantly enhance sampling efficiency. This is further supported by an effective graph updating strategy, skilled in managing dynamic graph modifications and adeptly handling the insertion and deletion of both edges and vertices. For ease of implementation, we propose a temporal-centric programming model, designed to simplify the development of various random walk algorithms on temporal graphs. To ensure optimal performance across storage constraints, TEA+ features a degree-aware hybrid storage architecture, capable of adeptly scaling in different memory environments. Experimental results showcase the prowess of TEA+ , as it attains up to three orders of magnitude speedups compared to current random walk engines on extensive temporal graphs.
- Open Access
- 8 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 182-198
TEA: A General-Purpose Temporal Graph Random Walk Engine
Many real-world graphs are temporal in nature, where the temporal information indicates when a particular edge is changed (e.g., edge insertion and deletion). Performing random walks on such temporal graphs is of paramount value. The state-of-the-art sampling strategies are tailored for conventional static graphs and thus cannot effectively tackle the dynamic nature of temporal graphs due to several significant efficiency challenges, i.e., high sampling complexity, gigantic index space, and poor programmability. In this paper, we present TEA, the first highly-efficient general-purpose TEmporal grAph random walk engine. At its core, TEA introduces a new hybrid sampling approach that combines two Monte Carlo sampling methods together to drastically reduce space complexity and achieve high sampling speed. TEA further employs a series of algorithmic and system-level optimizations to remarkably improve the sampling efficiency, as well as provide streaming graph support. Finally, we introduce a temporal-centric programming model to ease the implementation of various random walk algorithms on temporal graphs. Experimental results demonstrate that TEA can achieve up to 3 orders of magnitude speedups over the state-of-the-art random walk engines on large temporal graphs.
- 8 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 182-198
Open AccessTEA: A General-Purpose Temporal Graph Random Walk Engine
Many real-world graphs are temporal in nature, where the temporal information indicates when a particular edge is changed (e.g., edge insertion and deletion). Performing random walks on such temporal graphs is of paramount value. The state-of-the-art sampling strategies are tailored for conventional static graphs and thus cannot effectively tackle the dynamic nature of temporal graphs due to several significant efficiency challenges, i.e., high sampling complexity, gigantic index space, and poor programmability. In this paper, we present TEA, the first highly-efficient general-purpose TEmporal grAph random walk engine. At its core, TEA introduces a new hybrid sampling approach that combines two Monte Carlo sampling methods together to drastically reduce space complexity and achieve high sampling speed. TEA further employs a series of algorithmic and system-level optimizations to remarkably improve the sampling efficiency, as well as provide streaming graph support. Finally, we introduce a temporal-centric programming model to ease the implementation of various random walk algorithms on temporal graphs. Experimental results demonstrate that TEA can achieve up to 3 orders of magnitude speedups over the state-of-the-art random walk engines on large temporal graphs.
- Open Access
- 20 June 2022
- Published by Association for Computing Machinery (ACM) in ACM SIGMETRICS Performance Evaluation Review
- Vol. 50 (1) , 67-68
SimNet
While cycle-accurate simulators are essential tools for architecture research, design, and development, their practicality is limited by an extremely long time-to-solution for realistic applications under investigation. This work describes a concerted effort, where machine learning (ML) is used to accelerate microarchitecture simulation. First, an ML-based instruction latency prediction framework that accounts for both static instruction properties and dynamic processor states is constructed. Then, a GPU-accelerated parallel simulator is implemented based on the proposed instruction latency predictor, and its simulation accuracy and throughput are validated and evaluated against a state-of-the-art simulator. Leveraging modern GPUs, the ML-based simulator outperforms traditional CPU-based simulators significantly.
- 20 June 2022
- Published by Association for Computing Machinery (ACM) in ACM SIGMETRICS Performance Evaluation Review
- Vol. 50 (1) , 67-68
Open AccessSimNet
While cycle-accurate simulators are essential tools for architecture research, design, and development, their practicality is limited by an extremely long time-to-solution for realistic applications under investigation. This work describes a concerted effort, where machine learning (ML) is used to accelerate microarchitecture simulation. First, an ML-based instruction latency prediction framework that accounts for both static instruction properties and dynamic processor states is constructed. Then, a GPU-accelerated parallel simulator is implemented based on the proposed instruction latency predictor, and its simulation accuracy and throughput are validated and evaluated against a state-of-the-art simulator. Leveraging modern GPUs, the ML-based simulator outperforms traditional CPU-based simulators significantly.
- Open Access
- 10 October 2020
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (1) , 35
Correction to: A computationally efficient and scalable key management scheme for access control of media delivery in digital Pay-TV systems
- 10 October 2020
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (1) , 35
Open AccessCorrection to: A computationally efficient and scalable key management scheme for access control of media delivery in digital Pay-TV systems