Siddhisanket (Sid) Raskar

I am a post-doctoral researcher in the Data Sciences group with theArgonne Leadership Computing Facility(ALCF) at Argonne National Laboratory. I work on evaluating the efficacy of AI architectures for scientific machine learning and on the design of next-generation AI architectures for science

I obtained my Ph.D. under the guidance of Guang R. Gao on the topic of "Dataflow Software Pipelining for Codelet Model using hardware-software co-design” from Electrical and Computer Engineering department at the University of Delaware. I also have a Master’s in Computer Science from the University of Delaware and a Bachelor’s in Computer Engineering from the University of Pune, India.

I am interested in pursuing a research-oriented career in the field of computer architecture, high-performance computing, and machine learning.

Research Interests :

  • Computing and Dataflow Models
  • Computer Architecture and Systems
  • Compilers Technology and Runtime Systems
  • Program mapping and optimization under dataflow models


Publications

  • Scott Cheng, Jun-Liang Lin, Murali Emani, Siddhisanket Raskar, Sam Foreman, Zhen Xie, Venkatram Vishwanath, Mahmut Kandemir, Thorough Characterization and Analysis of Large Transformer Model Training At-Scale. ACM Sigmetrics/IFIP Performance 2024 (Submitted)
  • Reet Barik, Siddhisanket Raskar, Murali Emani, Venkatram Vishwanath, Characterizing the Performance of Triangle Counting on Graphcore's IPU Architecture. Tenth Workshop on Accelerator Programming and Directives (WACCPD 2023) at Supercompututing 2023, November 12-17, Denver, Colorado, USA.
  • Diego A Roa Perdomo, Rafael A Herrera Guaitero, Dawson Fox, Hervé Yviquel, Siddhisanket Raskar, Xiaoming Li, Jose M Monsalve Diaz, Towards Fault Tolerance and Resilience in the Sequential Codelet Model. The Latin America High Performance Computing Conference (CARLA2023), September 18 -22, 2023, Cartagena de Indias, Colombia.
  • Murali Emani, Sam Foreman, Varuni Sastry, Zhen Xie, Siddhisanket Raskar, William Arnold, Rajeev Thakur, Venkatram Vishwanath, Michael E Papka. A Comprehensive Performance Study of Large Language Models on Novel AI Accelerators. https://arxiv.org/abs/2310.04607
  • Jose M Monsalve Diaz, Rodrigo Ceccato de Freitas, Esteban Rangel, Siddhisanket Raskar, "LLVM's Frontend and Runtime modifications to support OpenMP in the GraphCore architecture", LDRD Expedition Report 2023. (Available on Request)
  • Zhen Xie, Siddhisanket Raskar, Murali Emani and Venkatram Vishwanath. TrainBF: High-Performance DNN Training Engine using BFloat16 on AI Accelerators . 29th International European Conference on Parallel and Distributed Computing 2023 (EuroPar'23), 28 August – 1 September 2023, Limassol Cyprus.
  • Siddhisanket Raskar, Jose M Monsalve Diaz, Thomas Applencourt, Kalyan Kumaran, and Guang Gao. 2023. Implementation of Dataflow Software Pipelining for Codelet Model. In Proceedings of the 2023 ACM/SPEC International Conference on Performance Engineering (ICPE’23), April 15–19, 2023, Coimbra, Portugal. ACM, New York, NY, USA, 12 pages.
  • Gaurav Verma, Siddhisanket Raskar, Zhen Xie, Abid M Malik, Murali Emani, Barbara Chapman. 2023. Transfer Learning Across Heterogeneous Features For Efficient Tensor Program Generation. In Venue, TBD. ACM, New York, NY, USA, 6 pages
  • Siddhisanket Raskar, Thomas Applencourt, Kalyan Kumaran, and Guang Gao. 2023. Towards Maximum Throughput of Dataflow Software Pipeline under Resource Constraints. In International Workshop on Programming Models and Applications for Multicores and Manycores (PMAM ’23), February 25–March 1, 2023, Montreal, QC, Canada. ACM, New York, NY, USA, 9 pages. https://doi.org/10.1145/3582514.3582521
  • Murali Emani, Zhne Xie, Siddhisanket Raskar et al., "A Comprehensive Evaluation of Novel AI Accelerators for Deep Learning Workloads," 2022 IEEE/ACM International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), Dallas, TX, USA, 2022, pp. 13-25, doi: 10.1109/PMBS56514.2022.00007.
  • Jose M Monsalve Diaz, Esteban Rangel, Siddhisanket Raskar, Johannes Doerfert, "A pathway to OpenMP In the GraphCore Architecture", LDRD Expedition Report 2022. (Available on Request)
  • Zhen Xie, Siddhisanket Raskar, and Murali Emani, "Throughput-oriented and Accuracy-aware DNN Training with BFloat16 on GPU." at ScaDL workshop at IPDPS, 2022.
  • Siddhisanket Raskar Dataflow Software Pipeliing for Codelet Model using Hardware-Software Co-design, University of Delaware, Summer 2021.
  • Siddhisanket Raskar, Thomas Applencourt, Kalyan Kumaran, and Guang Gao, "clCodeletPipe API Documentation : Implementation of Codelet Pipe on Intel Iris Pro Architecture, CAPSL Technical Memo 140, May 2021.
  • Siddhisanket Raskar, Thomas Applencourt, Kalyan Kumaran, and Guang Gao, "Realization of Dataflow Software Pipelining for Codelet Model using Hardware-Software Co-design", CAPSL Technical Memo 139, May 2021.
  • R. Kabrick, D. A. R. Perdomo, Siddhisanket Raskar, J. M. M. Diaz, D. Fox and G. R. Gao, "CODIR: Towards an MLIR Codelet Model Dialect," 2020 IEEE/ACM Fourth Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware (IPDRM), GA, USA, 2020, pp. 33-40, doi: 10.1109/IPDRM51949.2020.00009.
  • D. A. R. Perdomo, R. Kabrick, J. M. M. Diaz, Siddhisanket Raskar, D. Fox and G. R. Gao, "DEMAC: A Modular Platform for HW-SW Co-Design," 2020 IEEE/ACM Fourth Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware (IPDRM), GA, USA, 2020, pp. 25-32, doi: 10.1109/IPDRM51949.2020.00008.
  • Siddhisanket Raskar, Thomas Applencourt, Kalyan Kumaran and Guang Gao, "Position Paper: Extending Codelet Model for Dataflow Software Pipelining using Software-Hardware Co-Design,"2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), Milwaukee, WI, USA, 2019, pp.640-645. doi: 10.1109/COMPSAC.2019.10280
  • S. Zeng, J. M. Monsalve Diaz and Siddhisanket Raskar, " Toward A High-Performance Emulation Platform for Brain-Inspired Intelligent SystemsExploring Dataflow-Based Execution Model and Beyond," 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), Milwaukee, WI, USA, 2019, pp. 628-633. doi:10.1109/COMPSAC.2019.10278
  • Siddhisanket Raskar, J. M. Monsalve Diaz, Thomas Applencourt, Kalyan Kumaran, and Guang Gao, "Study of Dataflow Software Pipelining under Codelet Model using Cannons Algorithm", CAPSL Technical Memo 135, February 2020.
  • Diego Roa, Ryan Kabrick, Siddhisanket Raskar, J. M. Monsalve Diaz, Guang Gao, "Brain-Flow : A brain inspired dataflow implementation using DEMAC", CAPSL Technical Memo 134, October 2019.
  • Siddhisanket Raskar, Thomas Applencourt, Kalyan Kumaran, and Guang Gao, "Extending Codelet Model for Dataflow Software Pipelining using Software-Hardware Co-design", CAPSL Technical Memo 133, June 2019.
  • Siddhisanket Raskar and Guang Gao, "Legacy MPI Codes and its interoperability with fine grain task-parallel runtime systems for Exascale", ETI Technical Report 4, August 2015. (Available on Request)

Professional Service