[ISMM'25] EMD: Fair and Efficient Dynamic Memory De-bloating of Transparent Huge Pages
Parth Gangar, Ashish Panwar, K. Gopinath
24th ACM SIGPLAN International Symposium on Memory Management (ISMM) 2025.
Paper
[ASPLOS'25] POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
Aditya K Kamath, Ramya Prabhu, Jayashree Mohan, Simon Peter, Ramachandran Ramjee, Ashish Panwar
30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025.
Paper Code
[ASPLOS'25] vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
Ramya Prabhu, Ajay Nayak, Jayashree Mohan, Ramachandran Ramjee, Ashish Panwar
30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025.
Paper Code
[OSDI'24] Taming Throughput-Latency Trade-off in LLM Inference with Sarathi-Serve
Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, Ramachandran Ramjee
18th USENIX Symposium on Operating Systems Design and Implementation (OSDI) 2024.
Paper Code
[MLSys'24] VIDUR: A Large-Scale Simulation Framework for LLM Inference
Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee, Alexey Tumanov
7th Annual Conference on Machine Learning and Systems (MLSys) 2024.
Paper Code Demo
[PETS'24] SIGMA: Secure GPT Inference with Function Secret Sharing
Kanav Gupta, Neha Jawalkar, Ananta Mukherjee, Nishanth Chandran, Divya Gupta, Ashish Panwar, Rahul Sharma
24th Privacy Enhancing Technologies Symposium (PETS) 2024.
Paper
[IEEE CAL'24] Address Scaling: Architectural Support for Fine-Grained Thread-Safe Metadata Management
Deepanjali Mishra, Konstantinos Kanellopoulos, Ashish Panwar, Akshitha Sriraman, Vivek Seshadri, Onur Mutlu, Todd C Mowry
IEEE Computer Architecture Letters 2024.
Paper
[Arxiv] SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills
Amey Agrawal, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav S. Gulavani, Ramachandran Ramjee
Arxiv 2023.
Preprint
[MICRO'21] Trident: Harnessing Architectural Resources for All Page Sizes in x86 Processors
Venkat Sri Sai Ram, Ashish Panwar, Arkaprava Basu
54th IEEE/ACM International Symposium on Microarchitecture (MICRO) 2021.
Paper Code Slides Video
[PACT'21] nuKSM: NUMA-aware Memory De-duplication on Multi-socket Servers
Akash Panda, Ashish Panwar, Arkaprava Basu
30th International Conference on Parallel Architectures and Compilation Techniques (PACT) 2021.
Paper Code Slides Video
[ASPLOS'21] Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis
Ashish Panwar, Reto Achermann, Arkaprava Basu, Abhishek Bhattacharjee, K. Gopinath, Jayneel Gandhi
26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2021.
Paper Code Extended Abstract Slides Video
[ASPLOS'20] Mitosis: Transparently Self-Replicating Page-Tables for Large-Memory Machines
Reto Achermann, Ashish Panwar, Abhishek Bhattacharjee, Timothy Roscoe, Jayneel Gandhi
25th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2020.
Paper Code Slides Video
[ASPLOS'19] HawkEye: Efficient Fine-grained OS Support for Huge Pages
Ashish Panwar, Sorav Bansal, K. Gopinath
24th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2019.
Paper Code Slides Poster
[ASPLOS'18] Making Huge Pages Actually Useful
Ashish Panwar, Aravinda Prasad, K. Gopinath
23rd ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2018.
Paper Code Slides Poster
[APSys'16] A Case for Protecting Huge Pages from the Kernel
Ashish Panwar, Naman Patel, K. Gopinath
7th ACM SIGOPS Asia-Pacific Workshop on Systems (APSys) 2016.
Paper
[HiPC'15] Towards Practical Page Placement for a Green Memory Manager
Ashish Panwar and K. Gopinath
22nd IEEE International Conference on High Performance Computing (HiPC) 2015.
Paper Slides
  • From Basics to Breakthroughs: Tales from LLM Systems Research
    Workshop on Present and Future Computing Systems, CSA, IISc, 2024
  • Efficiently Serving Large Language Models
    Center for Networked Intelligence, IISc, 2024
  • Trident: Harnessing Architectural Resources for All Page Sizes in x86 Processors
    MICRO, 2021 (virtual)
  • Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis
    ASPLOS, 2021 (virtual)
  • System Software Enhancements for Efficient Memory Management
    India Design Review, Semiconductor Research Corporation (SRC), Bangalore, India, January 2020
  • OS and Hypervisor Support for Self-Replicating Page-Tables
    VMware Research, Palo Alto, US, 2019
  • Making Huge Pages Actually Useful
    • ACM Inter-Research-Institute Student Symposium, Kochi, India, February 2019
    • NetApp, Sunnyvale, US, April 2018
    • Qualcomm, Bangalore, India, March 2018
    • ASPLOS, Williamsburg, Virginia, US, 2018
  • Light-Weight Contexts: An OS Abstraction for Safety and Performance
    (Research paper—OSDI’16) Centre for Artificial Intelligence and Robotics, DRDO, Bangalore, India, October 2018
  • Towards Practical Page Placement for a Green Memory Manager
    HiPC, Bangalore, India, 2015

I have served or will be serving as a reviewer on the following program committees:

  • ACM Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2025
  • ACM Architectural Support for Programming Languages and Operating Systems (ASPLOS) 2024
  • Usenix Annual Technical Conference (ATC) 2025
  • Usenix Annual Technical Conference (ATC) 2024
  • ACM SIGPLAN International Symposium on Memory management (ISMM) 2024

External reviewer:

  • IEEE International Symposium on Performance Analysis of System and Software (ISPASS) 2025
  • ACM Transactions on Computer Systems (TOCS) 2023
  • ACM Transactions on Architecture and Code Optimization (TACO) 2022