关注
Ashish Panwar
Ashish Panwar
Senior Researcher, Microsoft Research India
在 microsoft.com 的电子邮件经过验证 - 首页
标题
引用次数
引用次数
年份
Making Huge Pages Actually Useful
A Panwar, A Prasad, K Gopinath
Proceedings of the Twenty-Third International Conference on Architectural …, 2018
1272018
HawkEye: Efficient Fine-grained OS Support for Huge Pages
A Panwar, S Bansal, K Gopinath
Proceedings of the Twenty-Fourth International Conference on Architectural …, 2019
1012019
Mitosis: Transparently Self-Replicating Page-Tables for Large-Memory Machines
R Achermann, A Panwar, A Bhattacharjee, T Roscoe, J Gandhi
Proceedings of the Twenty-Fifth International Conference on Architectural …, 2020
702020
Sarathi: Efficient llm inference by piggybacking decodes with chunked prefills
A Agrawal, A Panwar, J Mohan, N Kwatra, BS Gulavani, R Ramjee
arXiv preprint arXiv:2308.16369, 2023
442023
Sigma: Secure gpt inference with function secret sharing
K Gupta, N Jawalkar, A Mukherjee, N Chandran, D Gupta, A Panwar, ...
Cryptology ePrint Archive, 2023
312023
Taming throughput-latency tradeoff in llm inference with sarathi-serve
A Agrawal, N Kedia, A Panwar, J Mohan, N Kwatra, BS Gulavani, ...
arXiv preprint arXiv:2403.02310, 2024
272024
Trident: Harnessing architectural resources for all page sizes in x86 processors
VSS Ram, A Panwar, A Basu
MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture …, 2021
242021
Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis
A Panwar, R Achermann, A Basu, A Bhattacharjee, K Gopinath, J Gandhi
Proceedings of the 26th ACM International Conference on Architectural …, 2021
232021
A Case for Protecting Huge Pages from the Kernel
A Panwar, N Patel, K Gopinath
Proceedings of the 7th ACM SIGOPS Asia-Pacific Workshop on Systems, 1-8, 2016
122016
Vidur: A Large-Scale Simulation Framework For LLM Inference
A Agrawal, N Kedia, J Mohan, A Panwar, N Kwatra, B Gulavani, ...
Proceedings of Machine Learning and Systems 6, 351-366, 2024
52024
Towards Practical Page Placement for a Green Memory Manager
A Panwar, K Gopinath
High Performance Computing (HiPC), 2015 IEEE 22nd International Conference …, 2015
52015
nuKSM: NUMA-aware memory de-duplication on multi-socket servers
A Panda, A Panwar, A Basu
2021 30th International Conference on Parallel Architectures and Compilation …, 2021
42021
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
R Prabhu, A Nayak, J Mohan, R Ramjee, A Panwar
arXiv preprint arXiv:2405.04437, 2024
32024
Address Scaling: Architectural Support for Fine-Grained Thread-Safe Metadata Management
D Mishra, K Kanellopoulos, A Panwar, A Sriraman, V Seshadri, O Mutlu, ...
IEEE Computer Architecture Letters, 2024
2024
Operating System Support for Efficient Virtual Memory
A Panwar
Indian Institute of Science Bangalore, 2022
2022
Leveraging Architectural Support of Three Page Sizes with Trident
VSS Ram, A Panwar, A Basu
arXiv preprint arXiv:2011.12092, 2020
2020
An Allocation Framework for Optimizing Memory Power Consumption and Controlling Fragmentation
A Panwar
2015
Fast Local Page-Tables for Virtualized NUMA Servers with vMitosis Extended Abstract
A Panwar, R Achermann, A Basu, A Bhattacharjee, K Gopinath, J Gandhi
系统目前无法执行此操作,请稍后再试。
文章 1–18